Fusion of head and full-body detectors for multi-object tracking

Henschel R, Leal-Taixe L, Cremers D, Rosenhahn B (2018)

Publication Type: Conference contribution

Publication year: 2018

Publisher: IEEE Computer Society

Book Volume: 2018-June

Pages Range: 1509-1518

Conference Proceedings Title: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops

Event location: Salt Lake City, UT, USA

ISBN: 9781538661000

DOI: 10.1109/CVPRW.2018.00192

Abstract

In order to track all persons in a scene, the tracking-by-detection paradigm has proven to be a very effective approach. Yet, relying solely on a single detector is also a major limitation, as useful image information might be ignored. Consequently, this work demonstrates how to fuse two detectors into a tracking system. To obtain the trajectories, we propose to formulate tracking as a weighted graph labeling problem, resulting in a binary quadratic program. As such problems are NP-hard, the solution can only be approximated. Based on the Frank-Wolfe algorithm, we present a new solver that is crucial to handle such difficult problems. Evaluation on pedestrian tracking is provided for multiple scenarios, showing superior results over single detector tracking and standard QP-solvers. Finally, our tracker ranks 2nd on the MOT16 benchmark and 1st on the new MOT17 benchmark, outperforming over 90 trackers.

Involved external institutions

Gottfried Wilhelm Leibniz Universität Hannover DE Germany (DE) Technische Universität München (TUM) DE Germany (DE)

How to cite

APA:

Henschel, R., Leal-Taixe, L., Cremers, D., & Rosenhahn, B. (2018). Fusion of head and full-body detectors for multi-object tracking. In IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (pp. 1509-1518). Salt Lake City, UT, USA: IEEE Computer Society.

MLA:

Henschel, Roberto, et al. "Fusion of head and full-body detectors for multi-object tracking." Proceedings of the 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2018, Salt Lake City, UT, USA IEEE Computer Society, 2018. 1509-1518.

BibTeX: Download