Despite their high stability and compactness, chord-length shape features have received relatively little attention in the human\r\naction recognition literature. In this paper, we present a new approach for human activity recognition, based on chord-length\r\nshape features. The most interesting contribution of this paper is twofold.We first show how a compact, computationally efficient\r\nshape descriptor; the chord-length shape features are constructed using 1-D chord-length functions. Second, we unfold how to\r\nuse fuzzy membership functions to partition action snippets into a number of temporal states. On two benchmark action datasets\r\n(KTH and WEIZMANN), the approach yields promising results that compare favorably with those previously reported in the\r\nliterature, while maintaining real-time performance.
Loading....