一种混合高斯背景模型下的像素分类运动目标检测方法*

南京大学学报(自然科学版) ›› 2011, Vol. 47 ›› Issue (2): 195–200.

一种混合高斯背景模型下的像素分类运动目标检测方法*

高凯亮, 覃团发** , 陈跃波, 常侃

出版日期:2015-04-09 发布日期:2015-04-09
作者简介: ( 广西大学计算机与电子信息学院, 南宁, 530004)
基金资助:
广西自然科学基金( 桂科自 0991058) , 广西高校人才小高地建设创新团队资助计划项目(桂教人[ 2007] 71 号)

Detection of moving objects using pixel classification based on Gaussian mixture model

Gao K ai Liang, Qin T uan Fa, Chen Yue?Bo, Chang Kan

Online:2015-04-09 Published:2015-04-09
About author: (School of Computer and Electronic Information, Guangxi University, Nanning, 530004, China

摘要/Abstract

摘要： 运动目标检测在智能视频监控、人机交互、目标导航等诸多领域有着广泛应用. 背景减法是运动目标检测中应用较广泛的一种方法. 在该方法中, 背景建模和阈值化分割是最重要的步骤, 直接决定
了检测效果的好坏. 当目标本身变化比较大时, 若利用传统的基于全局阈值的分割法, 分割效果并不理想. 针对基于全局阈值分割差分图像存在的问题, 本文提出了一种基于混合高斯背景模型的像素分类运
动目标检测方法. 该方法首先利用混合高斯模型对背景建模, 克服了场景变化等因素带来的影响; 其次, 利用背景减法得到差分图像并对像素进行分类, 最后对分类后的像素集分别进行阈值化分割, 得到前景
目标. 实验结果表明, 与传统的基于全局阈值的分割法相比, 本文算法能够获得更好的检测效果和鲁棒性.

Abstract: Detection of moving objects (DM B) is widely used in many areas, such as intelligent video surveillance, human-machine interaction and target navigation. The background subtraction algorithm is widely used for DMB. In
the traditional algorithm, background image is generated from the reference frame and is abstracted from the current frame to form differential image. Afterwards, the moving regions are separated from the differential image by
predefined threshold. The procedure of generating background image is called background modeling and the procedure of separating moving objects is called moving regions segmentation. These two procedures are so crucial
that they are related to the detection performance directly. However, when detecting the objects with large variation, most of the time, this traditional algorithm based on global threshold suffers from performance
degradation. The reason is that the correctness of both background modeling and global threshold are no longer assured.In order to solve this problem, an object detecting algorithm using pixel classification based on Gaussian
mixture model is proposed. T he Gaussian mixture model, whose parameters and weighting factors are updated online, can overcome the influence of scenes change, such as branches swaying and illumination changing. In the
proposed algorithm, the usage of Gaussian mixture model to complete background modeling is the first step. Secondly, the pixels of the differential image, which is obtained by subtracting the extracted background from the
current frame, are separated into two parts by the predefined threshold, whose value is set by experiment. Because separating into two parts appears to have satisfied experimental result, considering the balance of both complexity
and performance, the number of separated parts is set as two. Owing to different characteristic of these two parts, their front images are generated separately. The method to produce the front image is to compare the pixel value
with different thresholds in different parts. The algorithm is implemented in Matlab 7 - 0, and two standard test sequences from the CVRR ( Computer
Vision and Rototics Research) database in UCSD ( U niversity of California San Diego) are used to verify the effeteness of the proposed algorithm. Comparison is made between the traditional algorithm based on global
threshold and the proposed one based on pixel classification. Experimental results show that the proposed algorithm can achieve much better detection rate and lower false alarm rate than the traditional one. In terms of the comparison of subjective result, the proposed algorithm obtains the outline of the moving objects clearly, which proved that the robustness of the proposed one can be guaranteed.

高凯亮, 覃团发** , 陈跃波, 常侃 . 一种混合高斯背景模型下的像素分类运动目标检测方法*

[J]. 南京大学学报(自然科学版), 2011, 47(2): 195–200.

Gao K ai Liang, Qin T uan Fa, Chen Yue?Bo, Chang Kan. Detection of moving objects using pixel classification based on Gaussian mixture model
[J]. Journal of Nanjing University(Natural Sciences), 2011, 47(2): 195–200.

参考文献

[ 1 ] Bai Y C, Zhang X G, Tang L. Transverse ve locity estimation based on Wigner-Hough transform. Journal of Nanjing University ( Natural Sciences), 2010, 46( 4) : 366~ 369. ( 柏业超, 张
兴敢, 唐岚. 基于 Wigner ?Hough 变换的横向速度估计. 南京大学学报(自然科学) , 2010, 46 ( 4) : 366~ 369) .
[ 2 ] Chen Z Z, Li B, Chen Q M, et al. Free way inte grated management system based on distribution monitor data unit series. Journal of Nanjing
University ( Natural Sciences) , 2010, 46( 4) : 394~ 397. (陈钊正, 李勃等. 基于分布式监控数字单元系列的高速公路综合管理系统. 南京大学学报(自然科学) , 2010, 46( 4) : 394~ 397) .
[ 3 ] Tao J G, Yu C H. Real?time detection and tracking of moving object. Intelligent Informa tion. T echnology Application, 2008, 2: 860~ 863.
[ 4 ] Tsai D M, Lai S C. Independent component analysis-based background subtraction for indoor surveillance. IEEE Transactions on Image Processing, 2009, 18( 1) : 158~ 160.
[ 5 ] Gupt S, Masound O, Martin R F K, et al. De tection and classification for vehicles. IEEE Transactions on Intelligent Transportation Systems, 2002, 1( 3) : 37~ 47.
[ 6 ] Massimo P. Background subtraction techniques: a review. IEEE International Conference on Systems, Man and Cybernetics, 2004: 3099~ 3104.
[ 7 ] Chen Y, Yu S S, Sun W W, et al. Objects de tection based on adaptive background models and multiple cues. International Colloquium on Computing, Communication, Control and M anagement, 2008, 285~ 289.
[ 8 ] Wren C R, Azarbayejani A, Darrell A, et al. Pfinder: Real?time tracking of the human body. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(7): 780~ 785.
[ 9 ] Stauffer C, Grimson W E L. Adaptive background mixture models for real?time tracking. IEEE Computer Vision and Pattern Recognition, 1999: 246~ 250.
[ 10] Huang X J, Zhou J M, Liu B Y. Moving objects detection approach based on adaptive mixture Gaussian background model. Journal of Computer Applications, 2010, 30( 1) : 71~ 74.
( 黄鑫娟, 周洁敏, 刘伯扬. 自适应混合高斯背景模型的运动目标检测方法. 计算机应用, 2010, 30(1): 71~ 74).
[ 11] Li G, Zeng R L, Lin L. Moving target detection in video monitoring system. Proceedings of the 6 th World Congress on Intelligent Control and Automation, , 2006, 21~ 23.
[ 12] Xia Y Q, Ning S H, Shen H. Moving targets detection algorithm based on background subtraction and frames subtraction. IEEE International Conference on Industrial Mechatronics and Automation, 2010: 122~ 125.
[ 13] Monnet A, M ittal N, Paragios V R. Background modeling and subtraction of dynamic scenes. Proceedings of the International Conference on Computer Vision, 2003, 1305~ 1312.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed