0519063 20240103223336.020200107235959.9 85082437719 10.1109/ICCVW.2019.00283 10 s. E cav_un_epca*0519174978-1-7281-5024-62473-99362300-2309PiscatawayIEEE2019 visual object tracking fast moving objects deblurring cav_un_auth*0293863 Kotera Jan UTIA-B Zpracování obrazové informace Image processing ZOI ZOI Department of Image Processing CZ Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0352947 Rozumnyi D. CZ cav_un_auth*0101209 Šroubek Filip UTIA-B Zpracování obrazové informace Department of Image Processing ZOI ZOI Department of Image Processing Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0075799 Matas J. CZ http://library.utia.cas.cz/separaty/2019/ZOI/kotera-0519063.pdf GA18-05360S GA ČR cav_un_auth*0361425 AP1701 AV ČR CZ cav_un_auth*0349658 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. cav_un_auth*0386778 ICCV 2019. International conference on computer vision 20191027 20191102 Seoul KR JD 10000 10200 10201 2020 4 PR RVO:67985556 http://hdl.handle.net/11104/0304198 cav_un_auth*0386528 FEL, ČVUT FEL, ČVUT CZ S 2019 85082437719 SCOPUS PUBMED WOS cav_un_epca*0519174 Proceedings of the IEEE International Conference on Computer Vision 2019 (ICCV 2019) 978-1-7281-5024-6 2473-9936 2473-9944 2300 2309 Piscataway IEEE 2019