复杂背景下运动目标的分割与跟踪
|
摘要
在图像处理领域，视频图像序列中运动目标的分割与跟踪是一个被广泛研究的热点。在众多的分割和跟踪方法中，本文将研究对象定位在具有一定复杂背景下单个平移运动的刚体，结合基于块的运动检测和主动轮廓模型分割目标的优点，提出了一个简单而有效的复杂背景下运动目标分割与跟踪系统，并取得了良好的效果。
本方案的实现过程为：
分割部分：对运动目标的前后三帧进行两次块匹配运动检测，通过找出两个匹配结果中运动图像块的公共部分，获得组成运动目标的图像块；求出运动目标图像块的形心作为运动目标的中心，以此中心为端点，向四周发散出角度间隔为θ的n条射线，射线的另一端终止于图像的边缘；在每条射线上按照一定的准则(点的梯度和与目标中心的距离在一定阈值范围内)找出n个初始轮廓点；以这些初始轮廓点作为主动轮廓模型(snake)的初始点，用改进的贪婪算法使snake收敛到待分割的运动目标轮廓上。
跟踪部分：根据刚体运动的特点(运动区域具有一致性和不发生较大的形变)求出运动目标的平均位移矢量，与在分割部分求出的目标的轮廓点的位置相加，作为下一帧跟踪的初始轮廓点，结合改进的snake能量函数使其更精确地收敛到运动目标轮廓上，达到准确跟踪的效果。
实验证明，本方案对于帧间位移较为明显的单个平移运动刚体，特别是外部轮廓较为平滑的物体具有良好的分割与跟踪效果。
In the field of image processing, the segmentation and tracking of moving object in video sequences is a hot research topic in recent years. Various of segmentation methods can be used according to different situations of moving objects and its background.
In this paper,we propose a new simple and effective system of
segmentation and tracking of moving object in a stationary complex
background. In this system,we combine the merits of motion detection
based on blockmatching algorithm and the object segmentation based on active contour(snake), and get a satisfied result through the testing of a serious of different video pictures.
Following are detailed steps of this system:
In the segmentation section,we use three successive frames to detect the motion infomation of the pictures,by using blockmatching algorithm in two successive frames twice,we can get two pictures composed of motion blocks of the moving object,then we find out the common motion blocks of the two pictures,experiments prove these blocks approximately compose the moving object.
After getting the motion blocks,we calculate the center of these blocks as the center of the moving object,thus we can use the center point as the origin,construct n straight linesjoining the boundry of the image and the center.On each line,we can find out a proper point near the object contour according to some criteria, then we use these n points as the initial points of the snake and let the snake converge on the object contour,thus finish the segmentation of the moving object.
In tracking section,we still adopt the snake to converge on the object contour by improving the energy functions,in the tracking frame,initial points are acquired by calculating the average inter-frame motion vector of the block,because all snaxels have approximately the
same motion vector as the moving object is proposed to be rigid and have no salient deformation.
Experiments prove that the system can be used to segment and track the single moving rigid object with comparatively large inter-frame vector,and the result is good enough especially to those objects with smooth contours.
本方案的实现过程为：
分割部分：对运动目标的前后三帧进行两次块匹配运动检测，通过找出两个匹配结果中运动图像块的公共部分，获得组成运动目标的图像块；求出运动目标图像块的形心作为运动目标的中心，以此中心为端点，向四周发散出角度间隔为θ的n条射线，射线的另一端终止于图像的边缘；在每条射线上按照一定的准则(点的梯度和与目标中心的距离在一定阈值范围内)找出n个初始轮廓点；以这些初始轮廓点作为主动轮廓模型(snake)的初始点，用改进的贪婪算法使snake收敛到待分割的运动目标轮廓上。
跟踪部分：根据刚体运动的特点(运动区域具有一致性和不发生较大的形变)求出运动目标的平均位移矢量，与在分割部分求出的目标的轮廓点的位置相加，作为下一帧跟踪的初始轮廓点，结合改进的snake能量函数使其更精确地收敛到运动目标轮廓上，达到准确跟踪的效果。
实验证明，本方案对于帧间位移较为明显的单个平移运动刚体，特别是外部轮廓较为平滑的物体具有良好的分割与跟踪效果。
In the field of image processing, the segmentation and tracking of moving object in video sequences is a hot research topic in recent years. Various of segmentation methods can be used according to different situations of moving objects and its background.
In this paper,we propose a new simple and effective system of
segmentation and tracking of moving object in a stationary complex
background. In this system,we combine the merits of motion detection
based on blockmatching algorithm and the object segmentation based on active contour(snake), and get a satisfied result through the testing of a serious of different video pictures.
Following are detailed steps of this system:
In the segmentation section,we use three successive frames to detect the motion infomation of the pictures,by using blockmatching algorithm in two successive frames twice,we can get two pictures composed of motion blocks of the moving object,then we find out the common motion blocks of the two pictures,experiments prove these blocks approximately compose the moving object.
After getting the motion blocks,we calculate the center of these blocks as the center of the moving object,thus we can use the center point as the origin,construct n straight linesjoining the boundry of the image and the center.On each line,we can find out a proper point near the object contour according to some criteria, then we use these n points as the initial points of the snake and let the snake converge on the object contour,thus finish the segmentation of the moving object.
In tracking section,we still adopt the snake to converge on the object contour by improving the energy functions,in the tracking frame,initial points are acquired by calculating the average inter-frame motion vector of the block,because all snaxels have approximately the
same motion vector as the moving object is proposed to be rigid and have no salient deformation.
Experiments prove that the system can be used to segment and track the single moving rigid object with comparatively large inter-frame vector,and the result is good enough especially to those objects with smooth contours.
引文
[1] 刘党辉，沈兰荪，视频运动对象分割技术的研究[J]，电路与系统学报，2002-09，7(3)：77-85．
[2] Neti A, Colonnese S, Russo G, et al. Automatic Moving object and Background Separation[J]. Signal Processing, 1998-04,66(2): 219-232.
[3] Munchurl Kim, Jae Gark Choi, Daehee Kim et al. A VOP Generation Tool: Automatic Segmentation of Moving Objects In Image Sequences Based on Spatio-Temporal Infomation[J]. IEEE Transactions on Circuits and Systems for Video Technology, 1999-12,9(8): 1216-1226.
[4] Sifakis E, Tziritas G. Moving Object Localisation Using a Multi-label Fast Matching Algorithm[J]. Signal Processing :Image Communication, 2001(16):963-976.
[5] Roland Mech, Michael Wollborn. A Noise Robust Method for 2D Shape Estimation of Moving Objects in Video Sequences Considering a Moving Camera[J]. Signal Processing, 1998(66): 203-217.
[6] A. Aydin Alatan,Levent Onural.,Michael Wollborn,etal. Image Sequence Analysis for Emerging Interactive Multimedia Services-The European COST 211 Framework [J]. IEEE Transactions on Circuits and Systems for Video Technology. 1998-11,(8,7):802-813.
[7] 刘李杰，蔡德钧，翁南钐，一种面向运动的视频对象分割算法[J]，计算机学报．2000，23(12)：1326-1331．
[8] GeraId Kuhne, Stephan Richter, Markus Beier. Motion—Based Segmentation and Contour-Based Classification of Video Objects[A].ACM Multimedia[C], 2001-09, 2001-10, ottawa,Ontario,Canada.
[9] 崔之祜，江春，陈丽鑫译(A.Murat Tekalp著)，数字视频处理[M] 北京：电子工业出版社．1998
[10] Jean-Marc Odobez, Patrick Bouthemy. Direct Incremental Model-Based Image Motion Segmentation for Video Analysis[J]. Signal Processing, 1998,66:143-155.
[11] 黄波，杨勇，王桥等，一种用于视频分割的快速运动估计方法[J]，电路与系统学报．2001-03，6(1)：69-71
[12] La Baule. OPtimization Model. [S]ISO//IEC JTC1/SC29/WGll, N3675, 200.10.
[13] Patras, L.; Hendriks, E.A.; Lagendijk, R.L. Video Segmentation by MAP Labeling of Watershed Segments[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001-03,23(3):326-332.
[14] 詹劲峰，戚飞虎，王海龙，基于时空马尔可夫随机场的运动目标分割技术
[J]．通信学报，2000-11，21(11)：63—68．
[15] Kuo Chung-Ming, Hsieh Chaur-Heh, Huang Yong-Ren, et al. A New Mesh Based Temporal-Spatial Segmentation for Image Sequence[A]. Computer Software and Applications Conference,2000. COMPSAC 2000. The 24th Annual International[C], 2000: 395-400.
[16] Mark Everingham,Barry Thomas. Supervision Segmentation and Tracking of Non-rigid Objects Using a"Mixture of Histograms" Model [A]. IEEE International Conference on Image Processing, 2001-10,1: 62—65.
[17] 吴枫，高鹏，高文，基于网格模型的运动估计技术[J]，电子学报，2000-05，28(5)：47-51
[18] Hsu Pohsiang, Liu Ray, Chen Tsuhan. A Low Bit-rate Video Based on Two-dimensional Mesh Motion Compensation With Adaptive Interpolation[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2001-01,11(1): 111-117.
[19] Aria Nosratinia, New Kernel for Mesh-Based Motion Estimation[J]. IEEE Transactions on Circuits and Systems for Video Technology. 2001-01,11(1):40-51.
[20] Celasun,Tekalp A M,Gokcetekin M H, et al. 2-D Mesh-Based Video Object Segmentation and Tracking with Occlusion Resolution. [J] Signal Processing:Image Communication, 2001-08, 16(10):949-962.
[21] 夏利民，谷士文，基于形变模型的图像分割和非刚性目标的跟踪[J]，模式识别与人工智能．2000-03，13(1)：64—68．
[22] Horance H.s.Ip, Dinggang shen. An Affine-Invariant Active Contour Model (AI-Snake) for Model-Based Segmentation[J]. Image and vision Computing,1998,16:135-146
[23] Harper P, Reilly R B. Color Based Video Segmentation Using Level Sets[A]. Image Processing, 2000. Proceedings.2000 International Conferenceon [C], 2000,3: 480-483.
[24] Fan,Jianping, Yu,Jun Gen Fujita, et al. Spatio-temporal Segmentation for Compact Video Representation [J]. Signal Processing: Image Communication, 2001 (16):553-566.
[25] 施可为，傅锡天，蔡安妮等，含人脸的前景在活动图像序列中的分割[J]，北京邮电大学学报，2000-03，23(1)：66-70．
[26] Eckehard Steinbach, Peter Eisert,Bernd Girod. Motion-Based Analysis and Segmentation of Image Sequence Using 3-D Scene Models[J]. Signal Processing, 1998-04,66(2): 233-247
[27] Thomas Meier, King N.Ngan. Automatic Segmentation of Moving Objects for Video Object Plane Generation[J]. IEEE Transactions on Circuits and Systems
for Video Technology, 1998-09,8(5):525-538.
[28] Gu Chuang,Lee Ming-chieh. Semiautomatic Segmentation and Tracking of Semantic Video Objects[J]. IEEE Transactions on Circuits and Systems for Video Technology, 1998-09, 8(5):572-584.
[29] 张颖，张兆阳，基于二次空间变换的快速时空分割[J]，中国图象图形学报(A版)，2000-09，5(9)：744-749
[30] Benois-Pineau J,Morier F,Barba D, et al. Hierarchical Segmentation of Video Sequences for Content Manipulation and Adaptive Coding[J]. Signal Processing, 1998(66): 181-201
[31] Nitsuwat S,Jin J S, Hudson H M. Motion-Based Video Segmentation Using Fuzzy Clustering and Classical Mixture Model[A]. Image Processing, 2000. Proceedings. 2000 International Conference[C], 2000(1):300-303
[32] Robert Castagno,Touradj Ebrahimi,Murat kunt. Video Segmentation Based on Multiple Feature for Interactive Multimedia Application [J]. IEEE Transactions on Circuits and Systems for Video Technology, 1998-09,8(5): 562-571
[33] Ioannis Kompatsiaris,Michael Gerassimos Strintzis. Spatio-Temporal Segmentation and Tracking of Objects for Visualization of Videoconference Image Sequences[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2000-12,10(8): 1388-1402.
[34] Srinivas Sista, Rangasami L. Kashyap. Unsupervised Video Segmentation and Object tracking[J]. Computer in Industry. 2000(42):127-146
[35] kim Jinsang, Chen Tom. Multiple Feature Clustering for Image Sequence Segmentation[J].Pattern Recognition Letters, 2001 (22): 1207-1217.
[36] Wang Demin, Claude Labit. Morphological Spatio-temporal Simplification for Video Image Segmentation. Signal Processing [J], Image Communication, 1997(11):161-170
[37] 卢官明，毕厚杰，基于数学形态学的图像序列分割[J]，南京邮电学院学报，1997-06，17(2)：54-57
[38] 韩军，熊琼，孙文彦等，自动分割及跟踪视频运动对象的一种实现方法[J]，中国图象图形学报(A版)，2001，8：732-738
[39] 黄友珍，黄艺，余兆明，基于修正分水岭算法和时域跟踪的视频自动分割[M]，数字视频，2000-01：5-8
[40] Daniel Gatica-Perez, Chuang Gu, Ming-Ting Sun. Semantic Video Object Extraction Using Four-Band Water Shed and Partition Lattice Operators [J], IEEE Transactions on Circuits and Systems for Video Technology, 2001-05,11(5):603-618
[41] Laurenz Wiskott.Segmentation from motion: combining Gabor-and Mallat-wavelets to overcome the aperture and correspondence problems [J].
Pattern recognition, 1999,32:1751-1766
[42] Saman Cooray Noel O'Connor, Sean Marlow, Thomas Curran. et al. Semi-automatic video object segmentation using recursive shortest spanning tree and binary partition tree[M]
[43] Daniel Gatica-Perez,Sun,Ming-Ting Chuang Gu. Multlview extensive partion operators for semantic video object extraction[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2001-07,11(7): 788-801
[44] Ioannis Kompatsiaris, Dimitrios Tzovaras, Michael G. Strintzis. 3-D Model-Based Segmentation of Videoconference Image Sequences [J]. IEEE Transactions on Circuits and Systems for Video Technology, 1998-09,8(5): 547-561
[45] 俞刚毅，黄艺，用于视频对象平面生成的运动对象自动分割[J]，电子与信息学报，2001-07，23(7)：657-662．
[46] 史力，张兆扬，使用修改的豪氏道夫距离自动提取运动对象(A版)[J]．中国图象图形学报，2001-07，6(7)：805-810
[47] Munchurl Kim, Jeon J G, Kwak J S, et al. Moving Object Segmentation in Video Sequences by User Interaction and Automatic Object Tracking [J]. Image and Vision Computing, 2001-04, 19(5): 245-260
[48] Candemir Toklu, A.Murat Tekalp, Tanju Erdem. Semi-Automatic Video Segmentation in the Presence of Occlusion [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2000-06,10(4):624-629
[49] Christopher Rasmussen, Gregory D.Hager. Probabilistic data association method for tracking complex visual objects [J] IEEE Transactions on Pattern Analysis and Machine Intelligence 2000-06,23(6): 560-576
[50] Holger Eggers, Fabrice Moscheni, Roberto Castagno. Robust object tracking based on spatial characterization of objects by additive invariant
[51] Francois Bremond, Monique Thonnat. Tracking multiple non-rigid objects in video sequences[J]. IEEE Transactions on Circuits and Systems for Video Technology, 1998-09,8(5): 585-591
[52] Fabrice Moscheni, et al. Object tracking based on temporal and spatial information [S]. ISO/IEC JTC1/SC29/WGllMPEG96/M0962
[53] Zhang Jun, Gao Jianbo, Lin Wei-song. Image Sequence Segmentation Using 3-D Structure Tensor and Curve Evolution [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2001-05,11(5): 629-641
[54] 施建良，余松煜，傅立言．基于最短描述长度的序列图像运动分割[J]，计算机学报，1999-08，22(8)：809-815
[55] M. Kass, A. Witkin and D. Terzopoulos. Snakes:Active contour models. Proceedings of First International Conference On Computer
Vision, 1987,259-269
[56] A. A. Amini, S. Tehrani, and T. E. Weymouth, Using dynamic programming for minimizing the energy of active contours in the presence of hard constraints. Proceeding, Second International Conference on Computer Vision, 1988, 95-99
[57] Donna J. Williams and Mubarak Shah, A Fast Algorithm for Active Contours and Curvature Estimation, CVGIP: Image Understanding, Vol.55, No.1, Jannuary, 14-26, 1992
[58] P. C. Yuen, G. C. Feng, J. P. Zhou, A contour detection method: Initialization and contour model, Patten Recognition Letters 20(1999), 141-148
[59] Lilian Ji, Hong Yan, Attractable snakes based on the greedy algorithm for contour extraction, Pattern Recognition 35(2002), 791-806
[60] Chun Leung Lam, Shiu Yin Yuen, An unbiased active contour algorithm for object tracking, Pattern Recognition Letters 19(1998), 491-498
[2] Neti A, Colonnese S, Russo G, et al. Automatic Moving object and Background Separation[J]. Signal Processing, 1998-04,66(2): 219-232.
[3] Munchurl Kim, Jae Gark Choi, Daehee Kim et al. A VOP Generation Tool: Automatic Segmentation of Moving Objects In Image Sequences Based on Spatio-Temporal Infomation[J]. IEEE Transactions on Circuits and Systems for Video Technology, 1999-12,9(8): 1216-1226.
[4] Sifakis E, Tziritas G. Moving Object Localisation Using a Multi-label Fast Matching Algorithm[J]. Signal Processing :Image Communication, 2001(16):963-976.
[5] Roland Mech, Michael Wollborn. A Noise Robust Method for 2D Shape Estimation of Moving Objects in Video Sequences Considering a Moving Camera[J]. Signal Processing, 1998(66): 203-217.
[6] A. Aydin Alatan,Levent Onural.,Michael Wollborn,etal. Image Sequence Analysis for Emerging Interactive Multimedia Services-The European COST 211 Framework [J]. IEEE Transactions on Circuits and Systems for Video Technology. 1998-11,(8,7):802-813.
[7] 刘李杰，蔡德钧，翁南钐，一种面向运动的视频对象分割算法[J]，计算机学报．2000，23(12)：1326-1331．
[8] GeraId Kuhne, Stephan Richter, Markus Beier. Motion—Based Segmentation and Contour-Based Classification of Video Objects[A].ACM Multimedia[C], 2001-09, 2001-10, ottawa,Ontario,Canada.
[9] 崔之祜，江春，陈丽鑫译(A.Murat Tekalp著)，数字视频处理[M] 北京：电子工业出版社．1998
[10] Jean-Marc Odobez, Patrick Bouthemy. Direct Incremental Model-Based Image Motion Segmentation for Video Analysis[J]. Signal Processing, 1998,66:143-155.
[11] 黄波，杨勇，王桥等，一种用于视频分割的快速运动估计方法[J]，电路与系统学报．2001-03，6(1)：69-71
[12] La Baule. OPtimization Model. [S]ISO//IEC JTC1/SC29/WGll, N3675, 200.10.
[13] Patras, L.; Hendriks, E.A.; Lagendijk, R.L. Video Segmentation by MAP Labeling of Watershed Segments[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001-03,23(3):326-332.
[14] 詹劲峰，戚飞虎，王海龙，基于时空马尔可夫随机场的运动目标分割技术
[J]．通信学报，2000-11，21(11)：63—68．
[15] Kuo Chung-Ming, Hsieh Chaur-Heh, Huang Yong-Ren, et al. A New Mesh Based Temporal-Spatial Segmentation for Image Sequence[A]. Computer Software and Applications Conference,2000. COMPSAC 2000. The 24th Annual International[C], 2000: 395-400.
[16] Mark Everingham,Barry Thomas. Supervision Segmentation and Tracking of Non-rigid Objects Using a"Mixture of Histograms" Model [A]. IEEE International Conference on Image Processing, 2001-10,1: 62—65.
[17] 吴枫，高鹏，高文，基于网格模型的运动估计技术[J]，电子学报，2000-05，28(5)：47-51
[18] Hsu Pohsiang, Liu Ray, Chen Tsuhan. A Low Bit-rate Video Based on Two-dimensional Mesh Motion Compensation With Adaptive Interpolation[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2001-01,11(1): 111-117.
[19] Aria Nosratinia, New Kernel for Mesh-Based Motion Estimation[J]. IEEE Transactions on Circuits and Systems for Video Technology. 2001-01,11(1):40-51.
[20] Celasun,Tekalp A M,Gokcetekin M H, et al. 2-D Mesh-Based Video Object Segmentation and Tracking with Occlusion Resolution. [J] Signal Processing:Image Communication, 2001-08, 16(10):949-962.
[21] 夏利民，谷士文，基于形变模型的图像分割和非刚性目标的跟踪[J]，模式识别与人工智能．2000-03，13(1)：64—68．
[22] Horance H.s.Ip, Dinggang shen. An Affine-Invariant Active Contour Model (AI-Snake) for Model-Based Segmentation[J]. Image and vision Computing,1998,16:135-146
[23] Harper P, Reilly R B. Color Based Video Segmentation Using Level Sets[A]. Image Processing, 2000. Proceedings.2000 International Conferenceon [C], 2000,3: 480-483.
[24] Fan,Jianping, Yu,Jun Gen Fujita, et al. Spatio-temporal Segmentation for Compact Video Representation [J]. Signal Processing: Image Communication, 2001 (16):553-566.
[25] 施可为，傅锡天，蔡安妮等，含人脸的前景在活动图像序列中的分割[J]，北京邮电大学学报，2000-03，23(1)：66-70．
[26] Eckehard Steinbach, Peter Eisert,Bernd Girod. Motion-Based Analysis and Segmentation of Image Sequence Using 3-D Scene Models[J]. Signal Processing, 1998-04,66(2): 233-247
[27] Thomas Meier, King N.Ngan. Automatic Segmentation of Moving Objects for Video Object Plane Generation[J]. IEEE Transactions on Circuits and Systems
for Video Technology, 1998-09,8(5):525-538.
[28] Gu Chuang,Lee Ming-chieh. Semiautomatic Segmentation and Tracking of Semantic Video Objects[J]. IEEE Transactions on Circuits and Systems for Video Technology, 1998-09, 8(5):572-584.
[29] 张颖，张兆阳，基于二次空间变换的快速时空分割[J]，中国图象图形学报(A版)，2000-09，5(9)：744-749
[30] Benois-Pineau J,Morier F,Barba D, et al. Hierarchical Segmentation of Video Sequences for Content Manipulation and Adaptive Coding[J]. Signal Processing, 1998(66): 181-201
[31] Nitsuwat S,Jin J S, Hudson H M. Motion-Based Video Segmentation Using Fuzzy Clustering and Classical Mixture Model[A]. Image Processing, 2000. Proceedings. 2000 International Conference[C], 2000(1):300-303
[32] Robert Castagno,Touradj Ebrahimi,Murat kunt. Video Segmentation Based on Multiple Feature for Interactive Multimedia Application [J]. IEEE Transactions on Circuits and Systems for Video Technology, 1998-09,8(5): 562-571
[33] Ioannis Kompatsiaris,Michael Gerassimos Strintzis. Spatio-Temporal Segmentation and Tracking of Objects for Visualization of Videoconference Image Sequences[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2000-12,10(8): 1388-1402.
[34] Srinivas Sista, Rangasami L. Kashyap. Unsupervised Video Segmentation and Object tracking[J]. Computer in Industry. 2000(42):127-146
[35] kim Jinsang, Chen Tom. Multiple Feature Clustering for Image Sequence Segmentation[J].Pattern Recognition Letters, 2001 (22): 1207-1217.
[36] Wang Demin, Claude Labit. Morphological Spatio-temporal Simplification for Video Image Segmentation. Signal Processing [J], Image Communication, 1997(11):161-170
[37] 卢官明，毕厚杰，基于数学形态学的图像序列分割[J]，南京邮电学院学报，1997-06，17(2)：54-57
[38] 韩军，熊琼，孙文彦等，自动分割及跟踪视频运动对象的一种实现方法[J]，中国图象图形学报(A版)，2001，8：732-738
[39] 黄友珍，黄艺，余兆明，基于修正分水岭算法和时域跟踪的视频自动分割[M]，数字视频，2000-01：5-8
[40] Daniel Gatica-Perez, Chuang Gu, Ming-Ting Sun. Semantic Video Object Extraction Using Four-Band Water Shed and Partition Lattice Operators [J], IEEE Transactions on Circuits and Systems for Video Technology, 2001-05,11(5):603-618
[41] Laurenz Wiskott.Segmentation from motion: combining Gabor-and Mallat-wavelets to overcome the aperture and correspondence problems [J].
Pattern recognition, 1999,32:1751-1766
[42] Saman Cooray Noel O'Connor, Sean Marlow, Thomas Curran. et al. Semi-automatic video object segmentation using recursive shortest spanning tree and binary partition tree[M]
[43] Daniel Gatica-Perez,Sun,Ming-Ting Chuang Gu. Multlview extensive partion operators for semantic video object extraction[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2001-07,11(7): 788-801
[44] Ioannis Kompatsiaris, Dimitrios Tzovaras, Michael G. Strintzis. 3-D Model-Based Segmentation of Videoconference Image Sequences [J]. IEEE Transactions on Circuits and Systems for Video Technology, 1998-09,8(5): 547-561
[45] 俞刚毅，黄艺，用于视频对象平面生成的运动对象自动分割[J]，电子与信息学报，2001-07，23(7)：657-662．
[46] 史力，张兆扬，使用修改的豪氏道夫距离自动提取运动对象(A版)[J]．中国图象图形学报，2001-07，6(7)：805-810
[47] Munchurl Kim, Jeon J G, Kwak J S, et al. Moving Object Segmentation in Video Sequences by User Interaction and Automatic Object Tracking [J]. Image and Vision Computing, 2001-04, 19(5): 245-260
[48] Candemir Toklu, A.Murat Tekalp, Tanju Erdem. Semi-Automatic Video Segmentation in the Presence of Occlusion [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2000-06,10(4):624-629
[49] Christopher Rasmussen, Gregory D.Hager. Probabilistic data association method for tracking complex visual objects [J] IEEE Transactions on Pattern Analysis and Machine Intelligence 2000-06,23(6): 560-576
[50] Holger Eggers, Fabrice Moscheni, Roberto Castagno. Robust object tracking based on spatial characterization of objects by additive invariant
[51] Francois Bremond, Monique Thonnat. Tracking multiple non-rigid objects in video sequences[J]. IEEE Transactions on Circuits and Systems for Video Technology, 1998-09,8(5): 585-591
[52] Fabrice Moscheni, et al. Object tracking based on temporal and spatial information [S]. ISO/IEC JTC1/SC29/WGllMPEG96/M0962
[53] Zhang Jun, Gao Jianbo, Lin Wei-song. Image Sequence Segmentation Using 3-D Structure Tensor and Curve Evolution [J]. IEEE Transactions on Circuits and Systems for Video Technology, 2001-05,11(5): 629-641
[54] 施建良，余松煜，傅立言．基于最短描述长度的序列图像运动分割[J]，计算机学报，1999-08，22(8)：809-815
[55] M. Kass, A. Witkin and D. Terzopoulos. Snakes:Active contour models. Proceedings of First International Conference On Computer
Vision, 1987,259-269
[56] A. A. Amini, S. Tehrani, and T. E. Weymouth, Using dynamic programming for minimizing the energy of active contours in the presence of hard constraints. Proceeding, Second International Conference on Computer Vision, 1988, 95-99
[57] Donna J. Williams and Mubarak Shah, A Fast Algorithm for Active Contours and Curvature Estimation, CVGIP: Image Understanding, Vol.55, No.1, Jannuary, 14-26, 1992
[58] P. C. Yuen, G. C. Feng, J. P. Zhou, A contour detection method: Initialization and contour model, Patten Recognition Letters 20(1999), 141-148
[59] Lilian Ji, Hong Yan, Attractable snakes based on the greedy algorithm for contour extraction, Pattern Recognition 35(2002), 791-806
[60] Chun Leung Lam, Shiu Yin Yuen, An unbiased active contour algorithm for object tracking, Pattern Recognition Letters 19(1998), 491-498