Learning human motion models from unsegmented videos

Roman Filipovych, Eraldo Ribeiro
2008 2008 IEEE Conference on Computer Vision and Pattern Recognition  
We present a novel method for learning human motion models from unsegmented videos. We propose a unified framework that encodes spatio-temporal relationships between descriptive motion parts and the appearance of individual poses. Sparse sets of spatial and spatio-temporal features are used. The method automatically learns static pose models and spatio-temporal motion parts. Neither motion cycles nor human figures need to be segmented for learning. We test the model on a publicly available
more » ... n dataset and demonstrate that our new method performs well on a number of classification tasks. We also show that classification rates are improved by increasing the number of pose models in the framework.
doi:10.1109/cvpr.2008.4587724 dblp:conf/cvpr/FilipovychR08 fatcat:gycafj3bb5hkzdquewze3hgfam