Online selection of discriminative features using bayes error rate for visual tracking

Authors:
Dawei Liang;Qingming Huang;Wen Gao;Hongxun Yao
Affiliations:
School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China;Graduate School of Chinese Academy of Sciences, Beijing, China;School of Electronic Engineering and Computer Science, Peking University, Beijing, China;School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China
Venue:
PCM'06 Proceedings of the 7th Pacific Rim conference on Advances in Multimedia Information Processing
Year:
2006

Citing 9
Cited 2

CONDENSATION—Conditional Density Propagation forVisual Tracking

International Journal of Computer Vision
Color-Based Probabilistic Tracking

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part I
Kernel-Based Object Tracking

IEEE Transactions on Pattern Analysis and Machine Intelligence
Real Time Face and Object Tracking as a Component of a Perceptual User Interface

WACV '98 Proceedings of the 4th IEEE Workshop on Applications of Computer Vision (WACV'98)
On-Line Selection of Discriminative Tracking Features

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
The Template Update Problem

IEEE Transactions on Pattern Analysis and Machine Intelligence
Ensemble Tracking

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Online Selecting Discriminative Tracking Features Using Particle Filter

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02

Adaptive Subclass Discriminant Analysis Color Space Learning for Visual Tracking

PCM '08 Proceedings of the 9th Pacific Rim Conference on Multimedia: Advances in Multimedia Information Processing
Combined feature evaluation for adaptive visual object tracking

Computer Vision and Image Understanding

Quantified Score

Hi-index	0.00

Visualization

Abstract

Online feature selection using Bayes error rate is proposed to address visual tracking problem, where the appearances of the tracked object and scene background change during tracking. Given likelihood functions of the object and background with respect to a feature, Bayes error rate is a natural way to evaluate discriminating power of the feature. From previous frame, object and background pixels are sampled to estimate likelihood functions of each color feature in the form of histogram. Then, all features are ranked according to their Bayes error rate. And the top N features with the smallest Bayes error rate are selected to generate a weight map for current frame, where mean shift is employed to find the local mode, and hence, the location of the object. Experimental results on real image sequences demonstrate the effectiveness of the proposed approach.