静态图像人体分割算法的研究
|
摘要
静态图像的人体分割是指从含有人的图像中将人体轮廓分割出来,它在计算机视觉中的人体行为理解、基于内容的图像编码、背景分割与替换、人体姿势分类等多个方面都有广泛应用。静态图像的人体分割面临着巨大的挑战,包括人体姿势的多样性,衣服颜色、纹理的各异性,灯光的变换性以及背景的复杂性等多个方面。一般地说,人体轮廓分割可以分为交互式和自动式分割,本文针对这两类方法进行了较为深入的研究,主要工作和研究成果如下：
首先,对于交互式人体分割,传统的图割(Graph Cuts)方法使用用户提供的前景和背景种子点来初始终端连接(Terminal Links),然后使用图的邻域特性来初始邻居连接(Neighborhood Links)。本文提出同时考虑图割中终端连接和邻居连接的方法,该方法使用完全相似图和稀疏表示两种方式通过计算超像素之间的相似性构建图结构,将终端连接和邻居连接嵌入到构建的相似图中,实现了交互式人体分割。实验表明该方法对复杂背景和参数变化具有很强的鲁棒性。
其次,对于自动式人体分割,本文提出了基于模型的人体自动式分割方法。该方法根据最大后验概率原理分别对人体躯干和腿部上半肢进行建模,在实现躯干和腿部上半肢检测的同时,为图割和参考信号的独立成分分析(Independent Component Analysis with Reference, ICA-R)提供种子点和参考信号,以完成使用图割分割人体,ICA-R凸显人体的目标。该类方法可以充分利用模型的全局特性和超像素的局部特性快速地完成人体分割。
再次,本文提出了层级树的自动式人体分割方法。该方法建立了邻近人体部分的模型,且根据树理论,将人体邻近部分的模型对应到树中各层结点,以此将人体姿势建模为树中从根结点到叶子结点加和。该方法可以有效避免对传统层级式方法和单个人体部分检测器的依赖性。
最后,本文根据期望最大化(Expectation-Maximization, EM)算法原理,提出了基于EM算法的人体分割方法,该方法利用EM算法的迭代更新特性对图案结构(Pictorial Structure)模型得到的姿势概率图进行细化以完成人体分割。该方法可以快速地实现对任意人体的分割。
Human body segmentation is to segment the human body from the static images which in-clude human body, and can be applied to many tasks of computer vision, such as human action understanding, content-based image coding, background removing, figure pose classification and so on. However, the body segmentation remains a challenging problem in computer vision. Difficulties arise from various body posture, different color and texture of clothes, various light-ing conditions and cluttered backgrounds. Generally speaking, the work can be divided into two categories:interaction method and automatic method. The main contribution is listed in the following:
First, for interaction method, the traditional method uses the user labeled foreground and background seeds to initialize terminal links (t-links) and neighborhood links (n-links). This thesis proposes a novel strategy to consider the initialization of t-links and n-links simultane-ously with similarity graph. To achieve the goal, this thesis employs the complete graph and sparse coding to construct the graph for interaction method of human body. The experiments show that the proposed strategy is robust to complex background and parameter changes.
Second, for automatic human body segmentation, this thesis proposes model based method. According to maximum a posteriori (MAP), this thesis proposes torso models and upper leg models to detect the torso and upper leg and provide the seeds of graph cut and reference of Independent component analysis with reference (ICA-R). This kind method can fully employ the top knowledge of models and the locality property of superpixel to finish human body seg-mentation efficiently.
Third, this thesis proposes the method based on hierarchical searching tree for human body segmentation. This method proposes the model of adjacent parts, which corresponds to the node of tree according to the tree theory. As a result, the pose is modeled as the summary of nodes of a path from the tree foot to the leaf. This method can effectively avoid the dependency of part detector and the dependency of the hierarchy of hierarchical scheme.
Finally, this thesis proposes the Expectation-Maximization (EM) method. This thesis pro-poses an EM based human body segmentation method according to the principle of EM. This method employs the iterate property of EM to refine the pose probability map obtained from pictorial structure model to finish the human body segmentation, which has no requirement of poses and can efficiently achieve the body segmentation.
首先,对于交互式人体分割,传统的图割(Graph Cuts)方法使用用户提供的前景和背景种子点来初始终端连接(Terminal Links),然后使用图的邻域特性来初始邻居连接(Neighborhood Links)。本文提出同时考虑图割中终端连接和邻居连接的方法,该方法使用完全相似图和稀疏表示两种方式通过计算超像素之间的相似性构建图结构,将终端连接和邻居连接嵌入到构建的相似图中,实现了交互式人体分割。实验表明该方法对复杂背景和参数变化具有很强的鲁棒性。
其次,对于自动式人体分割,本文提出了基于模型的人体自动式分割方法。该方法根据最大后验概率原理分别对人体躯干和腿部上半肢进行建模,在实现躯干和腿部上半肢检测的同时,为图割和参考信号的独立成分分析(Independent Component Analysis with Reference, ICA-R)提供种子点和参考信号,以完成使用图割分割人体,ICA-R凸显人体的目标。该类方法可以充分利用模型的全局特性和超像素的局部特性快速地完成人体分割。
再次,本文提出了层级树的自动式人体分割方法。该方法建立了邻近人体部分的模型,且根据树理论,将人体邻近部分的模型对应到树中各层结点,以此将人体姿势建模为树中从根结点到叶子结点加和。该方法可以有效避免对传统层级式方法和单个人体部分检测器的依赖性。
最后,本文根据期望最大化(Expectation-Maximization, EM)算法原理,提出了基于EM算法的人体分割方法,该方法利用EM算法的迭代更新特性对图案结构(Pictorial Structure)模型得到的姿势概率图进行细化以完成人体分割。该方法可以快速地实现对任意人体的分割。
Human body segmentation is to segment the human body from the static images which in-clude human body, and can be applied to many tasks of computer vision, such as human action understanding, content-based image coding, background removing, figure pose classification and so on. However, the body segmentation remains a challenging problem in computer vision. Difficulties arise from various body posture, different color and texture of clothes, various light-ing conditions and cluttered backgrounds. Generally speaking, the work can be divided into two categories:interaction method and automatic method. The main contribution is listed in the following:
First, for interaction method, the traditional method uses the user labeled foreground and background seeds to initialize terminal links (t-links) and neighborhood links (n-links). This thesis proposes a novel strategy to consider the initialization of t-links and n-links simultane-ously with similarity graph. To achieve the goal, this thesis employs the complete graph and sparse coding to construct the graph for interaction method of human body. The experiments show that the proposed strategy is robust to complex background and parameter changes.
Second, for automatic human body segmentation, this thesis proposes model based method. According to maximum a posteriori (MAP), this thesis proposes torso models and upper leg models to detect the torso and upper leg and provide the seeds of graph cut and reference of Independent component analysis with reference (ICA-R). This kind method can fully employ the top knowledge of models and the locality property of superpixel to finish human body seg-mentation efficiently.
Third, this thesis proposes the method based on hierarchical searching tree for human body segmentation. This method proposes the model of adjacent parts, which corresponds to the node of tree according to the tree theory. As a result, the pose is modeled as the summary of nodes of a path from the tree foot to the leaf. This method can effectively avoid the dependency of part detector and the dependency of the hierarchy of hierarchical scheme.
Finally, this thesis proposes the Expectation-Maximization (EM) method. This thesis pro-poses an EM based human body segmentation method according to the principle of EM. This method employs the iterate property of EM to refine the pose probability map obtained from pictorial structure model to finish the human body segmentation, which has no requirement of poses and can efficiently achieve the body segmentation.
引文
[1]章毓晋.图像工程(上册)图像处理[M].北京：清华大学出版社.2006.
[2]章毓晋.图像工程(中册)图像分析[M].北京：清华大学出版社,2006.
[3]章毓晋.图像工程(下册)图像理解[M].北京：清华大学出版社,2006.
[4]艾海舟,兴军亮.计算机视觉-算法与应用[M].北京：清华大学出版社,2010.
[5]ZHANG X. LI C, TONG X, et al. Efficient Human Pose Estimation via Parsing a Tree Structure Based Human Model[C]. ICCV, Kyoto, Japan.2009:1349-1356.
[6]HU Z, WANG G. LIN X, et al. Recovery of Upper Body Poses in Static Images based on Joints Detection[J]. Pattern Recognition Letters,2009,30(5):503-512.
[7]KASS M, WITKIN A P, TERZOPOULOS D. Snakes:Active Contour Models[J]. International Journal of Computer Vision,1988,1(4):321-331.
[8]李启翮.基于蛇模型的图像分割与目标轮廓跟踪研究[D].北京：清华大学控制科学与工程,2010.
[9]OSHER S, SETHIAN J A. Fronts Propagating with Curvature-Dependent Speed:Algorithms based on Hamilton-Jacobi Formulations [J]. Journal of Computational Physics,1988,79:12-49.
[10]MORTENSEN E N, BARRETT W A. Interactive Segmentation with Intelligent Scissors[J]. Graphical Models and Image Processing,1998,60(5):349-384.
[11]SHI J, MALIK J. Normalized Cuts and Image Segmentation[J]. IEEE Trans. Pattern Anal. Mach. Intell.,2000,22(8):888-905.
[12]BOYKOV Y, VEKSLER O, ZABIH R. Fast Approximate Energy Minimization via Graph Cuts[J], IEEE Trans. Pattern Anal. Mach. Intell..2001,23(11):1222-1239.
[13]刘嘉,王宏琦.一种基于图割的交互式图像分割方法[J].电子与信息学报,2008,30(8)：1973-1976.
[14]FREEDMAN D, ZHANG T. Interactive Graph Cut Based Segmentation with Shape Priors[C]. CVPR (1), San Diego, CA, US,2005:755-762.
[15]VEKSLER O. Star Shape Prior for Graph-Cut Image Segmentation[C]. ECCV (3), Palais des Congres Parc Chanot,2008:454-467.
[16]DAS P, VEKSLER O, ZAVADSKY V, et al. Semiautomatic Segmentation with Compact Shape Prior[J]. Image Vision Comput.,2009,27(1-2):206-219.
[17]HU Z, YAN H, LIN X. Clothing Segmentation using Foreground and Background Estimation based on The Constrained Delaunay Triangulation[J]. Pattern Recognition,2008,41 (5):1581-1592.
[18]ROTHER C, KOLMOGOROV V, BLAKE A. "GrabCut":Interactive Foreground Extraction using Iterated Graph Cuts[J]. ACM Trans. Graph.,2004,23(3):309-314.
[19]LEMPITSKY V, KOHLI P, ROTHER C, et al. Image Segmentation with a Bounding Box Prior[C]. ICCV, Kyoto, Japan,2009:277-284.
[20]MISHRA A K, ALOIMONOS Y, CHEONG L F. Active Segmentation with Fixation[C]. ICCV. Kyoto, Japan,2009:468-475.
[21]BOYKOV Y, KOLMOGOROV V. An Experimental Comparison of Min-cut/Max-flow Algorithms for Energy Minimization in Vision[C]. EMMCVPR, Kauai, Hawaii,2001:359-374.
[22]LI Y, SUN J, TANG C K, et al. Lazy Snapping[J]. ACM Trans. Graph.,2004,23(3):303-308.
[23]LIU J, SUN J, SHUM H Y. Paint Selection[J]. ACM Trans. Graph.,2009,28(3).
[24]MORI G, REN X, EFROS A A, et al. Recovering Human Body Configurations:Combining Segmen-tation and Recognition[C]. CVPR (2), Washington, DC,2004:326-333.
[25]NAVARATNAM R, THAYANANTHAN A, TORR P. et al. Hierarchical Part-Based Human Body Pose Estimation[C]. BMVC. Oxford, U.K.,2005:1-10.
[26]HU Z, LIN X, YAN H. Torso Detection in Static Images[C]. International Conference on Signal Processing (ICSP), Beijing, China.
[27]LIN Z, DAVIS L S, DOERMANN D S, et al. Hierarchical Part-Template Matching for Human Detec-tion and Segmentation[C]. ICCV, Rio de Janeiro, Brazil,2007:1-8.
[28]SRINIVASAN P, SHI J. Bottom-up Recognition and Parsing of the Human Body[C]. CVPR. Min-neapolis, Minnesota, USA,2007:1-8.
[29]MOHAN A, PAPAGEORGIOU C, POGGIO T. Example-Based Object Detection in Images by Com-ponents[J]. IEEE Trans. Pattern Anal. Mach. Intell.,2001,23(4):349-361.
[30]BOURDEV L D. MALIK J. Poselets:Body Part Detectors Trained using 3D Human Pose Annota-tions[C]. ICCV. Kyoto, Japan,2009:1365-1372.
[31]GAVRILA D M. A Bayesian, Exemplar-Based Approach to Hierarchical Shape Matching[J]. IEEE Trans. Pattern Anal. Mach. Intell.,2007,29(8):1408-1421.
[32]MORI G, MALIK J. Estimating Human Body Configurations using Shape Context Matching[C]. ECCV (3), Copenhagen. Denmark,2002:666-680.
[33]BELONGIE S, MALIK J, PUZICHA J. Shape Matching and Object Recognition using Shape Con-texts[J]. IEEE Trans. Pattern Anal. Mach. Intell.,2002,24(4):509-522.
[34]FELZENSZWALB P F, HUTTENLOCHER D P. Pictorial Structures for Object Recognition[J]. Inter-national Journal of Computer Vision.2005,61(1):55-79.
[35]RAMANAN D. Learning to Parse Images of Articulated Bodies[C]. Neural Information Processing Systems (NIPS), Vancouver, B.C., Canada,2006:1129-1136.
[36]MARCIN E, VITTORIO F. Better Appearance Models for Pictorial Structures[C]. BMVC, London, UK,2009.
[37]ANDRILUKA M, ROTH S, SCHIELE B. Pictorial Structures Revisited:People Detection and Artic-ulated Pose Estimation[C]. CVPR, Miami, FL, USA,2009:1014-1021.
[38]SAPP B, JORDAN C, TASKAR B. Adaptive Pose Priors for Pictorial Structures[C]. CVPR, San Francisco, USA,2010:422-429.
[39]FERRARI V, MARIN-JIMENEZ M J, ZISSERMAN A. Pose Search:Retrieving People using Their Pose[C]. CVPR, Miami, FL. USA,2009:1-8.
[40]SAPP B, TOSHEV A, TASKAR B. Cascaded Models for Articulated Pose Estimation[C]. ECCV (2), Crete, Greece,2010:406-420.
[41]JOHNSON S, EVERINGHAM M. Clustered Pose and Nonlinear Appearance Models for Human Pose Estimation[C]. BMVC, Wales, UK,2010:1-11.
[42]SINGH V K, NEVATIA R, HUANG C. Efficient Inference with Multiple Heterogeneous Part Detectors for Human Pose Estimation[C]. ECCV (3), Crete, Greece,2010:314-327.
[43]LEE M W, NEVATIA R. Body Part Detection for Human Pose Estimation and Tracking[C]. IEEE Workshop on Motion and Video Computing (WMVC), Austin, TX, USA,2007:23-30.
[44]MORI G. Guiding Model Search using Segmentation[C]. ICCV, Beijing, China,2005:1417-1423.
[45]BORENSTEIN E, MALIK J. Shape Guided Object Segmentation[C]. CVPR (1), New York, NY, USA, 2006:969-976.
[46]CHEN C, FAN G. Hybrid Body Representation for Integrated Pose Recognition, Localization and Segmentation[C]. CVPR, Anchorage, Alaska, USA,2008.
[47]BOURDEV L D, MAJI S, BROX T, et al. Detecting People using Mutually Consistent Poselet Acti- vations[C]. ECCV (6), Crete, Greece,2010:168-181.
[48]LEE M W, COHEN I. Proposal Maps Driven MCMC for Estimating Human Body Pose in Static Images[C]. CVPR (2), Washington, DC,2004:334-341.
[49]HUA G, YANG M H, WU Y. Learning to Estimate Human Pose with Data Driven Belief Propaga-tion[C]. CVPR (2), San Diego, CA, USA,2005:747-754.
[50]BUEHLER P, EVERINGHAM M, HUTTENLOCHER D P, et al. Long Term Arm and Hand Tracking for Continuous Sign Language TV Broadcasts[C]. BMVC, Leeds, UK,2008:1-11.
[51]LEE M W, COHEN I. Human Upper Body Pose Estimation in Static Images[C]. ECCV (2), Prague, Czech Republic,2004:126-138.
[52]TU Z, ZHU S C. Image Segmentation by Data-Driven Markov Chain Monte Carlo[J]. IEEE Trans. Pattern Anal. Mach. Intell..2002,24(5):657-673.
[53]CIPOLLA R, BLAKE A. The Dynamic Analysis of Apparent Contours[C]. ICCV, Osaka, Japan, 1990:616-623.
[54]MORTENSEN E N, BARRETT W A. Intelligent Scissors for Image Composition[C]. Proceedings of The 22nd Annual Conference on Computer Graphics and Interactive Techniques, Los Angeles, CA, USA,1995:191-198.
[55]MORTENSEN E N, BARRETT W A. Toboggan-Based Intelligent Scissors with a Four-Parameter Edge Model[C]. CVPR, Ft. Collins, CO, USA,1999:2452-2458.
[56]PEREZ P, BLAKE A. GANGNET M. JetStream:Probabilistic Contour Extraction with Particles[C]. ICCV, Vancouver. British Columbia,2001:524-531.
[57]MALLADI R, SETHIAN J A, VEMURI B C. Shape Modeling with Front Propagation:A Level Set Approach[J]. IEEE Trans. Pattern Anal. Mach. Intell.,1995,17(2):158-175.
[58]CASELLES V. KIMMEL R, SAPIRO G. Geodesic Active Contours[J]. International Journal of Com-puter Vision,1997,22(1):61-79.
[59]MUMFORD D, SHAH J. Optimal Approximation by Piecewise Smooth Functions and Associated Variational Problems[J]. Communications on Pure and Applied Mathematics,1989,42(3):577-685.
[60]CHAN T F, VESE L A. An Active Contour Model without Edges[C]. International Conference on Scale-Space Theories in Computer Vision, London, UK,1999:141-151.
[61]CREMERS D, ROUSSON M, DERICHE R. A Review of Statistical Approaches to Level Set Seg-mentation:Integrating Color, Texture, Motion and Shape[J]. International Journal of Computer Vision, 2007,72(2):195-215.
[62]ROUSSON M, PARAGIOS N. Prior Knowledge, Level Set Representations & Visual Grouping[J]. International Journal of Computer Vision,2008,76(3):231-243.
[63]OSHER S, PARAGIOS N. Geometric Level Set Methods in Imaging,Vision.and Graphics[M]. Secau-cus, NJ, USA:Springer-Verlag New York, Inc.,2003.
[64]LU W. RAJAPAKSE J C. ICA with Reference[J]. Neurocomputing,2006,69(16-18):2244-2257.
[65]PAL N R, PAL S K. A Review on Image Segmentation Techniques [J]. Pattern Recognition,1993, 26(9):1277-1294.
[66]陈志彬.非参数变形模型结合模糊技术的MRI图像分割[D].大连：大连理工信号与信息处理.2009.
[67]张少娟.图割在图像匹配中的应用研究[D].北京：北方工业大学应用数学.2010.
[68]GULSHAN V, ROTHER C, CRIMINISI A, et al. Geodesic Star Convexity for Interactive Image Segmentation[C]. CVPR, San Francisco, USA,2010:3129-3136.
[69]BOYKOV Y, JOLLY M P. Interactive Graph Cuts for Optimal Boundary and Region Segmentation of Objects in N-D lmages[C]. ICCV, Vancouver, British Columbia. Canada,2001:105-112.
[70]PENG B, ZHANG L, ZHANG D, et al. Image Segmentation by Iterated Region Merging with Local-ized Graph Cuts[J], Pattern Recognition,2011,44(10-11):2527-2538.
[71]REN X, MALIK J. Learning a Classification Model for Segmentation[C]. ICCV, Nice, France, 2003:10-17.
[72]COMANICIU D, MEER P. Mean Shift:A Robust Approach Toward Feature Space Analysis[J]. IEEE Trans. Pattern Anal. Mach. Intell,2002,24(5):603-619.
[73]FELZENSZWALB P, HUTTENLOCHER D. Enfficient Graph-based Image Segmentation[J]. Interna-tional Journal of Computer Vision,2004,9:167-181.
[74]FULKERSON B, VEDALDI A, SOATTO S. Class Segmentation and Object Localization with Super-pixel Neighborhoods[C]. ICCV, Kyoto, Japan,2009:670-677.
[75J LUCCHI A, SMITH K, ACHANTA R, et al. A Fully Automated Approach to Segmentation of Irreg-ularly Shaped Cellular Structures in EM Images[C], MICCAI (2), Beijing, China,2010:463-471.
[76]YANG J, YU K, GONG Y, et al. Linear Spatial Pyramid Matching using Sparse Coding for Image Classification[C], CVPR, Miami, FL, USA,2009:1794-1801.
[77]SERRE T, WOLF L, POGGIO T. Object Recognition with Features Inspired by Visual Cortex[C]. CVPR (2), San Diego, CA, USA,2005:994-1000.
[78]YAN S, WANG H. Semi-supervised Learning by Sparse Representation[C]. Proceedings of the SIAM International Conference on Data Mining, Sparks, NV, USA,2009:792-801.
[79]MK W, D K. Randomized Anline PCA Algorithms with Regret Bounds That Are Logarithmic in the Dimension[J], Journal of Machine Learning Research,2008,26(9):2287-2320.
[80]H A, LJ W. Principal Component Analysis[J], Wiley Interdisciplinary Reviews:Computational Statis-tics,2010,2(4):433-459.
[81]TICHAVSKY P, KOLDOVSKY Z, OJA E. Corrections to "Performance Analysis of the FastICA Al-gorithm and CramEr-Rao Bounds for Linear Independent Component Analysis"[J]. IEEE Transactions on Signal Processing,2008,56(4):1715-1716.
[82]HYVARINEN A, OJA E. Independent Component Analysis:Algorithms and Applications[J]. Neural Networks,2000,13(4-5):411-430.
[83]OLSHAUSEN B A, FIELD D J. Sparse Coding with an Overcomplete Basis Set:A Strategy Employed by V1?[J]. Vision Research,1997.37(23):3311-3325.
[84]CHEN S S, DONOHO D L, MICHAEL, et al. Atomic Decomposition by Basis Pursuit[J]. SIAM Journal on Scientific Computing,1998,20:33-61.
[85]LEE H, BATTLE A. RAINA R, et al. Efficient Sparse Coding Algorithms[C]. Neural Information Processing Systems (NIPS), Vancouver, B.C., Canada,2007:801-808.
[86]WRIGHT J, YANG A, GANESH A, et al. Robust Face Recognition via Sparse Representation [J]. IEEE Trans. Pattern Anal. Mach. Intell.,2009,31(2):210-227.
[87]YANG M, ZHANG L, YANG J. Robust Sparse Coding for Face Recognition[C]. CVPR, Colorado Springs, USA,2011:625-632.
[88]YANG J, J W, T H. Image Super-resolution as Sparse Representation of Raw Image Patches[C]. CVPR, Anchorage, Alaska, USA,2008:1-8.
[89]YANG J, WRIGHT J, HUANG T, et al. Image Super-Resolution Via Sparse Representation[J]. IEEE Transactions on Image Processing,2010,19(11):2861-2873.
[90]MAIRAL J, BACH F, PONCE J, et al. Discriminative Learned Dictionaries for Local Image Analy-sis[C]. CVPR, Anchorage, AK, USA,2008.
[91]Z F, Y X, L W. Image Decomposition and Texture Segmentation via Sparse Representation[J]. IEEE Signal Processing Letters.2008,15(4):641-644.
[92]ELAD M, AHARON M. Image Denoising via Sparse and Redundant Representations Over Learned Dictionaries [J]. IEEE Transactions on Image Processing,2006,15(12):3736-3745.
[93]HUANG J B, YANG M H. Fast Sparse Representation with Prototypes[C]. CVPR, San Francisco, USA,2010:3618-3625.
[94]CHERIAN A, SRA S, PAPANIKOLOPOULOS N. Denoising Sparse Noise via Online Dictionary Learning[C], IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Prague, Czech Republic,2011:2060-2063.
[95]HUANG J B, YANG M H. Estimating Human Pose from Occluded Images[C]. ACCV (1), Xi'an, China,2009:48-60.
[96]BINGPENG M, TIANJIANG W. Head Pose Estimation using Sparse Representation[C]. International Conference on Computer Engineering and Applications (ICCEA), Washington, DC, USA.2010:389-392.
[97]MEIX, LING H. Robust Visual Tracking using L1 Minimization[C]. ICCV. Kyoto, Japan,2009:1436-1443.
[98]MEI X, LING H, WU Y, et al. Minimum Error Bounded Efficient L1 Tracker with Occlusion Detec-tion[C]. CVPR, Colorado Springs, USA,2011:1257-1264.
[99]MEI X, LING H. Robust Visual Tracking and Vehicle Classification via Sparse Representation[J]. IEEE Trans. Pattern Anal. Mach. Intell.,2011,33(11):2259-2272.
[100]MURRAY J F, KREUTZ-DELGADO K. Learning Sparse Overcomplete Codes for Images[J]. J. VLSI Signal Process. Syst.,2007,46:1-13.
[101]TIBSHIRANI R, SAUNDERS M. ROSSET S. et al. Sparsity and Smoothness via the Fused Lasso[J]. Journal of the Royal Statistical Society Series B,2005:91-108.
[102]COTTER S, ADLER R, RAO R, et al. Forward Sequential Algorithms for Best Basis Selection[J]. IEE Proceedings on Vision, Image and Signal Processing,1999,146(5):235-244.
[103]MAIRAL J, BACH F. PONCE J, et al. Online Learning for Matrix Factorization and Sparse Coding[J]. Journal Mach. Learn. Res.,2010,11:19-60.
[104]ACHANTA R, SHAJI A, SMITH K, et al. SLIC Superpixels[R]. Beijing:EPFL,2010.
[105]BLAKE A, ROTHER C, BROWN M, et al. Interactive Image Segmentation using an Adaptive GMMRF Model[C]. ECCV (1), Prague, Czech Republic,2004:428-441.
[106]艾海舟.数字图像处理[M].北京：电子工业出版社,2001.
[107]MARTIN D R, FOWLKES C C, MALIK J. Learning to Detect Natural Image Boundaries using Local Brightness Color and Texture Cues[J]. IEEE Trans. Pattern Anal. Mach. Intell.,2004,26(5):530-549.
[108]MAIRE M, ARBELAEZ P, FOWLKES C, et al. Using Contours to Detect and Localize Junctions in Natural Images[C]. CVPR, Anchorage, Alaska, USA,2008.
[109]VIOLA P A, JONES M J. Rapid Object Detection using a Boosted Cascade of Simple Features[C]. CVPR(1), Kauai, Hawaii,2001:511-518.
[110]OPELT A, PINZ A, FUSSENEGGER M, et al. Generic Object Recognition with Boosting[J]. IEEE Trans. Pattern Anal. Mach. Intell.,2006,28(3):416-431.
[111]PAPAGEORGIOU C, POGGIO T. A Trainable System for Object Detection[J].2000. In press.
[112]COOTES T F, TAYLOR C J, COOPER D H, et al. Active Shape Models-Their Training and Applica-tion[J]. Computer Vision and Image Understanding,1995,61 (1):38-59.
[113]COOTES T F, TAYLOR C J. A Mixture Model for Representing Shape Variation[J]. Image and Vision Computing.1999,17(8):567-573.
[114]SRIVASTAVA A, JOSHI S H, MIO W, et al. Statistical Shape Analysis:Clustering, Learning, and Testing[J]. IEEE Trans. Pattern Anal. Mach. Intell.,2005,27(4):590-602.
[115]THAYANANTHAN A, STENGER B, TORR P H S, et al. Shape Context and Chamfer Matching in Cluttered Scenes[C]. CVPR (1), Madison, Wisconsin,2003:127-133.
[116]DUTA N, JAIN A K, P. DUBUISSON-JOLLY M. Automatic Construction of 2D Shape Models[J]. IEEE Trans. Pattern Anal. Mach. Intell.,2001,23(5):433-446.
[117]VIOLA P A, JONES M J. Robust Real-Time Face Detection[C]. ICCV, Vancouver, British Columbia, Canada,2001:747-754.
[118]SHOTTON J, WINN J M, ROTHER C, et al. TextonBoost:Joint Appearance, Shape and Context Modeling for Multi-class Object Recognition and Segmentation[C]. ECCV (1), Prague, Czech Repub-lic,2006:1-15.
[119]OPELT A, FUSSENEGGER M. PINZ A, et al. Weak Hypotheses and Boosting for Generic Object Detection and Recognilion[C]. ECCV (2), Prague, Czech Republic,2004:71-84.
[120]N D. Finding People in Images and Video Sequences[D]. Grenoble:Institut National Polytechnique de Grenoble,2006.
[121]MARTIN D, FOWLKES C, TAL D, et al. A Database of Human Segmented Natural Images and its Application to Evaluating Segmentation Algorithms and Measuring Ecological Statistics[C]. ICCV, Vancouver, British Columbia. Canada,2001,2:416-423.
[122]KIRKPATRICK S, JR. D G, VECCHI M P. Optimization by Simmulated Annealing[J]. Science,1983, 220(4598):671-680.
[123]COUR T, BENEZIT F, SHI J. Spectral Segmentation with Multiscale Graph Decomposition[C]. CVPR (2), San Diego, CA, USA,2005:1124-1131.
[124]DALAL N, TRIGGS B. Histograms of Oriented Gradients for Human Detection[C]. CVPR (1), San Diego, CA, USA,2005:886-893.
[125]FELZENSZWALB P F, GIRSHICK R B, MCALLESTER D, et al. Object Detection with Discrimina-tively Trained Part Based Models[J]. IEEE Trans. Pattern Anal. Mach. Intell.,2009,32(9):1627-1645.
[126]RAMANAN D. Using Segmentation to Verify Object Hypotheses[C]. CVPR, Minneapolis, Minnesota, USA.2007:1-8.
[127]LIN Z, DAVIS L S. A Pose-Invariant Descriptor for Human Detection and Segmentation[C]. ECCV (4), Palais des Congres Parc Chanot,2008:423-436.
[128]CHANG C C, LIN C J. LIBSVM:A Library for Support Vector Machines[J]. ACM Transactions on Intelligent Systems and Technology,2011,2:27:1-27:27. Software available at http://www.csie. ntu.edu.tw/-cjlin/libsvm.
[129]LIN Z, DAVIS L S, DOERMANN D S, et al. An Interactive Approach to Pose-Assisted and Appearance-based Segmentation of Humans[C]. ICCV, Rio de Janeiro, Brazil,2007:1-8.
[130]LIN Q H, ZHENG Y R, YIN F, et al. A Fast Algorithm for One-unit ICA-R[J]. Information Sciences, 2007,177(5):1265-1275.
[131]OTSU N. A Threshold Selection Method from Gray-Level Histograms [J]. IEEE Transactions on Systems, Man, and Cybernetics,1979,9:62-66.
[132]FERRARI V, MARIN-JIMENEZ M J, ZISSERMAN A. Progressive Search Space Reduction for Hu-man Pose Estimation[C]. CVPR, Anchorage, Alaska, USA,2008.
[133]YANG Y, RAMANAN D. Articulated Pose Estimation with Flexible Mixtures-of-parts[C]. CVPR, Colorado Springs, USA,2011:1385-1392.
[134]FELZENSZWALB P F, HUTTENLOCHER D P. Efficient Belief Propagation for Early Vision[C]. CVPR (1), Washington, DC,2004:261-268.
[135]ZHAO L, DAVIS L S. Iterative Figure-Ground Discrimination[C]. ICPR (1), England, UK,2004:67-70.
[136]LEVINSHTEIN A, SMINCHISESCU C, DICKINSON S J. Optimal Contour Closure by Superpixel Grouping[C]. ECCV (2), Crete, Greece,2010:480-493.
[137]ENDRES I, HOIEM D. Category Independent Object Proposals[C]. ECCV (5). Crete, Greece, 2010:575-588.
[138]MISHRA A K, ALOIMONOS Y, CHEONG LF. Active Segmentation with Fixation[C]. ICCV, Kyoto, Japan,2009:468-475.
[139]VINCENT L, SOILLE P. Watersheds in Digital Spaces:An Efficient Algorithm Based on Immersion Simulations[J]. IEEE Trans. Pattern Anal. Mach. Intell.,1991,13(6):583-598.
[140]LEVINSHTEIN A, STERE A, KUTULAKOS K N, et al. TurboPixels:Fast Superpixels using Geo-metric Flows[J]. IEEE Trans. Pattern Anal. Mach. Intell.,2009,31(12):2290-2297.
[2]章毓晋.图像工程(中册)图像分析[M].北京：清华大学出版社,2006.
[3]章毓晋.图像工程(下册)图像理解[M].北京：清华大学出版社,2006.
[4]艾海舟,兴军亮.计算机视觉-算法与应用[M].北京：清华大学出版社,2010.
[5]ZHANG X. LI C, TONG X, et al. Efficient Human Pose Estimation via Parsing a Tree Structure Based Human Model[C]. ICCV, Kyoto, Japan.2009:1349-1356.
[6]HU Z, WANG G. LIN X, et al. Recovery of Upper Body Poses in Static Images based on Joints Detection[J]. Pattern Recognition Letters,2009,30(5):503-512.
[7]KASS M, WITKIN A P, TERZOPOULOS D. Snakes:Active Contour Models[J]. International Journal of Computer Vision,1988,1(4):321-331.
[8]李启翮.基于蛇模型的图像分割与目标轮廓跟踪研究[D].北京：清华大学控制科学与工程,2010.
[9]OSHER S, SETHIAN J A. Fronts Propagating with Curvature-Dependent Speed:Algorithms based on Hamilton-Jacobi Formulations [J]. Journal of Computational Physics,1988,79:12-49.
[10]MORTENSEN E N, BARRETT W A. Interactive Segmentation with Intelligent Scissors[J]. Graphical Models and Image Processing,1998,60(5):349-384.
[11]SHI J, MALIK J. Normalized Cuts and Image Segmentation[J]. IEEE Trans. Pattern Anal. Mach. Intell.,2000,22(8):888-905.
[12]BOYKOV Y, VEKSLER O, ZABIH R. Fast Approximate Energy Minimization via Graph Cuts[J], IEEE Trans. Pattern Anal. Mach. Intell..2001,23(11):1222-1239.
[13]刘嘉,王宏琦.一种基于图割的交互式图像分割方法[J].电子与信息学报,2008,30(8)：1973-1976.
[14]FREEDMAN D, ZHANG T. Interactive Graph Cut Based Segmentation with Shape Priors[C]. CVPR (1), San Diego, CA, US,2005:755-762.
[15]VEKSLER O. Star Shape Prior for Graph-Cut Image Segmentation[C]. ECCV (3), Palais des Congres Parc Chanot,2008:454-467.
[16]DAS P, VEKSLER O, ZAVADSKY V, et al. Semiautomatic Segmentation with Compact Shape Prior[J]. Image Vision Comput.,2009,27(1-2):206-219.
[17]HU Z, YAN H, LIN X. Clothing Segmentation using Foreground and Background Estimation based on The Constrained Delaunay Triangulation[J]. Pattern Recognition,2008,41 (5):1581-1592.
[18]ROTHER C, KOLMOGOROV V, BLAKE A. "GrabCut":Interactive Foreground Extraction using Iterated Graph Cuts[J]. ACM Trans. Graph.,2004,23(3):309-314.
[19]LEMPITSKY V, KOHLI P, ROTHER C, et al. Image Segmentation with a Bounding Box Prior[C]. ICCV, Kyoto, Japan,2009:277-284.
[20]MISHRA A K, ALOIMONOS Y, CHEONG L F. Active Segmentation with Fixation[C]. ICCV. Kyoto, Japan,2009:468-475.
[21]BOYKOV Y, KOLMOGOROV V. An Experimental Comparison of Min-cut/Max-flow Algorithms for Energy Minimization in Vision[C]. EMMCVPR, Kauai, Hawaii,2001:359-374.
[22]LI Y, SUN J, TANG C K, et al. Lazy Snapping[J]. ACM Trans. Graph.,2004,23(3):303-308.
[23]LIU J, SUN J, SHUM H Y. Paint Selection[J]. ACM Trans. Graph.,2009,28(3).
[24]MORI G, REN X, EFROS A A, et al. Recovering Human Body Configurations:Combining Segmen-tation and Recognition[C]. CVPR (2), Washington, DC,2004:326-333.
[25]NAVARATNAM R, THAYANANTHAN A, TORR P. et al. Hierarchical Part-Based Human Body Pose Estimation[C]. BMVC. Oxford, U.K.,2005:1-10.
[26]HU Z, LIN X, YAN H. Torso Detection in Static Images[C]. International Conference on Signal Processing (ICSP), Beijing, China.
[27]LIN Z, DAVIS L S, DOERMANN D S, et al. Hierarchical Part-Template Matching for Human Detec-tion and Segmentation[C]. ICCV, Rio de Janeiro, Brazil,2007:1-8.
[28]SRINIVASAN P, SHI J. Bottom-up Recognition and Parsing of the Human Body[C]. CVPR. Min-neapolis, Minnesota, USA,2007:1-8.
[29]MOHAN A, PAPAGEORGIOU C, POGGIO T. Example-Based Object Detection in Images by Com-ponents[J]. IEEE Trans. Pattern Anal. Mach. Intell.,2001,23(4):349-361.
[30]BOURDEV L D. MALIK J. Poselets:Body Part Detectors Trained using 3D Human Pose Annota-tions[C]. ICCV. Kyoto, Japan,2009:1365-1372.
[31]GAVRILA D M. A Bayesian, Exemplar-Based Approach to Hierarchical Shape Matching[J]. IEEE Trans. Pattern Anal. Mach. Intell.,2007,29(8):1408-1421.
[32]MORI G, MALIK J. Estimating Human Body Configurations using Shape Context Matching[C]. ECCV (3), Copenhagen. Denmark,2002:666-680.
[33]BELONGIE S, MALIK J, PUZICHA J. Shape Matching and Object Recognition using Shape Con-texts[J]. IEEE Trans. Pattern Anal. Mach. Intell.,2002,24(4):509-522.
[34]FELZENSZWALB P F, HUTTENLOCHER D P. Pictorial Structures for Object Recognition[J]. Inter-national Journal of Computer Vision.2005,61(1):55-79.
[35]RAMANAN D. Learning to Parse Images of Articulated Bodies[C]. Neural Information Processing Systems (NIPS), Vancouver, B.C., Canada,2006:1129-1136.
[36]MARCIN E, VITTORIO F. Better Appearance Models for Pictorial Structures[C]. BMVC, London, UK,2009.
[37]ANDRILUKA M, ROTH S, SCHIELE B. Pictorial Structures Revisited:People Detection and Artic-ulated Pose Estimation[C]. CVPR, Miami, FL, USA,2009:1014-1021.
[38]SAPP B, JORDAN C, TASKAR B. Adaptive Pose Priors for Pictorial Structures[C]. CVPR, San Francisco, USA,2010:422-429.
[39]FERRARI V, MARIN-JIMENEZ M J, ZISSERMAN A. Pose Search:Retrieving People using Their Pose[C]. CVPR, Miami, FL. USA,2009:1-8.
[40]SAPP B, TOSHEV A, TASKAR B. Cascaded Models for Articulated Pose Estimation[C]. ECCV (2), Crete, Greece,2010:406-420.
[41]JOHNSON S, EVERINGHAM M. Clustered Pose and Nonlinear Appearance Models for Human Pose Estimation[C]. BMVC, Wales, UK,2010:1-11.
[42]SINGH V K, NEVATIA R, HUANG C. Efficient Inference with Multiple Heterogeneous Part Detectors for Human Pose Estimation[C]. ECCV (3), Crete, Greece,2010:314-327.
[43]LEE M W, NEVATIA R. Body Part Detection for Human Pose Estimation and Tracking[C]. IEEE Workshop on Motion and Video Computing (WMVC), Austin, TX, USA,2007:23-30.
[44]MORI G. Guiding Model Search using Segmentation[C]. ICCV, Beijing, China,2005:1417-1423.
[45]BORENSTEIN E, MALIK J. Shape Guided Object Segmentation[C]. CVPR (1), New York, NY, USA, 2006:969-976.
[46]CHEN C, FAN G. Hybrid Body Representation for Integrated Pose Recognition, Localization and Segmentation[C]. CVPR, Anchorage, Alaska, USA,2008.
[47]BOURDEV L D, MAJI S, BROX T, et al. Detecting People using Mutually Consistent Poselet Acti- vations[C]. ECCV (6), Crete, Greece,2010:168-181.
[48]LEE M W, COHEN I. Proposal Maps Driven MCMC for Estimating Human Body Pose in Static Images[C]. CVPR (2), Washington, DC,2004:334-341.
[49]HUA G, YANG M H, WU Y. Learning to Estimate Human Pose with Data Driven Belief Propaga-tion[C]. CVPR (2), San Diego, CA, USA,2005:747-754.
[50]BUEHLER P, EVERINGHAM M, HUTTENLOCHER D P, et al. Long Term Arm and Hand Tracking for Continuous Sign Language TV Broadcasts[C]. BMVC, Leeds, UK,2008:1-11.
[51]LEE M W, COHEN I. Human Upper Body Pose Estimation in Static Images[C]. ECCV (2), Prague, Czech Republic,2004:126-138.
[52]TU Z, ZHU S C. Image Segmentation by Data-Driven Markov Chain Monte Carlo[J]. IEEE Trans. Pattern Anal. Mach. Intell..2002,24(5):657-673.
[53]CIPOLLA R, BLAKE A. The Dynamic Analysis of Apparent Contours[C]. ICCV, Osaka, Japan, 1990:616-623.
[54]MORTENSEN E N, BARRETT W A. Intelligent Scissors for Image Composition[C]. Proceedings of The 22nd Annual Conference on Computer Graphics and Interactive Techniques, Los Angeles, CA, USA,1995:191-198.
[55]MORTENSEN E N, BARRETT W A. Toboggan-Based Intelligent Scissors with a Four-Parameter Edge Model[C]. CVPR, Ft. Collins, CO, USA,1999:2452-2458.
[56]PEREZ P, BLAKE A. GANGNET M. JetStream:Probabilistic Contour Extraction with Particles[C]. ICCV, Vancouver. British Columbia,2001:524-531.
[57]MALLADI R, SETHIAN J A, VEMURI B C. Shape Modeling with Front Propagation:A Level Set Approach[J]. IEEE Trans. Pattern Anal. Mach. Intell.,1995,17(2):158-175.
[58]CASELLES V. KIMMEL R, SAPIRO G. Geodesic Active Contours[J]. International Journal of Com-puter Vision,1997,22(1):61-79.
[59]MUMFORD D, SHAH J. Optimal Approximation by Piecewise Smooth Functions and Associated Variational Problems[J]. Communications on Pure and Applied Mathematics,1989,42(3):577-685.
[60]CHAN T F, VESE L A. An Active Contour Model without Edges[C]. International Conference on Scale-Space Theories in Computer Vision, London, UK,1999:141-151.
[61]CREMERS D, ROUSSON M, DERICHE R. A Review of Statistical Approaches to Level Set Seg-mentation:Integrating Color, Texture, Motion and Shape[J]. International Journal of Computer Vision, 2007,72(2):195-215.
[62]ROUSSON M, PARAGIOS N. Prior Knowledge, Level Set Representations & Visual Grouping[J]. International Journal of Computer Vision,2008,76(3):231-243.
[63]OSHER S, PARAGIOS N. Geometric Level Set Methods in Imaging,Vision.and Graphics[M]. Secau-cus, NJ, USA:Springer-Verlag New York, Inc.,2003.
[64]LU W. RAJAPAKSE J C. ICA with Reference[J]. Neurocomputing,2006,69(16-18):2244-2257.
[65]PAL N R, PAL S K. A Review on Image Segmentation Techniques [J]. Pattern Recognition,1993, 26(9):1277-1294.
[66]陈志彬.非参数变形模型结合模糊技术的MRI图像分割[D].大连：大连理工信号与信息处理.2009.
[67]张少娟.图割在图像匹配中的应用研究[D].北京：北方工业大学应用数学.2010.
[68]GULSHAN V, ROTHER C, CRIMINISI A, et al. Geodesic Star Convexity for Interactive Image Segmentation[C]. CVPR, San Francisco, USA,2010:3129-3136.
[69]BOYKOV Y, JOLLY M P. Interactive Graph Cuts for Optimal Boundary and Region Segmentation of Objects in N-D lmages[C]. ICCV, Vancouver, British Columbia. Canada,2001:105-112.
[70]PENG B, ZHANG L, ZHANG D, et al. Image Segmentation by Iterated Region Merging with Local-ized Graph Cuts[J], Pattern Recognition,2011,44(10-11):2527-2538.
[71]REN X, MALIK J. Learning a Classification Model for Segmentation[C]. ICCV, Nice, France, 2003:10-17.
[72]COMANICIU D, MEER P. Mean Shift:A Robust Approach Toward Feature Space Analysis[J]. IEEE Trans. Pattern Anal. Mach. Intell,2002,24(5):603-619.
[73]FELZENSZWALB P, HUTTENLOCHER D. Enfficient Graph-based Image Segmentation[J]. Interna-tional Journal of Computer Vision,2004,9:167-181.
[74]FULKERSON B, VEDALDI A, SOATTO S. Class Segmentation and Object Localization with Super-pixel Neighborhoods[C]. ICCV, Kyoto, Japan,2009:670-677.
[75J LUCCHI A, SMITH K, ACHANTA R, et al. A Fully Automated Approach to Segmentation of Irreg-ularly Shaped Cellular Structures in EM Images[C], MICCAI (2), Beijing, China,2010:463-471.
[76]YANG J, YU K, GONG Y, et al. Linear Spatial Pyramid Matching using Sparse Coding for Image Classification[C], CVPR, Miami, FL, USA,2009:1794-1801.
[77]SERRE T, WOLF L, POGGIO T. Object Recognition with Features Inspired by Visual Cortex[C]. CVPR (2), San Diego, CA, USA,2005:994-1000.
[78]YAN S, WANG H. Semi-supervised Learning by Sparse Representation[C]. Proceedings of the SIAM International Conference on Data Mining, Sparks, NV, USA,2009:792-801.
[79]MK W, D K. Randomized Anline PCA Algorithms with Regret Bounds That Are Logarithmic in the Dimension[J], Journal of Machine Learning Research,2008,26(9):2287-2320.
[80]H A, LJ W. Principal Component Analysis[J], Wiley Interdisciplinary Reviews:Computational Statis-tics,2010,2(4):433-459.
[81]TICHAVSKY P, KOLDOVSKY Z, OJA E. Corrections to "Performance Analysis of the FastICA Al-gorithm and CramEr-Rao Bounds for Linear Independent Component Analysis"[J]. IEEE Transactions on Signal Processing,2008,56(4):1715-1716.
[82]HYVARINEN A, OJA E. Independent Component Analysis:Algorithms and Applications[J]. Neural Networks,2000,13(4-5):411-430.
[83]OLSHAUSEN B A, FIELD D J. Sparse Coding with an Overcomplete Basis Set:A Strategy Employed by V1?[J]. Vision Research,1997.37(23):3311-3325.
[84]CHEN S S, DONOHO D L, MICHAEL, et al. Atomic Decomposition by Basis Pursuit[J]. SIAM Journal on Scientific Computing,1998,20:33-61.
[85]LEE H, BATTLE A. RAINA R, et al. Efficient Sparse Coding Algorithms[C]. Neural Information Processing Systems (NIPS), Vancouver, B.C., Canada,2007:801-808.
[86]WRIGHT J, YANG A, GANESH A, et al. Robust Face Recognition via Sparse Representation [J]. IEEE Trans. Pattern Anal. Mach. Intell.,2009,31(2):210-227.
[87]YANG M, ZHANG L, YANG J. Robust Sparse Coding for Face Recognition[C]. CVPR, Colorado Springs, USA,2011:625-632.
[88]YANG J, J W, T H. Image Super-resolution as Sparse Representation of Raw Image Patches[C]. CVPR, Anchorage, Alaska, USA,2008:1-8.
[89]YANG J, WRIGHT J, HUANG T, et al. Image Super-Resolution Via Sparse Representation[J]. IEEE Transactions on Image Processing,2010,19(11):2861-2873.
[90]MAIRAL J, BACH F, PONCE J, et al. Discriminative Learned Dictionaries for Local Image Analy-sis[C]. CVPR, Anchorage, AK, USA,2008.
[91]Z F, Y X, L W. Image Decomposition and Texture Segmentation via Sparse Representation[J]. IEEE Signal Processing Letters.2008,15(4):641-644.
[92]ELAD M, AHARON M. Image Denoising via Sparse and Redundant Representations Over Learned Dictionaries [J]. IEEE Transactions on Image Processing,2006,15(12):3736-3745.
[93]HUANG J B, YANG M H. Fast Sparse Representation with Prototypes[C]. CVPR, San Francisco, USA,2010:3618-3625.
[94]CHERIAN A, SRA S, PAPANIKOLOPOULOS N. Denoising Sparse Noise via Online Dictionary Learning[C], IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Prague, Czech Republic,2011:2060-2063.
[95]HUANG J B, YANG M H. Estimating Human Pose from Occluded Images[C]. ACCV (1), Xi'an, China,2009:48-60.
[96]BINGPENG M, TIANJIANG W. Head Pose Estimation using Sparse Representation[C]. International Conference on Computer Engineering and Applications (ICCEA), Washington, DC, USA.2010:389-392.
[97]MEIX, LING H. Robust Visual Tracking using L1 Minimization[C]. ICCV. Kyoto, Japan,2009:1436-1443.
[98]MEI X, LING H, WU Y, et al. Minimum Error Bounded Efficient L1 Tracker with Occlusion Detec-tion[C]. CVPR, Colorado Springs, USA,2011:1257-1264.
[99]MEI X, LING H. Robust Visual Tracking and Vehicle Classification via Sparse Representation[J]. IEEE Trans. Pattern Anal. Mach. Intell.,2011,33(11):2259-2272.
[100]MURRAY J F, KREUTZ-DELGADO K. Learning Sparse Overcomplete Codes for Images[J]. J. VLSI Signal Process. Syst.,2007,46:1-13.
[101]TIBSHIRANI R, SAUNDERS M. ROSSET S. et al. Sparsity and Smoothness via the Fused Lasso[J]. Journal of the Royal Statistical Society Series B,2005:91-108.
[102]COTTER S, ADLER R, RAO R, et al. Forward Sequential Algorithms for Best Basis Selection[J]. IEE Proceedings on Vision, Image and Signal Processing,1999,146(5):235-244.
[103]MAIRAL J, BACH F. PONCE J, et al. Online Learning for Matrix Factorization and Sparse Coding[J]. Journal Mach. Learn. Res.,2010,11:19-60.
[104]ACHANTA R, SHAJI A, SMITH K, et al. SLIC Superpixels[R]. Beijing:EPFL,2010.
[105]BLAKE A, ROTHER C, BROWN M, et al. Interactive Image Segmentation using an Adaptive GMMRF Model[C]. ECCV (1), Prague, Czech Republic,2004:428-441.
[106]艾海舟.数字图像处理[M].北京：电子工业出版社,2001.
[107]MARTIN D R, FOWLKES C C, MALIK J. Learning to Detect Natural Image Boundaries using Local Brightness Color and Texture Cues[J]. IEEE Trans. Pattern Anal. Mach. Intell.,2004,26(5):530-549.
[108]MAIRE M, ARBELAEZ P, FOWLKES C, et al. Using Contours to Detect and Localize Junctions in Natural Images[C]. CVPR, Anchorage, Alaska, USA,2008.
[109]VIOLA P A, JONES M J. Rapid Object Detection using a Boosted Cascade of Simple Features[C]. CVPR(1), Kauai, Hawaii,2001:511-518.
[110]OPELT A, PINZ A, FUSSENEGGER M, et al. Generic Object Recognition with Boosting[J]. IEEE Trans. Pattern Anal. Mach. Intell.,2006,28(3):416-431.
[111]PAPAGEORGIOU C, POGGIO T. A Trainable System for Object Detection[J].2000. In press.
[112]COOTES T F, TAYLOR C J, COOPER D H, et al. Active Shape Models-Their Training and Applica-tion[J]. Computer Vision and Image Understanding,1995,61 (1):38-59.
[113]COOTES T F, TAYLOR C J. A Mixture Model for Representing Shape Variation[J]. Image and Vision Computing.1999,17(8):567-573.
[114]SRIVASTAVA A, JOSHI S H, MIO W, et al. Statistical Shape Analysis:Clustering, Learning, and Testing[J]. IEEE Trans. Pattern Anal. Mach. Intell.,2005,27(4):590-602.
[115]THAYANANTHAN A, STENGER B, TORR P H S, et al. Shape Context and Chamfer Matching in Cluttered Scenes[C]. CVPR (1), Madison, Wisconsin,2003:127-133.
[116]DUTA N, JAIN A K, P. DUBUISSON-JOLLY M. Automatic Construction of 2D Shape Models[J]. IEEE Trans. Pattern Anal. Mach. Intell.,2001,23(5):433-446.
[117]VIOLA P A, JONES M J. Robust Real-Time Face Detection[C]. ICCV, Vancouver, British Columbia, Canada,2001:747-754.
[118]SHOTTON J, WINN J M, ROTHER C, et al. TextonBoost:Joint Appearance, Shape and Context Modeling for Multi-class Object Recognition and Segmentation[C]. ECCV (1), Prague, Czech Repub-lic,2006:1-15.
[119]OPELT A, FUSSENEGGER M. PINZ A, et al. Weak Hypotheses and Boosting for Generic Object Detection and Recognilion[C]. ECCV (2), Prague, Czech Republic,2004:71-84.
[120]N D. Finding People in Images and Video Sequences[D]. Grenoble:Institut National Polytechnique de Grenoble,2006.
[121]MARTIN D, FOWLKES C, TAL D, et al. A Database of Human Segmented Natural Images and its Application to Evaluating Segmentation Algorithms and Measuring Ecological Statistics[C]. ICCV, Vancouver, British Columbia. Canada,2001,2:416-423.
[122]KIRKPATRICK S, JR. D G, VECCHI M P. Optimization by Simmulated Annealing[J]. Science,1983, 220(4598):671-680.
[123]COUR T, BENEZIT F, SHI J. Spectral Segmentation with Multiscale Graph Decomposition[C]. CVPR (2), San Diego, CA, USA,2005:1124-1131.
[124]DALAL N, TRIGGS B. Histograms of Oriented Gradients for Human Detection[C]. CVPR (1), San Diego, CA, USA,2005:886-893.
[125]FELZENSZWALB P F, GIRSHICK R B, MCALLESTER D, et al. Object Detection with Discrimina-tively Trained Part Based Models[J]. IEEE Trans. Pattern Anal. Mach. Intell.,2009,32(9):1627-1645.
[126]RAMANAN D. Using Segmentation to Verify Object Hypotheses[C]. CVPR, Minneapolis, Minnesota, USA.2007:1-8.
[127]LIN Z, DAVIS L S. A Pose-Invariant Descriptor for Human Detection and Segmentation[C]. ECCV (4), Palais des Congres Parc Chanot,2008:423-436.
[128]CHANG C C, LIN C J. LIBSVM:A Library for Support Vector Machines[J]. ACM Transactions on Intelligent Systems and Technology,2011,2:27:1-27:27. Software available at http://www.csie. ntu.edu.tw/-cjlin/libsvm.
[129]LIN Z, DAVIS L S, DOERMANN D S, et al. An Interactive Approach to Pose-Assisted and Appearance-based Segmentation of Humans[C]. ICCV, Rio de Janeiro, Brazil,2007:1-8.
[130]LIN Q H, ZHENG Y R, YIN F, et al. A Fast Algorithm for One-unit ICA-R[J]. Information Sciences, 2007,177(5):1265-1275.
[131]OTSU N. A Threshold Selection Method from Gray-Level Histograms [J]. IEEE Transactions on Systems, Man, and Cybernetics,1979,9:62-66.
[132]FERRARI V, MARIN-JIMENEZ M J, ZISSERMAN A. Progressive Search Space Reduction for Hu-man Pose Estimation[C]. CVPR, Anchorage, Alaska, USA,2008.
[133]YANG Y, RAMANAN D. Articulated Pose Estimation with Flexible Mixtures-of-parts[C]. CVPR, Colorado Springs, USA,2011:1385-1392.
[134]FELZENSZWALB P F, HUTTENLOCHER D P. Efficient Belief Propagation for Early Vision[C]. CVPR (1), Washington, DC,2004:261-268.
[135]ZHAO L, DAVIS L S. Iterative Figure-Ground Discrimination[C]. ICPR (1), England, UK,2004:67-70.
[136]LEVINSHTEIN A, SMINCHISESCU C, DICKINSON S J. Optimal Contour Closure by Superpixel Grouping[C]. ECCV (2), Crete, Greece,2010:480-493.
[137]ENDRES I, HOIEM D. Category Independent Object Proposals[C]. ECCV (5). Crete, Greece, 2010:575-588.
[138]MISHRA A K, ALOIMONOS Y, CHEONG LF. Active Segmentation with Fixation[C]. ICCV, Kyoto, Japan,2009:468-475.
[139]VINCENT L, SOILLE P. Watersheds in Digital Spaces:An Efficient Algorithm Based on Immersion Simulations[J]. IEEE Trans. Pattern Anal. Mach. Intell.,1991,13(6):583-598.
[140]LEVINSHTEIN A, STERE A, KUTULAKOS K N, et al. TurboPixels:Fast Superpixels using Geo-metric Flows[J]. IEEE Trans. Pattern Anal. Mach. Intell.,2009,31(12):2290-2297.