应用于步态识别的人体轮廓提取
|
摘要
步态识别根据人走路的姿势进行身份识别。和其它生物特征相比,捕捉步态特征无需身体接触,不具有侵犯性。在步态识别中,完整的人体轮廓是特征提取、特征表达、目标分类与目标识别等后期处理的前提条件。因此,本课题的主要目的是研究运用目标分割技术从步态图像序列中提取人体轮廓。主要的工作包括以下几点:
①针对块匹配算法初始搜索点选择与实际情况存在差异的问题,在运用UCBDS法(unrestricted center-biased diamond search,非限制性中心倾向分布的钻石形搜索方法)进行运动估计时,采用中值法预测初始搜索点,并根据各候选块匹配度减少UCBDS法的搜索范围。
②研究了一种新的基于运动信息和分水岭变换的运动目标分割算法。采用改进的块匹配算法对人体目标运动进行估计,运用分水岭算法将当前帧图像分割成封闭而不重叠的小区域,应用仿射参数模型进行基于运动的块区域合并,从而完成人体轮廓的提取。实验结果表明,该算法提高了步态识别率。
③提出基于Snake模型的优化人体轮廓的方法。以基于运动信息和分水岭变换的运动目标分割算法得到的结果代替人工勾勒作为Snake模型的初始轮廓,实现了整个分割过程的自动化。Snake模型算法主要有变分法、动态规划法、Greedy算法。在本文中对Greedy算法进行了改进:通过修改外部能量函数区分真正的轮廓点和孤立的噪声点;构造了一个调节参数公式实现自动调节内部能量和外部能量的权值。实验结果表明,该方法能够在低对比度、局部动态背景下正确提取人体目标轮廓。
Gait recognition is the process of identifying individuals by the way they walk. Compared with other biometrics, such as fingerprint, face and iris, the identification by gait is unobtrusive and does not require touching the human body. In gait recognition, effective extraction of human contour is a prerequisite of subsequent processing including feature extraction, feature expression, target classification and target recognition. The goal of this thesis is to research human contour extraction algorithm. The main contributions are listed as follows:
①A new block-matching motion estimation algorithm based on UCBDS (unrestricted center-biased diamond search) is put forward in this thesis. For the original UCBDS, the motion vector of the current block is assumed to be zero, but this doesn’t match with the real condition. Aiming at a better prediction result, the median method is adopted to confirm the starting search position. In addition, according to the matching possibility of candidate blocks, the search region of UCBDS is decreased.
②This thesis presents a new motion object segmentation algorithm based on motion information and the watershed algorithm. Firstly, the improved block-matching estimation algorithm is used to estimate the motion fields of the image. Secondly, we apply the watershed algorithm to divide the current image into a number of closed and non-overlapping regions. Finally, we utilize the affine parameter model to merge these regions. The experiments show that this new algorithm can effectively extract human contour and improve the performance of gait recognition.
③An improved object contour method based on Snake model is investigated for an accurate object contour. The initial contour of Snake model is extracted automatically by the above algorithm rather than by manual work. In this paper, we use Greedy algorithm to compute the energy function of Snake model. The true points of contour and isolated noise points are distinguished automatically by applying a new external function. In addition, a formula is constructed to automatically adjust the weights of internal energy and external energy. The experiments show that the method can extract accurate contour under complex background.
①针对块匹配算法初始搜索点选择与实际情况存在差异的问题,在运用UCBDS法(unrestricted center-biased diamond search,非限制性中心倾向分布的钻石形搜索方法)进行运动估计时,采用中值法预测初始搜索点,并根据各候选块匹配度减少UCBDS法的搜索范围。
②研究了一种新的基于运动信息和分水岭变换的运动目标分割算法。采用改进的块匹配算法对人体目标运动进行估计,运用分水岭算法将当前帧图像分割成封闭而不重叠的小区域,应用仿射参数模型进行基于运动的块区域合并,从而完成人体轮廓的提取。实验结果表明,该算法提高了步态识别率。
③提出基于Snake模型的优化人体轮廓的方法。以基于运动信息和分水岭变换的运动目标分割算法得到的结果代替人工勾勒作为Snake模型的初始轮廓,实现了整个分割过程的自动化。Snake模型算法主要有变分法、动态规划法、Greedy算法。在本文中对Greedy算法进行了改进:通过修改外部能量函数区分真正的轮廓点和孤立的噪声点;构造了一个调节参数公式实现自动调节内部能量和外部能量的权值。实验结果表明,该方法能够在低对比度、局部动态背景下正确提取人体目标轮廓。
Gait recognition is the process of identifying individuals by the way they walk. Compared with other biometrics, such as fingerprint, face and iris, the identification by gait is unobtrusive and does not require touching the human body. In gait recognition, effective extraction of human contour is a prerequisite of subsequent processing including feature extraction, feature expression, target classification and target recognition. The goal of this thesis is to research human contour extraction algorithm. The main contributions are listed as follows:
①A new block-matching motion estimation algorithm based on UCBDS (unrestricted center-biased diamond search) is put forward in this thesis. For the original UCBDS, the motion vector of the current block is assumed to be zero, but this doesn’t match with the real condition. Aiming at a better prediction result, the median method is adopted to confirm the starting search position. In addition, according to the matching possibility of candidate blocks, the search region of UCBDS is decreased.
②This thesis presents a new motion object segmentation algorithm based on motion information and the watershed algorithm. Firstly, the improved block-matching estimation algorithm is used to estimate the motion fields of the image. Secondly, we apply the watershed algorithm to divide the current image into a number of closed and non-overlapping regions. Finally, we utilize the affine parameter model to merge these regions. The experiments show that this new algorithm can effectively extract human contour and improve the performance of gait recognition.
③An improved object contour method based on Snake model is investigated for an accurate object contour. The initial contour of Snake model is extracted automatically by the above algorithm rather than by manual work. In this paper, we use Greedy algorithm to compute the energy function of Snake model. The true points of contour and isolated noise points are distinguished automatically by applying a new external function. In addition, a formula is constructed to automatically adjust the weights of internal energy and external energy. The experiments show that the method can extract accurate contour under complex background.
引文
[1] http://www.ccw.com.cn/applic/news/htm2003/20030606_124GH.htm
[2] 叶波,文玉梅. 基于步态的人身份识别技术综述[J]. 计算机应用, 2005,25(11).
[3] 王亮,胡卫明等. 基于步态的身份识别[J]. 计算机学报. 2003,26(3):353-360.
[4] X.Zhuang, R.M.Haralick, Rigid Body Motion and the Optical Flow Image in Proceedings[J], IEEE First Intelligence Applications, Denver, 1984: 366-375.
[5] A Murat Tekalp. Digital Video Processing[M]. Englewood Cliffs, NJ: Pretice-Hall, 1995
[6] Koga T. Motion Compensated Interframe Coding for Video Conferenceing[J]. Proc Nat Telecommun Conf, 1981,3: G5.3.1~G5.3.5
[7] Li R X, Zeng B, Liou M L. A New Three-step Search Algorithm for Block Motion Estimation[J]. IEEE Trans on Circuits and System for Video Technology, 1994,4(4): 438~442
[8] Po L M, Ma W C. A Novel Four-step Search Algorithm for Fast Block Motion Estimation[J]. IEEE Trans on Circuits and System for Video Technology, 1996,6(3):313~317.
[9] Neti, Colonnese S, Russo C, et al. Automatic Moving object and Background Separation[J]. Signal Processing, 1998-04(2):219-232.
[10] Munchurl Kim, Jae Gark Choi, Daehee Kim et al. A VOP Generation Tool: Automatic Segmentation of Moving Objects In Image Sequences Based on Spatiotemporal Information[J]. IEEE Transactions on Circuits and Systems for Video Technology, 1999-12,9(8) :1216-1226.
[11] A.Aydin Alatan, Levent Onural, Michael Wollborn, et al. 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.
[12] 邱志强, 于起峰. 从建筑物序列恢复三维结构[J]. 武汉大学学报(工学版),2003, 第 36 卷,第 3 期.
[13] 章海涛,林海,潘志庚. 基于几何和图像的建筑物建模方法的实现[J]. 小型微型计算机系统,1998 年,第 8 期.
[14] Fan, Jianping, Yu, Jun Gen Fujita, et al. Spatiotemporal Segmentation for Compact Video Representation[J].Signal Processing: Image Communication,2001(16):553-566
[15] 施可为,傅锡天,蔡安妮等. 含人脸的前景在运动图像序列中的分割[J]. 北京邮电大学学报,2000-03,23(1):66-70
[16] Eckehard Steinbach, Peter Eisert, Bernd Girod. Motion-Based Analysis and Segmentation of Tmage Sequence Using 3-D Scene Models[J]. SignalProcessing, 1998-04,66(2):233-247
[17] 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
[18] Gu Chuang, Lee Ming-chieh. Semiautomatic Segmentation and Tracking of Semantic Video Objects[J]. IEEE Transactions on Circuits and System for Video Technology, l998-09,8(5):572-584
[19] 张颖,张兆阳,基于二次空间变换的快速时空分割[J],中国图像图形学报(A 版),2000-09,5(9):744-749
[20] Benois-Pineau J, Morier F, Barba D, et al. Hierarchical Segmentation of Video Sequences for Content Manipulation and Adaptive Coding[J]. Signal Processing, l998(66): 181-201.
[21] Berghoim F, Edge Focusing[J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1987,9(9):726-741.
[22] Bhahalosh Cnanda, Malay K.Kundu and Y Vani Padmaja. A Multi-Scale Morphologic Edge Detector[J]. Pattern Recognition,1998,31(10):1469-1478.
[23] Ziou D, Tabbone S. A Multi-Scale Edge Detector[J]. Pattern Recognition. 1993, 26(9): 1305-1314.
[24] Brown M A, Blackwell K T, and Khalak H G et al. Mufti-Scale Edge Detection and Feature Binding: An Intergrated Approach[J]. Pattern Recognition. 1983,31(10):1479-1490.
[25] 黄慧颖. 一种基于高斯滤波与矢量微分算子的小波多尺度边缘检测算法[J]. 沈阳化工学院学报, 2001,15(2): 105-107.
[26] Brink A B. Gray Level Thresholding of Images Using a Correlation Criterion[J]. Pattern Recognition Letters,1989,9:335-341.
[27] Mardia K V and Hainsworth T J. A Spatial Thresholding Method for Image Segmentation. IEEE Trans. Pattern Analysis and Machine Intelligence.1988,10:919-927
[28] Pun T . A New Method for Gray Level Picture Thresholding Using the Entropy of the Histogram. Signal Processing, 1980,2:223-237.
[29] 靳宏磊,朱蔚萍,李立源,陈维南. 二维灰度直方图的最佳分割方法[J]. 模式识别与人工智能. 1999, 12(3):329-333.
[30] 刘文萍,吴立德. 图像分割中闲值选取方法比较研究[J]. 模式识别与人工智能,1997,10(3): 271-277.
[31] Halt L O. Bensaid A M, Clarke, L P, and Velthuizen RP et al, A Comparison of Neural Network and Fuzzy Clustering Techniques in Segmenting Magnetic Resonances Images of the Brain[J].IEEE Trans, Neural Networks, 1992,3(5):672-681.
[32] Lin J.S, Cheng K.S and Mao C.W. A Fuzzy Hopfield Neural Network for Medial Images Segmentation[J]. IEEE Trans. Neural Science, 1996,43(4):2389.
[33] Liu Y W and Lee S U. On the Color Image Segmentation Algorithm Based on the Thresholding and the Fussy c-Means Techniques[J]. Pattern Recognition,1990,23(9):935-952.
[34] Sang Ho Park, Dong Yun, and Sang UK Lee. Color Image Segmentation Based on 3-D Clustering: Morphological Approach[J]. Pattern Recognition, 1998,31(8):1061-1076.
[35] Philippe Schmid. Segmentation of Digitized Dermstoscopic Images by Two Dimensional Color Clustering[J]. IEEE Trans. On Medical Imaging,1999,18(2):164-171.
[36] 陈燕新,戚飞虎. 基于竞争 Hopfield 网络的自动聚类图像分割方法[J]. 模式识别与人工智能.1998, 11(2):215-221.
[37] 胡世英,周源华. 模糊选择多分辫率 Kohonen 聚类网络用于灰度图像分割[J].电子学报. 1999, 27(10):34-37.
[38] Wang J P, Stochastic Relaxation an Partitions with Connected Components and Its Application to Image Segmentation[J]. IEEE Tranc. Pattern Analysis and Machine Intelligence, 1994,16:641-647.
[39] Peleg S. A New Probabilistic Relaxation Scueme[J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1980, 2:362-369.
[40] 戴剑彬,张大力. 图像分析中的松弛算法[J]. 中国图形图像学报. 1998,3A(2):96-99.
[41] Themeau A, Borel N. A Region Growing and Merging Algorithm to Color Segmentation[J]. Pattern Recognition, 1997, 30:1191-1203.
[42] Sandor T, Metcalf D, and Kim Y J. Segmentation of Brain CT Images Using the Concept of Region Growing[J]. Biomed Computer, 1991(29):133-147.
[43] Adams R and Bischof L. Seeded Region Growing[J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1994, 16:641-647.
[44] 尹平,王润生. 基于边缘信息的分开合并图像分割算法[J]. 中国图像图形学报,1998,3A(6): 450-454.
[45] Roland Mech and Michael Wollborn. A Noice Robust Method for 2D Shape Estimation of Moving Objects in Video Sequences Considering a Mewing Camera[J]. Signal Processing, 1998, 66(2):203-217
[46] 朱莉,朱音,黄贤武. 基于主动轮廓模型提取运动目标的图像分割技术[J]. 微电子学与计算机,2004 年,第 1 期:106-108,113
[47] Stringa E, et al. Real-time video-shot detection for scene surveillance applications [J]. IEEE Transactions on Image Processing, 2000, 1(9):69-79.
[48] Lipton A, Fujiyoshi H, Patil R. Moving target classification and tracking from real-time video[C]. NJ:Proc IEEE.
[49] 何卫华,李平等. 复杂背景下基于图像融合的运动目标轮廓提取算法[J]. 计算机应用. 2006,26(1).
[50] Meier T, King N. Automatic segmentation of moving objects for video objects plane generation[J]. IEEE Trans. on Circuits and System for Video Technology, 1998, 8(5):525-538.
[51] Neri A, Colonnese S, Russo G. Automatic moving object and background separation[J]. Signal Processing, 1998,66:219-232.
[52] Wei W, Ngan K N. Automatic video object segmentation for MPEG-4 [C]. Proceedings of SPIE-the International Society for Optical Engineering, 2003, 51,50:9-19.
[53] F. Meyer, S. Beucher. Morphology segmentation[J]. Visual Comm and Image Representation, 1990,1(1): 21-26.
[54] Liu L K, Feig E. A Block-based Gradient Descent Search Algorithm for Block Motion Estimation in Video Coding[J]. IEEE Trans on Circuits and System for Video Technology, 1996, 6(4):419-422.
[55] Tham J Y, Ranganath S, Ranganath M, et al. A Novel Unrestricted Center-biased Diamond Search Algorithm for Block Motion Estimation[J]. IEEE Transactions on Circuits and System for Video Technology, 1998, 8(4): 369-377.
[56] R. Gross and J. Shi. The CMU Motion of Body (mobo) Database. Technical Report CMU-RI-TR-01-18, Carnegie Mellon University, 2001.
[57] L. Vincent, MorphologicalApplications and Efficient Algorithms[M]. Vo1.12(2):pp.176-201. Gray Scale Reconstruction in Image Analysis: Trans. on Image Processing, 1993.
[58] K. Haris, S. Efstratiadis, Hybrid Image Segmentation Using Watersheds and Fast Region Merging[J]. IEEE Trans. on Image Processing, 1998, Vol.7(12): pp.1684-1699.
[59] P. R. Hill, C. N. Canagarajah, D. R. Bull, Image Segmentation Using a Texture Gradient Based Watershed Transform[J]. IEEE Trans. on Image Processing, 2004, VoI.12(12):pp.l 618-1633.
[60] C. Lantuejoul, Skeletonization in Quantitative Met Algraphy[J]. Issues of Digital Image Processing, the Netherlands:Sifthoff and Noordhoff, 1980.
[61] M. Susanta, C. Bhabatosh, MultiScale Morphological Segmentation of Gray-Scale Images[J]. IEEE Trans. on Image Processing, 2004, Vo1.12(5):pp.533-549.
[62] 马丽红,张宇,邓建平,基于形态开闭滤波二值标记和纹理特征的分水岭算法[J]. 中国图像图形学报, 2003, Vol.8(1):pp.77-83.
[63] S. Sarkar, Z. Liu, I. Robledo, P, Grother and K.Bowyer. The humanID gait challenge problem: data Sets, performance, and analysis[J]. IEEE Trans on Pattern Analysis and Machine Intelligence on Volume 27, Feb 2005 Page(s): 162-177.
[64] R. Duda, P. Hart, and D. Stork, Pattern Classification[M]. Wiley, 2001.
[65] Kass M,Winkin A,Terzopoulos D. Snakes: Active contour models[A].1n: Proceedings of First International Conference On Computer Vision[C],London, 1987: 259~269.
[66] 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[J]. In Proc. Second International Conference on Computer Vision, 1998, 95-99.
[67] Williams. D. J, and Shah. M.: A Fast Algorithm for Active Contours and Curvature Estimation. CVGIP:Image Understanding. 1996, 55(1), pp. 14-26.
[68] Kuno Y et al. Automated Detection of Human for Visual Surveillance System[J]. In:Proceedings of International Conference on Pattern Recognition,Vienna,1996. 865- 869.
[2] 叶波,文玉梅. 基于步态的人身份识别技术综述[J]. 计算机应用, 2005,25(11).
[3] 王亮,胡卫明等. 基于步态的身份识别[J]. 计算机学报. 2003,26(3):353-360.
[4] X.Zhuang, R.M.Haralick, Rigid Body Motion and the Optical Flow Image in Proceedings[J], IEEE First Intelligence Applications, Denver, 1984: 366-375.
[5] A Murat Tekalp. Digital Video Processing[M]. Englewood Cliffs, NJ: Pretice-Hall, 1995
[6] Koga T. Motion Compensated Interframe Coding for Video Conferenceing[J]. Proc Nat Telecommun Conf, 1981,3: G5.3.1~G5.3.5
[7] Li R X, Zeng B, Liou M L. A New Three-step Search Algorithm for Block Motion Estimation[J]. IEEE Trans on Circuits and System for Video Technology, 1994,4(4): 438~442
[8] Po L M, Ma W C. A Novel Four-step Search Algorithm for Fast Block Motion Estimation[J]. IEEE Trans on Circuits and System for Video Technology, 1996,6(3):313~317.
[9] Neti, Colonnese S, Russo C, et al. Automatic Moving object and Background Separation[J]. Signal Processing, 1998-04(2):219-232.
[10] Munchurl Kim, Jae Gark Choi, Daehee Kim et al. A VOP Generation Tool: Automatic Segmentation of Moving Objects In Image Sequences Based on Spatiotemporal Information[J]. IEEE Transactions on Circuits and Systems for Video Technology, 1999-12,9(8) :1216-1226.
[11] A.Aydin Alatan, Levent Onural, Michael Wollborn, et al. 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.
[12] 邱志强, 于起峰. 从建筑物序列恢复三维结构[J]. 武汉大学学报(工学版),2003, 第 36 卷,第 3 期.
[13] 章海涛,林海,潘志庚. 基于几何和图像的建筑物建模方法的实现[J]. 小型微型计算机系统,1998 年,第 8 期.
[14] Fan, Jianping, Yu, Jun Gen Fujita, et al. Spatiotemporal Segmentation for Compact Video Representation[J].Signal Processing: Image Communication,2001(16):553-566
[15] 施可为,傅锡天,蔡安妮等. 含人脸的前景在运动图像序列中的分割[J]. 北京邮电大学学报,2000-03,23(1):66-70
[16] Eckehard Steinbach, Peter Eisert, Bernd Girod. Motion-Based Analysis and Segmentation of Tmage Sequence Using 3-D Scene Models[J]. SignalProcessing, 1998-04,66(2):233-247
[17] 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
[18] Gu Chuang, Lee Ming-chieh. Semiautomatic Segmentation and Tracking of Semantic Video Objects[J]. IEEE Transactions on Circuits and System for Video Technology, l998-09,8(5):572-584
[19] 张颖,张兆阳,基于二次空间变换的快速时空分割[J],中国图像图形学报(A 版),2000-09,5(9):744-749
[20] Benois-Pineau J, Morier F, Barba D, et al. Hierarchical Segmentation of Video Sequences for Content Manipulation and Adaptive Coding[J]. Signal Processing, l998(66): 181-201.
[21] Berghoim F, Edge Focusing[J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1987,9(9):726-741.
[22] Bhahalosh Cnanda, Malay K.Kundu and Y Vani Padmaja. A Multi-Scale Morphologic Edge Detector[J]. Pattern Recognition,1998,31(10):1469-1478.
[23] Ziou D, Tabbone S. A Multi-Scale Edge Detector[J]. Pattern Recognition. 1993, 26(9): 1305-1314.
[24] Brown M A, Blackwell K T, and Khalak H G et al. Mufti-Scale Edge Detection and Feature Binding: An Intergrated Approach[J]. Pattern Recognition. 1983,31(10):1479-1490.
[25] 黄慧颖. 一种基于高斯滤波与矢量微分算子的小波多尺度边缘检测算法[J]. 沈阳化工学院学报, 2001,15(2): 105-107.
[26] Brink A B. Gray Level Thresholding of Images Using a Correlation Criterion[J]. Pattern Recognition Letters,1989,9:335-341.
[27] Mardia K V and Hainsworth T J. A Spatial Thresholding Method for Image Segmentation. IEEE Trans. Pattern Analysis and Machine Intelligence.1988,10:919-927
[28] Pun T . A New Method for Gray Level Picture Thresholding Using the Entropy of the Histogram. Signal Processing, 1980,2:223-237.
[29] 靳宏磊,朱蔚萍,李立源,陈维南. 二维灰度直方图的最佳分割方法[J]. 模式识别与人工智能. 1999, 12(3):329-333.
[30] 刘文萍,吴立德. 图像分割中闲值选取方法比较研究[J]. 模式识别与人工智能,1997,10(3): 271-277.
[31] Halt L O. Bensaid A M, Clarke, L P, and Velthuizen RP et al, A Comparison of Neural Network and Fuzzy Clustering Techniques in Segmenting Magnetic Resonances Images of the Brain[J].IEEE Trans, Neural Networks, 1992,3(5):672-681.
[32] Lin J.S, Cheng K.S and Mao C.W. A Fuzzy Hopfield Neural Network for Medial Images Segmentation[J]. IEEE Trans. Neural Science, 1996,43(4):2389.
[33] Liu Y W and Lee S U. On the Color Image Segmentation Algorithm Based on the Thresholding and the Fussy c-Means Techniques[J]. Pattern Recognition,1990,23(9):935-952.
[34] Sang Ho Park, Dong Yun, and Sang UK Lee. Color Image Segmentation Based on 3-D Clustering: Morphological Approach[J]. Pattern Recognition, 1998,31(8):1061-1076.
[35] Philippe Schmid. Segmentation of Digitized Dermstoscopic Images by Two Dimensional Color Clustering[J]. IEEE Trans. On Medical Imaging,1999,18(2):164-171.
[36] 陈燕新,戚飞虎. 基于竞争 Hopfield 网络的自动聚类图像分割方法[J]. 模式识别与人工智能.1998, 11(2):215-221.
[37] 胡世英,周源华. 模糊选择多分辫率 Kohonen 聚类网络用于灰度图像分割[J].电子学报. 1999, 27(10):34-37.
[38] Wang J P, Stochastic Relaxation an Partitions with Connected Components and Its Application to Image Segmentation[J]. IEEE Tranc. Pattern Analysis and Machine Intelligence, 1994,16:641-647.
[39] Peleg S. A New Probabilistic Relaxation Scueme[J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1980, 2:362-369.
[40] 戴剑彬,张大力. 图像分析中的松弛算法[J]. 中国图形图像学报. 1998,3A(2):96-99.
[41] Themeau A, Borel N. A Region Growing and Merging Algorithm to Color Segmentation[J]. Pattern Recognition, 1997, 30:1191-1203.
[42] Sandor T, Metcalf D, and Kim Y J. Segmentation of Brain CT Images Using the Concept of Region Growing[J]. Biomed Computer, 1991(29):133-147.
[43] Adams R and Bischof L. Seeded Region Growing[J]. IEEE Trans. Pattern Analysis and Machine Intelligence, 1994, 16:641-647.
[44] 尹平,王润生. 基于边缘信息的分开合并图像分割算法[J]. 中国图像图形学报,1998,3A(6): 450-454.
[45] Roland Mech and Michael Wollborn. A Noice Robust Method for 2D Shape Estimation of Moving Objects in Video Sequences Considering a Mewing Camera[J]. Signal Processing, 1998, 66(2):203-217
[46] 朱莉,朱音,黄贤武. 基于主动轮廓模型提取运动目标的图像分割技术[J]. 微电子学与计算机,2004 年,第 1 期:106-108,113
[47] Stringa E, et al. Real-time video-shot detection for scene surveillance applications [J]. IEEE Transactions on Image Processing, 2000, 1(9):69-79.
[48] Lipton A, Fujiyoshi H, Patil R. Moving target classification and tracking from real-time video[C]. NJ:Proc IEEE.
[49] 何卫华,李平等. 复杂背景下基于图像融合的运动目标轮廓提取算法[J]. 计算机应用. 2006,26(1).
[50] Meier T, King N. Automatic segmentation of moving objects for video objects plane generation[J]. IEEE Trans. on Circuits and System for Video Technology, 1998, 8(5):525-538.
[51] Neri A, Colonnese S, Russo G. Automatic moving object and background separation[J]. Signal Processing, 1998,66:219-232.
[52] Wei W, Ngan K N. Automatic video object segmentation for MPEG-4 [C]. Proceedings of SPIE-the International Society for Optical Engineering, 2003, 51,50:9-19.
[53] F. Meyer, S. Beucher. Morphology segmentation[J]. Visual Comm and Image Representation, 1990,1(1): 21-26.
[54] Liu L K, Feig E. A Block-based Gradient Descent Search Algorithm for Block Motion Estimation in Video Coding[J]. IEEE Trans on Circuits and System for Video Technology, 1996, 6(4):419-422.
[55] Tham J Y, Ranganath S, Ranganath M, et al. A Novel Unrestricted Center-biased Diamond Search Algorithm for Block Motion Estimation[J]. IEEE Transactions on Circuits and System for Video Technology, 1998, 8(4): 369-377.
[56] R. Gross and J. Shi. The CMU Motion of Body (mobo) Database. Technical Report CMU-RI-TR-01-18, Carnegie Mellon University, 2001.
[57] L. Vincent, MorphologicalApplications and Efficient Algorithms[M]. Vo1.12(2):pp.176-201. Gray Scale Reconstruction in Image Analysis: Trans. on Image Processing, 1993.
[58] K. Haris, S. Efstratiadis, Hybrid Image Segmentation Using Watersheds and Fast Region Merging[J]. IEEE Trans. on Image Processing, 1998, Vol.7(12): pp.1684-1699.
[59] P. R. Hill, C. N. Canagarajah, D. R. Bull, Image Segmentation Using a Texture Gradient Based Watershed Transform[J]. IEEE Trans. on Image Processing, 2004, VoI.12(12):pp.l 618-1633.
[60] C. Lantuejoul, Skeletonization in Quantitative Met Algraphy[J]. Issues of Digital Image Processing, the Netherlands:Sifthoff and Noordhoff, 1980.
[61] M. Susanta, C. Bhabatosh, MultiScale Morphological Segmentation of Gray-Scale Images[J]. IEEE Trans. on Image Processing, 2004, Vo1.12(5):pp.533-549.
[62] 马丽红,张宇,邓建平,基于形态开闭滤波二值标记和纹理特征的分水岭算法[J]. 中国图像图形学报, 2003, Vol.8(1):pp.77-83.
[63] S. Sarkar, Z. Liu, I. Robledo, P, Grother and K.Bowyer. The humanID gait challenge problem: data Sets, performance, and analysis[J]. IEEE Trans on Pattern Analysis and Machine Intelligence on Volume 27, Feb 2005 Page(s): 162-177.
[64] R. Duda, P. Hart, and D. Stork, Pattern Classification[M]. Wiley, 2001.
[65] Kass M,Winkin A,Terzopoulos D. Snakes: Active contour models[A].1n: Proceedings of First International Conference On Computer Vision[C],London, 1987: 259~269.
[66] 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[J]. In Proc. Second International Conference on Computer Vision, 1998, 95-99.
[67] Williams. D. J, and Shah. M.: A Fast Algorithm for Active Contours and Curvature Estimation. CVGIP:Image Understanding. 1996, 55(1), pp. 14-26.
[68] Kuno Y et al. Automated Detection of Human for Visual Surveillance System[J]. In:Proceedings of International Conference on Pattern Recognition,Vienna,1996. 865- 869.