Human Pose Tracking Using Multi-level Structured Models
Human Pose Tracking Using Multi-level Structured Models
- Neue Suche nach: Lee, Mun Wai
- Neue Suche nach: Nevatia, Ram
- Neue Suche nach: Lee, Mun Wai
- Neue Suche nach: Nevatia, Ram
Abstract Tracking body poses of multiple persons in monocular video is a challenging problem due to the high dimensionality of the state space and issues such as inter-occlusion of the persons’ bodies. We proposed a three-stage approach with a multi-level state representation that enables a hierarchical estimation of 3D body poses. At the first stage, humans are tracked as blobs. In the second stage, parts such as face, shoulders and limbs are estimated and estimates are combined by grid-based belief propagation to infer 2D joint positions. The derived belief maps are used as proposal functions in the third stage to infer the 3D pose using data-driven Markov chain Monte Carlo. Experimental results on realistic indoor video sequences show that the method is able to track multiple persons during complex movement such as turning movement with inter-occlusion.
Dokumentinformationen
Human Pose Tracking Using Multi-level Structured Models
Computer Vision – ECCV 2006 ; 6 ; 368-381
Lecture Notes in Computer Science ; 3953 , 6
2006-01-01
14 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Ähnliche Titel
Human Pose Tracking Using Multi-level Structured Models
| British Library Conference Proceedings | 2006
3D Human Pose Tracking Priors using Geodesic Mixture Models
| British Library Online Contents | 2017
Human attributes from 3D pose tracking
| British Library Online Contents | 2012
Region-based pose tracking with occlusions using 3D models
| British Library Online Contents | 2012
Multi-View Face Pose Classification by Tree-Structured Classifier
| British Library Conference Proceedings | 2005