Free viewpoint action recognition using motion history volumes. CVIU

Action recognition is an important and challenging topic in computer vision, with many important applications including video surveillance, automated cinematogra-phy and understanding of social interaction. Yet, most current work in gesture or action interpretation remains rooted in view-dependent representations. This paper introduces Motion History Volumes (MHV) as a free-viewpoint representation for human actions in the case of multiple calibrated, and background-subtracted, video cameras. We present algorithms for computing, aligning and comparing MHVs of dierent actions performed by dierent people in a variety of viewpoints. Alignment and comparisons are performed eciently using Fourier transforms in cylindrical co-ordinates around the vertical axis. Results indicate that this representation can be used to learn and recognize basic human action classes, independently of gender, body size and viewpoint. Key words: action recognition, view invariance, volumetric reconstruction