Visual object tracking via sparse reconstruction

Authors:
Li Li;Zhenjun Han;Jianbin Jiao;Qixiang Ye
Affiliations:
Graduate University of Chinese Academy of Sciences;Graduate University of Chinese Academy of Sciences;Graduate University of Chinese Academy of Sciences;Graduate University of Chinese Academy of Sciences
Venue:
ICIMCS '10 Proceedings of the Second International Conference on Internet Multimedia Computing and Service
Year:
2010

Citing 7
Cited 0

On-Line Selection of Discriminative Tracking Features

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
The Template Update Problem

IEEE Transactions on Pattern Analysis and Machine Intelligence
KPCA Plus LDA: A Complete Kernel Fisher Discriminant Framework for Feature Extraction and Recognition

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
Learning a dictionary of shape-components in visual cortex: comparison with neurons, humans and machines

Learning a dictionary of shape-components in visual cortex: comparison with neurons, humans and machines
Robust Object Tracking Via Online Dynamic Spatial Bias Appearance Models

IEEE Transactions on Pattern Analysis and Machine Intelligence
Robust Face Recognition via Sparse Representation

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a new approach based on sparse representation for visual object tracking. The sparse representation is implemented by exploiting L1--norm minimization, which most compactly expresses the object and rejects all other possible but less compact representations. With the coefficient vector of the sparse representation, we reconstruct the tracked object in an instantaneous sample set, which improves the tracking adaptation to background variation, object shape change, and partial occlusion. Our experiments on public datasets show state-of-the-art results, which are better than those of several representative tracking methods.