Viewpoint Manifolds for Action Recognition. (22nd September 2009)

• Record Type: Journal Article
• Authors: Souvenir, Richard; Parrigan, Kyle
• Other Names: Sato Yoichi Academic Editor.
• Is Part Of: EURASIP journal on image and video processing. Volume 2009(2009)
• Publication Date: 2009-09-22
• Subjects: Image processing -- Digital techniques -- Periodicals; Digital video -- Periodicals; Traitement d'images; Vidéo numérique; Digital video; Image processing -- Digital techniques; Periodicals; Electronic journal; Electronic journals; 621.367
• DOI: 10.1155/2009/738702
• Languages: English
• ISSNs: 1687-5176

Abstract

Abstract : 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.