Hausdorff matching based SVD-covariance descriptor for object tracking

Authors:
Wen Guo;Changsheng Xu;Songde Ma;Songqiao Huang
Affiliations:
Institute of Automation, Beijing, China and Shandong Institutes of Business and Technology, Yantai, China;Institute of Automation, Beijing, China;Institute of Automation, Beijing, China;SUNY, Binghamton, NY
Venue:
ICIMCS '10 Proceedings of the Second International Conference on Internet Multimedia Computing and Service
Year:
2010

Citing 7
Cited 0

Comparing Images Using the Hausdorff Distance

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
Spatiograms versus Histograms for Region-Based Tracking

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Covariance Tracking using Model Update Based on Lie Algebra

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Incremental Learning for Robust Visual Tracking

International Journal of Computer Vision
Region covariance: a fast descriptor for detection and classification

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
Sequential Karhunen-Loeve basis extraction and its application to images

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we propose a Hausdorff matching based SVD-covariance descriptor for object tracking. Object tracking is one of the most important tasks in computer vision and covariance descriptor for visual tracking has attracted many researchers in the field. The main issues we want to address in this paper consist of the difficulty brought by the non-Euclidean space elements choice of covariance matrices and the large expenditure caused by the measurement between different models calculated on Riemannian manifolds. We have designed an efficient and discriminative SVD-covariance representation feature. The measurement between the target and candidates can be realized through Hausdorff distance. Theoretically, this reduces the computational cost compared with the original measurement on Riemannian manifolds. The experimental results show that the proposed approach is able to generate the promising feature for visual tracking.