Context-Aware Correlation Filter Tracking

Matthias Mueller, Neil Smith, Bernard Ghanem

Research output: Chapter in Book/Report/Conference proceedingConference contribution

372 Scopus citations

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 languageEnglish (US)
Title of host publication2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages1387-1395
Number of pages9
ISBN (Print)9781538604571
DOIs
StatePublished - Nov 9 2017

Fingerprint Dive into the research topics of 'Context-Aware Correlation Filter Tracking'. Together they form a unique fingerprint.

Cite this