基于改进混合高斯模型的交通流背景检测算法

上海交通大学学报（自然版） ›› 2012, Vol. 46 ›› Issue (12): 1920-1925.

• 自动化技术、计算机技术 • 上一篇下一篇

基于改进混合高斯模型的交通流背景检测算法

吕复强1，王慧1，刘泓2

（1. 浙江大学工业控制技术国家重点实验室，杭州 310027；2. 浙江大学城市学院信息与电气工程学院，杭州 310015）

收稿日期:2012-05-17 出版日期:2012-12-29 发布日期:2012-12-29
基金资助:
国家自然科学基金资助项目（50908204），浙江省教育厅重点科研项目（Z201018730）

Traffic Flow Background Detection Algorithm Based on Improved Gaussian Mixture Model

LV　Fu-Qiang-1 , WANG Hui-1, LIU Hong-2

(1. State Key Laboratory of Industrial Control Technology, Zhejiang University, Hangzhou 310027;　2. Department of Information and Electronics, Zhejiang University City College, Hangzhou 310015, China)

Received:2012-05-17 Online:2012-12-29 Published:2012-12-29

摘要/Abstract

摘要： 针对交通流视频中道路背景像素较为统一的特点，提出一种基于时空信息的双混合高斯模型背景检测算法.该算法先构造像素时间域混合高斯模型进行时间域的检测，并采用双重阈值分别判断前景与背景.当某像素无法准确判断时，针对该像素邻域构造空间域混合高斯模型，以空间域的检测结果代替时间域的检测.通过不同的交通流视频中的测试和比较，验证了所提出的算法能有效地融合像素自身的时间信息与像素间的空间信息，提高了检测初始阶段的鲁棒性，同时有效地解决了出现停车现象时的误检测问题.

关键词: 交通流, 视频检测, 时空信息, 混合高斯模型, 决策融合

Abstract: Aiming at the uniform characteristics of background pixels in traffic flow video, a spatial-temporal dual Gaussian mixture model background detection algorithm was proposed. Firstly the temporal Gauss mixture model was built to detect the background in temporal domain, and a double-threshold method was introduced to detect the background and foreground. When the detection result was uncertain, the spatial Gauss mixture model was built, and the spatial detection result was used to replace the temporal detection result. The experimental comparisons with different traffic flow video demonstrate that the proposed algorithm in this paper improves robustness in the initial stage and decreases the detection fault also when parking phenomenon occurrs.

Key words: traffic flow, video detection, spatialtemporal information, Gaussian mixture model, decision fusion

中图分类号:

吕复强1, 王慧1, 刘泓2. 基于改进混合高斯模型的交通流背景检测算法[J]. 上海交通大学学报（自然版）, 2012, 46(12): 1920-1925.

LV　Fu-Qiang-1 , WANG Hui-1, LIU Hong-2. Traffic Flow Background Detection Algorithm Based on Improved Gaussian Mixture Model[J]. Journal of Shanghai Jiaotong University, 2012, 46(12): 1920-1925.

参考文献

［1］Wren C R, Azarbayejani A, Darrell T, et al. Pfinder: Realtime tracking of the human body［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1997, 19(7): 780785.
［2］Friedman N, Russell S. Image segmentation in video sequences: A probabilistic approach［C］∥Proceedings of the 13th Conference on Uncertainty in Artificial Intelligence. USA:Morgan Kaufmann Publishers, 1997: 175181.
［3］Stauffer C, Grimson W E L. Adaptive background mixture models for realtime tracking［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8): 747757.
［4］李娟，邵春福，杨励雅. 基于混合高斯模型的行人检测方法［J］. 吉林大学学报（工学版）, 2011, 41(1): 4145.
LI Juan, SHAO Chunfu, YANG Liya. Pedestrian detection based on improved Gaussian mixture model［J］. Journal of Jilin University(Engineering and Technology Edition), 2011, 41(1):4145.
［5］Zivkovic Z, van der Heijden F. Efficient adaptive density estimation per image pixel for the task of background subtraction［J］. Pattern Recognition Letters, 2006, 27(7): 773780.
［6］Piccardi M. Background subtraction technoques: A review［C］∥IEEE International Conference on Systems, Man and Cybernetics. Piscataway NJ: IEEE Publishers, 2004: 30993104.
［7］Zivkovic Z. Improved adaptive Gaussian mixture model for background subtraction［C］∥International Conference on Pattern Recognition. Washington, DC: IEEE Computer Society，2004:2831.
［8］KaewTraKulPond P, Bowden R. An improved adaptive background mixture model for realtime tracking with shadow detection［C］∥Proceedings of the 2th European Workshop on Advanced VideoBased Surveillance Systems. Boston: Kluwer Academic Publishers, 2001:135144.
［9］Elgammal A, Duraiswami R, Harwood D, et al. Background and foreground modeling using nonparametric kernel density estimation for visual surveillance［J］. Proceedings of the IEEE, 2002, 90(7): 11511163.
［10］Magee R D. Tracking multiple vehicles using foreground, background and motion models［J］. Image and Vision Computing, 2004, 22(2): 143155.
［11］Heikkila M, Pietikainen M. A texturebased method for modeling the background and detecting moving objects［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(4): 657662.
［12］Mason M, Duric Z. Using histograms to detect and track objects in color video［C］∥Proceedings of the 30th Conference on Applied Imagery Pattern Recognition Workshop. Washington, DC: IEEE Computer Society, 2001: 154159.
［13］王永忠, 梁彦，潘泉,等. 基于自适应混合高斯模型的时空背景建模［J］. 自动化学报, 2009(4): 371378.
WANG Yongzhong, LIANG Yan, PAN Quan, et al. Spatiotemporal background modeling based on adaptive mixture of gaussians［J］. Acta Automatica Sinica, 2009(4): 371378.
［14］陈明生，梁光明，孙即祥，等. 一种用于视频目标检测的时空背景建模方法［J］. 信号处理, 2010, 26(11): 16011606.
CHEN Mingsheng, LIANG Guangming, SUN Jixiang, et al. A temporalspatial background model for video objects detection［J］. Signal Processing， 2010, 26(11): 16011606.

[1]	薛晗，邵哲平，潘家财，张锋. 基于文化萤火虫算法-广义回归神经网络的船舶交通流量预测[J]. 上海交通大学学报, 2020, 54(4): 421-429.
[2]	蒋士正，许榕，陈启美. 基于变量选择-神经网络模型的复杂路网短时交通流预测[J]. 上海交通大学学报（自然版）, 2015, 49(02): 281-286.
[3]	甘浪雄1,2,3，张磊2,3，邹早建1，文元桥2,3，张恒2,3. 基于场方法的船舶交通流分析[J]. 上海交通大学学报（自然版）, 2014, 48(04): 551-557.

基于改进混合高斯模型的交通流背景检测算法

Traffic Flow Background Detection Algorithm Based on Improved Gaussian Mixture Model

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价