Title :
Video Segmentation Algorithm in Virtual Advertisement System
Author :
Linqiang, Chen ; Jianping, Han ; Linfeng, Zhang
Author_Institution :
Inst. of Graphics & Image, HangZhou Dianzi Univ., Hangzhou
Abstract :
Video object segmentation is a critical first step in virtual advertisement system. In this paper, we present belief propagation based method to increase the accuracy and efficiency of segmentation. The background color models are built as a mixture of a global color model and a per-pixel color model, while foreground color likelihood is modeled by spatially global Gaussian Mixture, and a realistic model of shadow effects is built also. The neighborhood dependencies are built with a MRF prior. Belief propagation is used to compute the marginal probability in MRF, and the video objects are segmented effectively. Experiment results show that the algorithm has the good performance, and has been used in our virtual advertisement system.
Keywords :
Gaussian processes; Markov processes; advertising data processing; belief networks; image colour analysis; image segmentation; probability; video signal processing; virtual reality; MRF prior; background color models; belief propagation based method; foreground color likelihood; global color model; marginal probability; per-pixel color model; shadow effects; spatially global Gaussian mixture; video object segmentation; video segmentation algorithm; virtual advertisement system; Belief propagation; Color; Graphics; Image segmentation; Interactive systems; Object segmentation; Pixel; Sun; Video sequences; Videoconference; Belief Propagation; Markov Random Field; Video Segmentation;
Conference_Titel :
Cyberworlds, 2008 International Conference on
Conference_Location :
Hangzhou
Print_ISBN :
978-0-7695-3381-0
