Human action recognition based on skeleton features

Based on human bone joints, skeleton information has clear and simple features is not easily affected by appearance factors. In this paper, an improved feature of Gist, ExGist, proposed to describe the joints for action recognition. The joint coordinates are extracted using OpenPose thermodynamic diagram, ExGist used extraction. advantage that it can effectively characterize local global while maintaining original advantages Gist feature. Compared with achieves better results different classifiers. Additionally, compared C3D APTNet, our model also obtains accuracy rate 89.2%.