This paper presents two approaches for the representation and recognition of human action in video, aiming for view-point invariance. The paper first presents new results using a 2D approach presented earlier. Inherent limitations of the 2D approach are discussed and a new 3D approach that builds on recent work on 3D model-based invariants, is presented. Each action is represented as a unique curve in a 3D invariance space, surrounded by an acceptance volume ('action volume'). Given a video sequence, 2D quantities from the image are calculated and matched against candidate action volumes in a probabilistic framework. The theory is presented followed by results on arbitrary projections of motion-capture data which demonstrate a high degree of tolerance to viewpoint change.
View invariants for human action recognition
2003-01-01
376217 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
View Invariants for Human Action Recognition
British Library Conference Proceedings | 2003
|Human action-recognition using mutual invariants
British Library Online Contents | 2005
|View Invariance for Human Action Recognition
British Library Online Contents | 2006
|View-invariance in action recognition
IEEE | 2001
|View-Invariance in Action Recognition
British Library Conference Proceedings | 2001
|