View Invariants for Human Action Recognition

This paper presents two approaches for the representation and recognition of human action in video, aiming for viewpoint 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.

• Type: Conference
• Year: 2003
• Where: CVPR
• Authors: Vasu Parameswaran, Rama Chellappa
• Keywords: 2D Approach, Candidate Action Volumes, Computer Vision, CVPR 2003, Human Action, Model-based Invariants, Viewpoint Invariance