Quick Browsing Approach for Surveillance Videos

Surveillance cameras have been widely installed in large cities to monitor and record human activities either in inside or outside environments. To efficiently utilize surveillance videos, how to extract valuable information from hundreds-of-hours videos becomes an important task. This paper proposes a quick browsing approach to help the user quickly look for targets of interest in surveillance videos. Our basic idea is to collect all of moving objects which carry the most significant information in a surveillance video to construct a corresponding compact video by tuning spatiotemporal positions of these moving objects. Our proposed compact video cannot only compress the video length but also preserve the essential activities involved in the original surveillance video. This paper presents the details of our browsing system and the approach to producing the compact video from a source surveillance video. Keywordssurveillance video, compact video, moving object, background modelling.