A Bayesian approach to human activity recognition
- 20 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
Presents a methodology for automatically identifying human action. We use a new approach to human activity recognition that incorporates a Bayesian framework. By tracking the movement of the head of the subject over consecutive frames of monocular grayscale image sequences, we recognize actions in the frontal or lateral view. Input sequences captured from a CCD camera are matched against stored models of actions. The action that is found to be closest to the input sequence is identified. In the present implementation, these actions include sitting down, standing up, bending down, getting up, hugging, squatting, rising from a squatting position, bending sideways, falling backward and walking. This methodology finds application in environments where constant monitoring of human activity is required, such as in department stores and airports.Keywords
This publication has 11 references indexed in Scilit:
- Recognizing human action in time-sequential images using hidden Markov modelPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Recognizing human actions in a static roomPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Automatic tracking of human motion in indoor scenes across multiple synchronized video streamsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- The representation and recognition of human movement using temporal templatesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Model-based tracking of self-occluding articulated objectsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Recognition of human body motion using phase space constraintsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Human Motion Analysis: A ReviewComputer Vision and Image Understanding, 1999
- Nonrigid Motion Analysis: Articulated and Elastic MotionComputer Vision and Image Understanding, 1998
- Human action learning via hidden Markov modelIEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans, 1997
- Towards Model-Based Recognition of Human Movements in Image SequencesCVGIP: Image Understanding, 1994