An improved real-time compressive tracking method

Authors:
Yan He;Guangzhu Xu;Bangjun Lei;Jing Jing;Fangmin Dong
Affiliations:
Three Gorges University, Yichang;Three Gorges University, Yichang;Three Gorges University, Yichang;Three Gorges University, Yichang;Three Gorges University, Yichang
Venue:
Proceedings of the Fifth International Conference on Internet Multimedia Computing and Service
Year:
2013

Citing 12
Cited 0

Kernel-Based Object Tracking

IEEE Transactions on Pattern Analysis and Machine Intelligence
Summed-area tables for texture mapping

SIGGRAPH '84 Proceedings of the 11th annual conference on Computer graphics and interactive techniques
Robust Real-Time Face Detection

International Journal of Computer Vision
Online Selection of Discriminative Tracking Features

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
Robust Visual Tracking and Vehicle Classification via Sparse Representation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Real-time visual tracking using compressive sensing

CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Tracking-Learning-Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Compressed sensing

IEEE Transactions on Information Theory
Near-Optimal Signal Recovery From Random Projections: Universal Encoding Strategies?

IEEE Transactions on Information Theory
Real-time compressive tracking

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III

Quantified Score

Hi-index	0.00

Visualization

Abstract

Robust object tracking is very challenging due to object pose variation, illumination changing and occlusion etc.. Tracking Methods based on dimensionality reducing by applying random projection can extract target features efficiently and greatly improve the tracking speed and are getting more and more attentions. This paper proposed an improved real-time compress tracking algorithm, which adopted a small number of randomly generated linear measurements of raw image as object features. Then these features are combined with online updating mechanism and Bayesian classifier to implement tracking. Experimental results on some challenging sequences show that this method has both improved the tracking performance in some degree and reduced the algorithm complexity.