Context-Aware Correlation Filter Tracking

Matthias Mueller, Neil Smith, Bernard Ghanem; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 1396-1404

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.

Related Material


[pdf] [Supp] [poster] [video]
[bibtex]
@InProceedings{Mueller_2017_CVPR,
author = {Mueller, Matthias and Smith, Neil and Ghanem, Bernard},
title = {Context-Aware Correlation Filter Tracking},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {July},
year = {2017}
}