TechWare: Video-based human action detection resources

The video-based human action detection is very useful in a wide range of applications including video surveillance, tele-monitoring of patients and senior people, medical diagnosis and training, video content analysis and search, and intelligent human computer interaction. Actions can be characterized by spatio-temporal patterns. The development of video-based action detection technology has been ongoing for decades. The third type of interest point features is called sparse spatiotemporal feature, developed by Dollar et al. There are many public data sets for human action recognition and detection. The University of Central Florida (UCF) sports action data set includes a set of sports actions collected from broadcast television channels such as the BBC and ESPN. Human action in video sequences can be seen as silhouettes of a moving torso and protruding limbs undergoing articulated motion.