Adaptively adjusted gaussian mixture models for surveillance applications

Authors:
Tianci Huang;Xiangzhong Fang;Jingbang Qiu;Takeshi Ikenaga
Affiliations:
Graduate School of Information, Production, and System, Waseda University, Fukuoka, Japan;Graduate School of Information, Production, and System, Waseda University, Fukuoka, Japan;Graduate School of Information, Production, and System, Waseda University, Fukuoka, Japan;Graduate School of Information, Production, and System, Waseda University, Fukuoka, Japan
Venue:
MMM'10 Proceedings of the 16th international conference on Advances in Multimedia Modeling
Year:
2010

Citing 2
Cited 0

Learning Patterns of Activity Using Real-Time Tracking

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)

Quantified Score

Hi-index	0.00

Visualization

Abstract

Segmentation of moving objects is the basic step for surveillance system. The Gaussian Mixture Model is one of the best models to cope with repetitive motions in a dynamic and complex environment. In this paper, an Adaptively Adjustment Mechanism was proposed by fully utilizing Gaussian distributions with least number so as to save the amount of computation. In addition to that, by applying proposed Gaussian Mixture Model scheme to edge segmented image and combining with data fusion method, the proposed algorithm was able to resist illumination change in scene and remove shadows of motion. Experiments proved the excellent performance.