Multiple feature fusion for object tracking

Authors:
Yu Zhou;Cong Rao;Qin Lu;Xiang Bai;Wenyu Liu
Affiliations:
Department of Electronics and Information Engineering, Huazhong University of Science and Technology, Wuhan, China;Department of Electronics and Information Engineering, Huazhong University of Science and Technology, Wuhan, China;Department of Electronics and Information Engineering, Huazhong University of Science and Technology, Wuhan, China;Department of Electronics and Information Engineering, Huazhong University of Science and Technology, Wuhan, China;Department of Electronics and Information Engineering, Huazhong University of Science and Technology, Wuhan, China
Venue:
IScIDE'11 Proceedings of the Second Sino-foreign-interchange conference on Intelligent Science and Intelligent Data Engineering
Year:
2011

Citing 9
Cited 0

Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns

IEEE Transactions on Pattern Analysis and Machine Intelligence
Histograms of Oriented Gradients for Human Detection

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Robust Fragments-based Tracking using the Integral Histogram

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Ensemble Tracking

IEEE Transactions on Pattern Analysis and Machine Intelligence
Incremental Learning for Robust Visual Tracking

International Journal of Computer Vision
Semi-supervised On-Line Boosting for Robust Tracking

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Likelihood Map Fusion for Visual Object Tracking

WACV '08 Proceedings of the 2008 IEEE Workshop on Applications of Computer Vision
Robust Object Tracking with Online Multiple Instance Learning

IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning Adaptive Metric for Robust Visual Tracking

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a novel object tracking method by fusing multiple features. The tracking task is formulated under Bayesian inference framework. The posterior probability is resolved by the sum of weighted likelihood observations. Graph based semi-supervised learning method is used for likelihood evaluation, and the distance between foreground and background histograms is used for weight estimation. We evaluate our tracking algorithm on some popular benchmark videos and achieve competitive results compared with some state-of-art algorithms.