Moving target detection algorithm based on improved Gaussian mixture model

WANG Dongfang; WANG Yude; WANG Jingwu

doi:10.7510/jgjs.issn.1001-3806.2014.06.011

In order to eliminate the defects of false detection of mixed Gaussian model under sudden illumination, a new algorithm combining Gaussian model with average background method was proposed to count the foreground pixels. Firstly, the background of Gaussian mixture model was initialized by using multi-frame averaging method when building the background model. Secondly, a counter for the number of foreground pixels of every frame was established and the false detection was eliminated based on the counter. Finally, the target was detected by using mathematical morphology and the foreground of the image was gotten. The results show that this improved algorithm not only overcomes the interference of the initial background but also eliminates the false detection when the illumination changes, and improves the detection rate of the moving targets.

Moving target detection algorithm based on improved Gaussian mixture model

Corresponding author: WANG Yude, wyude-01@163.com;

1. College of Physics and Engineering, Qufu Normal University, Qufu 273165, China

Received Date: 2013-10-30

Accepted Date: 2013-12-09

Available Online: 2014-11-25

Abstract: In order to eliminate the defects of false detection of mixed Gaussian model under sudden illumination, a new algorithm combining Gaussian model with average background method was proposed to count the foreground pixels. Firstly, the background of Gaussian mixture model was initialized by using multi-frame averaging method when building the background model. Secondly, a counter for the number of foreground pixels of every frame was established and the false detection was eliminated based on the counter. Finally, the target was detected by using mathematical morphology and the foreground of the image was gotten. The results show that this improved algorithm not only overcomes the interference of the initial background but also eliminates the false detection when the illumination changes, and improves the detection rate of the moving targets.

HTML

Reference (16)

[1]	BAI Y Ch, ZHANG X G, TANG L. Transverse velocity estimation based on Wigner-Hough transform[J].Journal of Nanjing University(Natural Science Edition), 2010, 46(4): 366-369(in Chi-nese).
[2]	HARITAOGLU I, HARWOOD D, DAVIS L S.Real-time surveil- lance of people and their activities[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8): 809-830.
[3]	WEI X F, LIU X. Research of image segmentation based on 2-D maximum entropy optimal threshold[J].Laser Technology, 2013, 37(4): 519-522(in Chinese).
[4]	HAO H G, CHEN J Q. Moving object detection algorithm based on five frame difference and background difference[J]. Computer Engineering, 2012, 38(4): 146-148(in Chinese).
[5]	TSAI D M, LAI S C. Independent component analysis based background subtraction for indoor surveillance[J].IEEE Transactions on Image Processing, 2009, 18(1): 158-160.
[6]	GUPT S, MASOUND O, MARTIN R F K, et al. Detection and classification for vehicles[J].IEEE Transactions on Intelligent Transportation Systems, 2002, 1(3): 37-47.
[7]	ZHOU L, ZHU H. Optical flow calculation based on dual subtraction for motion detection[J].Computer Simulation, 2009, 26(12): 168-171(in Chinese).
[8]	HE G M, LI L J, JIA Zh T. A rapid video segmentation algorithm based on symmetrical DFD[J].Mini-micro Systems, 2003, 24(6): 966-968(in Chinese).
[9]	BENNETT B, MAGEE D R, COHN A G, et al. Enhanced tracking and recognition of moving objects by reasoning about spatio-temporal continuity[J].Image and Vision Computing, 2008, 26(1): 67-81.
[10]	GAN Sh X. Moving targets detection using codebook[J].Journal of Image and Graphics, 2008, 13(2): 365-370(in Chinese).
[11]	MEI N N, WANG Zh J. Moving object detection algorithm based on Gaussian mixture model[J]. Computer Engineering and Design, 2012, 33(8): 3149-3153(in Chinese).
[12]	LI Y N, YU X C, TANG F, et al. Application of improved optic flow field in the supervisory control of nuclear explosion[J]. Laser Technology, 2013, 37(1): 118-120(in Chinese).
[13]	ZHOU J Y, WU X P, ZHANG Ch, et al. A moving object detection method based on sliding window gaussian mixture model[J].Journal of Electronics and Information Technology, 2013, 35(7): 1650-1656(in Chinese).
[14]	XU K, CHEN Sh X, YAN G. Moving object detection based on improved Gaussian model [J].Laser and Infrared, 2012, 42(7): 821-824(in Chinese).
[15]	NADIMI S, BEHAN B. Physical models for moving shadow and object detection in video[J].IEEE Transactions on Pattern Ana-lysis and Machine Intelligence, 2004, 26(8): 1079-1087.
[16]	TU L F, PENG Q, ZHONG S D. A moving object detection method adapted to camera jittering[J].Journal of Electronics Information Technology,2013,35(8):1914-1920(in Chinese).

Moving target detection algorithm based on improved Gaussian mixture model

Abstract

References

Proportional views

通讯作者: 陈斌, bchen63@163.com

Proportional views