Human Activity Recognition in Thermal Infrared Imagery

In this paper, we investigate human repetitive activity properties from thermal infrared imagery, where human motion can be easily detected from the background regardless of lighting conditions and colors of the human surfaces and backgrounds. We employ an efficient spatiotemporal representation for human repetitive activity recognition, which represents human motion sequence in a single image while preserving some temporal information. A statistical approach is used to extract features for activity recognition. Experimental results show that the proposed approach achieves good performance for human repetitive activity recognition.