Author(s)

Chen Xiaoman

Corresponding Author

Chen Xiaoman

ABSTRACT

Human motion capture is an important research direction in the field of computer vision. It aims to analyze images or videos to obtain human posture and motion parameters, and to further carry out posture recognition, semantic analysis and behavior understanding. Human motion capture refers to extracting the region containing useful information from the background image from the image sequence to make it a meaningful entity. Three-dimensional human motion capture data is increasingly used in animation, film production, games and other industries due to its strong visual reality and expressive force. Both professional animators and non professionals are inseparable from the browsing, searching and accumulation of materials. Therefore, the retrieval and reuse of large-scale motion capture data need to be supported by efficient, accurate and reliable retrieval methods. Based on the hybrid reality technology, this paper studies the human motion capture technology which combines depth map and 3D model.

KEYWORDS

Motion capture, 3-D model, Motion parameters, Data