Intra-Frame Object Tracking by Deblatting

0519063 - ÚTIA 2020 RIV US eng C - Konferenční příspěvek (zahraniční konf.)
Kotera, Jan - Rozumnyi, D. - Šroubek, Filip - Matas, J.
Intra-Frame Object Tracking by Deblatting.
Proceedings of the IEEE International Conference on Computer Vision 2019 (ICCV 2019). Piscataway: IEEE, 2019, s. 2300-2309. ISBN 978-1-7281-5024-6. ISSN 2473-9936. E-ISSN 2473-9944.
[ICCV 2019. International conference on computer vision. Seoul (KR), 27.10.2019-02.11.2019]
Grant CEP: GA ČR GA18-05360S
Grant ostatní: AV ČR(CZ) AP1701
Program: Akademická prémie - Praemium Academiae
Institucionální podpora: RVO:67985556
Klíčová slova: visual object tracking * fast moving objects * deblurring
Obor OECD: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
http://library.utia.cas.cz/separaty/2019/ZOI/kotera-0519063.pdf

Objects moving at high speed along complex trajectories often appear in videos, especially videos of sports. Such objects elapse non-negligible distance during exposure time of a single frame and therefore their position in the frame is not well defined. They appear as semi-transparent streaks due to the motion blur and cannot be reliably tracked by standard trackers. We propose a novel approach called Tracking by Deblatting based on the observation that motion blur is directly related to the intra-frame trajectory of an object. Blur is estimated by solving two intertwined inverse problems, blind deblurring and image matting, which we call deblatting. The trajectory is then estimated by fitting a piecewise quadratic curve, which models physically justifiable trajectories. As a result, tracked objects are precisely localized with higher temporal resolution than by conventional trackers. The proposed TbD tracker was evaluated on a newly created dataset of videos with ground truth obtained by a high-speed camera using a novel Trajectory-IoU metric that generalizes the traditional Intersection over Union and measures the accuracy of the intra-frame trajectory. The proposed method outperforms baseline both in recall and trajectory accuracy.
Trvalý link: http://hdl.handle.net/11104/0304198