Labelled silhouettes for human pose estimation
Data(s) |
22/03/2010
|
---|---|
Resumo |
This paper proposes a new method of using foreground silhouette images for human pose estimation. Labels are introduced to the silhouette images, providing an extra layer of information that can be used in the model fitting process. The pixels in the silhouettes are labelled according to the corresponding body part in the model of the current fit, with the labels propagated into the silhouette of the next frame to be used in the fitting for the next frame. Both single and multi-view implementations are detailed, with results showing performance improvements over only using standard unlabelled silhouettes. |
Formato |
application/pdf |
Identificador | |
Relação |
http://eprints.qut.edu.au/31436/1/c31436.pdf http://www.isspa2010.com/ Chen, Daniel C.Y. & Fookes, Clinton B. (2010) Labelled silhouettes for human pose estimation. In Proceedings of 10th International Conference on Information Science, Signal Processing and their Applications, Renaissance Hotel, Kuala Lumpur. |
Direitos |
Copyright 2010 [please consult the authors] |
Fonte |
Faculty of Built Environment and Engineering; Information Security Institute; School of Engineering Systems |
Palavras-Chave | #080104 Computer Vision #080106 Image Processing #pose estimation #motion capture #optical flow |
Tipo |
Conference Paper |