Quasi-invariants for human action representation and recognition
- 25 June 2003
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 307-310
- https://doi.org/10.1109/icpr.2002.1044699
Abstract
Although human action ecognition has been the subject of much esearch in the past, the issue of viewpoint invariance has eceived scarce attention. In this paper, we present an approach to detect human action with a high tolerance to viewpoint change. Canonical body poses are modeled in a view invariant manner to enable detection from a general viewpoint. While there exist no invariants for 3D to 2D projection, there exists a wealth of techniques in 2D invariance that can be used to advantage in 3D to 2D projection. We employ 2D invariants to recognize canonical poses of the human body leading to an effective way to represent and recognize human action which we evaluate theoretically and experimentally on 2D projections of publicly available human motion capture data.Keywords
This publication has 10 references indexed in Scilit:
- Cardboard people: a parameterized model of articulated image motionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Ghost: a human body part labeling system using silhouettesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- View-invariant representation and learning of human actionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Recognizing action events from multiple viewpointsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A Survey of Computer Vision-Based Human Motion CaptureComputer Vision and Image Understanding, 2001
- The Visual Analysis of Human Movement: A SurveyComputer Vision and Image Understanding, 1999
- Pfinder: real-time tracking of the human bodyPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1997
- View-Invariant Analysis of Cyclic MotionInternational Journal of Computer Vision, 1997
- First Sight: A human body outline labeling systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1995
- DETECTION OF ANTIBODY ACTIVITY IN HUMAN SERA AGAINST MENINGOCOCCAL CELL WALL ANTIGENS USING A GEL-IMMUNO-RADIO-ASSAY (GIRA)FEMS Microbiology Letters, 1980