Abstract

We present a novel feature description algorithm to de-scribe 3D local spatio-temporal features for human action recognition. Our descriptor avoids the singularity and limited discrimination power issues of traditional 3D descriptors by quantizing and describing visual features in the sim-plex topological vector space. Specifically, given a feature’s support region containing a set of 3D visual cues, we de-compose the cues’ orientation into three angles, transformthe decomposed angles into the simplex space, and describe them in such a space. Then, quadrant decomposition is performed to improve discrimination, and a final feature vector is composed from the resulting histograms. We develop intuitive visualization tools for analyzing feature characteristics in the simplex topological vector space. Experimentalresults demonstrate that our novel simplex-based orientation decomposition (SOD) descriptor substantially outperforms traditional 3D descriptors for the KTH, UCF Sport, and Hollywood-2 benchmark action datasets. In addition, the results show that our SOD descriptor is a superior individual descriptor for action recognition.