详情

原文传递 A deep learning approach for quality enhancement of surveillance video

题名：	A deep learning approach for quality enhancement of surveillance video
正文语种：	英文
作者：	Dandan Ding;Junchao Tong;Lingyi Kong
作者单位：	Hangzhou Normal University
关键词：	Convolutional Neural Network; image coding;intelligent vehicles; multimedia; traffic surveillance
摘要：	The growing number of surveillanee cameras imposes great demand on high efficiency video coding. Although modern video coding standards have significantly improved the video coding efficiency, they are designed for generaI video rather than surveilla nee video. The special characteristics of surveillance video leave a large space for further performance improvement. In this paper, we leverage a deep learning approach to enhance the quality of compressed surveillanee video. More specifically, we formulate the problem of frame enhancement as a regression problem and design a Residual Squeeze-and-Excitation Network (RSE-Net), to address it. RSE-Net extensively exploits the non-linear mapping between the reconstructed frame and the ground truth, with only a small number of parameters. Moreover, By improving You Only Look Onee (YOLO) network, we successfully detect the grouped vehicles within a frame. A novel model training scheme is then developed through learning from the grouped vehicles. With the proposed scheme, we train a global model for both foreground and background of surveillanee video. Experimental results show that our method achieves average 0.40 dB, 0.22 dB and 0.24dB PSNR gains over H.265/HEVC an chor in Al, LDP and RA con figurations, and produces visually pleasing results when applied to compressed surveillance video.
出版日期：	2020
出版年：	2020
期刊名称：	Journal of Intelligent Transportation Systems Technology Planning and Operations
卷：	Vol24
期：	No01-06
页码：	304-314