Activity recognition based on hidden Markov models

Authors:
Weiyao Huang;Jun Zhang;Zhijing Liu
Affiliations:
School of Computer Science and Technology, Xidian University, Xi' an, China;School of Computer Science and Technology, Xidian University, Xi' an, China;School of Computer Science and Technology, Xidian University, Xi' an, China
Venue:
KSEM'07 Proceedings of the 2nd international conference on Knowledge science, engineering and management
Year:
2007

Citing 4
Cited 1

W4: Real-Time Surveillance of People and Their Activities

IEEE Transactions on Pattern Analysis and Machine Intelligence
Introduction to the Special Section on Video Surveillance

IEEE Transactions on Pattern Analysis and Machine Intelligence
Adaptive Change Detection for Real-Time Surveillance Applications

VS '00 Proceedings of the Third IEEE International Workshop on Visual Surveillance (VS'2000)
Ant colony system: a cooperative learning approach to the traveling salesman problem

IEEE Transactions on Evolutionary Computation

Integrating the enriched feature with machine learning algorithms for human movement and fall detection

The Journal of Supercomputing

Quantified Score

Hi-index	0.04

Visualization

Abstract

Focusing on the application of Intelligent Security Supervisory Control System, this paper proposes a new human activity recognition approach in which the Background Subtraction and the Time-stepping are averaged by weights to implement the precise extraction of moving human contour. In this way, the incompleteness of the extracting objects contour resulting from the color comparability between the human and the background can be resolved. Moreover, an ant colony clustering algorithm is applied to estimate and classify the body posture. Finally, Discrete Hidden Markov Models is used for human posture training, modeling and activity matching to recognize the human motion. Experiment results have shown that this method gives stable performances and good robustness.