Abstract
Correlation filter (CF) based trackers have recently gained a lot of popularity due to their impressive performance on benchmark datasets, while maintaining high frame rates. A significant amount of recent research focuses on the incorporation of stronger features for a richer representation of the tracking target. However, this only helps to discriminate the target from background within a small neighborhood. In this paper, we present a framework that allows the explicit incorporation of global context within CF trackers. We reformulate the original optimization problem and provide a closed form solution for single and multi-dimensional features in the primal and dual domain. Extensive experiments demonstrate that this framework significantly improves the performance of many CF trackers with only a modest impact on frame rate.
Original language | English (US) |
---|---|
Title of host publication | 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) |
Publisher | Institute of Electrical and Electronics Engineers (IEEE) |
Pages | 1387-1395 |
Number of pages | 9 |
ISBN (Print) | 9781538604571 |
DOIs | |
State | Published - Nov 9 2017 |
Bibliographical note
KAUST Repository Item: Exported on 2020-10-01Acknowledgements: This work was supported by the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research through the VCC funding.