基于纹理信息的高分辨率无人机遥感图像分割
|
摘要
虽然近年来高分辨率遥感影像数据呈现急剧性增长,但日益增长的数据需求与落后的影像分析技术之间的矛盾却越来越突出,造成的原因主要是落后的影像分析技术不能把原始的遥感影像数据转化为工程应用中所需的数据。图像分割是从图像处理到图像分析的关键步骤,在图像工程中占有重要的地位。所以有必要对图像分割相关的两个方面进行了一定的分析和改进。
第一个方面是向对象影像分割算法分析和改进。在分析了面向对象的边缘检测和区域增长法两种面向对象影像分割方法的基础上,重点对区域增长法从两个方面进行了改进:第一,设计了新的增长规则;第二,增加了异质点去除环节。这样使算法减少过分割现象并在抗噪声方面也得到提升,最终使图像分割质量得到了有效的提升。
第二个方面是对纹理信息提取技术的研究。对比分析了Tamura纹理和灰度共生矩阵两种纹理信息提取方法重点对灰度共生矩阵各参数对纹理特征的影响进行深入的研究。为了使通过共生矩阵能得到更合理的纹理特征,首先对10种纹理特征间的相关性进行分析,从而选出具有代表性的纹理。然后对开窗大小与各纹理特征的间的关系进行分析,从而为计算共生矩阵时的开窗大小选择提供依据。
最后按照前面的研究结果把纹理特征和光谱特征结合起来对高分辨率无人机遥感影像进行了面向对象的分割,并进行了相应的定性和定量分析。定量分析方面与不考虑纹理信息的分割结果通过优度实验法进行了对比研究。结果表明考虑了纹理信息的面向对象分割能更真实有效的反映图像中地物目标的整体结构,为进一步有效的地物分类提供保障。
The contradictions between the increasing need of Remote Sensing Image Data and Outdated image segmentation technology is becoming increasingly evident, altHough the amount of High-Resolution Remote Sensing data growing exponentially in recent years. The outmoded Image Analysis technologies can not convert Raw Remote Sensing Image Data to be useful data for application in Engineering is tHough to be the major reason. Image segmentation is a key step in image processing and image analysis. So, it is necessary to renew the knowledge of Relevant Technologies and make improve, which include texture analysis and image segmentation algorithm in this thesis.
Study on Object-oriented Segmentation algorithm of Remote Sensing Image. Based on the analysis of the edge detection and Seeded Region Growing algorithm, a new algorithm was brought up, which is different from classical algorithm in two aspects:First, a new criterion of region growing is designed. Secondly, we propose a region merging rules based on the area and contrast, which can restrain the over-segmentation problem effectively and improve the anti-noise ability. Experiment results indicate that the method can improve the quality of image segmentation.
Study on texture information extraction technologies. The Comparison of the two kind of Texture information extraction technology was carried out. Through the study on the correlation of the 11 texture feature and the effect of the window size on texture features quality, a scientific basis for choosing texture feature and the optimum window size was presented.
According to the Research above, a texture image segmentation algorithm based on object-oriented which combines texture features and spectral characteristics was presented. In order to verify the accuracy of image segmentation, the new algorithm was applied to segmenting UAVRS images and a comparison between this approach and classical classification approaches has been carried out. The study conclusion shows that the new method is and more reliable comprehensive in reflecting the ground objects in the image.
第一个方面是向对象影像分割算法分析和改进。在分析了面向对象的边缘检测和区域增长法两种面向对象影像分割方法的基础上,重点对区域增长法从两个方面进行了改进:第一,设计了新的增长规则;第二,增加了异质点去除环节。这样使算法减少过分割现象并在抗噪声方面也得到提升,最终使图像分割质量得到了有效的提升。
第二个方面是对纹理信息提取技术的研究。对比分析了Tamura纹理和灰度共生矩阵两种纹理信息提取方法重点对灰度共生矩阵各参数对纹理特征的影响进行深入的研究。为了使通过共生矩阵能得到更合理的纹理特征,首先对10种纹理特征间的相关性进行分析,从而选出具有代表性的纹理。然后对开窗大小与各纹理特征的间的关系进行分析,从而为计算共生矩阵时的开窗大小选择提供依据。
最后按照前面的研究结果把纹理特征和光谱特征结合起来对高分辨率无人机遥感影像进行了面向对象的分割,并进行了相应的定性和定量分析。定量分析方面与不考虑纹理信息的分割结果通过优度实验法进行了对比研究。结果表明考虑了纹理信息的面向对象分割能更真实有效的反映图像中地物目标的整体结构,为进一步有效的地物分类提供保障。
The contradictions between the increasing need of Remote Sensing Image Data and Outdated image segmentation technology is becoming increasingly evident, altHough the amount of High-Resolution Remote Sensing data growing exponentially in recent years. The outmoded Image Analysis technologies can not convert Raw Remote Sensing Image Data to be useful data for application in Engineering is tHough to be the major reason. Image segmentation is a key step in image processing and image analysis. So, it is necessary to renew the knowledge of Relevant Technologies and make improve, which include texture analysis and image segmentation algorithm in this thesis.
Study on Object-oriented Segmentation algorithm of Remote Sensing Image. Based on the analysis of the edge detection and Seeded Region Growing algorithm, a new algorithm was brought up, which is different from classical algorithm in two aspects:First, a new criterion of region growing is designed. Secondly, we propose a region merging rules based on the area and contrast, which can restrain the over-segmentation problem effectively and improve the anti-noise ability. Experiment results indicate that the method can improve the quality of image segmentation.
Study on texture information extraction technologies. The Comparison of the two kind of Texture information extraction technology was carried out. Through the study on the correlation of the 11 texture feature and the effect of the window size on texture features quality, a scientific basis for choosing texture feature and the optimum window size was presented.
According to the Research above, a texture image segmentation algorithm based on object-oriented which combines texture features and spectral characteristics was presented. In order to verify the accuracy of image segmentation, the new algorithm was applied to segmenting UAVRS images and a comparison between this approach and classical classification approaches has been carried out. The study conclusion shows that the new method is and more reliable comprehensive in reflecting the ground objects in the image.
引文
[1] http://www.wangchao.net.cn/bbsdetail_860589.html科普:我国遥感技术国际领先
[2] ZhaoY,Zhang L,Li P,et al.Classification of High Spatial Resolution Imagery Using Improved Gaussian Markov Random-Field-Based Texture Features. IEEE Transactions on Geoscience and Remote Sensing,2007,45(5):1458-1468.
[3]张顺谦,杨秀蓉.神经网络和分形纹理在夜间云雾分离中的应用.遥感学报,2006,10(4):497-502.
[4]黄桂兰,郑肇葆.航片影像纹理分类方法的探讨.测绘通报,1997,(6):38-41.
[5]黄桂兰.影像纹理分类的马尔可夫随机场法与实验研究.中国图形图像学报,1999,4(4):317-320.
[6]朱长青,杨晓梅.具有更佳分辨率小波分解的遥感影像纹理分类.地理研究,1997,16(1):53-58.
[7] Pichler O,Teuner A,Hosticka B J.A Comparison of Texture Feature Extraction Using Adaptive Gabor Filter,Pyramidal and Tree Structured Wavelet Transforms. Pattern Recognition.1996, 29(5):733-742.
[4]朱彩英,蓝朝祯,靳国旺.纹理图象亮度闭值法提取SAR图象居民地.中国图象图形学报,2003,8(6):616-620.
[5]刘丽,匡纲要.图像纹理特征提取方法综述.中国图像图形学报,2009,14(4):622-633.
[6] CrossG R,Jain A K. Markov random field texture models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1983, 5(1):25-39.
[7] McCormick BH,Jayaramamurthy SN. Time series model for texture synthesis. International Journal of Computer Information Science, 1974, 3(4): 329-343.
[8] Randen T,Husoy JH. Filtering for texture classification: A comparative study. IEEE Transactions on Pattern Analysis and Machine Intelligence,1999,21(4): 291-310·
[9] Soille P. Morphological Image Analysis:Principles and Applications.Berlin, Germany: Springer Press, 2003.
[10] Miranda F P,MacDonald J A, Carr J R.Application of the semivariogram textural classifier(STC) for vegetation discrimination Using SIR-B data of Borneo. International Journal of Remote Sensing, 1992,13(12): 2349-2354.
[11]吴刚,杨敬安,王洪燕.一种基于变差函数的纹理图像分割方法.电子学报,2001,29(1):44-47.
[12] Ohanian PP,Dubes RC. Performance evaluation for four classes of textural features. Pattern Recognition,1992,25(8): 819-833·
[13] Clausi DA,Yue B. Comparing co-occurrence probabilities and markov random fields for texture analysis of SAR sea ice imagery.IEEE Transactions on Geoscience and Remote Sensing, 2004,42(1): 215-228.
[14] Clausi DA. Comparison and fusion of co-occurrence,Gabor and MRF texture for classification of SAR sea ice imagery. Atmosphere Oceans, 2001,39(4): 183-194.
[15]王建芳,包世泰,面向对象解译方法在遥感影像地物分类中的应用,热带地理,2006,26(3):234-242.
[16]黄慧萍.面向对象影像分析中的尺度问题研究:[博士学位论文]中国科学院遥感应用研究所,2003.
[17] Definients Image GmbH., eCognition User Guide,1999, Germany
[18]姚敏.数字图像处理.北京:机械工业出版社,2006.
[19]甘勇,马芳,熊坤.基于遗传算法和梯度算子的图像边缘检测.微计算机信息,2007,213(2):306-308.
[20]徐建华.图像处理与分析.北京:科学出版社,1992.
[21]崔屹.数字图像处理与技术.北京:电子工业出版社,1997.
[22]王润生.图像理解.长沙:国防科技大学出版社,1994.
[23]周新论,柳健,刘华志.数字图像处理.北京:国防工业出版社,1984.
[24]孙朝明,伏德贵.面向对象的边缘检测方法.机电一体化.2003,6:25-27
[25]周长发.精通Visual C++图像编程.北京:电子工业出版社2000.
[26] Hough P. V. Machine analysis of bubble chamber pictures. Proceedings of Int Conf High Energy Accelerators and Instrumentation. Switzerland: Geneva, 1959,554-556.
[27] P V C. Hough Method and means for recognizing complex patterns:USA, 3069654. 1962.
[28] DUDA R O, Hart P E. Use of the HT to detect lines and curves in picture. Comm ACM, 1972,15:11-15.
[29]杜艳红,张伟玉,常若葵等.基于Hough变换的线段检测算法的改进.天津农学院学报,2007,14(2):33-36.
[30]乔洁,李京华,杨志荣.基于Hough变换的道路边缘提取.交通与计算机,2008,1(26):62-64.
[31]张卫,杜尚丰.Hough变换在农田机械视觉导航中的应用.仪器仪表学报,2005,26(8)增:706-707.
[32]易玲.基于分级的快速霍夫变换直线检测.微计算机信息,2007,23(11):206-208.
[33] R Adams,L Bischof. Seeded region growing. IEEE Transactions on Pattern Analysis and Machine Intelligenee.1994,16(6):641-647.
[34]李政国.基于区域增长法的高空间分辨率遥感图像分割与实现:[优秀硕士学位论文].南宁:广西大学,2008.
[35]章毓晋.图象分割.科学出版社,北京,2000:1-4.
[36] John R,Smith and Shih-Fu Chang. Automated binary texture feature sets for image retrieval. In Proc. IEEE Int. Conf. Acoust., Speech, and Signal Proc., May 1996.
[37] Robert M. Haralick, K. Shanmugam, and Its’hak Dinstein. Texture features for image classification. IEEE Trans. On Sys, Man, and Cyb, SMC-3(6):610-621, 1973.
[38] R M Haralick.Statistical and Structural Approaches to Texture. Proc.IEEE,1979,67:786-804
[39] Hideyuki Tamura,et al.Texture Features Corresponding to Visual Pereception. IEEE Trans. On Systems,Man and Cybernetics,1978,8(6):460-473
[40]刘继敏.基于形状图象检索的研究:[博士学位论文].北京:中国科学院研究生院,2000.
[41] Ojala T,Pietik?inen M,Harwood D.A comparative study of texture measures with classification based on feature distributions. Pattern Recognition, 1996,29(1):51-59.
[42] Kenneth R Castleman.Digital image processing.Englewood cliff: Prentice Hall Press,1996.
[43] Dong-Chen He,Li Wang.Texture features based on texture spectrum. Pattern Recognition, 1991,24(5):391-399.
[44] H Tamura, S Mori, and T Yamawaki. Texture features corresponding to visual perception, IEEE Trans. On Systems, Man, and Cybernetics, vol. Smc-8, no. 6, June 1978.
[45] Niblack, et al.The QBIC project: querying images by content using color, texture, and shape.Proc of SPIE, Storage.and Retrieval for Image and Video Databases, Vol. 1908, February 1993, San Jose, pp. 173-187.
[46]朱彩英,蓝朝桢,靳国旺.纹理图像亮度阈值法提取SAR图像居民地.中国图像图形学报, 2003,8(6): 616-619.
[47] Haralick R, Shanmugam K, Dinstein I. Textural feature for image classification. IEEE Transactions on System, Man and Cybernetics, 1973, 3(6):610-621.
[48] Baraldi A, Parmiggiani F. An investigation of the textual characteristics associated with gray level co-occurrence matrix statistical parameters. IEEE Transactions on Geoscience andRemote Sensing, 1995,33(2): 293-304.
[49]薄华,马缚龙,焦李成.图像纹理的灰度共生矩阵计算问题的分析.电子学报,2006,34(1): 155-158.
[50]于海鹏,刘一星,王金满,张斌.木材表面纹理的灰度共生矩阵分析.哈尔滨:中国林学会木材科学分会第九次学术研讨会论文集,2004:314-322.
[51]苑丽红,杨勇,苗静.灰度共生矩阵提取纹理特征的实验结果分析.计算机应用,2009,29(4):1018-1021.
[52]章毓晋.图像工程.北京:清华大学出版社,2006,178-180
[53]王坤.数字图像分割和质量评价方法的研究:[优秀硕士学位论文].沈阳:东北大学,2006.
[54]刘锁兰,王洪元,程起才,等.基于优度法的图像分割性能评价.江南大学学报(自然科学版),2009,8(5):516-519.
[55]明冬萍,骆剑承,周成虎,等.高分辨率遥感影像特征分割及算法评价分析.地球信息科学.2006,8(1):103-109.
[2] ZhaoY,Zhang L,Li P,et al.Classification of High Spatial Resolution Imagery Using Improved Gaussian Markov Random-Field-Based Texture Features. IEEE Transactions on Geoscience and Remote Sensing,2007,45(5):1458-1468.
[3]张顺谦,杨秀蓉.神经网络和分形纹理在夜间云雾分离中的应用.遥感学报,2006,10(4):497-502.
[4]黄桂兰,郑肇葆.航片影像纹理分类方法的探讨.测绘通报,1997,(6):38-41.
[5]黄桂兰.影像纹理分类的马尔可夫随机场法与实验研究.中国图形图像学报,1999,4(4):317-320.
[6]朱长青,杨晓梅.具有更佳分辨率小波分解的遥感影像纹理分类.地理研究,1997,16(1):53-58.
[7] Pichler O,Teuner A,Hosticka B J.A Comparison of Texture Feature Extraction Using Adaptive Gabor Filter,Pyramidal and Tree Structured Wavelet Transforms. Pattern Recognition.1996, 29(5):733-742.
[4]朱彩英,蓝朝祯,靳国旺.纹理图象亮度闭值法提取SAR图象居民地.中国图象图形学报,2003,8(6):616-620.
[5]刘丽,匡纲要.图像纹理特征提取方法综述.中国图像图形学报,2009,14(4):622-633.
[6] CrossG R,Jain A K. Markov random field texture models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1983, 5(1):25-39.
[7] McCormick BH,Jayaramamurthy SN. Time series model for texture synthesis. International Journal of Computer Information Science, 1974, 3(4): 329-343.
[8] Randen T,Husoy JH. Filtering for texture classification: A comparative study. IEEE Transactions on Pattern Analysis and Machine Intelligence,1999,21(4): 291-310·
[9] Soille P. Morphological Image Analysis:Principles and Applications.Berlin, Germany: Springer Press, 2003.
[10] Miranda F P,MacDonald J A, Carr J R.Application of the semivariogram textural classifier(STC) for vegetation discrimination Using SIR-B data of Borneo. International Journal of Remote Sensing, 1992,13(12): 2349-2354.
[11]吴刚,杨敬安,王洪燕.一种基于变差函数的纹理图像分割方法.电子学报,2001,29(1):44-47.
[12] Ohanian PP,Dubes RC. Performance evaluation for four classes of textural features. Pattern Recognition,1992,25(8): 819-833·
[13] Clausi DA,Yue B. Comparing co-occurrence probabilities and markov random fields for texture analysis of SAR sea ice imagery.IEEE Transactions on Geoscience and Remote Sensing, 2004,42(1): 215-228.
[14] Clausi DA. Comparison and fusion of co-occurrence,Gabor and MRF texture for classification of SAR sea ice imagery. Atmosphere Oceans, 2001,39(4): 183-194.
[15]王建芳,包世泰,面向对象解译方法在遥感影像地物分类中的应用,热带地理,2006,26(3):234-242.
[16]黄慧萍.面向对象影像分析中的尺度问题研究:[博士学位论文]中国科学院遥感应用研究所,2003.
[17] Definients Image GmbH., eCognition User Guide,1999, Germany
[18]姚敏.数字图像处理.北京:机械工业出版社,2006.
[19]甘勇,马芳,熊坤.基于遗传算法和梯度算子的图像边缘检测.微计算机信息,2007,213(2):306-308.
[20]徐建华.图像处理与分析.北京:科学出版社,1992.
[21]崔屹.数字图像处理与技术.北京:电子工业出版社,1997.
[22]王润生.图像理解.长沙:国防科技大学出版社,1994.
[23]周新论,柳健,刘华志.数字图像处理.北京:国防工业出版社,1984.
[24]孙朝明,伏德贵.面向对象的边缘检测方法.机电一体化.2003,6:25-27
[25]周长发.精通Visual C++图像编程.北京:电子工业出版社2000.
[26] Hough P. V. Machine analysis of bubble chamber pictures. Proceedings of Int Conf High Energy Accelerators and Instrumentation. Switzerland: Geneva, 1959,554-556.
[27] P V C. Hough Method and means for recognizing complex patterns:USA, 3069654. 1962.
[28] DUDA R O, Hart P E. Use of the HT to detect lines and curves in picture. Comm ACM, 1972,15:11-15.
[29]杜艳红,张伟玉,常若葵等.基于Hough变换的线段检测算法的改进.天津农学院学报,2007,14(2):33-36.
[30]乔洁,李京华,杨志荣.基于Hough变换的道路边缘提取.交通与计算机,2008,1(26):62-64.
[31]张卫,杜尚丰.Hough变换在农田机械视觉导航中的应用.仪器仪表学报,2005,26(8)增:706-707.
[32]易玲.基于分级的快速霍夫变换直线检测.微计算机信息,2007,23(11):206-208.
[33] R Adams,L Bischof. Seeded region growing. IEEE Transactions on Pattern Analysis and Machine Intelligenee.1994,16(6):641-647.
[34]李政国.基于区域增长法的高空间分辨率遥感图像分割与实现:[优秀硕士学位论文].南宁:广西大学,2008.
[35]章毓晋.图象分割.科学出版社,北京,2000:1-4.
[36] John R,Smith and Shih-Fu Chang. Automated binary texture feature sets for image retrieval. In Proc. IEEE Int. Conf. Acoust., Speech, and Signal Proc., May 1996.
[37] Robert M. Haralick, K. Shanmugam, and Its’hak Dinstein. Texture features for image classification. IEEE Trans. On Sys, Man, and Cyb, SMC-3(6):610-621, 1973.
[38] R M Haralick.Statistical and Structural Approaches to Texture. Proc.IEEE,1979,67:786-804
[39] Hideyuki Tamura,et al.Texture Features Corresponding to Visual Pereception. IEEE Trans. On Systems,Man and Cybernetics,1978,8(6):460-473
[40]刘继敏.基于形状图象检索的研究:[博士学位论文].北京:中国科学院研究生院,2000.
[41] Ojala T,Pietik?inen M,Harwood D.A comparative study of texture measures with classification based on feature distributions. Pattern Recognition, 1996,29(1):51-59.
[42] Kenneth R Castleman.Digital image processing.Englewood cliff: Prentice Hall Press,1996.
[43] Dong-Chen He,Li Wang.Texture features based on texture spectrum. Pattern Recognition, 1991,24(5):391-399.
[44] H Tamura, S Mori, and T Yamawaki. Texture features corresponding to visual perception, IEEE Trans. On Systems, Man, and Cybernetics, vol. Smc-8, no. 6, June 1978.
[45] Niblack, et al.The QBIC project: querying images by content using color, texture, and shape.Proc of SPIE, Storage.and Retrieval for Image and Video Databases, Vol. 1908, February 1993, San Jose, pp. 173-187.
[46]朱彩英,蓝朝桢,靳国旺.纹理图像亮度阈值法提取SAR图像居民地.中国图像图形学报, 2003,8(6): 616-619.
[47] Haralick R, Shanmugam K, Dinstein I. Textural feature for image classification. IEEE Transactions on System, Man and Cybernetics, 1973, 3(6):610-621.
[48] Baraldi A, Parmiggiani F. An investigation of the textual characteristics associated with gray level co-occurrence matrix statistical parameters. IEEE Transactions on Geoscience andRemote Sensing, 1995,33(2): 293-304.
[49]薄华,马缚龙,焦李成.图像纹理的灰度共生矩阵计算问题的分析.电子学报,2006,34(1): 155-158.
[50]于海鹏,刘一星,王金满,张斌.木材表面纹理的灰度共生矩阵分析.哈尔滨:中国林学会木材科学分会第九次学术研讨会论文集,2004:314-322.
[51]苑丽红,杨勇,苗静.灰度共生矩阵提取纹理特征的实验结果分析.计算机应用,2009,29(4):1018-1021.
[52]章毓晋.图像工程.北京:清华大学出版社,2006,178-180
[53]王坤.数字图像分割和质量评价方法的研究:[优秀硕士学位论文].沈阳:东北大学,2006.
[54]刘锁兰,王洪元,程起才,等.基于优度法的图像分割性能评价.江南大学学报(自然科学版),2009,8(5):516-519.
[55]明冬萍,骆剑承,周成虎,等.高分辨率遥感影像特征分割及算法评价分析.地球信息科学.2006,8(1):103-109.