Viewpoint Manifolds for Action Recognition
EURASIP Journal on Image and Video Processing volume 2009, Article number: 738702 (2009)
Action recognition from video is a problem that has many important applications to human motion analysis. In real-world settings, the viewpoint of the camera cannot always be fixed relative to the subject, so view-invariant action recognition methods are needed. Previous view-invariant methods use multiple cameras in both the training and testing phases of action recognition or require storing many examples of a single action from multiple viewpoints. In this paper, we present a framework for learning a compact representation of primitive actions (e.g., walk, punch, kick, sit) that can be used for video obtained from a single camera for simultaneous action recognition and viewpoint estimation. Using our method, which models the low-dimensional structure of these actions relative to viewpoint, we show recognition rates on a publicly available dataset previously only achieved using multiple simultaneous views.
To access the full article, please see PDF.
About this article
Cite this article
Souvenir, R., Parrigan, K. Viewpoint Manifolds for Action Recognition. J Image Video Proc 2009, 738702 (2009). https://doi.org/10.1155/2009/738702