Viewpoint Invariant RGB-D Human Action Recognition


Viewpoint variation is a major challenge in video- based human action recognition. We exploit the simultaneous RGB and Depth sensing of RGB-D cameras to address this problem. Our technique capitalizes on the complementary spatio-temporal information in RGB and Depth frames of the RGB-D videos to achieve viewpoint invariant action recognition. We extract… (More)
DOI: 10.1109/DICTA.2017.8227505

12 Figures and Tables


  • Presentations referencing similar topics