基于Fisher分类器和计算智能的遥感图像变化检测
|
摘要
现有的变化检测技术多通过差异算子将多时相图像转换为单幅差异影像，对差异影像进行分析得到图像中的变化区域。参数模型在变化检测技术发展过程中起到了重要作用，它利用不同的函数根据差异影像分布提取图像中变化区域。然而，现有的模型大部分都是基于单函数估计，图像匹配率低，且受差异算子影响检测结果不稳定。虽然改进算法引入了图像的空间信息，但是检测过程仍然需要先进行分布假设。所以，参数模型的设置和差异影像数据的分布都对检测结果有较大影响。
本文针对这些问题进行研究，分别利用Fisher分类器和计算智能方法对图像进行检测，提高了算法的适用性。此外，为了避免由于差异算子不同引起的不稳定性，将分类对象从差异影像换成联合灰度直方图和联合特征向量，并通过小波变换和局部均值加权等方法引入图像空间信息提高检测精度。本论文主要工作概括如下：
1.提出一种基于Wavelet域隐马尔科夫树(HMT, Hidden Markov Tree)模型的遥感图像变化检测算法。算法利用双高斯混合模型对小波分解后的多层差异影像进行拟合，根据拟合结果判定待检测点类别。对得到的多层初始分割结果，利用HMT模型根据连续最大后验概率(SMAP, Sequential Maximum A Posteriori)融合，得到最终变化检测图。对真实遥感数据集进行实验证明，本算法可以得到较好的检测结果。
2.利用改进的动态Fisher分类器通过对二维联合直方图分类检测多时相遥感图像变化区域。算法利用自适应边缘检测方法提取训练数据。考虑图像空间关系，提出基于局部均值的动态Fisher判别分析(LMDFDA, Local Mean DynamicFisher Discriminant Analysis)，它将原算法中的全局均值替换为局部均值，增加了待检测点和训练数据的相关性。局部均值由经过均值漂移划分后，离待检测
像素最近的图像块决定。同时，根据当前检测结果动态调整局部均值和训练器参数，解决了由于初始训练数据选取不同而造成的不稳定性。实验结果证明，本算法提高了检测精度，检测结果稳定。
3.利用改进的动态模糊Fisher分类器，通过对多时相图像的联合直方图进行分类得到变化区域。在此基础上，根据图像空间关系对待检测点进行非局部均值加权，并以一定比例选取可靠性高的数据先进行标类，增加了数据的可分性和算法的可靠性。根据更新后的样本动态调整待检测点权重及分类器参数，直到所有像素判别完毕为止。本算法不受参数模型限制，不受差异算子影响并充分利用了图像的空间与时间信息。真实遥感数据结果表明本算法提高了检测精度。
4.提出一种无监督SAR图像变化检测算法，它不需要分布假设，而是通过对联合灰度直方图的分布特性进行判别得到变化区域。利用自适应边缘检测提取的训练数据，通过Fisher分类器对联合直方图进行判别分析，得到待检测点在不同小波层隶属度。根据邻域关系以及上下文进行融合，得到最终检测结果。对真实SAR图像进行实验，证明本算法可以得到较好的检测结果。
5.给出一种无监督SAR图像变化检测算法，利用BP神经网络(BPNN, BackPropagation Neural Network)对提取的联合特征向量进行检测得到变化区域。为了增加待检测点可分性，根据图像空间关系进行非局部均值加权。对加权后的数据，根据预测值选择可靠性高的数据先进行标类，并利用更新后的样本集合重新训练BPNN参数及权重，直到所有像素检测完毕。本算法不需要计算差异影像，不受参数模型限制。真实SAR图像结果证明基于联合特征向量算法的检测精度优于联合灰度直方图和差异影像结果。
6.利用数据聚类思想，通过进化算法寻找多时相SAR图像最小均方误差，得到变化检测结果。在原有Memetic算法基础上，针对图像自身特点，提出全新的搜索策略并根据当前检测结果动态调整局部搜索算法，实现了粗细结合的搜索过程。本算法不受分布模型限制，不需要先验知识，适用性较强。将改进的算法与遗传算法(GA, GeneticAlgorithm)、免疫克隆选择算法(ICSA, Immune CloneSelection Algorithm)及原Memetic算法(MA, Memetic algorithm)进行比较，实验证明，本算法可以快速收敛。
Most change detection algorithms generate the change maps based on the analysisof the difference images, which are obtained by a comparison between themultitemporal images. Statistical models play an important role in the development ofthe change detection techniques. They detect the changes in the multitemporal imageswith different distribution models. However, the single function models used in thestatistical models are too restrictive to fit all the data. Although the improved algorithmsintroduce the spatial information during the detection process, the initial segmentationsstill need the distribution assumption. Therefore, the detection accuracy of the changemaps based on the statistical models is dependent on the parameter model chosen andthe distribution of the difference images.
To improve the ability of the change detection algorithms, we focus the attentionon the distribution of the data itself to obtain the changed regions by using Fisherdiscriminant analysis and computational intelligence techniques. Furthermore, to avoidthe instability problem caused by the comparison operator, the processing elements ofthe classifiers are changed to the joint intensity histogram and the joint feature vector.The Wavelet transform and the non-local mean weighted method is used here tointegrate the spatial information. The main contribution of this thesis can besummarized as follows:
1. To overcome the restrictive of the single function models, a new approach isproposed by virtue of the double Gaussian mixture model and the Wavelet transform.After the decomposed low pass images are fitted by the double Gaussian mixturemodels, the change maps in different scales are fused using HMT model based onsequential maximum a posteriori estimation. The experiments of the real remote sensingimages confirm the effectiveness of the proposed algorithm.
2. The improved dynamic Fisher classifier is used here to detect the changes byanalyzing the joint intensity histogram of the multitemporal remote sensing images. Thealgorithm uses adaptive edge detection to get training data. Considering the spatialinformation, local mean dynamic Fisher discriminant analysis (LMDFDA) is proposedhere, which uses local mean instead of global mean to increase the correlation betweenthe unlabeled data and the training data. The local mean is calculated with the closestimage blocks segmented by the mean shift algorithm. The local mean and theparameters of the Fisher classifier are adjusted according to the current detection resultto avoid the influence of initial condition. The experiments indicate that the proposed algorithm is effective and feasible for real multitemporal remote sensing images.
3. A novel change detection approach based on the dynamic fuzzy Fisher classifierfor multitemporal remote sensing images is proposed in this thesis. To increase theseparability of the unlabeled pixels, a non-local mean weighted method is used tointroduce the spatial information. The unlabeled pixels are labeled with a predefinedprobability based on their predictive values. The weights of the unlabeled pixels and theparameters of the dynamic classifier are adjusted according to the updated samples untilall the pixels are classified. The proposed method is distribution free, context-sensitiveand not affected by the comparison operators.
4. An unsupervised technique for change detection area between two SAR imagesis proposed in this thesis. The algorithm uses adaptive edge detection to get trainingdata. The joint intensity histograms in different levels are used to decide themembership degree of unlabeled points through Fisher classifier. The fusion modelwhich considers the context relationship and inter-scale information improves theinsensitivity. The simulation results of two real SAR images show that the algorithm iseffective and has better detection results.
4. To avoid the instability caused by comparison operators, the joint feature vectorextracted from multitemporal images directly are introduced, which are input to a backpropagation neural network to detect the changes. Furthermore, a non-local meanweighted method is used to integrate the spatial information to increase the separabilityof the unlabeled pixels. The proposed method is distribution free, context sensitive andadjusted dynamically. Experimental results on real SAR images confirm theeffectiveness of the joint feature vector.
5. The clustering method is used here to find the change map by minimizing meansquare error (MMSE) with evolution algorithm. After introducing the image character, anew search strategy in Memetic algorithm was given here, which adjusted the localsearch algorithm according to the current detection result. The approach wasdistribution free and did not need priori knowledge. The experimental results obtainedon the real SAR images showed that the proposed method had a higher convergencespeed than GA、 ICSA and original MA, the detection results demonstrated theeffectiveness of the proposed algorithm.
本文针对这些问题进行研究，分别利用Fisher分类器和计算智能方法对图像进行检测，提高了算法的适用性。此外，为了避免由于差异算子不同引起的不稳定性，将分类对象从差异影像换成联合灰度直方图和联合特征向量，并通过小波变换和局部均值加权等方法引入图像空间信息提高检测精度。本论文主要工作概括如下：
1.提出一种基于Wavelet域隐马尔科夫树(HMT, Hidden Markov Tree)模型的遥感图像变化检测算法。算法利用双高斯混合模型对小波分解后的多层差异影像进行拟合，根据拟合结果判定待检测点类别。对得到的多层初始分割结果，利用HMT模型根据连续最大后验概率(SMAP, Sequential Maximum A Posteriori)融合，得到最终变化检测图。对真实遥感数据集进行实验证明，本算法可以得到较好的检测结果。
2.利用改进的动态Fisher分类器通过对二维联合直方图分类检测多时相遥感图像变化区域。算法利用自适应边缘检测方法提取训练数据。考虑图像空间关系，提出基于局部均值的动态Fisher判别分析(LMDFDA, Local Mean DynamicFisher Discriminant Analysis)，它将原算法中的全局均值替换为局部均值，增加了待检测点和训练数据的相关性。局部均值由经过均值漂移划分后，离待检测
像素最近的图像块决定。同时，根据当前检测结果动态调整局部均值和训练器参数，解决了由于初始训练数据选取不同而造成的不稳定性。实验结果证明，本算法提高了检测精度，检测结果稳定。
3.利用改进的动态模糊Fisher分类器，通过对多时相图像的联合直方图进行分类得到变化区域。在此基础上，根据图像空间关系对待检测点进行非局部均值加权，并以一定比例选取可靠性高的数据先进行标类，增加了数据的可分性和算法的可靠性。根据更新后的样本动态调整待检测点权重及分类器参数，直到所有像素判别完毕为止。本算法不受参数模型限制，不受差异算子影响并充分利用了图像的空间与时间信息。真实遥感数据结果表明本算法提高了检测精度。
4.提出一种无监督SAR图像变化检测算法，它不需要分布假设，而是通过对联合灰度直方图的分布特性进行判别得到变化区域。利用自适应边缘检测提取的训练数据，通过Fisher分类器对联合直方图进行判别分析，得到待检测点在不同小波层隶属度。根据邻域关系以及上下文进行融合，得到最终检测结果。对真实SAR图像进行实验，证明本算法可以得到较好的检测结果。
5.给出一种无监督SAR图像变化检测算法，利用BP神经网络(BPNN, BackPropagation Neural Network)对提取的联合特征向量进行检测得到变化区域。为了增加待检测点可分性，根据图像空间关系进行非局部均值加权。对加权后的数据，根据预测值选择可靠性高的数据先进行标类，并利用更新后的样本集合重新训练BPNN参数及权重，直到所有像素检测完毕。本算法不需要计算差异影像，不受参数模型限制。真实SAR图像结果证明基于联合特征向量算法的检测精度优于联合灰度直方图和差异影像结果。
6.利用数据聚类思想，通过进化算法寻找多时相SAR图像最小均方误差，得到变化检测结果。在原有Memetic算法基础上，针对图像自身特点，提出全新的搜索策略并根据当前检测结果动态调整局部搜索算法，实现了粗细结合的搜索过程。本算法不受分布模型限制，不需要先验知识，适用性较强。将改进的算法与遗传算法(GA, GeneticAlgorithm)、免疫克隆选择算法(ICSA, Immune CloneSelection Algorithm)及原Memetic算法(MA, Memetic algorithm)进行比较，实验证明，本算法可以快速收敛。
Most change detection algorithms generate the change maps based on the analysisof the difference images, which are obtained by a comparison between themultitemporal images. Statistical models play an important role in the development ofthe change detection techniques. They detect the changes in the multitemporal imageswith different distribution models. However, the single function models used in thestatistical models are too restrictive to fit all the data. Although the improved algorithmsintroduce the spatial information during the detection process, the initial segmentationsstill need the distribution assumption. Therefore, the detection accuracy of the changemaps based on the statistical models is dependent on the parameter model chosen andthe distribution of the difference images.
To improve the ability of the change detection algorithms, we focus the attentionon the distribution of the data itself to obtain the changed regions by using Fisherdiscriminant analysis and computational intelligence techniques. Furthermore, to avoidthe instability problem caused by the comparison operator, the processing elements ofthe classifiers are changed to the joint intensity histogram and the joint feature vector.The Wavelet transform and the non-local mean weighted method is used here tointegrate the spatial information. The main contribution of this thesis can besummarized as follows:
1. To overcome the restrictive of the single function models, a new approach isproposed by virtue of the double Gaussian mixture model and the Wavelet transform.After the decomposed low pass images are fitted by the double Gaussian mixturemodels, the change maps in different scales are fused using HMT model based onsequential maximum a posteriori estimation. The experiments of the real remote sensingimages confirm the effectiveness of the proposed algorithm.
2. The improved dynamic Fisher classifier is used here to detect the changes byanalyzing the joint intensity histogram of the multitemporal remote sensing images. Thealgorithm uses adaptive edge detection to get training data. Considering the spatialinformation, local mean dynamic Fisher discriminant analysis (LMDFDA) is proposedhere, which uses local mean instead of global mean to increase the correlation betweenthe unlabeled data and the training data. The local mean is calculated with the closestimage blocks segmented by the mean shift algorithm. The local mean and theparameters of the Fisher classifier are adjusted according to the current detection resultto avoid the influence of initial condition. The experiments indicate that the proposed algorithm is effective and feasible for real multitemporal remote sensing images.
3. A novel change detection approach based on the dynamic fuzzy Fisher classifierfor multitemporal remote sensing images is proposed in this thesis. To increase theseparability of the unlabeled pixels, a non-local mean weighted method is used tointroduce the spatial information. The unlabeled pixels are labeled with a predefinedprobability based on their predictive values. The weights of the unlabeled pixels and theparameters of the dynamic classifier are adjusted according to the updated samples untilall the pixels are classified. The proposed method is distribution free, context-sensitiveand not affected by the comparison operators.
4. An unsupervised technique for change detection area between two SAR imagesis proposed in this thesis. The algorithm uses adaptive edge detection to get trainingdata. The joint intensity histograms in different levels are used to decide themembership degree of unlabeled points through Fisher classifier. The fusion modelwhich considers the context relationship and inter-scale information improves theinsensitivity. The simulation results of two real SAR images show that the algorithm iseffective and has better detection results.
4. To avoid the instability caused by comparison operators, the joint feature vectorextracted from multitemporal images directly are introduced, which are input to a backpropagation neural network to detect the changes. Furthermore, a non-local meanweighted method is used to integrate the spatial information to increase the separabilityof the unlabeled pixels. The proposed method is distribution free, context sensitive andadjusted dynamically. Experimental results on real SAR images confirm theeffectiveness of the joint feature vector.
5. The clustering method is used here to find the change map by minimizing meansquare error (MMSE) with evolution algorithm. After introducing the image character, anew search strategy in Memetic algorithm was given here, which adjusted the localsearch algorithm according to the current detection result. The approach wasdistribution free and did not need priori knowledge. The experimental results obtainedon the real SAR images showed that the proposed method had a higher convergencespeed than GA、 ICSA and original MA, the detection results demonstrated theeffectiveness of the proposed algorithm.
引文
[1] Singh A. Digital change detection techniques using remotely-sense data. Int. J.Remote Sens.,1989,10(6):989–1003.
[2] Lu D, Mausel P, Brondízio E and Moran E. Change detection techniques. Int. J.Remote Sens.,2004,25(2):2365–2407.
[3] Radke R J, Andra S, Al-Kofahi O and Roysam B. Image change detectionalgorithms: A systematic survey. IEEE Trans. Image Process.,2005,14(3):294–307.
[4] Kaufmann R K, Seto K C. Change detection, accuracy, and bias in a changedetection techniques sequential analysis of Landsat imagery in the Pear River Delta,China: econometric techniques. Agriculture Ecosystems and Environment,2001,85:95–105.
[5] Zomer R J, Ustin S L and Carpenter C C. Land cover change along tropical andsubtropical riparian corridors within the Makalu Barun National Park andConservation Area, Nepal. Mountain Research and Development,2001,21:175–183.
[6] Lunetta R S, Ediriwickrema J, Johnson D M, Lyon J G and Mckerrow A. Impacts ofvegetation dynamics on the identification of land-cover change in a biologicallycomplex community in North Carolina, USA. Remote Sensing of Environment,2002,82:258–270.
[7] Weng Q. Land use change analysis in the Zhujiang Delta of China using satelliteremote sensing, GIS and stochastic modeling. Journal of EnvironmentalManagement,2002,64:273–284.
[8] Ling F, Li W B, Du Y and Li X D. Land cover change mapping at the subpixel scalewith different spatial-resolution remotely sensed imagery. IEEE Trans. Geosci.Remote Sens. Let.,2011,8(1):182-186.
[9] Jano A, Jefferies R L and Rockwell R F. The detection of vegetational change bymultitemporal analysis of Landsat data: the effects of goose foraging. Journal ofEcology,1998,86:93–99.
[10] Grover K, Quegan S and Freitas C D. Quantitative estimation of tropical forestcover by SAR. IEEE Trans. Geosci. Remote Sens.,1999,37:479–490.
[11] Collins R, Lipton A and Kanade T. Introduction to the special section on videosurveillance. IEEE Trans. Pattern Anal. Machine Intell.,2000,22(8):745–746.
[12] Stauffer C and Grimson W E. Learning patterns of activity using real-time tracking.IEEE Trans. Pattern Anal.Machine Intell..2000,22(8):747–757.
[13] Dumskyj M J, Aldington S J, Dore C J and Kohner E M. The accurate assessmentof changes in retinal vessel diameter using multiple frame electrocardio graphsynchronised fundus photography. Current Eye Research,1996,15(6):652–632.
[14] Rey D, Subsol G, Delingette H and Ayache N. Automatic detection andsegmentation of evolving processes in3D medical images: Application to multiplesclerosis. Medical Image Analysis,2002,6(2):163–179.
[15] Bosc M, Heitz F and Armspach J P. Automatic change detection in multimodalserial MRI: application to multiple sclerosis lesion evolution. Neuroimage,2003,20:643–656.
[16] Basavanhally A N, Ganesan S and Agner S. Computerized image-based detectionand grading of Lymphocytic Infiltration in HER2+breast cancer histopathology.IEEE Trans. Bio. Engin.,2010,57(3):642-653.
[17]李德仁．论21世纪遥感与GIS的发展．武汉大学学报：信息科学版,2005,28(2)：127—131.
[18] Loveland T R, Sohl T L, Stehman S V. A strategy for estimating the rates of recentUnited States land-cover changes. Photogrammetric Engineering and RemoteSensing,2002,68:1091–1099.
[19] Fung T. An assessment of TM imagery for land-cover change detection. IEEETrans. Geosci. Remote Sensing,1990,28(4):681–684.
[20] Joyce A T, Ivey G H and G.S.Burns. The use of Landsat MSS data for detectingland use changes in forestland. Proc. Of the14th Int. Sysposium on Remote Sensingof Environment, Ann Arbor, Michigan,1980.
[21] Hoffer R M and Lee K S. Forest change classification using SEASAT and SIR-Bsatellite SAR data. Proe.Of the1989,1989.
[22] Weismiller R A, Kristof S J, Scholz D K. Change detection in coastal zoneenvironments. Photogrammetric engineering and Remote Sensing,1997,43:1533-1539.
[23] Ghosh S, Bruzzone L, Patra S, Bovolo F and Ghosh A. A context-sensitivetechnique for unsupervised change detection based on Hopfield-type neuralnetworks. IEEE Trans. Geosci. Remote Sensing,2007,45(3):778–789.
[24] Patra S, Ghosh S, Ghosh A. Unsupervised change detection in remote-sensingimages using modified self-organizing feature map neural network, Int. Conf. onComputing: Theory and Applications (ICCTA-2007), Kolkata, India, IEEEComputer Society Press,2007:716–720.
[25] Chavez P S, MacKinnon D J. Automatic detection of vegetation changes in thesouthwestern United States using remotely sensed images. Photogram. Eng. RemoteSensing,1994,60(5):1285–1294.
[26] Bovolo F, Bruzzone L and Marchesi S. Analysis and adaptive estimation of theregistration noise distribution in multitemporal VHR images. IEEE Trans. Geosci.Rem. Sens.,2009,47(8):2658-2671.
[27] Bovolo F, Bruzzone L. A multilevel parcel-based approach to change detection invery high resolution multitemporal images. IEEE Int. Geosci. Remote Sens. Symp.,2005(3):2145–2148.
[28] Bovolo F. A multilevel parcel-based approach to change detection in very highresolution multitemporal images. IEEE Trans. Geosci. Rem. Sens. Let,2009,6(1):33-37.
[29] Lee J S. Digital image enhancement and noise filtering by use of local statistics.IEEE Trans. Pattern Anal. Mach. Intell.,1980, PAMI-2(2):165–168.
[30] Frost V S, Stiles J A, Shanmungan K S and Holtzman J C. A model for radarimages and its application to adaptive digital filtering of multiplicative noise. IEEETrans. Pattern Anal. Mach. Intell.,1982, PAMI-4(2):157–165.
[31] Kuan D T, Sawchuk A A, Strand T C and Chavel P. Adaptive noise smoothing filterfor images with signal-dependent noise. IEEE Trans. Pattern Anal.Mach. Intell.,1985, PAMI-7(2):165–177.
[32] Lopes A, Nerzy E, Touzi R and Laur H. Structure detection and statistical adaptivefiltering in SAR images. Int. J. Remote Sens.,1993,41:1735–1758.
[33] Bruzzone L and Prieto D. Automatic analysis of the difference image forunsupervised change detection. IEEE Trans. Geosci. Remote Sens.,2000,38(3):1171–1182.
[34] Bovolo F, Bruzzone L. A detail-preserving scale-driven approach to changedetection in multitemporal SAR images. IEEE Trans. Geosci. Remote Sens.,2005,43(12):2963-2972.
[35] Cihlar J, Pultz T J and Gray A L. Change detection with synthetic aperture radar.Int. J. Remote Sens.,1992,13:401–414.
[36] Hu H and Ban Y. Urban land-cover mapping and change detection with radarsatSAR data using neural network and rule-based classifiers. Int. Arch. Photogram.Rem. Sens. Spatial Info. Sci.37(Part B7), Beijing (2008).
[37] Martinis S, Twele A and Voigt S. Unsupervised extraction of Flood-Inducedbackscatter changes in SAR data using Markov image modeling on irregular graphs.IEEE Trans. Geosci. Remote Sens,2011,49(1):251-263.
[38] Fransson J E, Walter F, Blennow K, Gustavsson A. Detection of storm-damagedforested areas using airborne CARABAS-II VHF SAR image data. IEEE Trans.Geosci. Remote Sens.,2002,40(10):2170–2175.
[39] Simard M, Saatchi S. The use of decision tree and multiscale texture forclassification of JERS-1SAR data over tropical forest. IEEE Trans. Geosci. RemoteSens.,2000,33(5):2310-2321.
[40] Liew S C, Kam S P, Tuong T P, Chen P and Lim H. Application of multitemporalERS-1synthetic aperture radar in delineating rice cropping systems in the MekongRiver Delta, Vietnam. IEEE Trans. Geosci. Remote Sens.,1998,36(5):1412–1420.
[41] Townshend J and Justice C. Spatial variability of images and the monitoring ofchanges in the normalized difference vegetation index. International Journal ofRemote Sensing,1995,16:2187–2195.
[42]文贡坚.从新卫星遥感影像中自动发现变化区域.武汉大学博士后出站工作报告.2003.
[43] Celik T and Ma K. Unsupervised change detection for satellite images usingDual-Tree complex Wavelet transform. IEEE Trans. Geosci. Remote Sens.,2010,48(3):1199-2010.
[44] Bovolo F, Bruzzone L and Marconcini M. A novel approach to unsupervisedchange detection Based on a semisupervised SVM and a similarity measure. IEEETrans. Geosci. Remote Sens.,2008,46(7):2070-2082.
[45] Bovolo F, Camps-Valls G and Bruzzone L. A support vector domain method forchange detection in multitemporal images. Pattern Recognition Letters,2010,31(10):1148-1154.
[46] Bruzzone L and Carlin L. A multilevel context-based system for classification ofvery high spatial resolution images. IEEE Trans. Geosci.Remote Sens.,2006,44(9):2587–2600.
[47] Pacifici F, Del Frate F, Solimini C, and Emery W. An innovative neural-net methodto detect temporal changes in high-resolution optical satellite imagery. IEEE Trans.Geosci. Remote Sens.,2007,45(9):2940–2952.
[48] Camps-Valls G and Bruzzone L. Kernel-based methods for hyperspectral imageclassification. IEEE Trans. Geosci. Remote Sens.,2005,43(6):1351–1362.
[49] Kwon H and Nasrabadi N. Kernel orthogonal subspace projection for hyperspectralsignal classification. IEEE Trans. Geosci. Remote Sens.,2005,43(12):2952–2962.
[50] Samaniego L, Bardossy A and Schulz K. Supervised classification of remotelysensed imagery using a modified K-NN technique. IEEE Trans. Geosci. RemoteSens.,2008,46(7):2112–2125.
[51] Melgani F and Bruzzone L. Classification of hyperspectral remote sensing imageswith support vector machines. IEEE Trans. Geosci. Remote Sens.,2004,42(8):1778–1790.
[52] Stathakis D and Vasilakos A. Comparison of computational intelligence basedclassification techniques for remotely sensed optical image classification. IEEETrans. Geosci. Remote Sens.,2006,44(8):2305–2318.
[53] Moser G and Serpico S B. Automatic parameter optimization for support vectorregression for land and sea surface temperature estimation from remote sensing data.IEEE Trans. Geosci. Remote Sens.,2009,47(3):909–921.
[54] Schmidt F, Doute S and Schmitt B. Wavanglet: An efficient supervised classifierfor hyperspectral images. IEEE Trans. Geosci. Remote Sens.,2007,45(5):1374–1385.
[55] Grandi G D, Lucas R M and Kropacek J. Analysis by Wavelet frames of spatialstatistics in SAR data for characterizing structural properties of forests. IEEE Trans.Geosci. Remote Sens.,2009,47(2):494–507.
[56] Brera A M and Shahrokhi F. Application of Landsat data to monitor desertspreading in the Sahara region. Proc,of the12th Int．Symposium on Remote Sensingof Environment,Ann Arbor, Michigan,1978.
[57] Manavalan P, Kesavasamy K and Adiga S. Irrigated crops monitoring throughseasons using digital change detection analysis of1RD-LISS2data. Int．J．ofRemote Sensing,1995,16:633-640.
[58] Robinson W J. A critical review of the change detection and urban classificationliterature. Technical Memorandum CSC／TM-79／6235,Computer SciencesCorporation,Maryland,1979.
[59] Todd W J. Urban and regional land use change detected by using Landsat data.Journal of Research by the United States Geological Survey,1977,5:527-534.
[60] Weydahl D J. Change detection in SAR images. Geoscience and Remote SensingSymposium,1991:1421-1424.
[61] Bovolo F and Bruzzone L. A theoretical framework for unsupervised changedetection based on change vector analysis in the polar domain. IEEE Trans. Geosci.Remote Sens.,2007,45(1):218–236.
[62] Tian G. Sepctral signatures and vegetation indices of crops, Divisional RePort89/4,CSIRO Division of water Resource, Canberra,1989.
[63] Elvidge C D and Chen Z. Comparison of broad–band and narrow-band Red versusnear infrared vegetation indices. Remote Sensing of Environment,1995,54,38-48.
[64] Coiner J C. Using Landsat to monitor changed in vegetation cover induced bydesertification process. Proc. Of the14th int. symposium on remote sensing ofenvironment, ann arbor Michigan,1980.
[65] Nelson R F. Detection forest canopy change due to insect activity using LandsatMSS photogrammetric engineering and remote sensing,1983,49,1303-1314.
[66] Deng J S, Wang K, Deng Y H and Qi G J. PCA-based landuse change detection andanalysis using multitemporal and multisensor satellite data.Int. J. Remote Sens.,2008,29(16):4823–4838.
[67] Hanaizumi H, Okumura H and Fujimura S. Change detection from remotely sensedmulti-temporal images using spatial segmentation. Proc. Of the1991InternationalGeoscience and Remote Sensing Symposium(IGARSS91),1991:1079-1081.
[68] Jha C S and Unni N V M. Digital change detection of forest conversion of a drytropical forest region. Int. J. of Remote Sensing,1994,15:2543-2552.
[69] Dianat R and Kasaei S. Change detection in optical remote sensing images usingdifference-based methods and spatial information. IEEE Trans. Geosci. RemoteSens.,2010,7(1):215-219.
[70] Eghbali H J. K-S test for detecting changes from Landsat imagery data. IEEETransactions on Systems, Man and cybemetics,1979,9:17-23.
[71] Carincotte C, Derrode S and Bourennane S. Unsupervised change detection onSAR images using fuzzy hidden Markov chains. IEEE Trans. Geosci. Remote Sens.,2006,44(2):432-440.
[72] Deer P and Eklund P. Values for the fuzzy C-means classifier in change detectionfor remote sensing. Int. Conf. Information Processing and Management ofUncertainty,2002:187–194.
[73] Bazi Y, Melgani F, Bruzzone L and Vernazza G. A genetic expectation-maximization method for unsupervised change detection in multitemporal SARimagery international. Int. J. Remote Sens.,2009,30(24):6591-6610.
[74] Celik T. Changed detection in satellite images using a genetic algorithm approach.IEEE geosc. Remote Sens,2010,7(2):386-390.
[75] Bazi Y, Bruzzone L and Melgani F. An unsupervised approach based on thegeneralized Gaussian model to automatic change detection in multitemporal SARimages. IEEE Trans. Geosci. Remote Sens.,2005,43(4):874-887.
[76] Wang G T, Wang Y L and Jiao L C. Adaptive spatial neighborhood analysis andRayleigh-Gaussian distribution fitting for change detection in multi-temporal remotesensing images. Journal of Remote Sensing,2009,13(4):639-646.
[77] Moser G and Serpico S B. Generalized minimum-error thresholding forunsupervised change detection from SAR amplitude imagery. IEEE Trans. Geosc.Remote Sens.,2006,44(10):2972-2983.
[78] Celik T. Image change detection using Gaussian mixture model and geneticalgorithm. J. Vis. Commun. Image R.2010,21:965-974.
[79] Celik T. Bayesian change detection based on spatial sampling and Gaussianmixture model. Pattern Recognition Letters,2011,32:1635–1642.
[80] Kasetkasem K and Varshney P. An image change detection algorithm based onMarkov random field models. IEEE Trans. Geosci. Remote Sens.,2002,40(8):1815–1823.
[81] Melgani F and Bazi Y. MRF fusion approach to robust unsupervised changedetection in remote sensed imagery. IEEE Geosci. Remote Sens. Lett.,2006,3,(4):457–461.
[82] Celik T. Unsupervised multiscale change detection in multitemporal syntheticaperture radar images.17th European Signal Processing Conference,2009:1547-1551.
[83] Celik T. Multiscale change detection in multitemporal satellite images. IEEE Trans.Geosci. Remote Sens. Lett.,2009,6(4):820-824.
[84] Ding M, Tian Z, Jin Z, Xu M and Cao C X. Registration using robust kernelprincipal component for object-based change detection. IEEE Trans. Geosci.Remote Sens.,2010,7(4):761-765.
[85] Pacifici F. and Frate F D. Automatic change detection in Very High Resolutionimages with pulse-coupled neural networks. IEEE Trans. Geosci. Remote Sens.2010,4(1):58-62.
[86] Ma L, Zheng N, Yuan Z J and Zhang X T. A novel Dual-probe adaptive model forimage change detection. IEEE Signal Processing Letters,2010,17(10):863-866.
[87] Theiler J, Scovel C, Wohlberg B and Foy B R. Elliptically contoured distributionsfor anomalous change detection in hyperspectral Imagery. IEEE Trans. Geosci.Remote Sens. Lett.,2010,7(2):271-275.
[88] Bovolo F, Bruzzone L, Capobianco L, Garzelli A and Nencini F. Analysis of theeffects of pansharpening in change detection on VHR images. IEEE Trans. Geosci.Remote Sens.,2010,7(1):53-57.
[89]Sabry R. A new coherency formalism for change detection and phenomenology inSAR imagery: a field approach. IEEE Trans. Geosci. Remote Sens.,2009,6(3):458-462.
[90] Kita Y. A study of change detection from satellite images using joint intensityhistogram. Pattern Recognition,19th International Conference on Digital ObjectIdentifier,2008:1-4.
[91] Fisher A. The use of multiple measurements in taxonomic problems. Annals ofEugenics,7(2):179–188,1936.
[92] Zhao W, Nandhakumar N. Linear discriminant analysis of MPF for facerecognition. Proc. International Conference on Pattern Recognition,1998:185-188
[93] K. Marcel, D. Hans, K. Dietrich. Robustness of linear diseriminant analysis inautomatic speech recognition. The16th International Conference on patternRecognition,2002,3:371-374.
[94] Wilks S S. Mathematical statistics. Wiley, New York,1962:577-578.
[95] Duda R and Hart P. Pattern classification and scene analysis. Wiley, NewYork,1973.
[96] Foley D H, Sammon J W. An optimal set of discriminant vectors. IEEE TransCompute1975,24(3):281-289.
[97] Clausi D A. K-means iterative Fisher(KIF) unsupervised clustering algorithmapplied to image texture segmentation. Pattern Recognition,2002,35(9):1959-1972.
[98]陈果.图像阈值分割的Fisher准则函数法.仪器仪表学报,2003,24(6):564-567.
[99]童莹,邱晓晖.基于Fisher准则函数的二维阈值图像分割方法.电力系统通讯,2004,9:36-47
[100] Li L, Gong J, Chen W. Gray-level image thresholding based on Fisher linearprojection of two-dimensional histogram. Pattern Recognition,1997,30:743-749.
[101]刘永.基于Fisher准则的自适应图像分割算法.系统仿真技术,2009,5(3):161-165.
[102]温淑焕,唐英干.基于Fisher准则的多阈值图像分割方法.激光与红外,2008,38(7):741-744.
[103]张晶阳,刘夏.带有收敛因子的PSO-Fisher图像分割的方法.化工自动化及仪表,2010,37(12):93-95.
[104] Wu K L, Yu J and Yang M S. A novel fuzzy clustering algorithm based on afuzzy scatter matrix with optimality test. Pattern Recognition Letters,2005,26(5):639-652.
[105]曹苏群,王士同,陈晓峰等.基于模糊Fisher准则的半模糊聚类算法.电子与信息学报,2008,30(9):2162-2165.
[106]支晓斌,范九伦.基于模糊Fisher准则的自适应降维模糊聚类算法.电子与信息学报,2009,31(11):2653-2658.
[107] Mika S, Ratsch G, Weston J, Scholkopf B. Fisher discriminant analysis withkernels. IEEE Workshop on Neural Networks for Signal Processing.1999:41–48.
[108] Liu Q, Lu H and Ma S. Improving kernel Fisher discriminant analysis for facerecognition. IEEE Trans. Circuits Syst. Video Technol.,2004,14(1): pp.42–49.
[109]蔡自兴等.人工智能及其应用(第3版).北京:清华大学出版社,2003.
[110] Narendra K S. Identification and control of dynamic systems using neuralNetworks. IEEE Trans. On neural networks.1990, l(1):4-27.
[111]焦李成.神经网络系统理论.西安电子科技大学出版社,1995.
[112] Du H F, Jiao L C,Wang S A. clonal operator and antibody clone algorithms.Machine Learning and Cybernetics,2002,506–510.
[113] Moscato P. On evolution, search, optimization, genetic algorithms and martial arts:Towards memetic algorithms. Technical Report Caltech Concurrent ComputationProgram, Report826, California Institute of Technology, Pasadena, CA:1989.
[1] Singh A. Digital change detection techniques using remotely-sense data. Int. J.Remote Sens.,1989,10(6):989–1003.
[2] Lu D, Mausel P, Brondízio E and Moran E. Change detection techniques. Int. J.Remote Sens.,2004,25(2):2365–2407.
[3] Radke R J, Andra S, Al-Kofahi O and Roysam B. Image change detectionalgorithms: A systematic survey. IEEE Trans. Image Process.,2005,14(3):294–307.
[4] Foody G M. Monitoring the magnitude of Land-cover change around the southernlimits of the Sahara, photogramm.Eng.Remote Sens,2001,(67):841—847.
[5] Li Y, Zhao S and Zhao K. Land-cover changes in an Urban Lake Watershed in aMega-city, Central China. Environ. Monit. Assess.,2006,115(1-3):349—359.
[6] Ghosh S, Bruzzone L, Patra S, Bovolo F and Ghosh A. A context-sensitive techniquefor unsupervised change detection based on Hopfield-type neural networks. IEEETrans. Geosci. Remote Sensing,2007,45(3):778–789.
[7] Patra S, Ghosh S, Ghosh A. Unsupervised change detection in remote-sensingimages using modified self-organizing feature map neural network, Int. Conf. onComputing: Theory and Applications (ICCTA-2007), Kolkata, India, IEEEComputer Society Press,2007:716–720.
[8] Celik T and Ma K K. Unsupervised change detection for satellite images usingDual-Tree complex Wavelet transform. IEEE Trans. Geosci. Remote Sens.,2010,48(3):1199-2010.
[9] Fung T. An assessment of TM imagery for land-cover change detection. IEEE Trans.Geosci. Remote Sensing,28(4),1990:681–684.
[10] Bruzzone L and Carlin L. A multilevel context-based system for classification ofvery high spatial resolution images. IEEE Trans. Geosci.Remote Sens.,2006,44(9):2587–2600.
[11] Moser G and Serpico S B. Automatic parameter optimization for support vectorregression for land and sea surface temperature estimation from remote sensing data.IEEE Trans. Geosci. Remote Sens.,2009,47(3):909–921.
[12] Manavalan P, Kesavasamy K and Adiga S. Irrigated crops monitoring throughseasons using digital change detection analysis of1RD-LISS2data. Int．J．ofRemote Sensing,1995,16:633-640.
[13] Todd W J. Urban and regional land use change detected by using Landsat data.Journal of Research by the United States Geological Survey,1977,5:527-534
[14] Elvidge C D and Chen Z. Comparison of broad–band and narrow-band Red versusnear infrared vegetation indices. Remote Sensing of Environment,1995,54:38-48
[15] Deng J S, Wang K, Deng Y H and Qi G J. PCA-based landuse change detection andanalysis using multitemporal and multisensor satellite data.Int. J. Remote Sens.,2008,29(16):4823–4838.
[16] Bovolo F and Bruzzone L. A theoretical framework for unsupervised changedetection based on change vector analysis in the polar domain. IEEE Trans. Geosci.Remote Sens.,2007,45(1):218–236.
[17] Bruzzone L and Prieto D. Automatic analysis of the difference image forunsupervised change detection. IEEE Trans. Geosci. Remote Sens.,2000,38(3):1171–1182.
[18] Bazi Y, Bruzzone L and Melgani F. An unsupervised approach based on thegeneralized Gaussian model to automatic change detection in multitemporal SARimages. IEEE Trans. Geosci. Remote Sens.,2005,43(4):874-887.
[19] Wang G T, Wang Y L and Jiao L C. Adaptive spatial neighborhood analysis andRayleigh-Gaussian distribution fitting for change detection in multi-temporal remotesensing images, Journal of Remote Sensing,2009,13(4):639-646.
[20] Moser G and Serpico S B. Generalized minimum-error thresholding forunsupervised change detection from SAR amplitude imagery. IEEE Trans. Geosc.Remote Sens.,2006,44(10):2972-2983.
[21] Kasetkasem K and Varshney P. An image change detection algorithm based onMarkov random field models. IEEE Trans. Geosci. Remote Sens.,2002,40(8):1815–1823.
[22] Mallat S. A theory for multiresolution signal decomposition:The Waveletrepresentation. IEEE Trans.Patt.Anal.Machine Intell.1989,11(7):674-693
[23]张跃进,谢听.基于IHS和小波变换的遥感图像融合方法研究.华东交通大学学报,2008,25(1).49-52.
[24] Gunawan D. Denoising images using Wavelet transform. Proceedings of the IEEEPacific Rim Conference on Communications, Computers and Signal Processing.Victoria BC, USA,1999:83-85.
[25]谢杰成,张大力,徐文立著.小波图像去噪综述.中国图像图形学报,2002,7(3).209-217.
[26]潘泉,张磊,孟晋丽,张洪才著.小波滤波方法及应用.北京:清华大学出版社,2005.
[27] Bovolo F., Bruzzone L. A detail-preserving scale-driven approach to changedetection in multitemporal SAR images. IEEE Trans. Geosci. Remote Sens.,2005,43(12):2963-2972.
[28] Aas K, Eikvil L and Huseby R. Applications of hidden Markov chains in imageanalysis. Pattern Recognition,1999,32(4):703–713.
[29] Carincotte C, Derrode S and Bourennane S. Unsupervised change detection onSAR images using fuzzy hidden Markov chains. IEEE Trans. Geosci. Remote Sens.,2006,44(2):432-440.
[30] Choi H, Richard G. Multiscale image segmentation using Wavelet-domain hiddenMarkov models. IEEE Transactions on Image Processing,2001,10(9),1309-1321.
[31] Sha Y H, Cong L, Sun Q and Jiao L C. Unsupervised image segmenttation usingContourlet domain hidden Markov trees model. ICIAR2005,3656:32-39.
[1] Bazi Y, Melgani F, Bruzzone L and Vernazza G. A genetic expectation-maximizationmethod for unsupervised change detection in multitemporal SAR imageryinternational. Int. J. Remote Sens.,2009,30(24):6591-6610.
[2] Bazi Y, Bruzzone L, Melgani F. An unsupervised approach based on the generalizedGaussian model to automatic change detection in multitemporal SAR images. IEEETrans. Geosci. Remote Sens,2005,43(4):874-887.
[3] Bazi Y, Bruzzone L, Melgani F. Automatic Identification of the Number and Valuesof Decision Thresholds in the Log-ratio Image for Change Detection in SAR Images.IEEE Trans. Geosci. Remote Sens,2006,3(3):349-353.
[4] Bovolo F, Bruzzone L. A theoretical framework for unsupervised change detectionbased on change vector analysis in polar domain. IEEE Trans. Geosci. Remote Sens,2007,45(3):778-789.
[5] Kita Y. A study of change detection from satellite images using joint intensityhistogram. Pattern Recognition,19th International Conference on Digital ObjectIdentifier,2008:1-4.
[6] Sugiyama M. Dimensionality reduction of multimodal labeled data by local Fisherdiscriminant analysis. Machine Learning Research,2007,8:1027-1061.
[7] Wei L, Wang S J, Xu F F. Neighborhood margin Fisher discriminant analysis.Journal of Electronics&Information Technology,2009,31(3):509-513.
[8] Nummiaro K, Koller-Meier E, Van Gool L. An adaptive color-based particle filter.Image and Vision Computing,2002,21(1):99-110.
[9] Comaniciu D, Ramesh V, Meer P. Real-Time tracking of non-rigid objects usingmean shift. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR),2000,142-149.
[10] Comaniciu D, Meer P. Robust analysis of feature spaces: Color imagesegmentation. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)1997:750-755.
[11] Zhou X S, Comaniciu D, Krishnan S. An information fusion framework for robustshape tracking. IEEE Trans. Pattern Anal. Machine Intell.,2005,27:115–129.
[12] Comaniciu D. A common framework for nonlinear diffusion, adaptive smoothing,bilateral filtering and mean shift. Image and Video Computing,2003,22(1):73-81.
[13] Comaniciu D, Meer P. Mean shift: A robust approach toward feature space analysis.IEEE Trans. on Pattern Analysis and Machine Intelligence,2002,24(5):603619.
[14] Li X R, Wu F C, Hu Z Y. Convergence of a mean shift algorithm. Journal ofSoftware,2005,16(3):365374.
[15] Christoudias C M, Georgescu B. Synergism in low level vision. The16th Int’l Conf.on Pattern Recognition,2002,4:150155.
[16] Fisher A. The use of multiple measurements in taxonomic problems. Annals ofEugenics,1936,7(2):179–188.
[17] Duda O, Hart P E, Stor D G. Pattern classification. Wiley, New York,2001.
[18]陈果.图像阈值分割的Fisher准则函数法.仪器仪表学报,2003,24(6):564-567.
[19]童莹,邱晓晖.基于Fisher准则函数的二维阈值图像分割方法.电力系统通讯,2004,9:36-47.
[20] Li L, Gong J, Chen W. Gray-level image thresholding based on Fisher linearprojection of two-dimensional histogram. Pattern Recognition,1997,30:743-749.
[21]刘永.基于Fisher准则的自适应图像分割算法.系统仿真技术,2009,5(3):161-165.
[22]温淑焕,唐英干.基于Fisher准则的多阈值图像分割方法.激光与红外,2008,38(7):741-744.
[23] Wang G T, Wang Y L, Jiao L C. Adaptive spatial neighborhood analysis andRayleigh-Gaussian distribution fitting for change detection in multi-temporal remotesensing images.Journal of Remote Sensing,2009,13(4):639-646.
[24] Bovolo F, Bruzzone L. A detail-preserving scale-driven approach to changedetection in multitemporal SAR images. IEEE Trans. Geosci. Remote Sens.,2005,43(12):2963-2972.
[1] Coppin P R, Jonckheere I, Nachaerts K. Digital change detection in ecosystemmonitoring: A review. Int. J. Remote Sens,2003,24:1–33.
[2] Lu D, Mausel P, Brondizio E.Change detection techniques. Int. J. Remote Sens,2004,25(12):2365–2407.
[3] Brera A M, Shahrokhi F. Application of Landsat data to monitor desert spreading inthe Sahara region. Proc, of the12th Int. Symposium on Remote Sensing ofEnvironment, Ann Arbor, Michigan,1978.
[4] Manavalan P, Kesavasamy K, Adiga S. Irrigated crops monitoring through seasonsusing digital change detection analysis of1RD-LISS2data. Int．J．of RemoteSensing,1995,16:633-640.
[5] Weydahl D J. Change detection in SAR images. Proc．of the1991Int．Geoscienceand Remote Sensing Symposium,1991:1421-1424.
[6] Robinson W J. A critical review of the change detection and urban classificationliterature. Technical Memorandum CSC／TM-79／6235, Computer SciencesCorporation, Maryland,1979.
[7] Deng J S, Wang K, Deng Y H and Qi G J. PCA-based landuse change detection andanalysis using multitemporal and multisensor satellite data.Int. J. Remote Sens,2008,29(16):4823–4838.
[8] Inglada J. Similarity measures for multisensor remote sensing images. Proc.IGARSS,2002,1:104–106.
[9] Fung T. An assessment of TM imagery for land-cover change detection. IEEE Trans.Geosci. Remote Sensing,28(4),1990:681–684.
[10] Derrode S, Mercier G, Pieczynski W. Unsupervised change detection in SARimages using a multicomponent hidden Markov chain model. Analysis ofMultiTemporal Remote Sensing Images,2003,(3):195–203.
[11] Deer P. Digital change detection in remotely sensed imagery using fuzzy set theory.Ph.D. thesis, Dept. Geography Comput. Sci, Univ.Adelaide, Australia,1998.
[12] Hegde S. Modeling land cover change:A fuzzy approach.M.S. thesis. Int. Inst.Geo-Inf. Sci. Earth Obs, Enschede, The Netherlands,2003.
[13] Nemmour H Y. Combining comparative and simultaneous analysis approachesbased on fuzzy integration for change detection. Proc.20th ISPRS Congress,Geo-Imagery Bridging Continents.
[14] Carincotte C, Derrode S, Bourennane S. Unsupervised change detection on SARimages using fuzzy hidden Markov chains. IEEE Trans. Geosci. Remote Sens,2006,44(2):432-440.
[15] Aas K, Eikvil L, Huseby R. Applications of hidden Markov chains in imageanalysis.Pattern Recognit,1999,32,(4):703–713.
[16] Kita Y. A study of change detection from satellite images using joint intensityhistogram. Pattern Recognition,19th International Conference on Digital ObjectIdentifier,2008:1-4.
[17] Fisher R A.The use of multiple measurements in taxonomic problems. Annals ofEugenics,1936,7(2):179一188.
[18] Wu K.L, Yu J, Yang M.S. A novel fuzzy clustering algorithm based on a fuzzyscatter matrix with optimality test. Pattern Recognition Letters,2005,26(5):639-652.
[19]曹苏群,王士同,陈晓峰等.基于模糊Fisher准则的半模糊聚类算法.电子与信息学报,2008,30(9):2162-2165.
[20]支晓斌,范九伦.基于模糊Fisher准则的自适应降维模糊聚类算法.电子与信息学报,2009,31(11):2653-2658.
[21] Buades A, Coll B, Morel J.M. A non local algorithm for image denoising. Proc.Comp. Vis. Pattern Recognition.2005,2:60-65.
[22] Bazi Y, Bruzzone L, Melgani F. An unsupervised approach based on thegeneralized gaussian model to automatic change detection in multitemporal SARimages. IEEE Trans. Geosci. Remote Sens,2005,43(4):874-887.
[23] Wang G T, Wang Y L, Jiao L C. Adaptive spatial neighborhood analysis andRayleigh-Gaussian distribution fitting for change detection in multi-temporal remotesensing images. Journal of Remote Sensing,2009,13(4):639-646.
[24] Bovolo F, Bruzzone L. A detail-preserving scale-driven approach to changedetection in multitemporal SAR images. IEEE Trans. Geosci. Remote Sens.,2005,43(12):2963-2972.
[1] Cihlar J, Pultz T J,Gray A L. Change detection with synthetic aperture radar. Int. J.Remote Sens,1992,13:401–414.
[2] Hu H,Ban Y. Urban land-cover mapping and change detection with radarsat SARdata using neural network and rule-based classifiers. Int. Arch. Photogram. Rem.Sens. Spatial Info, Beijing,2008.
[3] Martinis S, Twele A,Voigt S. Unsupervised extraction of Flood-Induced backscatterchanges in SAR data using Markov image modeling on irregular graphs. IEEE Trans.Geosci. Remote Sens,2011,49(1):251-263.
[4] Fransson J E, Walter F, Blennow K, Gustavsson A,Ulander L M H. Detection ofstorm-damaged forested areas using airborne CARABAS-II VHF SAR image data.IEEE Trans. Geosci. Remote Sens,2002,40(10):2170–2175.
[5] Coppin P R, Bauer M E. Processing of multitemporal Landsat TM imagery tooptimize extraction of forest cover change features. IEEE Trans. Geosci. RemoteSens,1994,33(4):918–927.
[6] Liew S C, Kam S P, Tuong T P, Chen P, Lim H. Application of multitemporal ERS-1synthetic aperture radar in delineating rice cropping systems in the Mekong RiverDelta, Vietnam. IEEE Trans. Geosci. Remote Sens,1998,36(5):1412–1420.
[7] Celik T. A Bayesian approach to unsupervised multiscale change detectioninsynthetic aperture radar images. Signal process,2010,90(5):1471-1147.
[8] Bazi Y, Melgani F, Bruzzone L, Vernazza G. A genetic expectation-maximizationmethod for unsupervised change detection in multitemporal SAR imageryInternational. Int. J. Remote Sens,2009,30(24):6591-6610.
[9] Bazi Y, Bruzzone L, Melgani F. An unsupervised approach based on the generalizedgaussian model to automatic change detection in multitemporal SAR images. IEEETrans. Geosci. Remote Sens,2005,43(4):874-888.
[10] Moser G, Serpico S B. Generalized minimum-error thresholding for unsupervisedchange detection from SAR amplitude imagery. IEEE Trans. Geosc. Remote Sens,2006,44(10):2972-2983.
[11] Bovolo F, Bruzzone L. A detail-preserving scale-driven approach to changedetection in multitemporal SAR images. IEEE Trans. Geosci. Remote Sens.,2005,43(12):2963-2972.
[12] Lee J S. Digital image enhancement and noise filtering by use of local statistics.IEEE Trans. Pattern Anal. Mach. Intell,1980,2(2):165–168.
[13] Frost V S, Stiles J A, Shanmungan K S,Holtzman J C. A model for radar imagesand its application to adaptive digital filtering of multiplicative noise. IEEE Trans.Pattern Anal. Mach. Intell,1982,4(2):157–165.
[14] Kuan D T, Sawchuk A A, Strand T C, Chavel P. Adaptive noise smoothing filter forimages with signal-dependent noise. IEEE Trans. Pattern Anal.Mach. Intell,1985,7(2):165–177.
[15] Lopes A, Nerzy E, Touzi R, Laur H. Structure detection and statistical adaptivefiltering in SAR images. Int. J. Remote Sens,1993,41:1735–1758.
[16] Villasenor D, Fatland D R, Hinzman L D. Change detection on Alaska’s north slopeusing repeat-pass ERS-1SAR imagery. IEEE Trans. Geosci. Remote Sens,1993,31(1):227–236.
[17] Wang G T, Wang Y L, Jiao L C. Adaptive spatial neighborhood analysis andRayleigh-Gaussian distribution fitting for change detection in multi-temporal remotesensing images. Journal of Remote Sensing,2009,13(4):639-646.
[18] Radke R. J.Image change detection algorithms: a systematic survey. IEEE Trans.I.P,2005,14(3):294-307.
[19] Melgani F, Bazi Y. MRF fusion approach to robust unsupervised change detectionin remote sensed imagery. IEEE Geosci. Remote Sens. Lett,2006,3(4):457–461.
[20] Pajares G. A Hopfield neural nework for image change detection. IEEE Trans.Neural network,2006,17(5):1250-1264.
[21] Bovolo F. A multilevel parcel-based approach to change detection in very highresolution multitemporal images. IEEE Geosci. Remote Sens. Lett,2009,6(1):33-37.
[22] Marchesi S, Bovolo F, Bruzzone L. A context-sensitive technique robust toregistration noise for change detection in VHR multispectral images. IEEE Trans.Image Processing,2010,19(7):1877-1889.
[23] Kita Y. A study of change detection from satellite images using joint intensityhistogram. Pattern Recognition,19th International Conference on Digital ObjectIdentifier,2008:1-4.
[24] Mallat S. A theory for multiresolution signal decomposition:The Waveletrepresentation. IEEE Trans.Patt.Anal.Machine Intell.1989,11(7):674-693.
[25] Xin F F, Jiao L C, Wang G. SAR images change detection based on Waveletdomain Fisher classifier.Infrared Millim.Waves,2011,30(2):173-178.
[26] Choi H, Richard G. Multiscale image segmentation using Wavelet-domain hiddenMarkov models. IEEE Trans. Image Processing,2001,10(9),1309-1321.
[27] Sha Y H, Cong L, Sun Q and Jiao L C. Unsupervised image segmenttation usingContourlet domain hidden Markov trees model. ICIAR2005,3656:32-39.
[28] Bovolo F, Camps-Valls G, Bruzzone L.A support vector domain method for changedetection in multitemporal images. Pattern Recognition Letters,2010,31(10):1148-1154.
[1] Radke R J. Image change detection algorithms: a systematic survey. IEEE Trans. I.P,2005,14(3):294-307.
[2] Celik T. A Bayesian approach to unsupervised multiscale change detection insynthetic aperture radar images. Signal process,2010,90(5):1471-1147.
[3] Bazi Y, Melgani F, Bruzzone L. A genetic expectation-maximization method forunsupervised change detection in multitemporal SAR imagery. International. Int. J.Remote Sens,2009,30(24):6591-6610.
[4] Bazi Y, Bruzzone L, Melgani F. An unsupervised approach based on the generalizedgaussian model to automatic change detection in multitemporal SAR images. IEEETrans. Geosci. Remote Sens,2005,43(4):874-888.
[5] Moser G, Serpico S B. Generalized minimum-error thresholding for unsupervisedchange detection from SAR amplitude imagery. IEEE Trans. Geosc. Remote Sens,2006,44(10):2972-2983.
[6] Bovolo F, Bruzzone L. A detail-preserving scale-driven approach to changedetection in multitemporal SAR images. IEEE Trans. Geosci. Remote Sens.,2005,43(12):2963-2972.
[7] Melgani F, Bazi Y. MRF fusion approach to robust unsupervised change detection inremote sensed imagery. IEEE Geosci. Remote Sens. Lett,2006,3,(4):457–461.
[8] Pajares G. A Hopfield neural nework for image change detection. IEEE. Trans.Neural network,2006,17(5):1250-1264.
[9] Bovolo F. A multilevel parcel-based approach to change detection in very highresolution multitemporal images. IEEE Geosci. Remote Sens. Lett,2009,6(1):33-37.
[10] Marchesi S, Bovolo F, Bruzzone L. A context-sensitive technique robust toregistration noise for change detection in VHR multispectral images. IEEE Trans. I.P,2010.
[11] Celik T. Changed detection in satellite images using a genetic algorithm approach,IEEE geosc. Remote Sens,2010,7(2):386-390.
[12] Mallat S. A theory for multiresolution signal decomposition:The Waveletrepresentation. IEEE Trans. Patt.Anal.Machine Intell,1989,11(7):674-693.
[13] Zhang X, Jiao L.C, Liu F. Spectral clustering ensemble applied to SAR imagesegmentation. IEEE Trans. Geosc. Remote Sens,2008,46(7):2126-2136.
[14] Nason G P, Silverman B W. The stationary Wavelet transform and some statisticalapplications. New York: Springer-Verlag,1995,103:281-300.
[15] Rumelhart D E, McClell J L. Parallel. distributed processing. Cambridge, Ma: MITpress,1986.
[16] Buades A, Coll B, Morel J M. A non-local algorithm for image denoising. IEEEComputer Vision and Pattern Recognition,2005,2:60-65.
[17] Celik T. Unsupervised change detection in satellite images using principalcomponent analysis and k-means clustering. IEEE Trans. Geosc. Remote Sens lett,2009,6(4):772-776.
[1] Lu D, Mausel P, Brondízio E, Moran E. Change detection techniques. Int. J. RemoteSens,2004,25(2):2365–2407.
[2] Celik T. A Bayesian approach to unsupervised multiscale change detection insynthetic aperture radar images. Signal process.2010,90(5):1471-1147.
[3] Bazi Y, Melgani F, Bruzzone L, Vernazza G. A genetic expectation-maximizationmethod for unsupervised change detection in multitemporal SAR imageryInternational. Int. J. Remote Sens,2009,30(24):6591-6610.
[4] Bazi Y, Bruzzone L, Melgani F. An unsupervised approach based on the generalizedGaussian model to automatic change detection in multitemporal SAR images. IEEETrans. Geosci. Remote Sens,2005,43(4):874-887.
[5] Moser G, Serpico S B. Generalized minimum-error thresholding for unsupervisedchange detection from SAR amplitude imagery. IEEE Trans. Geosc. Remote Sens,2006,44(10):2972-2983.
[6] Bruzzone L, Prieto D. Automatic analysis of the difference image for unsupervisedchange detection. IEEE Trans. Geosci. Remote Sens,2000,38(3):1171–1182.
[7] Wang G T, Wang Y L, Jiao L C. Adaptive spatial neighborhood analysis andRayleigh-Gaussian distribution fitting for change detection in multi-temporal remotesensing images. Journal of Remote Sensing,2009,13(4):639-646.
[8] Celik T. Image change detection using Gaussian mixture model and geneticalgorithm. J. Vis. Commun. Image R,2010,21:965-974.
[9] Celik T. Bayesian change detection based on spatial sampling and Gaussian mixturemodel, Pattern Recognition Letters,2011,32:1635–1642.
[10] Ghosh S, Bruzzone L, Patra S, Bovolo F, Ghosh A. A context-sensitive techniquefor unsupervised change detection based on Hopfield-type neural networks. IEEETrans. Geosci. Remote Sensing,2007,45(3):778–789.
[11] Hartigan A, Wong M. A K-means clustering algorithm. Appl. Statist,1979,28:100–108.
[12] Celik T. Changed detection in satellite images using a genetic algorithm approach.IEEE geosc. Remote Sens,2010,7(2):386-390.
[13]陈国良,王煦法等.遗传算法及其应用.北京：人民邮电出版社,1999.
[14] Du H F, Jiao L C, Wang S A. Clonal operator and antibody clone algorithms.Machine Learning and Cybernetics,2002,506–510.
[15] Moscato P. On evolution, search, optimization, genetic algorithms and martial arts:Towards memetic algorithms, Technical Report Caltech Concurrent ComputationProgram, Report826, California Institute of Technology, Pasadena, CA;1989.
[16] Elbeltagi E, Hegazy T, Grierson D. Comparison among five evolutionary-basedoptimization algorithms,Journal of Advanced Engineering Informatics, ElsevierScience,2005,19(1):43–53.
[17] Nguyen Q H, Ong Y S, Lim M H.A probabilistic memetic framework. IEEE,Transactions on Evolutionary Computation,2009,13(3):604-623.
[18]薛嘉庆.最优化原理与方法.北京:冶金工业出版社,1983.
[19]王凌.智能优化算法及其应用.北京:清华大学出版社,2001.
[20]李继东,张学杰.基于遗传算法的多维模糊分类器构造的研究.软件学报.2005,16(5):779~785.
[21]邢文训,谢金星.现代优化计算方法.北京：清华大学,1999.
[22] Ong Y S, Lim M H, Zhu N, Wong K W. Classification of adaptive memeticalgorithms: A comparative study. IEEE Trans. Syst, Man Cybern, Part B:Cybern,2006,36(1):141–152.
[23] Noman N, Iba H. Accelerating differential evolution using an adaptive local search.IEEE Trans. Evol. Comput,2008,12(1):107–125.
[24] Lozano M, Herrera F, Krasnogor N. Real-coded memetic algorithms with crossoverhill-climbing. Evol. Comput,2004,12(3):273–302.
[25] Krasnogor N, Smith J. A tutorial for competent memetic algorithms: Model,taxonomy, and design issues. IEEE Trans. Evol. Comput,2005,9(5):474–488.
[26] Jeong S, Hasegawa S, Shimoyama K, Obayashi S.Development and investigationof efficient GA/PSO-HYBRID algorithm applicable to real-world designoptimization. IEEE Comput. Intell. Mag,2009,4(3):36–44.
[27] Chiam S C, Tan K C, Mamun A. A memetic model of evolutionary PSO forcomputational finance applications. Expert Syst. Applicat,2009,36(2):3695–3711.
[28] Tan K C, Chiam S C. Balancing exploration and exploitation with adaptivevariation for evolutionary multi-objective optimization. Eur. J. Oper. Res,2009,197(2):701–713.
[29] Ang J H, Tan K C, Mamun A. An evolutionary memetic algorithm for ruleextraction. Expert Syst. Applicat,2010,37(2):1302–1315.
[30] Zhu Z, Ong Y. S, Dash M. Wrapper-filter feature selection algorithm using amemetic framework. IEEE Trans. Syst, Man, Cybern. B,2007,37(1):70–76.
[31] Hasan S, SARker R, Essam D, Cornforth D. Memetic algorithms for solvingjob-shop scheduling problems. Memetic Comput,2009,1(1):69–83.
[32] Batenburg K. An evolutionary algorithm for discrete tomography. Discrete Appl.Math,2005,151(1–3):36–54.
[33] Tirronen V, Neri F, K rkk inen T, Majava K, Rossi T. An enhanced memeticdifferential evolution in filter design for defect detection in paper production. Evol.Comput,2008,16(4):529–555.
[34] Gesù V. D, Bosco G. L, Millonzi F, Valenti C. A memetic algorithm for binaryimage reconstruction.in Lecture Notes in Computer Science,2008,4958:384–395.
[35] Gesù V. D, Bosco G L, Millonzi F, Valenti C. Discrete tomography reconstructionthrough a new memetic algorithm. Lecture Notes in Computer Science,2008,4974:347–352.
[36] Bovolo F, Bruzzone L. A detail-preserving scale-driven approach to changedetection in multitemporal SAR images. IEEE Trans. Geosci. Remote Sens.,2005,43(12):2963-2972.
[2] Lu D, Mausel P, Brondízio E and Moran E. Change detection techniques. Int. J.Remote Sens.,2004,25(2):2365–2407.
[3] Radke R J, Andra S, Al-Kofahi O and Roysam B. Image change detectionalgorithms: A systematic survey. IEEE Trans. Image Process.,2005,14(3):294–307.
[4] Kaufmann R K, Seto K C. Change detection, accuracy, and bias in a changedetection techniques sequential analysis of Landsat imagery in the Pear River Delta,China: econometric techniques. Agriculture Ecosystems and Environment,2001,85:95–105.
[5] Zomer R J, Ustin S L and Carpenter C C. Land cover change along tropical andsubtropical riparian corridors within the Makalu Barun National Park andConservation Area, Nepal. Mountain Research and Development,2001,21:175–183.
[6] Lunetta R S, Ediriwickrema J, Johnson D M, Lyon J G and Mckerrow A. Impacts ofvegetation dynamics on the identification of land-cover change in a biologicallycomplex community in North Carolina, USA. Remote Sensing of Environment,2002,82:258–270.
[7] Weng Q. Land use change analysis in the Zhujiang Delta of China using satelliteremote sensing, GIS and stochastic modeling. Journal of EnvironmentalManagement,2002,64:273–284.
[8] Ling F, Li W B, Du Y and Li X D. Land cover change mapping at the subpixel scalewith different spatial-resolution remotely sensed imagery. IEEE Trans. Geosci.Remote Sens. Let.,2011,8(1):182-186.
[9] Jano A, Jefferies R L and Rockwell R F. The detection of vegetational change bymultitemporal analysis of Landsat data: the effects of goose foraging. Journal ofEcology,1998,86:93–99.
[10] Grover K, Quegan S and Freitas C D. Quantitative estimation of tropical forestcover by SAR. IEEE Trans. Geosci. Remote Sens.,1999,37:479–490.
[11] Collins R, Lipton A and Kanade T. Introduction to the special section on videosurveillance. IEEE Trans. Pattern Anal. Machine Intell.,2000,22(8):745–746.
[12] Stauffer C and Grimson W E. Learning patterns of activity using real-time tracking.IEEE Trans. Pattern Anal.Machine Intell..2000,22(8):747–757.
[13] Dumskyj M J, Aldington S J, Dore C J and Kohner E M. The accurate assessmentof changes in retinal vessel diameter using multiple frame electrocardio graphsynchronised fundus photography. Current Eye Research,1996,15(6):652–632.
[14] Rey D, Subsol G, Delingette H and Ayache N. Automatic detection andsegmentation of evolving processes in3D medical images: Application to multiplesclerosis. Medical Image Analysis,2002,6(2):163–179.
[15] Bosc M, Heitz F and Armspach J P. Automatic change detection in multimodalserial MRI: application to multiple sclerosis lesion evolution. Neuroimage,2003,20:643–656.
[16] Basavanhally A N, Ganesan S and Agner S. Computerized image-based detectionand grading of Lymphocytic Infiltration in HER2+breast cancer histopathology.IEEE Trans. Bio. Engin.,2010,57(3):642-653.
[17]李德仁．论21世纪遥感与GIS的发展．武汉大学学报：信息科学版,2005,28(2)：127—131.
[18] Loveland T R, Sohl T L, Stehman S V. A strategy for estimating the rates of recentUnited States land-cover changes. Photogrammetric Engineering and RemoteSensing,2002,68:1091–1099.
[19] Fung T. An assessment of TM imagery for land-cover change detection. IEEETrans. Geosci. Remote Sensing,1990,28(4):681–684.
[20] Joyce A T, Ivey G H and G.S.Burns. The use of Landsat MSS data for detectingland use changes in forestland. Proc. Of the14th Int. Sysposium on Remote Sensingof Environment, Ann Arbor, Michigan,1980.
[21] Hoffer R M and Lee K S. Forest change classification using SEASAT and SIR-Bsatellite SAR data. Proe.Of the1989,1989.
[22] Weismiller R A, Kristof S J, Scholz D K. Change detection in coastal zoneenvironments. Photogrammetric engineering and Remote Sensing,1997,43:1533-1539.
[23] Ghosh S, Bruzzone L, Patra S, Bovolo F and Ghosh A. A context-sensitivetechnique for unsupervised change detection based on Hopfield-type neuralnetworks. IEEE Trans. Geosci. Remote Sensing,2007,45(3):778–789.
[24] Patra S, Ghosh S, Ghosh A. Unsupervised change detection in remote-sensingimages using modified self-organizing feature map neural network, Int. Conf. onComputing: Theory and Applications (ICCTA-2007), Kolkata, India, IEEEComputer Society Press,2007:716–720.
[25] Chavez P S, MacKinnon D J. Automatic detection of vegetation changes in thesouthwestern United States using remotely sensed images. Photogram. Eng. RemoteSensing,1994,60(5):1285–1294.
[26] Bovolo F, Bruzzone L and Marchesi S. Analysis and adaptive estimation of theregistration noise distribution in multitemporal VHR images. IEEE Trans. Geosci.Rem. Sens.,2009,47(8):2658-2671.
[27] Bovolo F, Bruzzone L. A multilevel parcel-based approach to change detection invery high resolution multitemporal images. IEEE Int. Geosci. Remote Sens. Symp.,2005(3):2145–2148.
[28] Bovolo F. A multilevel parcel-based approach to change detection in very highresolution multitemporal images. IEEE Trans. Geosci. Rem. Sens. Let,2009,6(1):33-37.
[29] Lee J S. Digital image enhancement and noise filtering by use of local statistics.IEEE Trans. Pattern Anal. Mach. Intell.,1980, PAMI-2(2):165–168.
[30] Frost V S, Stiles J A, Shanmungan K S and Holtzman J C. A model for radarimages and its application to adaptive digital filtering of multiplicative noise. IEEETrans. Pattern Anal. Mach. Intell.,1982, PAMI-4(2):157–165.
[31] Kuan D T, Sawchuk A A, Strand T C and Chavel P. Adaptive noise smoothing filterfor images with signal-dependent noise. IEEE Trans. Pattern Anal.Mach. Intell.,1985, PAMI-7(2):165–177.
[32] Lopes A, Nerzy E, Touzi R and Laur H. Structure detection and statistical adaptivefiltering in SAR images. Int. J. Remote Sens.,1993,41:1735–1758.
[33] Bruzzone L and Prieto D. Automatic analysis of the difference image forunsupervised change detection. IEEE Trans. Geosci. Remote Sens.,2000,38(3):1171–1182.
[34] Bovolo F, Bruzzone L. A detail-preserving scale-driven approach to changedetection in multitemporal SAR images. IEEE Trans. Geosci. Remote Sens.,2005,43(12):2963-2972.
[35] Cihlar J, Pultz T J and Gray A L. Change detection with synthetic aperture radar.Int. J. Remote Sens.,1992,13:401–414.
[36] Hu H and Ban Y. Urban land-cover mapping and change detection with radarsatSAR data using neural network and rule-based classifiers. Int. Arch. Photogram.Rem. Sens. Spatial Info. Sci.37(Part B7), Beijing (2008).
[37] Martinis S, Twele A and Voigt S. Unsupervised extraction of Flood-Inducedbackscatter changes in SAR data using Markov image modeling on irregular graphs.IEEE Trans. Geosci. Remote Sens,2011,49(1):251-263.
[38] Fransson J E, Walter F, Blennow K, Gustavsson A. Detection of storm-damagedforested areas using airborne CARABAS-II VHF SAR image data. IEEE Trans.Geosci. Remote Sens.,2002,40(10):2170–2175.
[39] Simard M, Saatchi S. The use of decision tree and multiscale texture forclassification of JERS-1SAR data over tropical forest. IEEE Trans. Geosci. RemoteSens.,2000,33(5):2310-2321.
[40] Liew S C, Kam S P, Tuong T P, Chen P and Lim H. Application of multitemporalERS-1synthetic aperture radar in delineating rice cropping systems in the MekongRiver Delta, Vietnam. IEEE Trans. Geosci. Remote Sens.,1998,36(5):1412–1420.
[41] Townshend J and Justice C. Spatial variability of images and the monitoring ofchanges in the normalized difference vegetation index. International Journal ofRemote Sensing,1995,16:2187–2195.
[42]文贡坚.从新卫星遥感影像中自动发现变化区域.武汉大学博士后出站工作报告.2003.
[43] Celik T and Ma K. Unsupervised change detection for satellite images usingDual-Tree complex Wavelet transform. IEEE Trans. Geosci. Remote Sens.,2010,48(3):1199-2010.
[44] Bovolo F, Bruzzone L and Marconcini M. A novel approach to unsupervisedchange detection Based on a semisupervised SVM and a similarity measure. IEEETrans. Geosci. Remote Sens.,2008,46(7):2070-2082.
[45] Bovolo F, Camps-Valls G and Bruzzone L. A support vector domain method forchange detection in multitemporal images. Pattern Recognition Letters,2010,31(10):1148-1154.
[46] Bruzzone L and Carlin L. A multilevel context-based system for classification ofvery high spatial resolution images. IEEE Trans. Geosci.Remote Sens.,2006,44(9):2587–2600.
[47] Pacifici F, Del Frate F, Solimini C, and Emery W. An innovative neural-net methodto detect temporal changes in high-resolution optical satellite imagery. IEEE Trans.Geosci. Remote Sens.,2007,45(9):2940–2952.
[48] Camps-Valls G and Bruzzone L. Kernel-based methods for hyperspectral imageclassification. IEEE Trans. Geosci. Remote Sens.,2005,43(6):1351–1362.
[49] Kwon H and Nasrabadi N. Kernel orthogonal subspace projection for hyperspectralsignal classification. IEEE Trans. Geosci. Remote Sens.,2005,43(12):2952–2962.
[50] Samaniego L, Bardossy A and Schulz K. Supervised classification of remotelysensed imagery using a modified K-NN technique. IEEE Trans. Geosci. RemoteSens.,2008,46(7):2112–2125.
[51] Melgani F and Bruzzone L. Classification of hyperspectral remote sensing imageswith support vector machines. IEEE Trans. Geosci. Remote Sens.,2004,42(8):1778–1790.
[52] Stathakis D and Vasilakos A. Comparison of computational intelligence basedclassification techniques for remotely sensed optical image classification. IEEETrans. Geosci. Remote Sens.,2006,44(8):2305–2318.
[53] Moser G and Serpico S B. Automatic parameter optimization for support vectorregression for land and sea surface temperature estimation from remote sensing data.IEEE Trans. Geosci. Remote Sens.,2009,47(3):909–921.
[54] Schmidt F, Doute S and Schmitt B. Wavanglet: An efficient supervised classifierfor hyperspectral images. IEEE Trans. Geosci. Remote Sens.,2007,45(5):1374–1385.
[55] Grandi G D, Lucas R M and Kropacek J. Analysis by Wavelet frames of spatialstatistics in SAR data for characterizing structural properties of forests. IEEE Trans.Geosci. Remote Sens.,2009,47(2):494–507.
[56] Brera A M and Shahrokhi F. Application of Landsat data to monitor desertspreading in the Sahara region. Proc,of the12th Int．Symposium on Remote Sensingof Environment,Ann Arbor, Michigan,1978.
[57] Manavalan P, Kesavasamy K and Adiga S. Irrigated crops monitoring throughseasons using digital change detection analysis of1RD-LISS2data. Int．J．ofRemote Sensing,1995,16:633-640.
[58] Robinson W J. A critical review of the change detection and urban classificationliterature. Technical Memorandum CSC／TM-79／6235,Computer SciencesCorporation,Maryland,1979.
[59] Todd W J. Urban and regional land use change detected by using Landsat data.Journal of Research by the United States Geological Survey,1977,5:527-534.
[60] Weydahl D J. Change detection in SAR images. Geoscience and Remote SensingSymposium,1991:1421-1424.
[61] Bovolo F and Bruzzone L. A theoretical framework for unsupervised changedetection based on change vector analysis in the polar domain. IEEE Trans. Geosci.Remote Sens.,2007,45(1):218–236.
[62] Tian G. Sepctral signatures and vegetation indices of crops, Divisional RePort89/4,CSIRO Division of water Resource, Canberra,1989.
[63] Elvidge C D and Chen Z. Comparison of broad–band and narrow-band Red versusnear infrared vegetation indices. Remote Sensing of Environment,1995,54,38-48.
[64] Coiner J C. Using Landsat to monitor changed in vegetation cover induced bydesertification process. Proc. Of the14th int. symposium on remote sensing ofenvironment, ann arbor Michigan,1980.
[65] Nelson R F. Detection forest canopy change due to insect activity using LandsatMSS photogrammetric engineering and remote sensing,1983,49,1303-1314.
[66] Deng J S, Wang K, Deng Y H and Qi G J. PCA-based landuse change detection andanalysis using multitemporal and multisensor satellite data.Int. J. Remote Sens.,2008,29(16):4823–4838.
[67] Hanaizumi H, Okumura H and Fujimura S. Change detection from remotely sensedmulti-temporal images using spatial segmentation. Proc. Of the1991InternationalGeoscience and Remote Sensing Symposium(IGARSS91),1991:1079-1081.
[68] Jha C S and Unni N V M. Digital change detection of forest conversion of a drytropical forest region. Int. J. of Remote Sensing,1994,15:2543-2552.
[69] Dianat R and Kasaei S. Change detection in optical remote sensing images usingdifference-based methods and spatial information. IEEE Trans. Geosci. RemoteSens.,2010,7(1):215-219.
[70] Eghbali H J. K-S test for detecting changes from Landsat imagery data. IEEETransactions on Systems, Man and cybemetics,1979,9:17-23.
[71] Carincotte C, Derrode S and Bourennane S. Unsupervised change detection onSAR images using fuzzy hidden Markov chains. IEEE Trans. Geosci. Remote Sens.,2006,44(2):432-440.
[72] Deer P and Eklund P. Values for the fuzzy C-means classifier in change detectionfor remote sensing. Int. Conf. Information Processing and Management ofUncertainty,2002:187–194.
[73] Bazi Y, Melgani F, Bruzzone L and Vernazza G. A genetic expectation-maximization method for unsupervised change detection in multitemporal SARimagery international. Int. J. Remote Sens.,2009,30(24):6591-6610.
[74] Celik T. Changed detection in satellite images using a genetic algorithm approach.IEEE geosc. Remote Sens,2010,7(2):386-390.
[75] Bazi Y, Bruzzone L and Melgani F. An unsupervised approach based on thegeneralized Gaussian model to automatic change detection in multitemporal SARimages. IEEE Trans. Geosci. Remote Sens.,2005,43(4):874-887.
[76] Wang G T, Wang Y L and Jiao L C. Adaptive spatial neighborhood analysis andRayleigh-Gaussian distribution fitting for change detection in multi-temporal remotesensing images. Journal of Remote Sensing,2009,13(4):639-646.
[77] Moser G and Serpico S B. Generalized minimum-error thresholding forunsupervised change detection from SAR amplitude imagery. IEEE Trans. Geosc.Remote Sens.,2006,44(10):2972-2983.
[78] Celik T. Image change detection using Gaussian mixture model and geneticalgorithm. J. Vis. Commun. Image R.2010,21:965-974.
[79] Celik T. Bayesian change detection based on spatial sampling and Gaussianmixture model. Pattern Recognition Letters,2011,32:1635–1642.
[80] Kasetkasem K and Varshney P. An image change detection algorithm based onMarkov random field models. IEEE Trans. Geosci. Remote Sens.,2002,40(8):1815–1823.
[81] Melgani F and Bazi Y. MRF fusion approach to robust unsupervised changedetection in remote sensed imagery. IEEE Geosci. Remote Sens. Lett.,2006,3,(4):457–461.
[82] Celik T. Unsupervised multiscale change detection in multitemporal syntheticaperture radar images.17th European Signal Processing Conference,2009:1547-1551.
[83] Celik T. Multiscale change detection in multitemporal satellite images. IEEE Trans.Geosci. Remote Sens. Lett.,2009,6(4):820-824.
[84] Ding M, Tian Z, Jin Z, Xu M and Cao C X. Registration using robust kernelprincipal component for object-based change detection. IEEE Trans. Geosci.Remote Sens.,2010,7(4):761-765.
[85] Pacifici F. and Frate F D. Automatic change detection in Very High Resolutionimages with pulse-coupled neural networks. IEEE Trans. Geosci. Remote Sens.2010,4(1):58-62.
[86] Ma L, Zheng N, Yuan Z J and Zhang X T. A novel Dual-probe adaptive model forimage change detection. IEEE Signal Processing Letters,2010,17(10):863-866.
[87] Theiler J, Scovel C, Wohlberg B and Foy B R. Elliptically contoured distributionsfor anomalous change detection in hyperspectral Imagery. IEEE Trans. Geosci.Remote Sens. Lett.,2010,7(2):271-275.
[88] Bovolo F, Bruzzone L, Capobianco L, Garzelli A and Nencini F. Analysis of theeffects of pansharpening in change detection on VHR images. IEEE Trans. Geosci.Remote Sens.,2010,7(1):53-57.
[89]Sabry R. A new coherency formalism for change detection and phenomenology inSAR imagery: a field approach. IEEE Trans. Geosci. Remote Sens.,2009,6(3):458-462.
[90] Kita Y. A study of change detection from satellite images using joint intensityhistogram. Pattern Recognition,19th International Conference on Digital ObjectIdentifier,2008:1-4.
[91] Fisher A. The use of multiple measurements in taxonomic problems. Annals ofEugenics,7(2):179–188,1936.
[92] Zhao W, Nandhakumar N. Linear discriminant analysis of MPF for facerecognition. Proc. International Conference on Pattern Recognition,1998:185-188
[93] K. Marcel, D. Hans, K. Dietrich. Robustness of linear diseriminant analysis inautomatic speech recognition. The16th International Conference on patternRecognition,2002,3:371-374.
[94] Wilks S S. Mathematical statistics. Wiley, New York,1962:577-578.
[95] Duda R and Hart P. Pattern classification and scene analysis. Wiley, NewYork,1973.
[96] Foley D H, Sammon J W. An optimal set of discriminant vectors. IEEE TransCompute1975,24(3):281-289.
[97] Clausi D A. K-means iterative Fisher(KIF) unsupervised clustering algorithmapplied to image texture segmentation. Pattern Recognition,2002,35(9):1959-1972.
[98]陈果.图像阈值分割的Fisher准则函数法.仪器仪表学报,2003,24(6):564-567.
[99]童莹,邱晓晖.基于Fisher准则函数的二维阈值图像分割方法.电力系统通讯,2004,9:36-47
[100] Li L, Gong J, Chen W. Gray-level image thresholding based on Fisher linearprojection of two-dimensional histogram. Pattern Recognition,1997,30:743-749.
[101]刘永.基于Fisher准则的自适应图像分割算法.系统仿真技术,2009,5(3):161-165.
[102]温淑焕,唐英干.基于Fisher准则的多阈值图像分割方法.激光与红外,2008,38(7):741-744.
[103]张晶阳,刘夏.带有收敛因子的PSO-Fisher图像分割的方法.化工自动化及仪表,2010,37(12):93-95.
[104] Wu K L, Yu J and Yang M S. A novel fuzzy clustering algorithm based on afuzzy scatter matrix with optimality test. Pattern Recognition Letters,2005,26(5):639-652.
[105]曹苏群,王士同,陈晓峰等.基于模糊Fisher准则的半模糊聚类算法.电子与信息学报,2008,30(9):2162-2165.
[106]支晓斌,范九伦.基于模糊Fisher准则的自适应降维模糊聚类算法.电子与信息学报,2009,31(11):2653-2658.
[107] Mika S, Ratsch G, Weston J, Scholkopf B. Fisher discriminant analysis withkernels. IEEE Workshop on Neural Networks for Signal Processing.1999:41–48.
[108] Liu Q, Lu H and Ma S. Improving kernel Fisher discriminant analysis for facerecognition. IEEE Trans. Circuits Syst. Video Technol.,2004,14(1): pp.42–49.
[109]蔡自兴等.人工智能及其应用(第3版).北京:清华大学出版社,2003.
[110] Narendra K S. Identification and control of dynamic systems using neuralNetworks. IEEE Trans. On neural networks.1990, l(1):4-27.
[111]焦李成.神经网络系统理论.西安电子科技大学出版社,1995.
[112] Du H F, Jiao L C,Wang S A. clonal operator and antibody clone algorithms.Machine Learning and Cybernetics,2002,506–510.
[113] Moscato P. On evolution, search, optimization, genetic algorithms and martial arts:Towards memetic algorithms. Technical Report Caltech Concurrent ComputationProgram, Report826, California Institute of Technology, Pasadena, CA:1989.
[1] Singh A. Digital change detection techniques using remotely-sense data. Int. J.Remote Sens.,1989,10(6):989–1003.
[2] Lu D, Mausel P, Brondízio E and Moran E. Change detection techniques. Int. J.Remote Sens.,2004,25(2):2365–2407.
[3] Radke R J, Andra S, Al-Kofahi O and Roysam B. Image change detectionalgorithms: A systematic survey. IEEE Trans. Image Process.,2005,14(3):294–307.
[4] Foody G M. Monitoring the magnitude of Land-cover change around the southernlimits of the Sahara, photogramm.Eng.Remote Sens,2001,(67):841—847.
[5] Li Y, Zhao S and Zhao K. Land-cover changes in an Urban Lake Watershed in aMega-city, Central China. Environ. Monit. Assess.,2006,115(1-3):349—359.
[6] Ghosh S, Bruzzone L, Patra S, Bovolo F and Ghosh A. A context-sensitive techniquefor unsupervised change detection based on Hopfield-type neural networks. IEEETrans. Geosci. Remote Sensing,2007,45(3):778–789.
[7] Patra S, Ghosh S, Ghosh A. Unsupervised change detection in remote-sensingimages using modified self-organizing feature map neural network, Int. Conf. onComputing: Theory and Applications (ICCTA-2007), Kolkata, India, IEEEComputer Society Press,2007:716–720.
[8] Celik T and Ma K K. Unsupervised change detection for satellite images usingDual-Tree complex Wavelet transform. IEEE Trans. Geosci. Remote Sens.,2010,48(3):1199-2010.
[9] Fung T. An assessment of TM imagery for land-cover change detection. IEEE Trans.Geosci. Remote Sensing,28(4),1990:681–684.
[10] Bruzzone L and Carlin L. A multilevel context-based system for classification ofvery high spatial resolution images. IEEE Trans. Geosci.Remote Sens.,2006,44(9):2587–2600.
[11] Moser G and Serpico S B. Automatic parameter optimization for support vectorregression for land and sea surface temperature estimation from remote sensing data.IEEE Trans. Geosci. Remote Sens.,2009,47(3):909–921.
[12] Manavalan P, Kesavasamy K and Adiga S. Irrigated crops monitoring throughseasons using digital change detection analysis of1RD-LISS2data. Int．J．ofRemote Sensing,1995,16:633-640.
[13] Todd W J. Urban and regional land use change detected by using Landsat data.Journal of Research by the United States Geological Survey,1977,5:527-534
[14] Elvidge C D and Chen Z. Comparison of broad–band and narrow-band Red versusnear infrared vegetation indices. Remote Sensing of Environment,1995,54:38-48
[15] Deng J S, Wang K, Deng Y H and Qi G J. PCA-based landuse change detection andanalysis using multitemporal and multisensor satellite data.Int. J. Remote Sens.,2008,29(16):4823–4838.
[16] Bovolo F and Bruzzone L. A theoretical framework for unsupervised changedetection based on change vector analysis in the polar domain. IEEE Trans. Geosci.Remote Sens.,2007,45(1):218–236.
[17] Bruzzone L and Prieto D. Automatic analysis of the difference image forunsupervised change detection. IEEE Trans. Geosci. Remote Sens.,2000,38(3):1171–1182.
[18] Bazi Y, Bruzzone L and Melgani F. An unsupervised approach based on thegeneralized Gaussian model to automatic change detection in multitemporal SARimages. IEEE Trans. Geosci. Remote Sens.,2005,43(4):874-887.
[19] Wang G T, Wang Y L and Jiao L C. Adaptive spatial neighborhood analysis andRayleigh-Gaussian distribution fitting for change detection in multi-temporal remotesensing images, Journal of Remote Sensing,2009,13(4):639-646.
[20] Moser G and Serpico S B. Generalized minimum-error thresholding forunsupervised change detection from SAR amplitude imagery. IEEE Trans. Geosc.Remote Sens.,2006,44(10):2972-2983.
[21] Kasetkasem K and Varshney P. An image change detection algorithm based onMarkov random field models. IEEE Trans. Geosci. Remote Sens.,2002,40(8):1815–1823.
[22] Mallat S. A theory for multiresolution signal decomposition:The Waveletrepresentation. IEEE Trans.Patt.Anal.Machine Intell.1989,11(7):674-693
[23]张跃进,谢听.基于IHS和小波变换的遥感图像融合方法研究.华东交通大学学报,2008,25(1).49-52.
[24] Gunawan D. Denoising images using Wavelet transform. Proceedings of the IEEEPacific Rim Conference on Communications, Computers and Signal Processing.Victoria BC, USA,1999:83-85.
[25]谢杰成,张大力,徐文立著.小波图像去噪综述.中国图像图形学报,2002,7(3).209-217.
[26]潘泉,张磊,孟晋丽,张洪才著.小波滤波方法及应用.北京:清华大学出版社,2005.
[27] Bovolo F., Bruzzone L. A detail-preserving scale-driven approach to changedetection in multitemporal SAR images. IEEE Trans. Geosci. Remote Sens.,2005,43(12):2963-2972.
[28] Aas K, Eikvil L and Huseby R. Applications of hidden Markov chains in imageanalysis. Pattern Recognition,1999,32(4):703–713.
[29] Carincotte C, Derrode S and Bourennane S. Unsupervised change detection onSAR images using fuzzy hidden Markov chains. IEEE Trans. Geosci. Remote Sens.,2006,44(2):432-440.
[30] Choi H, Richard G. Multiscale image segmentation using Wavelet-domain hiddenMarkov models. IEEE Transactions on Image Processing,2001,10(9),1309-1321.
[31] Sha Y H, Cong L, Sun Q and Jiao L C. Unsupervised image segmenttation usingContourlet domain hidden Markov trees model. ICIAR2005,3656:32-39.
[1] Bazi Y, Melgani F, Bruzzone L and Vernazza G. A genetic expectation-maximizationmethod for unsupervised change detection in multitemporal SAR imageryinternational. Int. J. Remote Sens.,2009,30(24):6591-6610.
[2] Bazi Y, Bruzzone L, Melgani F. An unsupervised approach based on the generalizedGaussian model to automatic change detection in multitemporal SAR images. IEEETrans. Geosci. Remote Sens,2005,43(4):874-887.
[3] Bazi Y, Bruzzone L, Melgani F. Automatic Identification of the Number and Valuesof Decision Thresholds in the Log-ratio Image for Change Detection in SAR Images.IEEE Trans. Geosci. Remote Sens,2006,3(3):349-353.
[4] Bovolo F, Bruzzone L. A theoretical framework for unsupervised change detectionbased on change vector analysis in polar domain. IEEE Trans. Geosci. Remote Sens,2007,45(3):778-789.
[5] Kita Y. A study of change detection from satellite images using joint intensityhistogram. Pattern Recognition,19th International Conference on Digital ObjectIdentifier,2008:1-4.
[6] Sugiyama M. Dimensionality reduction of multimodal labeled data by local Fisherdiscriminant analysis. Machine Learning Research,2007,8:1027-1061.
[7] Wei L, Wang S J, Xu F F. Neighborhood margin Fisher discriminant analysis.Journal of Electronics&Information Technology,2009,31(3):509-513.
[8] Nummiaro K, Koller-Meier E, Van Gool L. An adaptive color-based particle filter.Image and Vision Computing,2002,21(1):99-110.
[9] Comaniciu D, Ramesh V, Meer P. Real-Time tracking of non-rigid objects usingmean shift. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR),2000,142-149.
[10] Comaniciu D, Meer P. Robust analysis of feature spaces: Color imagesegmentation. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR)1997:750-755.
[11] Zhou X S, Comaniciu D, Krishnan S. An information fusion framework for robustshape tracking. IEEE Trans. Pattern Anal. Machine Intell.,2005,27:115–129.
[12] Comaniciu D. A common framework for nonlinear diffusion, adaptive smoothing,bilateral filtering and mean shift. Image and Video Computing,2003,22(1):73-81.
[13] Comaniciu D, Meer P. Mean shift: A robust approach toward feature space analysis.IEEE Trans. on Pattern Analysis and Machine Intelligence,2002,24(5):603619.
[14] Li X R, Wu F C, Hu Z Y. Convergence of a mean shift algorithm. Journal ofSoftware,2005,16(3):365374.
[15] Christoudias C M, Georgescu B. Synergism in low level vision. The16th Int’l Conf.on Pattern Recognition,2002,4:150155.
[16] Fisher A. The use of multiple measurements in taxonomic problems. Annals ofEugenics,1936,7(2):179–188.
[17] Duda O, Hart P E, Stor D G. Pattern classification. Wiley, New York,2001.
[18]陈果.图像阈值分割的Fisher准则函数法.仪器仪表学报,2003,24(6):564-567.
[19]童莹,邱晓晖.基于Fisher准则函数的二维阈值图像分割方法.电力系统通讯,2004,9:36-47.
[20] Li L, Gong J, Chen W. Gray-level image thresholding based on Fisher linearprojection of two-dimensional histogram. Pattern Recognition,1997,30:743-749.
[21]刘永.基于Fisher准则的自适应图像分割算法.系统仿真技术,2009,5(3):161-165.
[22]温淑焕,唐英干.基于Fisher准则的多阈值图像分割方法.激光与红外,2008,38(7):741-744.
[23] Wang G T, Wang Y L, Jiao L C. Adaptive spatial neighborhood analysis andRayleigh-Gaussian distribution fitting for change detection in multi-temporal remotesensing images.Journal of Remote Sensing,2009,13(4):639-646.
[24] Bovolo F, Bruzzone L. A detail-preserving scale-driven approach to changedetection in multitemporal SAR images. IEEE Trans. Geosci. Remote Sens.,2005,43(12):2963-2972.
[1] Coppin P R, Jonckheere I, Nachaerts K. Digital change detection in ecosystemmonitoring: A review. Int. J. Remote Sens,2003,24:1–33.
[2] Lu D, Mausel P, Brondizio E.Change detection techniques. Int. J. Remote Sens,2004,25(12):2365–2407.
[3] Brera A M, Shahrokhi F. Application of Landsat data to monitor desert spreading inthe Sahara region. Proc, of the12th Int. Symposium on Remote Sensing ofEnvironment, Ann Arbor, Michigan,1978.
[4] Manavalan P, Kesavasamy K, Adiga S. Irrigated crops monitoring through seasonsusing digital change detection analysis of1RD-LISS2data. Int．J．of RemoteSensing,1995,16:633-640.
[5] Weydahl D J. Change detection in SAR images. Proc．of the1991Int．Geoscienceand Remote Sensing Symposium,1991:1421-1424.
[6] Robinson W J. A critical review of the change detection and urban classificationliterature. Technical Memorandum CSC／TM-79／6235, Computer SciencesCorporation, Maryland,1979.
[7] Deng J S, Wang K, Deng Y H and Qi G J. PCA-based landuse change detection andanalysis using multitemporal and multisensor satellite data.Int. J. Remote Sens,2008,29(16):4823–4838.
[8] Inglada J. Similarity measures for multisensor remote sensing images. Proc.IGARSS,2002,1:104–106.
[9] Fung T. An assessment of TM imagery for land-cover change detection. IEEE Trans.Geosci. Remote Sensing,28(4),1990:681–684.
[10] Derrode S, Mercier G, Pieczynski W. Unsupervised change detection in SARimages using a multicomponent hidden Markov chain model. Analysis ofMultiTemporal Remote Sensing Images,2003,(3):195–203.
[11] Deer P. Digital change detection in remotely sensed imagery using fuzzy set theory.Ph.D. thesis, Dept. Geography Comput. Sci, Univ.Adelaide, Australia,1998.
[12] Hegde S. Modeling land cover change:A fuzzy approach.M.S. thesis. Int. Inst.Geo-Inf. Sci. Earth Obs, Enschede, The Netherlands,2003.
[13] Nemmour H Y. Combining comparative and simultaneous analysis approachesbased on fuzzy integration for change detection. Proc.20th ISPRS Congress,Geo-Imagery Bridging Continents.
[14] Carincotte C, Derrode S, Bourennane S. Unsupervised change detection on SARimages using fuzzy hidden Markov chains. IEEE Trans. Geosci. Remote Sens,2006,44(2):432-440.
[15] Aas K, Eikvil L, Huseby R. Applications of hidden Markov chains in imageanalysis.Pattern Recognit,1999,32,(4):703–713.
[16] Kita Y. A study of change detection from satellite images using joint intensityhistogram. Pattern Recognition,19th International Conference on Digital ObjectIdentifier,2008:1-4.
[17] Fisher R A.The use of multiple measurements in taxonomic problems. Annals ofEugenics,1936,7(2):179一188.
[18] Wu K.L, Yu J, Yang M.S. A novel fuzzy clustering algorithm based on a fuzzyscatter matrix with optimality test. Pattern Recognition Letters,2005,26(5):639-652.
[19]曹苏群,王士同,陈晓峰等.基于模糊Fisher准则的半模糊聚类算法.电子与信息学报,2008,30(9):2162-2165.
[20]支晓斌,范九伦.基于模糊Fisher准则的自适应降维模糊聚类算法.电子与信息学报,2009,31(11):2653-2658.
[21] Buades A, Coll B, Morel J.M. A non local algorithm for image denoising. Proc.Comp. Vis. Pattern Recognition.2005,2:60-65.
[22] Bazi Y, Bruzzone L, Melgani F. An unsupervised approach based on thegeneralized gaussian model to automatic change detection in multitemporal SARimages. IEEE Trans. Geosci. Remote Sens,2005,43(4):874-887.
[23] Wang G T, Wang Y L, Jiao L C. Adaptive spatial neighborhood analysis andRayleigh-Gaussian distribution fitting for change detection in multi-temporal remotesensing images. Journal of Remote Sensing,2009,13(4):639-646.
[24] Bovolo F, Bruzzone L. A detail-preserving scale-driven approach to changedetection in multitemporal SAR images. IEEE Trans. Geosci. Remote Sens.,2005,43(12):2963-2972.
[1] Cihlar J, Pultz T J,Gray A L. Change detection with synthetic aperture radar. Int. J.Remote Sens,1992,13:401–414.
[2] Hu H,Ban Y. Urban land-cover mapping and change detection with radarsat SARdata using neural network and rule-based classifiers. Int. Arch. Photogram. Rem.Sens. Spatial Info, Beijing,2008.
[3] Martinis S, Twele A,Voigt S. Unsupervised extraction of Flood-Induced backscatterchanges in SAR data using Markov image modeling on irregular graphs. IEEE Trans.Geosci. Remote Sens,2011,49(1):251-263.
[4] Fransson J E, Walter F, Blennow K, Gustavsson A,Ulander L M H. Detection ofstorm-damaged forested areas using airborne CARABAS-II VHF SAR image data.IEEE Trans. Geosci. Remote Sens,2002,40(10):2170–2175.
[5] Coppin P R, Bauer M E. Processing of multitemporal Landsat TM imagery tooptimize extraction of forest cover change features. IEEE Trans. Geosci. RemoteSens,1994,33(4):918–927.
[6] Liew S C, Kam S P, Tuong T P, Chen P, Lim H. Application of multitemporal ERS-1synthetic aperture radar in delineating rice cropping systems in the Mekong RiverDelta, Vietnam. IEEE Trans. Geosci. Remote Sens,1998,36(5):1412–1420.
[7] Celik T. A Bayesian approach to unsupervised multiscale change detectioninsynthetic aperture radar images. Signal process,2010,90(5):1471-1147.
[8] Bazi Y, Melgani F, Bruzzone L, Vernazza G. A genetic expectation-maximizationmethod for unsupervised change detection in multitemporal SAR imageryInternational. Int. J. Remote Sens,2009,30(24):6591-6610.
[9] Bazi Y, Bruzzone L, Melgani F. An unsupervised approach based on the generalizedgaussian model to automatic change detection in multitemporal SAR images. IEEETrans. Geosci. Remote Sens,2005,43(4):874-888.
[10] Moser G, Serpico S B. Generalized minimum-error thresholding for unsupervisedchange detection from SAR amplitude imagery. IEEE Trans. Geosc. Remote Sens,2006,44(10):2972-2983.
[11] Bovolo F, Bruzzone L. A detail-preserving scale-driven approach to changedetection in multitemporal SAR images. IEEE Trans. Geosci. Remote Sens.,2005,43(12):2963-2972.
[12] Lee J S. Digital image enhancement and noise filtering by use of local statistics.IEEE Trans. Pattern Anal. Mach. Intell,1980,2(2):165–168.
[13] Frost V S, Stiles J A, Shanmungan K S,Holtzman J C. A model for radar imagesand its application to adaptive digital filtering of multiplicative noise. IEEE Trans.Pattern Anal. Mach. Intell,1982,4(2):157–165.
[14] Kuan D T, Sawchuk A A, Strand T C, Chavel P. Adaptive noise smoothing filter forimages with signal-dependent noise. IEEE Trans. Pattern Anal.Mach. Intell,1985,7(2):165–177.
[15] Lopes A, Nerzy E, Touzi R, Laur H. Structure detection and statistical adaptivefiltering in SAR images. Int. J. Remote Sens,1993,41:1735–1758.
[16] Villasenor D, Fatland D R, Hinzman L D. Change detection on Alaska’s north slopeusing repeat-pass ERS-1SAR imagery. IEEE Trans. Geosci. Remote Sens,1993,31(1):227–236.
[17] Wang G T, Wang Y L, Jiao L C. Adaptive spatial neighborhood analysis andRayleigh-Gaussian distribution fitting for change detection in multi-temporal remotesensing images. Journal of Remote Sensing,2009,13(4):639-646.
[18] Radke R. J.Image change detection algorithms: a systematic survey. IEEE Trans.I.P,2005,14(3):294-307.
[19] Melgani F, Bazi Y. MRF fusion approach to robust unsupervised change detectionin remote sensed imagery. IEEE Geosci. Remote Sens. Lett,2006,3(4):457–461.
[20] Pajares G. A Hopfield neural nework for image change detection. IEEE Trans.Neural network,2006,17(5):1250-1264.
[21] Bovolo F. A multilevel parcel-based approach to change detection in very highresolution multitemporal images. IEEE Geosci. Remote Sens. Lett,2009,6(1):33-37.
[22] Marchesi S, Bovolo F, Bruzzone L. A context-sensitive technique robust toregistration noise for change detection in VHR multispectral images. IEEE Trans.Image Processing,2010,19(7):1877-1889.
[23] Kita Y. A study of change detection from satellite images using joint intensityhistogram. Pattern Recognition,19th International Conference on Digital ObjectIdentifier,2008:1-4.
[24] Mallat S. A theory for multiresolution signal decomposition:The Waveletrepresentation. IEEE Trans.Patt.Anal.Machine Intell.1989,11(7):674-693.
[25] Xin F F, Jiao L C, Wang G. SAR images change detection based on Waveletdomain Fisher classifier.Infrared Millim.Waves,2011,30(2):173-178.
[26] Choi H, Richard G. Multiscale image segmentation using Wavelet-domain hiddenMarkov models. IEEE Trans. Image Processing,2001,10(9),1309-1321.
[27] Sha Y H, Cong L, Sun Q and Jiao L C. Unsupervised image segmenttation usingContourlet domain hidden Markov trees model. ICIAR2005,3656:32-39.
[28] Bovolo F, Camps-Valls G, Bruzzone L.A support vector domain method for changedetection in multitemporal images. Pattern Recognition Letters,2010,31(10):1148-1154.
[1] Radke R J. Image change detection algorithms: a systematic survey. IEEE Trans. I.P,2005,14(3):294-307.
[2] Celik T. A Bayesian approach to unsupervised multiscale change detection insynthetic aperture radar images. Signal process,2010,90(5):1471-1147.
[3] Bazi Y, Melgani F, Bruzzone L. A genetic expectation-maximization method forunsupervised change detection in multitemporal SAR imagery. International. Int. J.Remote Sens,2009,30(24):6591-6610.
[4] Bazi Y, Bruzzone L, Melgani F. An unsupervised approach based on the generalizedgaussian model to automatic change detection in multitemporal SAR images. IEEETrans. Geosci. Remote Sens,2005,43(4):874-888.
[5] Moser G, Serpico S B. Generalized minimum-error thresholding for unsupervisedchange detection from SAR amplitude imagery. IEEE Trans. Geosc. Remote Sens,2006,44(10):2972-2983.
[6] Bovolo F, Bruzzone L. A detail-preserving scale-driven approach to changedetection in multitemporal SAR images. IEEE Trans. Geosci. Remote Sens.,2005,43(12):2963-2972.
[7] Melgani F, Bazi Y. MRF fusion approach to robust unsupervised change detection inremote sensed imagery. IEEE Geosci. Remote Sens. Lett,2006,3,(4):457–461.
[8] Pajares G. A Hopfield neural nework for image change detection. IEEE. Trans.Neural network,2006,17(5):1250-1264.
[9] Bovolo F. A multilevel parcel-based approach to change detection in very highresolution multitemporal images. IEEE Geosci. Remote Sens. Lett,2009,6(1):33-37.
[10] Marchesi S, Bovolo F, Bruzzone L. A context-sensitive technique robust toregistration noise for change detection in VHR multispectral images. IEEE Trans. I.P,2010.
[11] Celik T. Changed detection in satellite images using a genetic algorithm approach,IEEE geosc. Remote Sens,2010,7(2):386-390.
[12] Mallat S. A theory for multiresolution signal decomposition:The Waveletrepresentation. IEEE Trans. Patt.Anal.Machine Intell,1989,11(7):674-693.
[13] Zhang X, Jiao L.C, Liu F. Spectral clustering ensemble applied to SAR imagesegmentation. IEEE Trans. Geosc. Remote Sens,2008,46(7):2126-2136.
[14] Nason G P, Silverman B W. The stationary Wavelet transform and some statisticalapplications. New York: Springer-Verlag,1995,103:281-300.
[15] Rumelhart D E, McClell J L. Parallel. distributed processing. Cambridge, Ma: MITpress,1986.
[16] Buades A, Coll B, Morel J M. A non-local algorithm for image denoising. IEEEComputer Vision and Pattern Recognition,2005,2:60-65.
[17] Celik T. Unsupervised change detection in satellite images using principalcomponent analysis and k-means clustering. IEEE Trans. Geosc. Remote Sens lett,2009,6(4):772-776.
[1] Lu D, Mausel P, Brondízio E, Moran E. Change detection techniques. Int. J. RemoteSens,2004,25(2):2365–2407.
[2] Celik T. A Bayesian approach to unsupervised multiscale change detection insynthetic aperture radar images. Signal process.2010,90(5):1471-1147.
[3] Bazi Y, Melgani F, Bruzzone L, Vernazza G. A genetic expectation-maximizationmethod for unsupervised change detection in multitemporal SAR imageryInternational. Int. J. Remote Sens,2009,30(24):6591-6610.
[4] Bazi Y, Bruzzone L, Melgani F. An unsupervised approach based on the generalizedGaussian model to automatic change detection in multitemporal SAR images. IEEETrans. Geosci. Remote Sens,2005,43(4):874-887.
[5] Moser G, Serpico S B. Generalized minimum-error thresholding for unsupervisedchange detection from SAR amplitude imagery. IEEE Trans. Geosc. Remote Sens,2006,44(10):2972-2983.
[6] Bruzzone L, Prieto D. Automatic analysis of the difference image for unsupervisedchange detection. IEEE Trans. Geosci. Remote Sens,2000,38(3):1171–1182.
[7] Wang G T, Wang Y L, Jiao L C. Adaptive spatial neighborhood analysis andRayleigh-Gaussian distribution fitting for change detection in multi-temporal remotesensing images. Journal of Remote Sensing,2009,13(4):639-646.
[8] Celik T. Image change detection using Gaussian mixture model and geneticalgorithm. J. Vis. Commun. Image R,2010,21:965-974.
[9] Celik T. Bayesian change detection based on spatial sampling and Gaussian mixturemodel, Pattern Recognition Letters,2011,32:1635–1642.
[10] Ghosh S, Bruzzone L, Patra S, Bovolo F, Ghosh A. A context-sensitive techniquefor unsupervised change detection based on Hopfield-type neural networks. IEEETrans. Geosci. Remote Sensing,2007,45(3):778–789.
[11] Hartigan A, Wong M. A K-means clustering algorithm. Appl. Statist,1979,28:100–108.
[12] Celik T. Changed detection in satellite images using a genetic algorithm approach.IEEE geosc. Remote Sens,2010,7(2):386-390.
[13]陈国良,王煦法等.遗传算法及其应用.北京：人民邮电出版社,1999.
[14] Du H F, Jiao L C, Wang S A. Clonal operator and antibody clone algorithms.Machine Learning and Cybernetics,2002,506–510.
[15] Moscato P. On evolution, search, optimization, genetic algorithms and martial arts:Towards memetic algorithms, Technical Report Caltech Concurrent ComputationProgram, Report826, California Institute of Technology, Pasadena, CA;1989.
[16] Elbeltagi E, Hegazy T, Grierson D. Comparison among five evolutionary-basedoptimization algorithms,Journal of Advanced Engineering Informatics, ElsevierScience,2005,19(1):43–53.
[17] Nguyen Q H, Ong Y S, Lim M H.A probabilistic memetic framework. IEEE,Transactions on Evolutionary Computation,2009,13(3):604-623.
[18]薛嘉庆.最优化原理与方法.北京:冶金工业出版社,1983.
[19]王凌.智能优化算法及其应用.北京:清华大学出版社,2001.
[20]李继东,张学杰.基于遗传算法的多维模糊分类器构造的研究.软件学报.2005,16(5):779~785.
[21]邢文训,谢金星.现代优化计算方法.北京：清华大学,1999.
[22] Ong Y S, Lim M H, Zhu N, Wong K W. Classification of adaptive memeticalgorithms: A comparative study. IEEE Trans. Syst, Man Cybern, Part B:Cybern,2006,36(1):141–152.
[23] Noman N, Iba H. Accelerating differential evolution using an adaptive local search.IEEE Trans. Evol. Comput,2008,12(1):107–125.
[24] Lozano M, Herrera F, Krasnogor N. Real-coded memetic algorithms with crossoverhill-climbing. Evol. Comput,2004,12(3):273–302.
[25] Krasnogor N, Smith J. A tutorial for competent memetic algorithms: Model,taxonomy, and design issues. IEEE Trans. Evol. Comput,2005,9(5):474–488.
[26] Jeong S, Hasegawa S, Shimoyama K, Obayashi S.Development and investigationof efficient GA/PSO-HYBRID algorithm applicable to real-world designoptimization. IEEE Comput. Intell. Mag,2009,4(3):36–44.
[27] Chiam S C, Tan K C, Mamun A. A memetic model of evolutionary PSO forcomputational finance applications. Expert Syst. Applicat,2009,36(2):3695–3711.
[28] Tan K C, Chiam S C. Balancing exploration and exploitation with adaptivevariation for evolutionary multi-objective optimization. Eur. J. Oper. Res,2009,197(2):701–713.
[29] Ang J H, Tan K C, Mamun A. An evolutionary memetic algorithm for ruleextraction. Expert Syst. Applicat,2010,37(2):1302–1315.
[30] Zhu Z, Ong Y. S, Dash M. Wrapper-filter feature selection algorithm using amemetic framework. IEEE Trans. Syst, Man, Cybern. B,2007,37(1):70–76.
[31] Hasan S, SARker R, Essam D, Cornforth D. Memetic algorithms for solvingjob-shop scheduling problems. Memetic Comput,2009,1(1):69–83.
[32] Batenburg K. An evolutionary algorithm for discrete tomography. Discrete Appl.Math,2005,151(1–3):36–54.
[33] Tirronen V, Neri F, K rkk inen T, Majava K, Rossi T. An enhanced memeticdifferential evolution in filter design for defect detection in paper production. Evol.Comput,2008,16(4):529–555.
[34] Gesù V. D, Bosco G. L, Millonzi F, Valenti C. A memetic algorithm for binaryimage reconstruction.in Lecture Notes in Computer Science,2008,4958:384–395.
[35] Gesù V. D, Bosco G L, Millonzi F, Valenti C. Discrete tomography reconstructionthrough a new memetic algorithm. Lecture Notes in Computer Science,2008,4974:347–352.
[36] Bovolo F, Bruzzone L. A detail-preserving scale-driven approach to changedetection in multitemporal SAR images. IEEE Trans. Geosci. Remote Sens.,2005,43(12):2963-2972.