A Survey of Human Pose Estimation from Single Images

Abstract

Abstract:

Pose estimation from images is to detect the position where the human body is located in the image and computes the orientation and scale for each body part, the results of pose estimation is always classified as 2D and 3D, and the approaches to these results can be divided as modelbased approaches and modelfree approaches. In this paper we first give a simple introduction to the background and applications of pose estimation, then conceptions relevant to pose estimations are discussed, and the different representations of the results produced are compared, the remaining part of this paper focuses on the human body detection and human pose estimation, which are discussed in detail, all the different methods are discussed theoretically by applicability, at the end of this paper.The problems remaining to be located are analyzed.

Key words: human pose estimation;object detection;human body model;single image

TANG Zesheng,WANG Zhaozhong. A Survey of Human Pose Estimation from Single Images[J]. J4, 2011, 33(11): 89-97.

References

［1］Virone G,Sixsmith A. Activity Prediction for InHome Activity Monitoring［C］∥Proc of International Conference on Intelligent Environments, 2008:14.
［2］Vincze M,Zillich M,Ponweiser W,et al. Integrated Vision System for the Semantic Interpretation of Activities Where a Person Handles Objects［J］. Computer Vision and Image Understanding, 2009, 113(6):682692.
［3］Jansen B, Temmermans F,Deklerck R. 3D Human Pose Recognition for Home Monitoring of Elderly［C］∥Proc of the International Conference of Engineering in Medicine and Biology Society, 2007:40494051.
［4］Ramanan D, Forsyth D A,Zisserman A. Strike a Pose:Tracking People by Finding Stylized Pose［C］∥Proc of IEEE Conference on Computer Vision and Pattern Recognition, 2005:271278.
［5］Huo Feifei, Hendriks E, Paclik P,et al. Markerless Human Motion Capture and Pose Recognition［C］∥Proc of Workshop on Image Analysis for Multimedia Interactive Services, 2009:1316.
［6］Peng Bo, Qian Gang,Ma Yunqian. Recognizing Body Poses Using Multilinear Analysis and SemiSupervised Learning［J］. Pattern Recognition Letters, 2009, 30(14):12891294.
［7］Bray M, Kohli P,Torr P H S. Posecut: Simultaneous Segmentation and 3D Pose Estimation of Humans Using Dynamic GraphCuts［C］∥Proc of European Conference on Computer Vision, 2006:642655.
［8］Shan Ganlin, Ji Bing, Zhou Yunfeng. A Review of 3d Poses Estimation from a Monocular Image Sequence［C］∥Proc of International Congress on Image and Signal Processing, 2009:15.
［9］Hen Yap Wooi,Paramesran R. Single Camera 3d Human Pose Estimation: A Review of Current Techniques［C］∥Proc of International Conference for Technical Postgraduates, 2009:18.
［10］黎洪松,李达.人体运动分析研究的若干新进展［J］.模式识别与人工智能, 2009, 22(1):7078.
［11］王亮,胡卫明,谭铁牛.人运动的视觉分析综述［J］.计算机学报, 2002, 25(3):225237.
［12］Felzenszwalb P F,Huttenlocher D P. Efficient Matching of Pictorial Structures［C］∥Proc of IEEE Conference on Computer Vision and Pattern Recognition, 2000:6673.
［13］Ioffe S,Forsyth D A. Human Tracking with Mixtures of Trees［C］∥Proc of International Conference on Computer Vision, 2001:690695.
［14］Ramanan D,Forsyth D A. Finding and Tracking People from the Bottom up［C］∥Proc of IEEE Conference on Computer Vision and Pattern Recognition, 2003:467474.
［15］Ferrari V, MarlnJimnez M J,Zisserman A. Pose Search: Retrieving People Using Their Pose［C］∥Proc of IEEE Conference on Computer Vision and Pattern Recognition, 2009:18.
［16］Marcin E,Vittorio F. Better Appearance Models for Pictorial Structures［C］∥Proc of British Machine Vision Conference, 2009.
［17］Singh M, Mandal M,Basu A. Pose Recognition Using the Radon Transform［C］∥Proc of Midwest Symposium on Circuits and Systems, 2005:10911094.
［18］Jiang Hao. Human Pose Estimation Using Consistent MaxCovering［C］∥Proc of International Conference on Computer Vision, 2009:13571364.
［19］Guo Feng,Qian Gang. 3D Human Motion Tracking Using Manifold Learning［C］∥Proc of International Conference on Image Processing, 2007:357360.
［20］Agarwal A,Triggs B. 3D Human Pose from Silhouettes by Relevance Vector Regression［C］∥Proc of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004:882888.
［21］Seemann E, Leibe B, Mikolajczyk K,et al. An Evaluation of Local ShapeBased Features for Pedestrian Detection［C］∥Proc of British Machine Vision Conference, 2005.
［22］Rother C, Kolmogorov V,Blake A. “Grabcut”: Interactive Foreground Extraction Using Iterated Graph Cuts［J］.ACM Trans on Graphics, 2004, 23(3):309314.
［23］Sun Yunda, Yuan Baozong, Miao Zhenjiang,et al. Better Foreground Segmentation for Static Cameras via New Energy form and Dynamic GraphCut［C］∥Proc of International Conference on Pattern Recognition, 2006:4952.
［24］Han Shoudong, Tao Wenbing, Wu Xianglin, et al. Fast Image Segmentation Based on Multilevel Banded ClosedForm Method［J］. Pattern Recognition Letters, 2010, 31(3):216225.
［25］Wang Song, Kubota T,Richardson T. Shape Correspondence Through Landmark Sliding［C］∥Proc of IEEE Conference on Computer Vision and Pattern Recognition,2004:143150.
［26］Belongie S, Malik J,Puzicha J. Shape Matching and Object Recognition Using Shape Contexts［J］. IEEE Trans on Pattern Analysis and Machine Intelligence, 2001, 24(24):509522.
［27］Shotton J, Blake A,Cipolla R. ContourBased Learning for Object Detection［C］∥Proc of International Conference on Computer Vision, 2005:503510.
［28］Dalal N,Triggs B. Histograms of Oriented Gradients for Human Detection［C］∥Proc of IEEE Conference on Computer Vision and Recognition, 2005:886893.
［29］Freeman W T,Roth M. Orientation Histograms for Hand Gesture Recognition［C］∥Proc of International Workshop on Automatic Face and Gesture Recognition, 1994:296301.
［30］Freeman W T, Tanaka K, Ohta J, et al. Computer Vision for Computer Games［C］∥Proc of IEEE International Conference on Automatic Face and Gesture Recognition, 1996:100.
［31］曾春,李晓华,周激流. 基于感兴趣区域梯度方向直方图的行人检测［J］.计算机工程, 2009,35(24):182184.
［32］Rogez G, Rihan J, Ramalingam S, et al. Randomized Trees for Human Pose Detection［C］∥Proc of IEEE Conference on Computer Vision and Pattern Recognition, 2008:18.
［33］Chen Cheng, Yang Yi, Nie Feiping, et al. 3d Human Pose Recovery from Image by Efficient Visual Feature Selection［J］. Computer Vision and Image Understanding, 2011,115(3):290299.
［34］Okada R, Soatto S. Relevant Feature Selection for Human Pose Estimation and Localization in Cluttered Images［C］∥Proc of European Conference on Computer Vision, 2008:434445.
［35］Ronfard R, Schmid C, Triggs B. Learning to Parse Pictures of People［C］∥Proc of European Conference on Computer Vision, 2002:700714.
［36］Mohan A, Papageorgiou C, Poggio T. ExampleBased Object Detection in Images by Components［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001,23(4):349361.
［37］Andriluka M, Roth S,Schiele B. Monocular 3D Pose Estimation and Tracking by Detection［C］∥Proc of IEEE Conference on Computer Vision and Pattern Recognition, 2010:623630.
［38］Daubney B, Gibson D, Campbell N. Monocular 3D Human Pose Estimation Using Sparse Motion Features［C］∥Proc of International Conference on Computer Vision, 2009:10501057.
［39］Wang Yi,Qian Gang. Robust Human Pose Recognition Using Unlabeled Markers［C］∥Proc of Workshop on Applications of Computer Vision, 2008:17.
［40］Kohli P, Rihan J, Bray M, et al. Simultaneous Segmentation and Pose Estimation of Humans using Dynamic Graph Cuts［J］. International Journal of Computer Vision, 2008, 79(3):285298.
［41］http://www.robots.ox.ac.uk/~vgg/data/stickmen/.
［42］http://www.vision.ee.ethz.ch/~calvin/articulated_human_pose_estimation_code/.
［43］Yang Yi,Ramanan D.Articulated Pose Estimation with Flexible MixturesofParts［C］∥Proc of the 24th IEEE Conf on Computer Vision and Pattern Recognition, 2011:13851392.
［44］http://phoenix.ics.uci.edu/software/pose/.
［45］Ramanan D. Learning to Parse Images of Articulated Objects［J］. Neural Info Proc Systems, 2006.
［46］http://www.ics.uci.edu/~dramanan/papers/parse/index.html.
［47］Andriluka M, Roth S,Schiele B. Pictorial Structures Revisited: People Detection and Articulated Pose Estimation［C］∥Proc of IEEE Conference on Computer Vision and Pattern Recognition,2009.
［48］http://www.mis.tudarmstadt.de/node/381.
［49］杜友田,陈峰,徐文立,等. 基于视觉的人的运动识别综述［J］. 电子学报，2007, 35(1):8490.
［50］Montabone S,Soto A. Human Detection Using a Mobile Platform and Novel Features Derived from a Visual Saliency Mechanism［J］. Image and Vision Computing, 2010, 28(3):391402.
［51］Sigal L, Bhatia S, Roth S, et al. Tracking LooseLimbed People［C］∥Proc of IEEE Conference on Computer Vision and Pattern Recognition, 2004:421428.