Human motion recognition using clay representation of trajectories

In this paper, we propose a novel human motion recognition approach that incorporates two fundamental concepts. First, the Shape Context and a clustering method are used to extract moving articulated parts from a video sequence. Then, we represent the moving articulated parts by trajectories. Our trajectory extraction approach provides good tolerance under various background and lighting conditions. Significantly, landmark point selection is not necessary in our approach, since trajectory generation is based on the extraction of moving articulated parts. The second concept is that the extracted trajectories are seen as forces pushing the articulated parts. Those forces are applied to a claylike deformed material, which is used to represent the trajectories' behavior. The experiment results show that the proposed approach is robust against noise and incorrectly extracted trajectories, such as redundant and missing trajectories.