Motion matters: a novel framework for compressing surveillance videos

Abstract

Currently, video surveillance plays a very important role in the fields of public safety and security. For storing the videos that usually contain extremely long sequences, it requires huge space. Video compression techniques can be used to release the storage load to some extent, such as H.264/AVC. However, the existing codecs are not sufficiently effective and efficient for encoding surveillance videos as they do not specifically consider the characteristic of surveillance videos, i.e. the background of surveillance video has intensive redundancy. This paper introduces a novel framework for compressing such videos. We first train a background dictionary based on a small number of observed frames. With the trained background dictionary, we then separate every frame into the background and motion (foreground), and store the compressed motion together with the reconstruction coefficient of the background corresponding to the background dictionary. The decoding is carried out on the encoded frame in an inverse procedure. The experimental results on extensive surveillance videos demonstrate that our proposed method significantly reduces the size of videos while gains much higher PSNR compared to the state of the art codecs.