On the effect of temporal information on monocular 3d human pose estimation

We address the task of estimating 3D human poses from monocular camera sequences. Many works make use of multiple consecutive frames for the estimation of a 3D pose in a frame. Although such an approach should ease the pose estimation task substantially since multiple consecutive frames allow to solve for 2D projection ambiguities in principle, it has not yet been investigated systematically how much we can improve the 3D pose estimates when using multiple consecutive frames opposed to single frame information. In this paper we analyze the difference in quality of 3D pose estimates based on different numbers of consecutive frames from which 2D pose estimates are available. We validate the use of temporal information on two major different approaches for human pose estimation - modeling and learning approaches. The results of our experiments show that both learning and modeling approaches benefit from using multiple frames opposed to single frame input but that the benefit is small when the 2D pose estimates show a high quality in terms of precision.

[1]  Neill W. Campbell,et al.  Monocular 3D human pose estimation using sparse motion features , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.

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

[3]  Michael Arens,et al.  Reconstructing The Missing Dimension: From 2D To 3D Human Pose Estimation , 2011 .

[4]  G. Johansson.  Visual perception of biological motion and a model for its analysis , 1973 .

[5]  Neill W Campbell,et al.  IEEE worshop on Tracking Humans for Evaluation of their Motion in Image Sequences 2009 - Held in conjunction with ICCV , 2009 .

[6]  Moritz Tenorth,et al.  The TUM Kitchen Data Set of everyday manipulation activities for motion tracking and action recognition , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.

[7]  Michael J. Black,et al.  HumanEva: Synchronized Video and Motion Capture Dataset for Evaluation of Articulated Human Motion , 2006 .

[8]  Raquel Urtasun,et al.  Implicitly Constrained Gaussian Process Regression for Monocular Non-Rigid Pose Estimation , 2010, NIPS.

[9]  David J. Fleet,et al.  Priors for people tracking from small training sets , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

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

[11]  R. F. Rashid,et al.  Towards a system for the interpretation of moving light displays , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  Michael J. Black,et al.  HumanEva: Synchronized Video and Motion Capture Dataset and Baseline Algorithm for Evaluation of Articulated Human Motion , 2010, International Journal of Computer Vision.

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

[14]  David J. Fleet,et al.  Temporal motion models for monocular and multiview 3D human body tracking , 2006, Comput. Vis. Image Underst..

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

[16]  F. Xavier Roca,et al.  Action-specific motion prior for efficient Bayesian 3D human body tracking , 2009, Pattern Recognit..

[17]  Theodora A. Varvarigou,et al.  A dataset for workflow recognition in industrial scenes , 2011, 2011 18th IEEE International Conference on Image Processing.

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

[19]  Ramakant Nevatia,et al.  Monocular human pose tracking using multi frame part dynamics , 2009, 2009 Workshop on Motion and Video Computing (WMVC).