Pose-conditioned joint angle limits for 3D human pose reconstruction

Estimating 3D human pose from 2D joint locations is central to the analysis of people in images and video. To address the fact that the problem is inherently ill posed, many methods impose a prior over human poses. Unfortunately these priors admit invalid poses because they do not model how joint-limits vary with pose. Here we make two key contributions. First, we collect a motion capture dataset that explores a wide range of human poses. From this we learn a pose-dependent model of joint limits that forms our prior. Both dataset and prior are available for research purposes. Second, we define a general parametrization of body pose and a new, multi-stage, method to estimate 3D pose from 2D joint locations using an over-complete dictionary of poses. Our method shows good generalization while avoiding impossible poses. We quantitatively compare our method with recent work and show state-of-the-art results on 2D to 3D pose estimation using the CMU mocap dataset. We also show superior results using manual annotations on real images and automatic detections on the Leeds sports pose dataset.

[1]  Hsi-Jian Lee,et al.  Determination of 3D human body postures from a single view , 1985, Comput. Vis. Graph. Image Process..

[2]  H Hatze.  A three-dimensional multivariate model of passive human joint torques and articular boundaries. , 1997, Clinical biomechanics.

[3]  Camillo J. Taylor,et al.  Reconstruction of Articulated Objects from Point Correspondences in a Single Uncalibrated Image , 2000, Comput. Vis. Image Underst..

[4]  Ioannis A. Kakadiaris,et al.  Estimating Anthropometry and Pose from a Single Uncalibrated Image , 2001, Comput. Vis. Image Underst..

[5]  Cristian Sminchisescu,et al.  Building Roadmaps of Local Minima of Visual Models , 2002, ECCV.

[6]  Marko Munih,et al.  Identifying shoulder and elbow passive moments and muscle contributions during static flexion-extension movements in the sagittal plane , 2002, IEEE/RSJ International Conference on Intelligent Robots and Systems.

[7]  Takeo Kanade,et al.  Ambiguities in Visual Tracking of Articulated Objects Using Two- and Three-Dimensional Models , 2003, Int. J. Robotics Res..

[8]  Cristian Sminchisescu,et al.  Estimating Articulated Human Motion with Covariance Scaled Sampling , 2003, Int. J. Robotics Res..

[9]  Aaron Hertzmann,et al.  Style-based inverse kinematics , 2004, ACM Trans. Graph..

[10]  R. Chellappa,et al.  View independent human body pose estimation from a single perspective image , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[11]  Pascal Fua,et al.  Hierarchical implicit surface joint limits for human body tracking , 2005, Comput. Vis. Image Underst..

[12]  Jitendra Malik,et al.  Recovering 3D human body configurations using shape contexts , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Y. Yacoob,et al.  Statistical Estimation of Human Anthropometry from a Single Uncalibrated Image , 2008 .

[14]  Jinxiang Chai,et al.  Modeling 3D human poses from uncalibrated monocular images , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[15]  Michael J. Black,et al.  Estimating human shape and pose from a single image , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[16]  Jitendra Malik,et al.  Poselets: Body part detectors trained using 3D human pose annotations , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[17]  Søren Hauberg,et al.  Gaussian-Like Spatial Priors for Articulated Tracking , 2010, ECCV.

[18]  Simon Lucey,et al.  Deterministic 3D Human Pose Estimation Using Rigid Structure , 2010, ECCV.

[19]  Hao Jiang.  3D Human Pose Reconstruction Using Millions of Exemplars , 2010, 2010 20th International Conference on Pattern Recognition.

[20]  Bernt Schiele,et al.  Monocular 3D pose estimation and tracking by detection , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[21]  Jinxiang Chai,et al.  Intuitive Interactive Human-Character Posing with Millions of Example Poses , 2011, IEEE Computer Graphics and Applications.

[22]  Takeo Igarashi,et al.  Retrieval and Visualization of Human Motion Data via Stick Figures , 2012, Comput. Graph. Forum.

[23]  T. Kanade,et al.  Reconstructing 3 D Human Pose from 2 D Image Landmarks , 2012 .

[24]  Philip H. S. Torr,et al.  Fast Human Pose Detection Using Randomized Hierarchical Cascades of Rejectors , 2012, International Journal of Computer Vision.

[25]  T. Kanade,et al.  Reconstructing 3D Human Pose from 2D Image Landmarks , 2012, ECCV.

[26]  Ying He,et al.  A Sketching Interface for Sitting Pose Design in the Virtual Environment , 2012, IEEE Transactions on Visualization and Computer Graphics.

[27]  Qiang Ji,et al.  Data-Free Prior Model for Upper Body Pose Estimation and Tracking , 2013, IEEE Transactions on Image Processing.

[28]  Roland Göcke,et al.  Monocular Image 3D Human Pose Estimation under Self-Occlusion , 2013, 2013 IEEE International Conference on Computer Vision.

[29]  Bedrich Benes,et al.  Sketching human character animations by composing sequences from large motion database , 2013, The Visual Computer.

[30]  Tae-Kyun Kim,et al.  Unconstrained Monocular 3D Human Pose Estimation by Action Detection and Cross-Modality Regression Forest , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[31]  Peter V. Gehler,et al.  Human Pose Estimation with Fields of Parts , 2014, ECCV.

[32]  Michael Schünke,et al.  PROMETHEUS LernAtlas der Anatomie , 2014 .

[33]  Youjie Zhou,et al.  Pose Locality Constrained Representation for 3D Human Pose Reconstruction , 2014, ECCV.