Search
Hierarchical Estimation of Human Upper Body Based on 2D Observation Utilizing Evolutionary Programming and 'Genetic Memory'
Abstract
New method of the human body pose estimation based on single camera 2D observation is presented. It employs 3D model of the human body, and genetic algorithm combined with annealed particle filter for searching the global optimum of model state, best matching the object's 2D observation. Additionally, motion cost metric is employed, considering current pose and history of the body movement, favouring the estimates with the lowest changes of motion speed comparing to previous poses. The ''genetic memory'' concept is introduced for the genetic processing of both current and past states of 3D model. State-of-the art in the field of human body tracking is presented and discussed. Details of implemented method are described. Results of experimental evaluation of developed algorithm are included and discussed.
Cite as
Full text
full text is not available in portal
Keywords
Details
- Category:
- Conference activity
- Type:
- materiały konferencyjne indeksowane w Web of Science
- Published in:
-
Communications in Computer and Information Science
no. 149,
pages 82 - 90,
ISSN: 1865-0929 - Title of issue:
- 4th International Conference on Multimedia Communications, Services and Security (MCSS 2011) strony 82 - 90
- Language:
- English
- Publication year:
- 2011
- Bibliographic description:
- Szczuko P..: Hierarchical Estimation of Human Upper Body Based on 2D Observation Utilizing Evolutionary Programming and 'Genetic Memory', W: 4th International Conference on Multimedia Communications, Services and Security (MCSS 2011), 2011, ,.
- Verified by:
- Gdańsk University of Technology
seen 119 times