Content-Based Video Copy Detection: PRISMA at TRECVID 2010
Juan Manuel Barrios, Benjamín Bustos · 2010
We developed a Video Copy Detection system that uses video-only information, extracts global descriptors from groups of frames, uses a pivot-based index for comparing groups, and defines a voting algorithm for copy localization. We submitted four Runs to TRECVID 2010 CCD task: PRISMA.m.balanced.ehdNgryhst: a combination of edge histogram and gray histogram. PRISMA.m.balanced.ehdNclrhst: a combination of edge histogram and color histogram. PRISMA.m.nofa.ehdNgryhst: a combination of edge histogram and gray histogram. PRISMA.m.nofa.ehdNghT10: a combination of edge histogram and gray histogram with a different threshold. The results shows that the combination of edge histogram and gray histogram is slightly better than edge histogram and color histogram. The results of submitted Runs were positioned above the median, and considering just video-only Runs, were the bests positioned for Balanced and Nofa profile. The results shows that our pivot-based index enables to discard 99.9 % of distance evaluations and still have good effectiveness, and that global descriptors can achieve competitive results with TRECVID transformations. 1