Video Structured Description: A Novel Solution for Visual Surveillance

摘要

Video structured description was proposed for visual surveillance system in this paper, and a prototype system was also introduced. As a novel video information processing method, it employs knowledge model of certain surveillance scenario and image/video understanding to distill visual knowledge from video. Benefit from knowledge modeling, visual information distilled by the proposed method could be shared by other informative systems much easier than before. A technical overview was given and some key characteristics were also discussed.