Tongxin xuebao (Jan 2023)
Background reference frame generation method for surveillance video based on image block codebook model
Abstract
To solve the problems that the background reference frames are seriously contaminated by the foreground, and the bit rate increases suddenly incurred by the one-time transmission of the background frames, a progressive background frame generation method with image block as the basic unit was proposed for surveillance video application.An image block codebook model based on clustering was formulated.The image blocks at the same position in the video sequence were effectively clustered by using perceptual hash-based element matching.The background symbol was accurately detected by using the characteristics of the background image area.A complete background frame was produced by extracting the background blocks in different frames based on the codebook model.Experimental results demonstrate that the proposed method achieves 17.89% coding efficiency for luma component compared with standard HM16.20, and can effectively improve the quality of the produced background reference frame.Besides, the proposed method complexity meets the real-time requirements of video applications.
