Surveillance Video Denoising Based on Background Modeling

Yunhai Liu; Baolei Xi; Heyi Guo; Xiaochen Quan; Shengtian Yang

ChinaCom2008-Signal Processing for Communications Symposium

Research Article

Surveillance Video Denoising Based on Background Modeling

Cite: BibTeX Plain Text

@INPROCEEDINGS{10.1109/CHINACOM.2008.4685224,
    author={Yunhai Liu and Baolei Xi and Heyi Guo and Xiaochen Quan and Shengtian Yang},
    title={Surveillance Video Denoising Based on Background Modeling},
    proceedings={ChinaCom2008-Signal Processing for Communications Symposium},
    publisher={IEEE},
    proceedings_a={CHINACOM2008-SPC},
    year={2008},
    month={11},
    keywords={Surveillance video denoising; segmentation; background models; 3D median filter},
    doi={10.1109/CHINACOM.2008.4685224}
}

Yunhai Liu
Baolei Xi
Heyi Guo
Xiaochen Quan
Shengtian Yang
Year: 2008
Surveillance Video Denoising Based on Background Modeling
CHINACOM2008-SPC
IEEE
DOI: 10.1109/CHINACOM.2008.4685224

Yunhai Liu¹, Baolei Xi², Heyi Guo², Xiaochen Quan², Shengtian Yang¹

1: Institute of Information and Communication Engineering, Zhejiang University, Hangzhou 310027, China; Zhejiang Provincial Key Laboratory of Information Network Technology, Hangzhou 310027, China
2: Institute of Information and Communication Engineering, Zhejiang University, Hangzhou 310027, China

Abstract

Because of the characteristics of photoelectric sensors and the working environment of cameras, real-time surveillance video contains much noise, which does not only decrease the subjective visual quality, but also increases the output bitrate of video encoder. The effect of partial spatio-temporal smoothing is not evident. According to the characteristics of surveillance video, we propose a novel algorithm based on video content, setting up adaptive background models to accomplish foreground segmentation, reducing background noise via model parameters and foreground noise via 3D median filter. To the sequences of “hall_monitor” polluted with Gaussian or Poisson noise, the results show that the new algorithm increases PSNR about 8dB, and saves over 90% of encoder output bitrate.

Keywords: Surveillance video denoising; segmentation; background models; 3D median filter

Published: 2008-11-21
Publisher: IEEE
Modified: 2010-05-16

: http://dx.doi.org/10.1109/CHINACOM.2008.4685224