Multi-modal face tracking in multi-camera environments

Authors:
Hang-Bong Kang;Sang-Hyun Cho
Affiliations:
Dept. of Computer Engineering, Catholic University of Korea, Puchon City Kyonggi-Do, Korea;Dept. of Computer Engineering, Catholic University of Korea, Puchon City Kyonggi-Do, Korea
Venue:
CAIP'05 Proceedings of the 11th international conference on Computer Analysis of Images and Patterns
Year:
2005

Citing 2
Cited 0

Elliptical Head Tracking Using Intensity Gradients and Color Histograms

CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Multi-Modal Face Tracking Using Bayesian Network

AMFG '03 Proceedings of the IEEE International Workshop on Analysis and Modeling of Faces and Gestures

Quantified Score

Hi-index	0.00

Visualization

Abstract

Reliable tracking has been an active research field in the computer vision. This paper presents a probabilistic face tracking method that uses multiple ingredients and integrates tracking from multiple cameras to increase reliability and overcome the occlusion cases. Color and edge ingredients are fused using Bayesian Network and context factors are used to represent the significance of each modality in fusion. We extend our multi-modal tracking method to multi-camera environments where it is possible to track the face of interest well even though the faces are severely occluded or lost due to handoff in some camera views. Desirable tracking results are obtained when compared to those of other tracking method.