ITJ - Computer Vision Workload Analysis Case Study of Video Surveillance Systems.pdf

Volume 09 Issue 02 Published, May 19, 2005 ISSN 1535-864X DOI: 10.1535/itj.0902 ® Intel Technology Journal Compute-Intensive, Highly Parallel Applications and Uses Computer Vision Workload Analysis: Case Study of Video Surveillance Systems More information, including current and past issues of Intel Technology Journal, can be found at: /technology/itj/index.htm Computer Vision Workload Analysis: Case Study of Video Surveillance Systems Trista P. Chen, Corporate Technology Group, Intel Corporation Horst Haussecker, Corporate Technology Group, Intel Corporation Alexander Bovyrin, Corporate Technology Group, Intel Corporation Roman Belenov, Corporate Technology Group, Intel Corporation Konstantin Rodyushkin, Corporate Technology Group, Intel Corporation Alexander Kuranov, Corporate Technology Group, Intel Corporation Victor Eruhimov, Corporate Technology Group, Intel Corporation Index words: computer vision, workload analysis, RMS, video surveillance, foreground detection, estimation- maximization, Gaussian mixture, particle filter, condensation filter, Markov chain Monte Carlo, eigen analysis, singular value decomposition, optical flow, motion estimation ABSTRACT Our characterization of individual CV algorithms as well as complete CV systems can be used to guide algorithm The vast accumulation of digital data requires new classes researchers to develop new algo