A Hough transform-based voting framework for action recognition

Angela Yao, Jue Gall, Luc Van Gool
2010 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition  
We present a method to classify and localize human actions in video using a Hough transform voting framework. Random trees are trained to learn a mapping between densely-sampled feature patches and their corresponding votes in a spatio-temporal-action Hough space. The leaves of the trees form a discriminative multi-class codebook that share features between the action classes and vote for action centers in a probabilistic manner. Using low-level features such as gradients and optical flow, we
more » ... monstrate that Hough-voting can achieve state-of-the-art performance on several datasets covering a wide range of action-recognition scenarios.
doi:10.1109/cvpr.2010.5539883 dblp:conf/cvpr/YaoGG10 fatcat:7d6slbftqvhbzafwsykupd2laq