Počet záznamů: 1
Restoration of Fast Moving Objects
- 1.
SYSNO ASEP 0533754 Druh ASEP J - Článek v odborném periodiku Zařazení RIV J - Článek v odborném periodiku Poddruh J Článek ve WOS Název Restoration of Fast Moving Objects Tvůrce(i) Kotera, Jan (UTIA-B)
Matas, J. (CZ)
Šroubek, Filip (UTIA-B) RID, ORCIDCelkový počet autorů 3 Zdroj.dok. IEEE Transactions on Image Processing. - : Institute of Electrical and Electronics Engineers - ISSN 1057-7149
Roč. 29, č. 1 (2020), s. 8577-8589Poč.str. 13 s. Forma vydání Tištěná - P Jazyk dok. eng - angličtina Země vyd. US - Spojené státy americké Klíč. slova Blind deconvolution ; motion deblurring ; motion estimation ; shape estimation ; image matting ; alternating direction method of multipliers Vědní obor RIV JD - Využití počítačů, robotika a její aplikace Obor OECD Computer hardware and architecture CEP GA18-05360S GA ČR - Grantová agentura ČR Způsob publikování Omezený přístup Institucionální podpora UTIA-B - RVO:67985556 UT WOS 000564245800004 EID SCOPUS 85090867037 DOI 10.1109/TIP.2020.3016490 Anotace We have proposed a method for restoration of fast moving objects from a single image. If an object is photographed at motion in front of a static background, the object will be blurred while the background sharp and partially occluded by the object. The goal is to recover the object appearance from such blurred image. We adopt the image formation model for fast moving objects and consider objects undergoing 2D translation and rotation. For this scenario we formulate the estimation of the object shape, appearance, and motion from a single image and known background as a constrained optimization problem with appropriate regularization terms. Both similarities and differences with blind deconvolution are discussed with the latter caused mainly by the coupling of the object appearance and shape in the acquisition model. Necessary conditions for solution uniqueness are derived and a numerical solution based on the alternating direction method of multipliers is presented. The proposed method is evaluated on a new dataset. Pracoviště Ústav teorie informace a automatizace Kontakt Markéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201. Rok sběru 2021 Elektronická adresa https://ieeexplore.ieee.org/document/9171560
Počet záznamů: 1