A deep learning approach for quality enhancement of surveillance video

被引:17
作者
Ding, Dandan [1 ]
Tong, Junchao [1 ]
Kong, Lingyi [1 ]
机构
[1] Hangzhou Normal Univ, Sch Informat Sci & Engn, Hangzhou, Zhejiang, Peoples R China
基金
国家重点研发计划;
关键词
Convolutional Neural Network; image coding; intelligent vehicles; multimedia; traffic surveillance;
D O I
10.1080/15472450.2019.1670659
中图分类号
U [交通运输];
学科分类号
08 ; 0823 ;
摘要
The growing number of surveillance 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 general video rather than surveillance 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 surveillance 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 Once (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 surveillance video. Experimental results show that our method achieves average 0.40?dB, 0.22?dB and 0.24?dB PSNR gains over H.265/HEVC anchor in AI, LDP and RA configurations, and produces visually pleasing results when applied to compressed surveillance video.
引用
收藏
页码:304 / 314
页数:11
相关论文
共 26 条
  • [1] [Anonymous], 2017, P IEEE VTC JUN
  • [2] MET18 Deficiency Increases the Sensitivity of Yeast to Oxidative Stress and Shortens Replicative Lifespan by Inhibiting Catalase Activity
    Chen, Ya-qin
    Liu, Xin-guang
    Zhao, Wei
    Cui, Hongjing
    Ruan, Jie
    Yuan, Yuan
    Tu, Zhiguang
    [J]. BIOMED RESEARCH INTERNATIONAL, 2017, 2017 : 1 - 9
  • [3] A Convolutional Neural Network Approach for Post-Processing in HEVC Intra Coding
    Dai, Yuanying
    Liu, Dong
    Wu, Feng
    [J]. MULTIMEDIA MODELING (MMM 2017), PT I, 2017, 10132 : 28 - 39
  • [4] Compression Artifacts Reduction by a Deep Convolutional Network
    Dong, Chao
    Deng, Yubin
    Loy, Chen Change
    Tang, Xiaoou
    [J]. 2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV), 2015, : 576 - 584
  • [5] Image Super-Resolution Using Deep Convolutional Networks
    Dong, Chao
    Loy, Chen Change
    He, Kaiming
    Tang, Xiaoou
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2016, 38 (02) : 295 - 307
  • [6] Skip Decision and Reference Frame Selection for Low-Complexity H.264/AVC Surveillance Video Coding
    Gorur, Pushkar
    Amrutur, Bharadwaj
    [J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2014, 24 (07) : 1156 - 1169
  • [7] Identity Mappings in Deep Residual Networks
    He, Kaiming
    Zhang, Xiangyu
    Ren, Shaoqing
    Sun, Jian
    [J]. COMPUTER VISION - ECCV 2016, PT IV, 2016, 9908 : 630 - 645
  • [8] He XY, 2018, IEEE IMAGE PROC, P216, DOI 10.1109/ICIP.2018.8451086
  • [9] Hu J, 2018, PROC CVPR IEEE, P7132, DOI [10.1109/TPAMI.2019.2913372, 10.1109/CVPR.2018.00745]
  • [10] *ITU T, 2003, H2642003 ITUT AUD MU