A low-power surveillance video coding system with early background subtraction and adaptive frame memory compression

Abstract

Various commercial video surveillance systems have become popular in recent years. The increasing demand for video surveillance systems which support high resolutions and operate with battery power makes it important to reduce the power consumption and to prolong battery lifetimes. H.264/AVC video coding standard and HEVC standard are widely used in many video surveillance systems due to their high compression efficiency. However, the high computation complexity of video coding standards requires a considerable amount of power consumption. This paper proposes a novel low-power surveillance video coding system that reduces both the internal power consumption inside the video encoder chip and the external power consumption by the external memory outside the chip. The proposed algorithm attempts to segment the input video into the foreground and background (BG) according to integer motion estimation (IME) information and adaptively controls the complexity of video compression modules according to the segmentation results. In order to reduce the external power consumption further, adaptive frame memory compression (FMC) using the segmentation results from the BG subtraction is proposed. The adaptive selection of the compression ratios and processing units for the FMC significantly improves the compression efficiency of the FMC. The proposed system reduces power consumption by up to 61.6% compared to a conventional video surveillance system.