Improved Algorithms for Motion Detection of Intelligent Video Surveillance System

Abstract:

Real-time segmentation of moving regions in image sequences is a fundamental step in video monitoring systems. This paper presents an improved motion detection algorithm in a dynamic scene based on change detection. The algorithm integrates the temporal differencing method and background subtraction method to achieve better performance. Background subtraction is a typical change detection approach to segment foreground, but the continuous or abrupt variations of lighting conditions that cause unexpected changes in intensities on the background reference image. So we combine the background subtraction’s result with temporal difference’s result. The foreground mask is segmented by both the methods of background subtraction and temporal differencing. Finally, a post-processing is applied on the obtained object mask to reduce regions and smooth the moving region boundary. Experimental results demonstrate that the proposed method can update the background exactly and quickly along with the variation of illumination, and the moving objects can be extracted effectively.

• Periodical: Advanced Materials Research (Volume 505)
• Pages: 367-372
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.505.367
• Online since: April 2012
• Authors: Yan Ling Wang, Xiao Li Wang, Guang Lun Li
• Keywords: Background Subtraction, Background Updating, Object Detection, Temporal Differencing, Video Surveillance System

References

[1] Grimson Wel, Stauffer C., Romano R. and Lee L:IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Santa Barbara, CA, USA, 23-25 Jun 1998), 1998, p.22

DOI: 10.1109/cvpr.1998.698583

[2] N.Paragios, R.Deriche: IEEE Transactions on Pattern Analysis and Machine Intelligence (USA, Apr 2000), Vol.22, p.266.

[3] S.Fejes, L.S. Davis: Computer Vision and Image Understanding, Vol.74 (1999) No.2, p.101.

[4] KIM JB, KIM HJ: Pattern Recognition Letters, Vol.24 (2003) No.1-3, p.113.

[5] A. El Maadi, X. Maldague: Infrared Physics & Technology, Vol.49 (2007) No.3, p.261.

[6] Zhang Y: Pattern Recognition, Vol.29 (1996) No.8, p.1335.

[7] Y.H. Yang, M.D. Levine: Machine Vision Applications, Vol.5 (1992) No.1, p.17.

[8] P.Spagnolo, T.D' Orazio, M. Leo and A. Distante: Image and Vision Computing, Vol.24 (2006) No.5, p.411.

DOI: 10.1016/j.imavis.2006.01.001

[9] Yu Shih Ming, Chang Tseng Din: Image and Vision Computing, Vol.23 (2005) No.4, p.417.

[10] S.G. Sun, H. Park: Optical Engineering, Vol.40 (2005) No.11, p.2638.

[11] S.C. Cheung, C. Kamath: Video Communications and Image Processing, SPIE Electronic Imaging (San Jose, January 2004), p.881.

[12] A.J. Lipton, H. Fujiyoshi and R.S. Patil: IEEE Workshop on Applications of Computer Vision (USA, Oct 1998), p.8.

[13] Herrero-Jaraba, Elias, Onite-Uranuela, Carios, Fernando, Buldain and David: Pattern Recogition Letters, Vol.24 (2003) No.12, p.2079.