Nonlinear Body Pose Estimation from Depth Images

This paper focuses on real-time markerless motion capture. The body pose of a person is estimated from depth images using an Iterative Closest Point algorithm. We present a very efficient approach, that estimates up to 28 degrees of freedom from 1000 data points with 4Hz. This is achieved by nonlinear optimization techniques using an analytically derived Jacobian and highly optimized correspondence search.

[1]  David G. Lowe,et al.  Fitting Parameterized Three-Dimensional Models to Images , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Lutz Falkenhagen.  Hierarchical Block-Based Disparity Estimation Considering Neighbourhood Constraints , 1997 .

[3]  Jitendra Malik,et al.  Tracking people with twists and exponential maps , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[4]  Thomas B. Moeslund,et al.  A Survey of Computer Vision-Based Human Motion Capture , 2001, Comput. Vis. Image Underst..

[5]  D. Scharstein,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, Proceedings IEEE Workshop on Stereo and Multi-Baseline Vision (SMBV 2001).

[6]  Mads Nielsen,et al.  Computer Vision — ECCV 2002 , 2002, Lecture Notes in Computer Science.

[7]  Pascal Fua,et al.  Model-Based Silhouette Extraction for Accurate People Tracking , 2002, ECCV.

[8]  Bodo Rosenhahn,et al.  Adaptive Pose Estimation for Different Corresponding Entities , 2002, DAGM-Symposium.

[9]  Ayoub Al-Hamadi,et al.  Solutions for Model-Based Analysis of Human Gait , 2003, DAGM-Symposium.

[10]  Trevor Darrell,et al.  Constraining human body tracking , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[11]  Reinhard Koch,et al.  Real-time multi-stereo depth estimation on GPU with approximative discontinuity handling , 2004 .

[12]  Nicol N. Schraudolph,et al.  3D hand tracking by rapid stochastic gradient descent using a skinning model , 2004 .