基于多尺度特征的图像匹配与目标定位研究
|
摘要
水下环境的复杂性使得水下图像的信息量缺乏,给目标识别和定位带来一定障碍,特别是对于非结构化目标的提取与识别存在很大的困难,这也是当前水下信息处理领域研究的热点之一。由于多尺度真实地反映出现实世界的表现形式,因此受到了学界的广泛重视。目前对尺度的概念有多种解释,如采用不同分辨率作为图像尺度的,也有以图像尺寸大小为尺度的,有的以距离远近作为尺度,还有以卷积核的参数为尺度。本文以海底目标为研究对象,重点研究了基于高斯尺度空间的非结构目标多尺度模型的建立,多尺度特征的提取,多尺度特征的图像匹配以及在水下非结构目标定位中的应用。
论文首先回顾了基于视觉的水下多尺度理论的发展及现状,讨论了多尺度的定义及其基本理论,阐明了不同的尺度表达模型的特点。重点研究了高斯尺度空间理论,高斯尺度空间成为图像研究中的一个重要方面,是由于高斯尺度空间理论简单以及高斯函数本身的许多独特性质。通常的尺度变换会随着尺度的增加图像越来越模糊,更多的细节被丢失,采用高斯差函数可以保留这些细节信息。在高斯尺度空间的构造中正确选用尺度参数,以使图像信息的变化呈现均匀的特点显得尤其重要。目前许多高斯尺度空间应用中采用的层之间的尺度参数关系并不明确,使得分层效果不理想。论文基于视觉特征模型提出一种自适应高斯尺度参数的算法,并通过试验验证了它的有效性,从而为图像的高层次处理如目标识别等提供信息量稳定变化的尺度空间。
尺度不变性是衡量特征提取算法的一个重要因素。针对水下图像噪声大的特点,本文提出了具有抗噪特性的尺度不变特征提取算法,算法是建立在Harris角点特征和高斯尺度空间的基础之上,在不同尺度下提取同一目标的Harris角点,从最高层的特征点开始往下搜索它们的对应点,本文还给出了该算法下求特征尺度的方法,实验表明多尺度特征点具有较强的抗噪能力和尺度不变性,且计算量少。SIFT(ScaleInvariant Feature Transform)算子因其具有良好的尺度、旋转、光照等不变特性而在图像匹配中得到广泛的应用,本文给出了水下图像的SIFT特征提取效果。结合熵的理论,本文给出多尺度熵的定义,并在此基础上通过多尺度熵差提取了水下烟囱图像的外部轮廓。
本文接着研究了基于SIFT算法的水下图像匹配技术。为了增加匹配数,我们分析了彩色图像特征检测的可行性,指出了此算法在彩色图像处理中的应用潜力,并为后续工作提供借鉴及参考。针对SIFT算法采用128维向量来表征一个特征点导致计算量过大的缺陷,本文给出了基于圆形窗口的SIFT简化算法,对每个特征点只采用12维特征向量表示,在不明显降低匹配数量的同时,较大提高了计算机处理的实时性。同时,由于原算法中主方向的获得是通过对8维方向向量的统计获得,导致主方向产生量化误差,简化的SIFT算法由于采用圆形窗口,不存在量化误差,因此旋转不变性优于原算法,实验结果也验证了该结论。
论文最后讨论了上述研究成果在目标定位中的应用。首先描述坐标之间的转化关系以及多种相机标定方法,并采用Zhang的平面标定算法对相机进行内部参数标定;再利用SIFT特征匹配方法求得稳定的匹配点对求得基本矩阵与本质矩阵,分解后得到单目相机的外部运动参数,通过采用立体视觉方法和运动恢复结构SFM(structure from motion)方法得到目标的三维信息,实现目标的定位。本章最后给出了目标三维信息获取的流程和计算机仿真,实验结果表明了本文方法能够满足水下机器作业的精度要求。
本文针对水下机器人作业中基于视觉的目标定位问题开展了一系列的研究工作,其研究成果可为水下智能机器人作业提供理论依据和技术手段。
The complexity of the underwater environment results in the problem of lacking information underwater,which lead to the high difficulty in dealing with object recognition and localization. The situation becomes even worse when we wish to extract the features of non-structural object and recognize it.The multi-scale representation has attracted considerable attention recently since it describes the the performance of the real world. At present, there are a variety of explanations about the concept of scale such as resolution, image size, quantitative, the distance and convolution kernel and so on. This dissertation aims at the seafloor object and undertakes some works such as constructing the multi-scale model, multi-scale feature extraction, the image matching , the application of object localization and so on.The research is based on Gaussian scale space in the underwater environment.
Firstly, the development and present situation of vision-based multi-scale theory underwater were reviewed, and the definition of multi-scale and its basic theory are discussed. Then the characteristics of different scale model are introduced. We focus on the Gaussian scale space theory. Gaussian scale-space is an important domain in image study. Because of the simplicity of the theory and the unique property of Gaussian function, Gaussian scale-space is applied in scale-space theory. As the scale increases, more and more information is lost. Those information can be preserved by DOG function (Difference of Gaussian). It is crucial to choose appropriate scale parameter during constructing Gaussian scale-space.At present, Many applications in Gaussian scale-space about the scale parameter is not clear, which may lead to bad effect of layer. The paper proposes a kind of adaptive algorithm of scale parameter in terms of the module of visual characters. Experimental results show that the uniformly distributed information in scale-space will be useful for higher-level image processing technologies such as object recognition.
Scale invariance is a key factor to evaluate the feature extraction algorithm. For the noise of underwater image, a kind of scale-invariant feature extraction algorithm is proposed which hold the anti-noise characteristics and based on Harris comer and Gaussian scale space.We extract the Harris corners in different scale. Then, the points detected at the highest level of the pyramid are correctly propagated to the lower level. The corners detected repeatedly in different levels are chosen as final feature points. At last, the characteristic scale is obtained based on maximum entropy method. The experimental results show that the algorithm has low computation cost, strong anti-noise capability and excellent performance in the presence of significant scale changes. Due to the invariance of scale、rotation、illumination,SIFT (Scale Invariant Feature Transform) descriptor was commonly used in image matching domain. Feature extraction experiments are carried out with SIFT.Conbined with traditional Entropy a concept of Multi-Scale Entropy was given. The non-structural object contours of the hydrothermal chminey undersea are extracted with the advantages of the Maximal Multi-Scale Entropy Difference (MMSED), which provides the basis for the following processing.
We next mainly discuss the matching methods in underwater environment based on SIFT. In order to increase the number of matches,color feature extraction is analyzed. The potential value of the method in the color image is presented,which can provide reference to the future work. However, the fact the presentation of one feature point needs 128 dimensions that will reduce the algorithm efficiency of real-time.we develope a simplified algorithm based on SIFT (SSIFT) to express a feature point with only 12 dimensions which based on a circular window to improve the efficiency of matching. The experiment results show that the algorithm can reduce the rate of time complexity and maintaining a relatively good matching rate at the same time.Furthermore, there is no quantization errors in SSfFT which exist in SIFT resulted by orientation assignment.
Finally, we discuss the object localization application underwater. We describe the the relationship between the different coordinates as well as the methods of camera calibration. The plane camera calibration algorithm of Zhang's is then used to get camera internal calibration. The fundermental matrix and essential matrix is obtained by SIFT matching. After the decomposition of external motion parameters with single-eye camera, we use structure from motion method to obtain three-dimensional information and carry out object localization. Finally, we give the three-dimensional information acquisition process and the computer simulation result.The results show that the method can meet the demand of underwater manipulation precision.
A series of studies have been done in this dissertation for the object localization based on underwater robot manipulation. The conclusion can provide theory basis and technical means for the underwater intelligent robot.
论文首先回顾了基于视觉的水下多尺度理论的发展及现状,讨论了多尺度的定义及其基本理论,阐明了不同的尺度表达模型的特点。重点研究了高斯尺度空间理论,高斯尺度空间成为图像研究中的一个重要方面,是由于高斯尺度空间理论简单以及高斯函数本身的许多独特性质。通常的尺度变换会随着尺度的增加图像越来越模糊,更多的细节被丢失,采用高斯差函数可以保留这些细节信息。在高斯尺度空间的构造中正确选用尺度参数,以使图像信息的变化呈现均匀的特点显得尤其重要。目前许多高斯尺度空间应用中采用的层之间的尺度参数关系并不明确,使得分层效果不理想。论文基于视觉特征模型提出一种自适应高斯尺度参数的算法,并通过试验验证了它的有效性,从而为图像的高层次处理如目标识别等提供信息量稳定变化的尺度空间。
尺度不变性是衡量特征提取算法的一个重要因素。针对水下图像噪声大的特点,本文提出了具有抗噪特性的尺度不变特征提取算法,算法是建立在Harris角点特征和高斯尺度空间的基础之上,在不同尺度下提取同一目标的Harris角点,从最高层的特征点开始往下搜索它们的对应点,本文还给出了该算法下求特征尺度的方法,实验表明多尺度特征点具有较强的抗噪能力和尺度不变性,且计算量少。SIFT(ScaleInvariant Feature Transform)算子因其具有良好的尺度、旋转、光照等不变特性而在图像匹配中得到广泛的应用,本文给出了水下图像的SIFT特征提取效果。结合熵的理论,本文给出多尺度熵的定义,并在此基础上通过多尺度熵差提取了水下烟囱图像的外部轮廓。
本文接着研究了基于SIFT算法的水下图像匹配技术。为了增加匹配数,我们分析了彩色图像特征检测的可行性,指出了此算法在彩色图像处理中的应用潜力,并为后续工作提供借鉴及参考。针对SIFT算法采用128维向量来表征一个特征点导致计算量过大的缺陷,本文给出了基于圆形窗口的SIFT简化算法,对每个特征点只采用12维特征向量表示,在不明显降低匹配数量的同时,较大提高了计算机处理的实时性。同时,由于原算法中主方向的获得是通过对8维方向向量的统计获得,导致主方向产生量化误差,简化的SIFT算法由于采用圆形窗口,不存在量化误差,因此旋转不变性优于原算法,实验结果也验证了该结论。
论文最后讨论了上述研究成果在目标定位中的应用。首先描述坐标之间的转化关系以及多种相机标定方法,并采用Zhang的平面标定算法对相机进行内部参数标定;再利用SIFT特征匹配方法求得稳定的匹配点对求得基本矩阵与本质矩阵,分解后得到单目相机的外部运动参数,通过采用立体视觉方法和运动恢复结构SFM(structure from motion)方法得到目标的三维信息,实现目标的定位。本章最后给出了目标三维信息获取的流程和计算机仿真,实验结果表明了本文方法能够满足水下机器作业的精度要求。
本文针对水下机器人作业中基于视觉的目标定位问题开展了一系列的研究工作,其研究成果可为水下智能机器人作业提供理论依据和技术手段。
The complexity of the underwater environment results in the problem of lacking information underwater,which lead to the high difficulty in dealing with object recognition and localization. The situation becomes even worse when we wish to extract the features of non-structural object and recognize it.The multi-scale representation has attracted considerable attention recently since it describes the the performance of the real world. At present, there are a variety of explanations about the concept of scale such as resolution, image size, quantitative, the distance and convolution kernel and so on. This dissertation aims at the seafloor object and undertakes some works such as constructing the multi-scale model, multi-scale feature extraction, the image matching , the application of object localization and so on.The research is based on Gaussian scale space in the underwater environment.
Firstly, the development and present situation of vision-based multi-scale theory underwater were reviewed, and the definition of multi-scale and its basic theory are discussed. Then the characteristics of different scale model are introduced. We focus on the Gaussian scale space theory. Gaussian scale-space is an important domain in image study. Because of the simplicity of the theory and the unique property of Gaussian function, Gaussian scale-space is applied in scale-space theory. As the scale increases, more and more information is lost. Those information can be preserved by DOG function (Difference of Gaussian). It is crucial to choose appropriate scale parameter during constructing Gaussian scale-space.At present, Many applications in Gaussian scale-space about the scale parameter is not clear, which may lead to bad effect of layer. The paper proposes a kind of adaptive algorithm of scale parameter in terms of the module of visual characters. Experimental results show that the uniformly distributed information in scale-space will be useful for higher-level image processing technologies such as object recognition.
Scale invariance is a key factor to evaluate the feature extraction algorithm. For the noise of underwater image, a kind of scale-invariant feature extraction algorithm is proposed which hold the anti-noise characteristics and based on Harris comer and Gaussian scale space.We extract the Harris corners in different scale. Then, the points detected at the highest level of the pyramid are correctly propagated to the lower level. The corners detected repeatedly in different levels are chosen as final feature points. At last, the characteristic scale is obtained based on maximum entropy method. The experimental results show that the algorithm has low computation cost, strong anti-noise capability and excellent performance in the presence of significant scale changes. Due to the invariance of scale、rotation、illumination,SIFT (Scale Invariant Feature Transform) descriptor was commonly used in image matching domain. Feature extraction experiments are carried out with SIFT.Conbined with traditional Entropy a concept of Multi-Scale Entropy was given. The non-structural object contours of the hydrothermal chminey undersea are extracted with the advantages of the Maximal Multi-Scale Entropy Difference (MMSED), which provides the basis for the following processing.
We next mainly discuss the matching methods in underwater environment based on SIFT. In order to increase the number of matches,color feature extraction is analyzed. The potential value of the method in the color image is presented,which can provide reference to the future work. However, the fact the presentation of one feature point needs 128 dimensions that will reduce the algorithm efficiency of real-time.we develope a simplified algorithm based on SIFT (SSIFT) to express a feature point with only 12 dimensions which based on a circular window to improve the efficiency of matching. The experiment results show that the algorithm can reduce the rate of time complexity and maintaining a relatively good matching rate at the same time.Furthermore, there is no quantization errors in SSfFT which exist in SIFT resulted by orientation assignment.
Finally, we discuss the object localization application underwater. We describe the the relationship between the different coordinates as well as the methods of camera calibration. The plane camera calibration algorithm of Zhang's is then used to get camera internal calibration. The fundermental matrix and essential matrix is obtained by SIFT matching. After the decomposition of external motion parameters with single-eye camera, we use structure from motion method to obtain three-dimensional information and carry out object localization. Finally, we give the three-dimensional information acquisition process and the computer simulation result.The results show that the method can meet the demand of underwater manipulation precision.
A series of studies have been done in this dissertation for the object localization based on underwater robot manipulation. The conclusion can provide theory basis and technical means for the underwater intelligent robot.
引文
[1]陈鹰,潘依雯著.深海科考探险日记.浙江:浙江大学出版社,2003.
[2]Hu Zuojin,Wang Changming and Zhu Zhangqing.Research of signal processing system based on multi-model adaptive control methods.In:Intelligent Transportation Systems,Nanjing Univ,Nanjing,China,2003(2):1091-1093
[3]Garcia J E.Adapted Distributed Localization of Sensors in Underwater Acoustic Networks.In:oceans 2006,Asia Pacific,Univ of Hannover,2007:1-3
[4]Jones E.The Application of Software Radio Techniques to Underwater Acoustic Communications.In:oceans 2007,Europe,2007:1-6
[5]ChuKuei Tu,YiChiu Lin.Using wavelet packet decomposition technique on fuzzy classify model for underwater acoustic signal recognition.Underwater Technology,2002:302-306
[6]Postolache O Girao and P Pereira M.Underwater Acoustic Source Localization Based on Passive Sonar and Intelligent Processing.In:Instrumentation and Measurement Technology Conference Proceedings,IMTC,2007:1-4
[7]邓跃红,聂双双.基于小波变换的水下超声波测距方法研究.郑州大学学报:工学版,2007(28):74-79
[8]LU Yingchun,S Enfang.Feature extraction techniques of underwater objects based on active sonar-an overview.Journal of Harbin Engineering University,1997:42-53
[9]陈荣盛等.水下机器人作业目标控制和目标识别.船舶力学,1998,2(1):62-68
[10]王学民等.图像处理技术在赤潮生物自动识别中的应用.计算机辅助设计与图形学学报,2004,16(2):158-163
[11]J P Malkasse,G Kerven.A pre-processing framework for automatic underwater images denoising.In:European Conference on Propagation and Systems,Brest,France,2005:14-18
[12]Santos Victor J,Sentieiro and J.The role of vision for underwater vehicles.In:Autonomous Underwater Vehicle Technology.Cambridge,MA,USA,1994:28-35
[13]Shaomin Zhang,Negahdaripour S.Recovery of 3D depth map from image shading for underwaterapplications.In:OCEANS 1997,Halifax,NS,Canada,1997:618-624
[14]Delaunoy Olivier,Gracias Nuno.Towards Detecting Changes in Underwater Image Sequences.In:OCEANS 2008,2008:1-8
[15]Schechner Y,Karpel N.Clear underwater vision.Computer Vision and Pattern Recognition.in:CVPR 2003,2003:536-543
[16]SonCheol Yu,Ura T,Fujii T.Navigation of autonomous underwater vehicles based on artificial underwater landmarks.In:OCEANS 2001,2001:409-416
[17]Katsikas S K,Lainiotis D G.Partitioning algorithms in underwater passive target tracking.In:OCEANS 1993,1993:463-468
[18]陆玲,陈国明,林红.水下结构物点蚀缺陷的识别与定量分析.石油大学学报:自然科学版,2005(29):79-82
[19]陈荣盛,袁小海.水下机器人光视觉信息获取及处理算法.船舶力学,1999(3):62-69
[20]朱炜,贾衡天等.水下目标的特征提取及识别.系统工程与电子技术,2008(30):171-175
[21]Zhao Kun,Zeng Yi,Peng Fuyuan,Tian Yan,Xu,Yiping.Moving object segmentation based on optical flow field.In:MIPPR 2007,Wuhan,China,2007,Proc SPIE 2007,678923-1-678923-1
[22]罗琳,彭复员,徐国华.基于纹理特征的水下烟囱图像识别.高技术通讯,2005(15):14-18
[23]彭复员,罗琳,李自力等.基于分形的激光水下图像分割研究.华中科技大学学报:自然科学版,2004(32):101-102
[24]彭复员,陈敬东,余西.基于函数变换的水下图像目标分割和特征提取.高技术通讯,2006(16):16-20
[25]Wesley E,Snyder著,林学訚等译.机器视觉教程.2004.
[26]J Morlet,G Arens,I Forgeau,D Giard.Wave Propagation and Sampling Theory.Geophysics,1982(47):202-236
[27]Meyer Y.Wavelet with compact support.Zygm and Lecture,1986:1-8
[28]Mallat s.A compact multiresolution representation:the wavelet model.1987:2-7
[29]I Daubechies.Orthonormal bases of compactly supported wavelet.Math,1988.
[30]Hoag D F,Ingle V K.Underwater image compression using the wavelet transforms.In:OCEANS 1993,1994(2):532-537
[31]Lindeberg tony.Scale-space theory:A basic tool for analyzing structures at different scales.Journal of applied statistics,1994(21):223-270
[32]Lagstad P.Detecting linear motion of an object in a sequence of monocular underwater images.AUV96,1996:342-347
[33]Lowe D G.Object recognition from local scale-invariant features.International Conference on Computer Vision,Corfu,Greece,1999:1150-1157
[34]]Espiau F X,Rives P,Extracting robust features and 3D reconstruction in underwater images.In:OCEANS 2001,2001:4012-4018
[35]焦李成,谭山.图像的多尺度几何分析:回顾和展望.电子学报,2004(31):1974-1981.
[36]熊惠霖,张天序,桑农.基于小波多尺度表示的图像匹配研究.红外与激光工程,1999,28(3):1-4
[37]陈鹰,叶勤,钟志勇.基于小波变换的雷达与光学图像匹配算法研究.测绘学报,2000,29(3):244-249
[38]张艳,王涛,路威.基于小波图像金字塔的图像自动匹配.测绘学院学报,2002,19(1):24-27
[39]熊兴华,陈鹰,王任享.基于小波和线矩的实孔径雷达图像与TM图像的匹配.测绘学报,2000,29(1):23-29
[40]王郑耀等.基于视觉特征的尺度空间信息量度量.中国图像图形学报,2005:922-928
[41]刘维,庞永杰,李岩.利用小波变换进行水下图像边缘提取的一种方法.哈尔滨工程大学学报.2003(24):384-389
[42]杨述斌,彭复员,谢志远等.基于相关和小波分析的激光水下目标检测研究.计算机仿真,2003(20):17-19
[43]Rosenfeld A,Thurston M.Edge and curve detection for visual scene analysis.IEEE Trans,Computer,1971(20):562-569
[44]A R Hanson and E M Riseman.Processing cones:A parallel computational structure for scene analysis.Computer and Information Science,Univ.of Massachusetts,Amherst,Massachusetts,1973.
[45]S Tanimoto and A Klinger.Structured Computer Vision.New York,1980.
[46]J L Crowley.A Representation for Visual Information.PhD thesis,Carnegie-Mellon University,Robotics Institute,Pittsburgh,Pennsylvania,1981.
[47] M Kelly.In Machine Intelligence.volumn 6,university of Edinburgh press, 1971.
[48] A Klinger.Pattem and search statistics. In Optimizing Methods in Statistics (J.S.Rustagi,ed.), (New York), Academic Press, 1971.
[49] S G Mallat.A theory for multiresolution signal decomposition: The wavelet representation.IEEE Trans,Pattern Analysis and Machine Intell, vol 11, 1989:673-694
[50] J J Koenderink,A J.van Doom. Representation of local geometry in the visual system.biological cybernetics, 1987(55):367-375
[51]Lindeberg tony.Scale-space A framework for handing image structures at multiple scales.In: processings of the conference European organization for Nuclear Research school of computing,Egmond aan zee,The Netherland, 996:8-21
[52] Lindeberg tony.Scale-space for Discrete signals.In: IEEE transactions on pattern analysis and machine intelligence,1990:233-25.3
[53] R Jain, R Kasturi and B G Schunck.Machine Vision.New York, 1994.
[54] Milan Sonka, Vaclav Hlavac, Roger Boyle. Image processing, analysis, and machine vision.人民邮电出版社.2001:84-87
[55] Lowe D G.Distinctive image features from scale-invariant keypoints.International Journal of Computer Vision,2004,60(2):91-110
[56] Mikolajczyk K,C Schmid.Scale and affine invariant interest point detectors. international Journal of Computer Vision,2004,60(1):62-86
[57] Y Dufournaud, C. Schmid, R Horaud.Matching images with different resolutions, in:CVPR'00,2000, 612-618
[58] Koenderink J J.The structure of images.In Biological Cybernetics,1983:362-396
[59] Marr David. Vision.San Francisco CA, USA, Freeman Publishers, 1982.
[60] Stephen Se, Lowe D, Little J.Global Localization using Distinctive Visual Features.Intelligent Robots and System ,2002:226-231
[61] Stephen Se, Lowe D, Little J. Vision-based mobile robot localization and mapping using scale-invariant features.Robotics and Automation,2001:2051-2058
[62] Moravec H. Rover visual obstacle avoidance. In: International Joint Conference on Artificial Intelligence, Vancouver, Canada, 1981:785-790
[63] Harris C,Stephens M. A combined comer and edge detector. In: Fourth Alvey Vision Conference, Manchester, UK,1988:147-151
[64] Zhang Z, Deriche R, Faugeras O. A robust technique for matchingtwo uncalibrated images through the recovery of the unknown epipolar geometry.Artificial Intelligence,1994(78):87-119
[65]Torr P.Motion Segmentation and Outlier Detection.PhD Thesis, Dept of Engineering Science, University of Oxford, UK,1994.
[66]Schmid C and Mohr R. Local grayvalue invariants for image retrieval. IEEE Trans On Pattern Analysis and Machine Intelligence,1997,19(5):530-533
[67]Shokoufandeh A, Marsic I, Dickinson S J. View-based object recognition using saliency maps. Image and Vision Computing,1999(17):444-460
[68] Lindeberg T. Detecting salient blob-like image structures and their scales with a scale space primal sketch: a method for focus-of-attention. International Journal of Computer Vision,1993,11(3):282-318
[69]Baumberg A. Reliable feature matching across widely separated views. In :Computer Vision and Pattern Recognition, Hilton Head, South Carolina,2000:773-781
[70]Tuytelaars T,Van Gool L. Wide baseline stereo based on local, affmely invariant regions. In British Machine Vision Conference, Bristol, UK,2000:412-422
[71]Mikolajczyk K,Schmid C. An affine invariant interest point detector. In European Conference on Computer Vision (ECCV), Copenhagen, Denmark,2002:128-142
[72] Schaffalitzky F, Zisserman A. Multi-view matching for unordered image sets, or 'How do I organize my holiday snaps?'. In European Conference on Computer Vision,Copenhagen, Denmark, 2002:413-431
[73] Brown M,Lowe D G. Invariant features from interest point groups. In British Machine Vision Conference, Cardiff, Wales,2002:656-664
[74]Nelson R C,Selinger A. Large-scale tests of a keyed, appearance-based 2-D object recognition system. Vision Research,1998,38(15):2469-88
[75]Pope A R,Lowe D G. Probabilistic models of appearance for 2-D object recognition.International Journal of Computer Vision,2000,40(2):149-167
[76]Carneiro G and Jepson A D. Phase-based local features. In European Conference on Computer Vision (ECCV), Copenhagen, Denmark,2002:282-296
[77]Schiele B, Crowley J L. Recognition without correspondence using multidimensional receptive field histograms.International Journal of Computer Vision, 2000, 36(1): 31-50.
[78]Basri R and Jacobs D W.Recognition using region correspondences.International Journal of Computer Vision,1997,25(2):144-166
[79]贾云德.机器视觉.北京:科学出版社,2003.
[80]Canny J.A Computational Approach to Edge Detection.IEEE Transactions on Patten Analysis and Machine Intelligence,1986,8(6):679-698
[81]S M Smith,M Brady.SUSAN-a new approach to low level image processing.International Jaurnal of Computer Vision,1997,23(1):45-78
[82]T Kadir,A Zisserman and M Brady.An affine invariant salient region detector.In:ECCV 2000,404-416
[83]Sebastian Nowozin.Object Classification using Local Image Features.Phd thesis,2006.
[84]Ando S.Consistent gradient operators.Pattern Analysis and Machine Intelligence,2000,22(3):252-265
[85]Kass A,Witkin A,Terzopoulos D.Snakes:active contour modes.ICCV 1987:259-268
[86]周彦博,张志广.可变形物体轮廓的提取.电子学报,1998,26(7):133-138
[87]Peterfreund N.Robust tracking with Spatio-snakes:Kalman filtering approach.In:The 1998 IEEE 6th International Conference on Computer Vision,Bombay,India,1998:433-439
[88]Cham T J,Cipolla R.Stereo coupled active contours.In:Proceedings of the International Conference on CVPR,San Juan,DuertoRico:IEEE Computer Society Press,1997:1094-1099
[89]Esin C F,Leung C K.Image Segmentation by edge pixel classification with maximum entropy.Intelligent Multimedia,Video and Speed Processing,2001:283-286
[90]Bergholm F.Edge Focusing.IEEE Transaction on PAMI,1987,9(6):726-741
[91]Kadir T,Brady M.Scale,Saliency and Image description.International Journal of Computer Vision,2001,45(2):83-105
[92]Fraundorfer F Ober,S Bischof,Natural.salient image patches for robot localization.Pattern Recognition,ICPR 2004:881-884
[93]Prachya Chalermwat.High performance automatic image registration for remote sensing.1999.
[94]J B Antoine,Maintz,Max A.Viergever.A survey of medical image registration.MedicalImage Analysis.1998,2(1):1-36
[95]苏康,金善良.智能地物景像匹配定位技术研究.红外与激光工程,2000,29(1):1-3
[96]FangHsuan Cheng.Point pattern matching algorithm invariant to geometrical transformation and distortion.Pattern Recognition Letters,1996,17:1429-1435
[97]Kanade T,Okutomi M.A stereo matching algorithm with an adaptive window:Theory and Experiment,IEEE Transactions on Pattern Analysis and Machine Intelligence,1994,16(9):920-932
[98]Super B J,Kiariaquist W N.Patch-based stereo in general binocular viewing.Theory and Experiment,PAMI,1997,3(19):247-252
[99]Raymond V E,Clifton M S,Unconstrained stereoscopic matching of lines.Vision Research,2000,40:151-162
[100]张登荣,郭兆胜,沈国状.一种遥感数字图像匹配的合成算法.浙江大学学报:理学版,2005,32(6):716-720
[101]Cai L D,Mayhew J.A note on some phase differencing algorithm for disparity estimation.International Journal of Computer Vision,1997,22(2):111-124
[102]Zhou J,Xu Y,Yu W R.Phase matching with multiresolution wavelet transform.In:Proceedings of SPIE,2002,4661(10):82-91
[103]L G Brown.A survey of image registration techniques.ACM Computing Surveys,1992,24(4):324-376
[104]安如.基于角点特征的飞行器导航图像匹配算法研究.南京大学博士论文,2005.
[105]陈宁江,李介谷.用归一化灰度组合法进行图像匹配.红外与激光工程,2000,29(5):4-9
[106]桂志国,薄瑞峰,韩焱.基于投影特征的图像匹配的快速算法.华北工学院测试技术学报,2000,14(1):18-20
[107]周志强,陈哲.贝叶斯景象匹配技术.北京航空航天大学学报,1999,25(3):337-341
[108]王珏,孙小惟.基于圆投影及直方图不变特征的图像匹配方法.自动化技术与应用,2007,26(8):80-82,76
[109]田金文,柳健,张天序.基于模糊信息理论的景象匹配方法.红外与激光工 程,1998,27(3):28-31
[110]高世海,戴文刚,田仲.空域和频域相结合的景象匹配算法.中国图像图形学报,2000,5(4):344-348
[111]赵立初,施鹏飞,俞勇.模扳图像匹配中的亚像元定位新方法.红外与毫米波学报,1999,18(5):407-411
[112]张桂林,徐捷,郑云慧.频域相关技术在图像匹配中的应用.模式识别与人工智能,1997,10(1):87-91
[113]冯桂,卢健,宗坚.图像直方图不变特征在图像匹配定位中的应用.计算机辅助设计与图形学学报,2000,12(2):146-148
[114]李静,杨涛,潘泉,程咏梅.基于不变特征的运动视频序列自动配准算法.中国图像图形学报,2008,13(2):335-344
[115]潘泉,程咏梅.离散不变矩算法及其在目标识别中的应用.电子与信息学报,2001,23(1):30-36
[116]刘小军,杨杰,刘惠等.基于主成份分析的仿射不变特征图像匹配方法.系统仿真学报,2008,20(4):977-980,1001
[117]高世海,戴文刚,田仲.应用分形特征的景象匹配仿真.中国图像图形学报,2000,5(9):730-733
[118]丁明跃,吴晏,彭嘉雄.用于飞行器导航的边缘匹配方法研究.宇航学报,1998,19(3):72-78
[119]Jun Wei Han,Lei Guo.A shape-based image retrieval method using salient edges.Signal Processing:Image Communication,2003,18:141-156
[120]Ming Xie.Cooperative strategy for matching multi-level edge primitives.Image and Vision Computing,1995,13(2):89-99
[121]Alexander Toet,Walter P,Hajema.Genetic contour matching.Pattern Recognition Letters,1995,16:849-856
[122]Ji Zhou,Jiaoying Shi.Stefanov.A robust algorithm for feature point matching.Computers & Graphics,2002,26:429-436
[123]Abd-Almageed E,EIKonyaly S Saraya.Point feature matching adopting Walsh transform.SPIE Intelligent Robots and Computer,1997:74-84
[124]L Chmielewski,P Gut,P F Kuko lowicz,et al.Robust feature-based image registration using modified Hausdorff distance measure with the evolving quantile rank.In:East-West Vision,EWV'02,2002:23-28
[125]Bijita Biswas,Amit Konar,Achintya K,Mukherjee.Image matching with fuzzy moment descriptors.Engineering Applications of Artificial Intelligence,2001:42-49
[126]Younian wang.Principles and applications of structural image matching.ISPRS Journal of Photogrammetry and Remote Sensing,1998,53:153-165
[127]赵坤.水下非结构化环境中的特征提取与匹配算法研究.华中科技大学硕士论文,2007.
[128]A Bosch,A Zisserman and X Muoz.Scene classification using a hybrid generative/discriminative approach.IEEE Trans,Pattern Analysis and Machine Intell,2008,30(04):712-727
[129]Gevers K,Smeulders A W M.Color-based object recognition.Pattern Recognition,1999,32:452-464
[130]Mortensen E N,Hongli Deng,Shapiro L.Computer Vision and Pattern Recognition 2004,In:CVPR 2004,IEEE Computer Society Conference,2004,184-190
[131]马颂德,张正友.计算机视觉.北京:科学出版社.1998:52-69
[132]TSAI R Y.An efficient and accurate camera calibration technique for 3D machine vision.In:Proceedings of IEEE Conference On Computer Vision and Pattern Recognition,1986(3):364-374
[133]TSAI Roger Y.A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses.IEEE Journal of Robotics and Automation,1987,3(4):323-334
[134]邱茂林,马颂德,李毅.计算机视觉中摄像机定标综述.自动化学报,2000,26(1):43-55
[135]Faugeras O.Three-Dimensional Computer Vision:a Geometric Viewpoint.IT Press,1993.
[136]Faugeras O,Luong Q T and Maybank S.Camera self-calibration:theory and experiments.In:Proceedings of the 2nd European Conference on Computer Vision,Italy,1992:321-334
[137]Hartley R,Hayman E,L de Agapito and I Reid.Camera Calibration and the Search for Infinity.In:ICCV 99,1999:510-516
[138]Ma S D.A self-calibration technique foe active system.Robot Automation,1996,12(1):114-120
[139]Moons T,Gool L,Proesmans M.Affine reconstruction from perspective image pairs with a relative object-camera translation in between.In:PAMI,1996,18(1):77-83.
[140]Zhang Zhengyou.A flexible new technique for camera calibration.Pattern Analysis and Machine Intelligence,2000,22(11):1330-1334
[141]张广军.机器视觉.北京:科学出版社,2005.
[142]Longuet-Higgins H C.A computer algorithm for reconstruction a scene from two projections.Nature,1981,293:133-135
[2]Hu Zuojin,Wang Changming and Zhu Zhangqing.Research of signal processing system based on multi-model adaptive control methods.In:Intelligent Transportation Systems,Nanjing Univ,Nanjing,China,2003(2):1091-1093
[3]Garcia J E.Adapted Distributed Localization of Sensors in Underwater Acoustic Networks.In:oceans 2006,Asia Pacific,Univ of Hannover,2007:1-3
[4]Jones E.The Application of Software Radio Techniques to Underwater Acoustic Communications.In:oceans 2007,Europe,2007:1-6
[5]ChuKuei Tu,YiChiu Lin.Using wavelet packet decomposition technique on fuzzy classify model for underwater acoustic signal recognition.Underwater Technology,2002:302-306
[6]Postolache O Girao and P Pereira M.Underwater Acoustic Source Localization Based on Passive Sonar and Intelligent Processing.In:Instrumentation and Measurement Technology Conference Proceedings,IMTC,2007:1-4
[7]邓跃红,聂双双.基于小波变换的水下超声波测距方法研究.郑州大学学报:工学版,2007(28):74-79
[8]LU Yingchun,S Enfang.Feature extraction techniques of underwater objects based on active sonar-an overview.Journal of Harbin Engineering University,1997:42-53
[9]陈荣盛等.水下机器人作业目标控制和目标识别.船舶力学,1998,2(1):62-68
[10]王学民等.图像处理技术在赤潮生物自动识别中的应用.计算机辅助设计与图形学学报,2004,16(2):158-163
[11]J P Malkasse,G Kerven.A pre-processing framework for automatic underwater images denoising.In:European Conference on Propagation and Systems,Brest,France,2005:14-18
[12]Santos Victor J,Sentieiro and J.The role of vision for underwater vehicles.In:Autonomous Underwater Vehicle Technology.Cambridge,MA,USA,1994:28-35
[13]Shaomin Zhang,Negahdaripour S.Recovery of 3D depth map from image shading for underwaterapplications.In:OCEANS 1997,Halifax,NS,Canada,1997:618-624
[14]Delaunoy Olivier,Gracias Nuno.Towards Detecting Changes in Underwater Image Sequences.In:OCEANS 2008,2008:1-8
[15]Schechner Y,Karpel N.Clear underwater vision.Computer Vision and Pattern Recognition.in:CVPR 2003,2003:536-543
[16]SonCheol Yu,Ura T,Fujii T.Navigation of autonomous underwater vehicles based on artificial underwater landmarks.In:OCEANS 2001,2001:409-416
[17]Katsikas S K,Lainiotis D G.Partitioning algorithms in underwater passive target tracking.In:OCEANS 1993,1993:463-468
[18]陆玲,陈国明,林红.水下结构物点蚀缺陷的识别与定量分析.石油大学学报:自然科学版,2005(29):79-82
[19]陈荣盛,袁小海.水下机器人光视觉信息获取及处理算法.船舶力学,1999(3):62-69
[20]朱炜,贾衡天等.水下目标的特征提取及识别.系统工程与电子技术,2008(30):171-175
[21]Zhao Kun,Zeng Yi,Peng Fuyuan,Tian Yan,Xu,Yiping.Moving object segmentation based on optical flow field.In:MIPPR 2007,Wuhan,China,2007,Proc SPIE 2007,678923-1-678923-1
[22]罗琳,彭复员,徐国华.基于纹理特征的水下烟囱图像识别.高技术通讯,2005(15):14-18
[23]彭复员,罗琳,李自力等.基于分形的激光水下图像分割研究.华中科技大学学报:自然科学版,2004(32):101-102
[24]彭复员,陈敬东,余西.基于函数变换的水下图像目标分割和特征提取.高技术通讯,2006(16):16-20
[25]Wesley E,Snyder著,林学訚等译.机器视觉教程.2004.
[26]J Morlet,G Arens,I Forgeau,D Giard.Wave Propagation and Sampling Theory.Geophysics,1982(47):202-236
[27]Meyer Y.Wavelet with compact support.Zygm and Lecture,1986:1-8
[28]Mallat s.A compact multiresolution representation:the wavelet model.1987:2-7
[29]I Daubechies.Orthonormal bases of compactly supported wavelet.Math,1988.
[30]Hoag D F,Ingle V K.Underwater image compression using the wavelet transforms.In:OCEANS 1993,1994(2):532-537
[31]Lindeberg tony.Scale-space theory:A basic tool for analyzing structures at different scales.Journal of applied statistics,1994(21):223-270
[32]Lagstad P.Detecting linear motion of an object in a sequence of monocular underwater images.AUV96,1996:342-347
[33]Lowe D G.Object recognition from local scale-invariant features.International Conference on Computer Vision,Corfu,Greece,1999:1150-1157
[34]]Espiau F X,Rives P,Extracting robust features and 3D reconstruction in underwater images.In:OCEANS 2001,2001:4012-4018
[35]焦李成,谭山.图像的多尺度几何分析:回顾和展望.电子学报,2004(31):1974-1981.
[36]熊惠霖,张天序,桑农.基于小波多尺度表示的图像匹配研究.红外与激光工程,1999,28(3):1-4
[37]陈鹰,叶勤,钟志勇.基于小波变换的雷达与光学图像匹配算法研究.测绘学报,2000,29(3):244-249
[38]张艳,王涛,路威.基于小波图像金字塔的图像自动匹配.测绘学院学报,2002,19(1):24-27
[39]熊兴华,陈鹰,王任享.基于小波和线矩的实孔径雷达图像与TM图像的匹配.测绘学报,2000,29(1):23-29
[40]王郑耀等.基于视觉特征的尺度空间信息量度量.中国图像图形学报,2005:922-928
[41]刘维,庞永杰,李岩.利用小波变换进行水下图像边缘提取的一种方法.哈尔滨工程大学学报.2003(24):384-389
[42]杨述斌,彭复员,谢志远等.基于相关和小波分析的激光水下目标检测研究.计算机仿真,2003(20):17-19
[43]Rosenfeld A,Thurston M.Edge and curve detection for visual scene analysis.IEEE Trans,Computer,1971(20):562-569
[44]A R Hanson and E M Riseman.Processing cones:A parallel computational structure for scene analysis.Computer and Information Science,Univ.of Massachusetts,Amherst,Massachusetts,1973.
[45]S Tanimoto and A Klinger.Structured Computer Vision.New York,1980.
[46]J L Crowley.A Representation for Visual Information.PhD thesis,Carnegie-Mellon University,Robotics Institute,Pittsburgh,Pennsylvania,1981.
[47] M Kelly.In Machine Intelligence.volumn 6,university of Edinburgh press, 1971.
[48] A Klinger.Pattem and search statistics. In Optimizing Methods in Statistics (J.S.Rustagi,ed.), (New York), Academic Press, 1971.
[49] S G Mallat.A theory for multiresolution signal decomposition: The wavelet representation.IEEE Trans,Pattern Analysis and Machine Intell, vol 11, 1989:673-694
[50] J J Koenderink,A J.van Doom. Representation of local geometry in the visual system.biological cybernetics, 1987(55):367-375
[51]Lindeberg tony.Scale-space A framework for handing image structures at multiple scales.In: processings of the conference European organization for Nuclear Research school of computing,Egmond aan zee,The Netherland, 996:8-21
[52] Lindeberg tony.Scale-space for Discrete signals.In: IEEE transactions on pattern analysis and machine intelligence,1990:233-25.3
[53] R Jain, R Kasturi and B G Schunck.Machine Vision.New York, 1994.
[54] Milan Sonka, Vaclav Hlavac, Roger Boyle. Image processing, analysis, and machine vision.人民邮电出版社.2001:84-87
[55] Lowe D G.Distinctive image features from scale-invariant keypoints.International Journal of Computer Vision,2004,60(2):91-110
[56] Mikolajczyk K,C Schmid.Scale and affine invariant interest point detectors. international Journal of Computer Vision,2004,60(1):62-86
[57] Y Dufournaud, C. Schmid, R Horaud.Matching images with different resolutions, in:CVPR'00,2000, 612-618
[58] Koenderink J J.The structure of images.In Biological Cybernetics,1983:362-396
[59] Marr David. Vision.San Francisco CA, USA, Freeman Publishers, 1982.
[60] Stephen Se, Lowe D, Little J.Global Localization using Distinctive Visual Features.Intelligent Robots and System ,2002:226-231
[61] Stephen Se, Lowe D, Little J. Vision-based mobile robot localization and mapping using scale-invariant features.Robotics and Automation,2001:2051-2058
[62] Moravec H. Rover visual obstacle avoidance. In: International Joint Conference on Artificial Intelligence, Vancouver, Canada, 1981:785-790
[63] Harris C,Stephens M. A combined comer and edge detector. In: Fourth Alvey Vision Conference, Manchester, UK,1988:147-151
[64] Zhang Z, Deriche R, Faugeras O. A robust technique for matchingtwo uncalibrated images through the recovery of the unknown epipolar geometry.Artificial Intelligence,1994(78):87-119
[65]Torr P.Motion Segmentation and Outlier Detection.PhD Thesis, Dept of Engineering Science, University of Oxford, UK,1994.
[66]Schmid C and Mohr R. Local grayvalue invariants for image retrieval. IEEE Trans On Pattern Analysis and Machine Intelligence,1997,19(5):530-533
[67]Shokoufandeh A, Marsic I, Dickinson S J. View-based object recognition using saliency maps. Image and Vision Computing,1999(17):444-460
[68] Lindeberg T. Detecting salient blob-like image structures and their scales with a scale space primal sketch: a method for focus-of-attention. International Journal of Computer Vision,1993,11(3):282-318
[69]Baumberg A. Reliable feature matching across widely separated views. In :Computer Vision and Pattern Recognition, Hilton Head, South Carolina,2000:773-781
[70]Tuytelaars T,Van Gool L. Wide baseline stereo based on local, affmely invariant regions. In British Machine Vision Conference, Bristol, UK,2000:412-422
[71]Mikolajczyk K,Schmid C. An affine invariant interest point detector. In European Conference on Computer Vision (ECCV), Copenhagen, Denmark,2002:128-142
[72] Schaffalitzky F, Zisserman A. Multi-view matching for unordered image sets, or 'How do I organize my holiday snaps?'. In European Conference on Computer Vision,Copenhagen, Denmark, 2002:413-431
[73] Brown M,Lowe D G. Invariant features from interest point groups. In British Machine Vision Conference, Cardiff, Wales,2002:656-664
[74]Nelson R C,Selinger A. Large-scale tests of a keyed, appearance-based 2-D object recognition system. Vision Research,1998,38(15):2469-88
[75]Pope A R,Lowe D G. Probabilistic models of appearance for 2-D object recognition.International Journal of Computer Vision,2000,40(2):149-167
[76]Carneiro G and Jepson A D. Phase-based local features. In European Conference on Computer Vision (ECCV), Copenhagen, Denmark,2002:282-296
[77]Schiele B, Crowley J L. Recognition without correspondence using multidimensional receptive field histograms.International Journal of Computer Vision, 2000, 36(1): 31-50.
[78]Basri R and Jacobs D W.Recognition using region correspondences.International Journal of Computer Vision,1997,25(2):144-166
[79]贾云德.机器视觉.北京:科学出版社,2003.
[80]Canny J.A Computational Approach to Edge Detection.IEEE Transactions on Patten Analysis and Machine Intelligence,1986,8(6):679-698
[81]S M Smith,M Brady.SUSAN-a new approach to low level image processing.International Jaurnal of Computer Vision,1997,23(1):45-78
[82]T Kadir,A Zisserman and M Brady.An affine invariant salient region detector.In:ECCV 2000,404-416
[83]Sebastian Nowozin.Object Classification using Local Image Features.Phd thesis,2006.
[84]Ando S.Consistent gradient operators.Pattern Analysis and Machine Intelligence,2000,22(3):252-265
[85]Kass A,Witkin A,Terzopoulos D.Snakes:active contour modes.ICCV 1987:259-268
[86]周彦博,张志广.可变形物体轮廓的提取.电子学报,1998,26(7):133-138
[87]Peterfreund N.Robust tracking with Spatio-snakes:Kalman filtering approach.In:The 1998 IEEE 6th International Conference on Computer Vision,Bombay,India,1998:433-439
[88]Cham T J,Cipolla R.Stereo coupled active contours.In:Proceedings of the International Conference on CVPR,San Juan,DuertoRico:IEEE Computer Society Press,1997:1094-1099
[89]Esin C F,Leung C K.Image Segmentation by edge pixel classification with maximum entropy.Intelligent Multimedia,Video and Speed Processing,2001:283-286
[90]Bergholm F.Edge Focusing.IEEE Transaction on PAMI,1987,9(6):726-741
[91]Kadir T,Brady M.Scale,Saliency and Image description.International Journal of Computer Vision,2001,45(2):83-105
[92]Fraundorfer F Ober,S Bischof,Natural.salient image patches for robot localization.Pattern Recognition,ICPR 2004:881-884
[93]Prachya Chalermwat.High performance automatic image registration for remote sensing.1999.
[94]J B Antoine,Maintz,Max A.Viergever.A survey of medical image registration.MedicalImage Analysis.1998,2(1):1-36
[95]苏康,金善良.智能地物景像匹配定位技术研究.红外与激光工程,2000,29(1):1-3
[96]FangHsuan Cheng.Point pattern matching algorithm invariant to geometrical transformation and distortion.Pattern Recognition Letters,1996,17:1429-1435
[97]Kanade T,Okutomi M.A stereo matching algorithm with an adaptive window:Theory and Experiment,IEEE Transactions on Pattern Analysis and Machine Intelligence,1994,16(9):920-932
[98]Super B J,Kiariaquist W N.Patch-based stereo in general binocular viewing.Theory and Experiment,PAMI,1997,3(19):247-252
[99]Raymond V E,Clifton M S,Unconstrained stereoscopic matching of lines.Vision Research,2000,40:151-162
[100]张登荣,郭兆胜,沈国状.一种遥感数字图像匹配的合成算法.浙江大学学报:理学版,2005,32(6):716-720
[101]Cai L D,Mayhew J.A note on some phase differencing algorithm for disparity estimation.International Journal of Computer Vision,1997,22(2):111-124
[102]Zhou J,Xu Y,Yu W R.Phase matching with multiresolution wavelet transform.In:Proceedings of SPIE,2002,4661(10):82-91
[103]L G Brown.A survey of image registration techniques.ACM Computing Surveys,1992,24(4):324-376
[104]安如.基于角点特征的飞行器导航图像匹配算法研究.南京大学博士论文,2005.
[105]陈宁江,李介谷.用归一化灰度组合法进行图像匹配.红外与激光工程,2000,29(5):4-9
[106]桂志国,薄瑞峰,韩焱.基于投影特征的图像匹配的快速算法.华北工学院测试技术学报,2000,14(1):18-20
[107]周志强,陈哲.贝叶斯景象匹配技术.北京航空航天大学学报,1999,25(3):337-341
[108]王珏,孙小惟.基于圆投影及直方图不变特征的图像匹配方法.自动化技术与应用,2007,26(8):80-82,76
[109]田金文,柳健,张天序.基于模糊信息理论的景象匹配方法.红外与激光工 程,1998,27(3):28-31
[110]高世海,戴文刚,田仲.空域和频域相结合的景象匹配算法.中国图像图形学报,2000,5(4):344-348
[111]赵立初,施鹏飞,俞勇.模扳图像匹配中的亚像元定位新方法.红外与毫米波学报,1999,18(5):407-411
[112]张桂林,徐捷,郑云慧.频域相关技术在图像匹配中的应用.模式识别与人工智能,1997,10(1):87-91
[113]冯桂,卢健,宗坚.图像直方图不变特征在图像匹配定位中的应用.计算机辅助设计与图形学学报,2000,12(2):146-148
[114]李静,杨涛,潘泉,程咏梅.基于不变特征的运动视频序列自动配准算法.中国图像图形学报,2008,13(2):335-344
[115]潘泉,程咏梅.离散不变矩算法及其在目标识别中的应用.电子与信息学报,2001,23(1):30-36
[116]刘小军,杨杰,刘惠等.基于主成份分析的仿射不变特征图像匹配方法.系统仿真学报,2008,20(4):977-980,1001
[117]高世海,戴文刚,田仲.应用分形特征的景象匹配仿真.中国图像图形学报,2000,5(9):730-733
[118]丁明跃,吴晏,彭嘉雄.用于飞行器导航的边缘匹配方法研究.宇航学报,1998,19(3):72-78
[119]Jun Wei Han,Lei Guo.A shape-based image retrieval method using salient edges.Signal Processing:Image Communication,2003,18:141-156
[120]Ming Xie.Cooperative strategy for matching multi-level edge primitives.Image and Vision Computing,1995,13(2):89-99
[121]Alexander Toet,Walter P,Hajema.Genetic contour matching.Pattern Recognition Letters,1995,16:849-856
[122]Ji Zhou,Jiaoying Shi.Stefanov.A robust algorithm for feature point matching.Computers & Graphics,2002,26:429-436
[123]Abd-Almageed E,EIKonyaly S Saraya.Point feature matching adopting Walsh transform.SPIE Intelligent Robots and Computer,1997:74-84
[124]L Chmielewski,P Gut,P F Kuko lowicz,et al.Robust feature-based image registration using modified Hausdorff distance measure with the evolving quantile rank.In:East-West Vision,EWV'02,2002:23-28
[125]Bijita Biswas,Amit Konar,Achintya K,Mukherjee.Image matching with fuzzy moment descriptors.Engineering Applications of Artificial Intelligence,2001:42-49
[126]Younian wang.Principles and applications of structural image matching.ISPRS Journal of Photogrammetry and Remote Sensing,1998,53:153-165
[127]赵坤.水下非结构化环境中的特征提取与匹配算法研究.华中科技大学硕士论文,2007.
[128]A Bosch,A Zisserman and X Muoz.Scene classification using a hybrid generative/discriminative approach.IEEE Trans,Pattern Analysis and Machine Intell,2008,30(04):712-727
[129]Gevers K,Smeulders A W M.Color-based object recognition.Pattern Recognition,1999,32:452-464
[130]Mortensen E N,Hongli Deng,Shapiro L.Computer Vision and Pattern Recognition 2004,In:CVPR 2004,IEEE Computer Society Conference,2004,184-190
[131]马颂德,张正友.计算机视觉.北京:科学出版社.1998:52-69
[132]TSAI R Y.An efficient and accurate camera calibration technique for 3D machine vision.In:Proceedings of IEEE Conference On Computer Vision and Pattern Recognition,1986(3):364-374
[133]TSAI Roger Y.A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses.IEEE Journal of Robotics and Automation,1987,3(4):323-334
[134]邱茂林,马颂德,李毅.计算机视觉中摄像机定标综述.自动化学报,2000,26(1):43-55
[135]Faugeras O.Three-Dimensional Computer Vision:a Geometric Viewpoint.IT Press,1993.
[136]Faugeras O,Luong Q T and Maybank S.Camera self-calibration:theory and experiments.In:Proceedings of the 2nd European Conference on Computer Vision,Italy,1992:321-334
[137]Hartley R,Hayman E,L de Agapito and I Reid.Camera Calibration and the Search for Infinity.In:ICCV 99,1999:510-516
[138]Ma S D.A self-calibration technique foe active system.Robot Automation,1996,12(1):114-120
[139]Moons T,Gool L,Proesmans M.Affine reconstruction from perspective image pairs with a relative object-camera translation in between.In:PAMI,1996,18(1):77-83.
[140]Zhang Zhengyou.A flexible new technique for camera calibration.Pattern Analysis and Machine Intelligence,2000,22(11):1330-1334
[141]张广军.机器视觉.北京:科学出版社,2005.
[142]Longuet-Higgins H C.A computer algorithm for reconstruction a scene from two projections.Nature,1981,293:133-135