000133148 001__ 133148 000133148 005__ 20250115151521.0 000133148 0247_ $$2doi$$a10.1007/s11554-011-0194-9 000133148 0248_ $$2sideral$$a137792 000133148 037__ $$aART-2012-137792 000133148 041__ $$aeng 000133148 100__ $$aMontañés Laborda, Miguel Angel 000133148 245__ $$aReal-time GPU color-based segmentation of football players 000133148 260__ $$c2012 000133148 5203_ $$aIn this paper, we propose a multi-camera application capable of processing high resolution images and extracting features based on colors patterns over graphic processing units (GPU). The goal is to work in real time under the uncontrolled environment of a sport event like a football match. Since football players are composed for diverse and complex color patterns, a Gaussian Mixture Models (GMM) is applied as segmentation paradigm, in order to analyze sport live images and video. Optimization techniques have also been applied over the C++ implementation using profiling tools focused on high performance. Time consuming tasks were implemented over NVIDIA’s CUDA platform, and later restructured and enhanced, speeding up the whole process significantly. Our resulting code is around 4–11 times faster on a low cost GPU than a highly optimized C++ version on a central processing unit (CPU) over the same data. Real time has been obtained processing until 64 frames per second. An important conclusion derived from our study is the scalability of the application to the number of cores on the GPU. 000133148 540__ $$9info:eu-repo/semantics/openAccess$$aAll rights reserved$$uhttp://www.europeana.eu/rights/rr-f/ 000133148 590__ $$a1.156$$b2012 000133148 591__ $$aENGINEERING, ELECTRICAL & ELECTRONIC$$b117 / 243 = 0.481$$c2012$$dQ2$$eT2 000133148 591__ $$aIMAGING SCIENCE & PHOTOGRAPHIC TECHNOLOGY$$b9 / 23 = 0.391$$c2012$$dQ2$$eT2 000133148 591__ $$aCOMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE$$b62 / 115 = 0.539$$c2012$$dQ3$$eT2 000133148 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion 000133148 700__ $$0(orcid)0000-0001-8093-8346$$aTorres Moreno, Enrique F.$$uUniversidad de Zaragoza 000133148 700__ $$aMartínez del Rincón, Jesús 000133148 700__ $$0(orcid)0000-0002-9582-8964$$aHerrero Jaraba, José Elías$$uUniversidad de Zaragoza 000133148 7102_ $$15007$$2035$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Arquit.Tecnología Comput. 000133148 7102_ $$15008$$2785$$aUniversidad de Zaragoza$$bDpto. Ingeniería Electrón.Com.$$cÁrea Tecnología Electrónica 000133148 773__ $$g7 (2012), 267-279$$pJOURNAL OF REAL-TIME IMAGE PROCESSING$$tJOURNAL OF REAL-TIME IMAGE PROCESSING$$x1861-8200 000133148 8564_ $$s1475917$$uhttps://zaguan.unizar.es/record/133148/files/texto_completo.pdf$$yVersión publicada 000133148 8564_ $$s1308959$$uhttps://zaguan.unizar.es/record/133148/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada 000133148 909CO $$ooai:zaguan.unizar.es:133148$$particulos$$pdriver 000133148 951__ $$a2025-01-15-15:14:41 000133148 980__ $$aARTICLE