Component-Based Human Body Tracking for Posture Estimation
To track a human body and estimate its posture, a component-based approach is less susceptible to changes in posture and lighting. This paper proposes model-based tracking with a component-based human body model comprised of 10 components and their hierarchical link. The proposed method first divides a video frame into blobs based on color, groups the blobs to make components, and matches the components to human body parts. Instead of matching blobs individually, the proposed model-based tacking uses components and their links. This paper shows the making of coarse-to-fine searches, so it offers a model that can make human-body matching more time-efficient.
Unable to display preview. Download preview PDF.
- 1.Colombo, C., Bimbo, A.D., Valli, A.: Non Intrusive Full Body Tracking for Real-time Aatar Animation. Proc. of International workshop on very low bitrate video coding (2001) 36–51Google Scholar
- 2.Huang, Y., Huang, T. S.: Model-based Human Body Tracking. Proc. of ICPR. (2002) 552–555Google Scholar
- 3.Lee, K. M., Street, W. N.: Model-based Detection, Segmentation and Classification using On-line Shape Learning. Machine vision and application, Vol. 19, No. 4 (2003)Google Scholar
- 4.Matsushita, Y., Nishino, K., Ikeuchi, K., Sakauchi, M.: Illumination Normalization with Time-dependent Intrinsic Images for Video Surveillance. IEEE trans. on PAMI, 26(10) (2004) 1336–1347Google Scholar
- 5.Mori, G., Malik, J.: Estimating Human Body Configurations using Shape Context Matching. Proc. of ECCV (2002) 666–680Google Scholar
- 6.Wren, C., Azarbayejani, A., Darrell, T., Pentland, A.: Pfinder: Real-time Tracking of the Human Body. IEEE trans. on PAMI, Vol. 11, No. 9 (1997)Google Scholar