Compact Video Streaming & Background Extraction using Pyramidal Optical flow Reduction.

Abstract

The increasing demand of the cameras for surveillance systems not only requires the large storage devices but also requires the reduction in the time to browse the whole video.  The major problem in current scenario is use of the surveillance cameras in which they provide unedited raw data. Video browsing and retrieval are inconvenient due to inherent spatio-temp oral redundancies, where some time intervals may have no activity, or have activities that occur in a small image region. To meet such requirements video summarization is the only solution. Hence in our proposed work video summarization algorithm based on pyramidal reduction for surveillance videos is accomplished. Surveillances video summarization is not only related to reduction of size of the video but also to track the important objects in the video by maintaining the chronology.