TRIC-track: tracking by regression with incrementally learned cascades

Wang, Xiaomeng; Valstar, Michel F.; Martinez, Brais; Khan, Muhammad Haris; Pridmore, Tony

Abstract

This paper proposes a novel approach to part-based track- ing by replacing local matching of an appearance model by direct prediction of the displacement between local image patches and part locations. We propose to use cascaded regression with incremental learning to track generic objects without any prior knowledge of an object’s structure or appearance. We exploit the spatial constraints between parts by implicitly learning the shape and deformation parameters of the object in an online fashion. We integrate a multiple temporal scale motion model to initialise our cascaded regression search close to the target and to allow it to cope with occlusions. Experimental results show that our tracker ranks first on the CVPR 2013 Benchmark.

Citation

Wang, X., Valstar, M. F., Martinez, B., Khan, M. H., & Pridmore, T. (2015, December). TRIC-track: tracking by regression with incrementally learned cascades. Presented at 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile

• Presentation Conference Type: Conference Paper (published)
• Conference Name: 2015 IEEE International Conference on Computer Vision (ICCV)
• Start Date: Dec 7, 2015
• End Date: Dec 13, 2015
• Acceptance Date: Sep 15, 2015
• Online Publication Date: Dec 13, 2015
• Publication Date: Dec 13, 2015
• Deposit Date: Jan 21, 2016
• Publicly Available Date: Jan 21, 2016
• Peer Reviewed: Peer Reviewed
• Pages: 4337-4345
• Book Title: 2015 IEEE International Conference on Computer Vision (ICCV)
• ISBN: 978-1-4673-8390-5
• DOI: https://doi.org/10.1109/ICCV.2015.493
• Public URL: https://nottingham-repository.worktribe.com/output/981181
• Publisher URL: https://ieeexplore.ieee.org/document/7410850
• Additional Information: © 2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
• Contract Date: Jan 21, 2016