Research ArticleOpen AccessGoogle Scholar indexed
Human Body Tracking and Pose Estimation Using Modified Camshift Algorithm
Department of Information and Telecommunication Engineering, Korea Aerospace University, Go-yang, South Korea
Department of Information and Telecommunication Engineering, Korea Aerospace University, Go-yang, South Korea
Department of Information and Telecommunication Engineering, Korea Aerospace University, Go-yang, South Korea
Department of Information and Telecommunication Engineering, Korea Aerospace University, Go-yang, South Korea
Department of Information and Telecommunication Engineering, Korea Aerospace University, Go-yang, South Korea
Department of Information and Telecommunication Engineering, Korea Aerospace University, Go-yang, South Korea
- 1 Department of Information and Telecommunication Engineering, Korea Aerospace University, Go-yang, South Korea
- 2 Department of Information and Telecommunication Engineering, Korea Aerospace University, Go-yang, South Korea
- 3 Department of Information and Telecommunication Engineering, Korea Aerospace University, Go-yang, South Korea
- 4 Department of Information and Telecommunication Engineering, Korea Aerospace University, Go-yang, South Korea
- 5 Department of Information and Telecommunication Engineering, Korea Aerospace University, Go-yang, South Korea
- 6 Department of Information and Telecommunication Engineering, Korea Aerospace University, Go-yang, South Korea
Journal of Software Engineering and Applications·Volume 06 (2013)·Pages 37–42·Published 30 May 2013·DOI10.4236/jsea.2013.65B008
Copy link · social · email
Abstract
In this paper, we propose multiple CAMShift Algorithm based on Kalman filter and weighted search windows that extracts skin color area and tracks several human body parts for real-time human tracking system. The CAMShift Algorithm we propose searches the skin color region by detecting the skin color area from background model. Kalman filter stabilizes the floated search area of CAMShift Algorithm. Each occlusion areas are avoided by using weighted window of non-search areas and main-search area. And shadows are eliminated from background model and intensity of shadow. The proposed modified Camshaft algorithm can estimate human pose in real-time and achieves 96.82% accuracy even in the case of occlusions.
KeywordsBody TrackingCAMShiftPose EstimationKalman FilterWeighted Search Windows
- J. Shotton, el al. ,“Real-time Human Pose Recognition in Parts from Single Depth Images,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 20-25 June, 2011, pp. 1297-1304.
- G. R. Bradski, “Computer Vision Face Tracking for Use in a Perceptual User Interface,” Intel Technology Journal , 2nd Quarter, 1998.
- Xun Cai, Long Jiang, et al., “A New Region Gaussian Background Model for Video Surveillance,” Natural Computation , 2008, Vol. 6, pp. 123-127.
- V. Vezhnevets, V. Sazonov and A. Andreeva, “A Survey on Pixel-based Skin Color Detection Techniques,” Graphi-con03 , 2003, pp. 85-92.
- P. Peer, J. Kovac and F. Solina, “Human Skin Colour Clustering for Face Detection,” Eurocon 2003.