0345450 20240103193650.720110816235959.9 000293961900002 80053895602 10.1007/s00138-010-0251-6 10 s. cav_un_epca*02542180932-8092225 (2011)741-750Springer Dynamic texture Optical flow SVD cav_un_auth*0216372 Chetverikov D. HU cav_un_auth*0273706 Fazekas S. HU cav_un_auth*0101093 Haindl Michal Rozpoznávání obrazu Department of Pattern Recognition RO RO UTIA-B Department of Pattern Recognition Ústav teorie informace a automatizace AV ČR, v. v. i. http://library.utia.cas.cz/separaty/2011/RO/haindl-0345450.pdf GA102/08/0593 GA ČR cav_un_auth*0239567 507752 XE EC cav_un_auth*0200689 CEZ:AV0Z10750506 Depending on application, temporal texture can be viewed as either foreground or background. We address two related problems: finding regions of dynamic texture in a video and detecting moving targets in a dynamic texture. We propose efficient and fast methods for both cases. The methods can be potentially used in real-time applications of machine vision. First, we show how the optical flow residual can be used to find dynamic texture in video. The algorithm is a practical, real-time simplification of the sophisticated and powerful but time-consuming method (Fazekas et al. in Int J Comput Vis 82:48–63, 2009). We give numerous examples of detecting and segmenting fire, smoke, water and other dynamic textures in real-world videos acquired by static and moving cameras. Then we apply the singular value decomposition (SVD) to a temporal data window in a video to detect targets in dynamic texture via the residual of the largest singular value. 2012 BD 4 A 4a 20231122134102.9 http://hdl.handle.net/11104/0186722 COMPUTERSCIENCEARTIFICIALINTELLIGENCE|COMPUTERSCIENCECYBERNETICS|ENGINEERINGELECTRICALELECTRONIC 1.324 0.132 7.6 0.00254 0.669 711 76 0.501 Q1 60.988 44.225 Q2 Q3 2011 Soubory v repozitáři: haindl-0345450.pdf 80053895602 SCOPUS 000293961900002 WOS cav_un_epca*0254218 Machine Vision and Applications 0932-8092 1432-1769 Roč. 22 č. 5 2011 741 750 Springer