Markerless human motion capture by Markov random field and dynamic graph cuts with color constraints

Autor:	Zhenjiang Miao, Chengkai Wan, DianYong Zhang, Baozong Yuan, Jia Li
Rok vydání:	2009
Předmět:	Markov random field General Computer Science business.industry Computer science 3D reconstruction ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Process (computing) Human motion Motion capture Cut Key (cryptography) Computer vision Artificial intelligence business Pose
Zdroj:	Science in China Series F: Information Sciences. 52:252-259
ISSN:	1862-2836 1009-2757
DOI:	10.1007/s11432-009-0040-x
Popis:	Currently, many vision-based motion capture systems require passive markers attached to key locations on the human body. However, such systems are intrusive with limited application. The algorithm that we use for human motion capture in this paper is based on Markov random field (MRF) and dynamic graph cuts. It takes full account of the impact of 3D reconstruction error and integrates human motion capture and 3D reconstruction into MRF-MAP framework. For more accurate and robust performance, we extend our algorithm by incorporating color constraints into the pose estimation process. The advantages of incorporating color constraints are demonstrated by experimental results on several video sequences.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::6ca926e9cce953f6bc23dce65a71d651 https://doi.org/10.1007/s11432-009-0040-x Zobrazit plný text záznamu Full text from SpringerLink