Dynamic Human Pose Estimation using Markov Chain Monte Carlo Approach
Authors:
- 1 January 2005
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 168-175
Abstract
This paper addresses the problem of tracking human body pose in monocular video including automatic pose initialization and re-initialization after tracking failures caused by partial occlusion or unreliable observations. We proposed a method based on data-driven Markov chain Monte Carlo (DD-MCMC) that uses bottom-up techniques to generate state proposals for pose estimation and initialization. This method allows us to exploit different image cues and consolidate the inferences using a representation known as the proposal maps. We present experimental results with an indoor video sequence.Keywords
This publication has 16 references indexed in Scilit:
- Automatic partitioning of high dimensional search spaces associated with articulated body motion capture2005
- Tracking loose-limbed people2004
- Variational mixture smoothing for non-linear dynamical systems2004
- Human body tracking with auxiliary measurements2004
- 3D Human Body Tracking Using Deterministic Temporal Motion Models2004
- Combining Geometric- and View-Based Approaches for Articulated Pose Estimation2004
- Human Pose Estimation Using Learnt Probabilistic Region Similarities and Partial Configurations2004
- Kinematic jump processes for monocular 3D human tracking2003
- Image segmentation by data-driven markov chain monte carloIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002
- 10.1007/978-1-4899-4485-6Crossref Listing of Deleted Dois, 2000