Adaptive object tracking using bayesian network and memory

Authors:
Hang-Bong Kang;Sang-Hyun Cho
Affiliations:
Catholic University of Korea, Puchon city, Kyonggi-Do, Korea;Catholic University of Korea, Puchon city, Kyonggi-Do, Korea
Venue:
Proceedings of the ACM 2nd international workshop on Video surveillance & sensor networks
Year:
2004

Citing 6
Cited 0

CONDENSATION—Conditional Density Propagation forVisual Tracking

International Journal of Computer Vision
Contour Tracking by Stochastic Propagation of Conditional Density

ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume I - Volume I
Object Tracking with an Adaptive Color-Based Particle Filter

Proceedings of the 24th DAGM Symposium on Pattern Recognition
Kernel-Based Object Tracking

IEEE Transactions on Pattern Analysis and Machine Intelligence
Multi-Modal Face Tracking Using Bayesian Network

AMFG '03 Proceedings of the IEEE International Workshop on Analysis and Modeling of Faces and Gestures
Robust online appearance models for visual tracking

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents an adaptive object tracking method that integrates the cues from color likelihood and edge likelihood, and that adapts itself to abrupt appearance changing objects. We use a Bayesian network based multi-modal fusion method of color and edge information. To handle the cases of sudden appearance changes, occlusion, disappearance and reappearance of tracked objects, a memory model is also introduced. The proposed tracker has the following characteristics. First, multiple modalities are integrated in the Bayesian network to evaluate the posterior of each feature. Secondly, context factors are computed in order to select best object state. Finally, a memory-based appearance model is introduced to handle abrupt appearance changes. Our method is robust and versatile for a modest computational cost. Desirable tracking results are obtained.