基于稀疏特征的交通流视频检测算法

南京大学学报(自然科学版) ›› 2015, Vol. 51 ›› Issue (2): 264–270.

基于稀疏特征的交通流视频检测算法

张鹏，黄毅，阮雅端，陈启美*

出版日期:2015-03-02 发布日期:2015-03-02
作者简介:(南京大学电子科学与工程学院,南京,210023)
基金资助:
国家科技重大专项(2012ZX03005-004-003) , 国家自然科学基金(61105015)

Traffic flow detection algorithm based on sparse feature

Zhang PengHuang YiChen Qimei*

Online:2015-03-02 Published:2015-03-02
About author:(School of Electronic Science and Engineering,Nanjing University,Nanjing,210023,China)

摘要/Abstract

摘要： 基于背景建模的交通流参数视频检测方法易受车辆遮挡、光线变化、雨雪等外界环境条件干扰等而误判；基于机器学习方法的机理不同，改变帧间像素动态变化解析的方式，而着重于车辆样本空间的目标识别提取，具有抗干扰优势。为此，在深度学习的基础上，文中提出了基于稀疏特征的交通流检测算法。其构建高斯混合背景模型，提取交通视频的运动目标，以稀疏编码处理目标的尺度不变特征来获得稀疏特征；经最大池化的稀疏特征维度降低、线性支持向量机训练、背景建模方法误判样本去除，从而计算获得交通流参数。测试结果表明：与背景建模方法比较，该算法去除了60%~80%误判，准确率提高了12%~17%，对外界干扰大、分辨率不高的视频图像优势显著。

Abstract: The accuracy of traditional traffic flow detection based on background modeling is not high,because it is susceptible to external environmental interference.In this paper,a video-based traffic flow detection algorithm using sparse feature is propsed.Moving objects are firstly detected with Gaussian mixture background modeling method.Then the scale-invariant feature transform(SIFT) of the objects are calculated and sparse coding is used to handle the SIFT.For the purpose of reducing sparse feature dimensions,the max pooling strategy is introduced.Afterwards,the pooling-process results are used to train the linear support vector machine(SVM).Finally,we use the SVM to remove the negative samples,thus calculate better traffic flow parameters.Test results show that our algorithm has outstanding performance on low resolution images:the negative sample removal rate is 60% to 80%, accuracy improved 12% to 17% higher than background modeling method

张鹏，黄毅，阮雅端，陈启美*. 基于稀疏特征的交通流视频检测算法[J]. 南京大学学报(自然科学版), 2015, 51(2): 264–270.

Zhang PengHuang YiChen Qimei*. Traffic flow detection algorithm based on sparse feature[J]. Journal of Nanjing University(Natural Sciences), 2015, 51(2): 264–270.

参考文献

[1] 吴聪, 李勃, 董蓉, 等. 基于车型聚类的交通流参数视频检测. 自动化学报, 2011, 37(5): 69-576.
[2] 唐琎李青. 一种快速的模板匹配算法. 计算机应用, 2010, 30(06): 1559-1561.
[3] 高凯亮, 覃团发, 陈跃波, 等. 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, 47(2): 195-200.
[4] 余孔梁. 基于视频的车型识别技术研究. 浙江: 浙江大学, 2008.
[5]郭德全, 杨红雨, 刘东权, 等. 基于稀疏性的图像去噪综述. 计算机应用研究, 2012, 29(2): 406-413.
[7] 徐焕宇, 孙权森, 李大禹, 等. 基于投影的稀疏表示与非局部正则化图像复原方法. 电子学报, 2014 , 42(7): 1299-1304.
[8] Yang J, Yu K, Gong Y, et al. Linear spatial pyramid matching using sparse coding for image classification//Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on. IEEE, 2009: 1794-1801.
[9] Han B, Davis L S. Density-based multifeature background subtraction with support vector machine[J]. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2012, 34(5): 1017-1023.
[10] Zivkovic Z, van der Heijden F. Efficient adaptive density estimation per image pixel for the task of background subtraction. Pattern recognition letters, 2006, 27(7): 773-780.
[11] Lee H, Battle A, Raina R, et al. Efficient sparse coding algorithms//Advances in neural information processing systems. 2006: 801-808.
[12] Horng S J, Su M Y, Chen Y H, et al. A novel intrusion detection system based on hierarchical clustering and support vector machines. Expert systems with Applications, 2011, 38(1): 306-313.
[13] 白龙飞, 王文剑, 郭虎升. 一种新的支持向量机主动学习策略[J]. 南京大学学报: 自然科学版, 2012, 48(2): 182.
[14] 包文颖, 胡清华, 王长忠. 基于多粒度数据压缩的支持向量机. 南京大学学报 (自然科学版), 2013, 5: 014.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed