基于HOG特征和SVM的前向车辆识别方法

计算机科学 ›› 2013, Vol. 40 ›› Issue (Z11): 329-332.

基于HOG特征和SVM的前向车辆识别方法

李星,郭晓松,郭君斌

第二炮兵工程大学兵器发射理论与技术国家重点实验室西安710025;第二炮兵工程大学兵器发射理论与技术国家重点实验室西安710025;第二炮兵工程大学兵器发射理论与技术国家重点实验室西安710025

出版日期:2018-11-16 发布日期:2018-11-16

HOG-Feature and SVM Based Method for Forward Vehicle Recognition

LI Xing,GUO Xiao-song and GUO Jun-bin

Online:2018-11-16 Published:2018-11-16

摘要/Abstract

摘要： 为了解决汽车安全驾驶辅助系统中的前向车辆实时识别问题,提出了一种基于梯度方向直方图特征和支持向量机的前向车辆识别方法。通过分割提取车辆底部阴影特征生成假设区域,采用基于直方图分析的方法实现车辆底部阴影的准确分割,综合分析车底阴影的水平边缘特征和垂直边缘特征完成假设区域的生成；使用基于梯度方向直方图特征和支持向量机得到的车辆分类器对获得的车辆假设区域进行验证,剔除了假设区域中的非车辆区域。利用采集的道路视频对提出的方法进行了车辆识别实验,结果表明,该方法能够在不同光照条件下自适应地进行实时车辆识别,其中在正常光照下的识别率为96.52%,误识别率为3.59%。

关键词: 梯度方向直方图,支持向量机,车辆分类器,前向车辆检测,汽车安全辅助驾驶系统

Abstract: A HOG-feature and SVM based method was proposed for real-time forward vehicle recognition in automotive safety driver assistant systems．The shadow underneath vehicle was segmented accurately by using histogram analysis method and the initial candidates were generated by combining horizontal and vertical edge feature of shadow．These initial candidates were further verified by using a vehicle classifier based on the histogram of gradient and support vector machine．The experimental results show that the proposed method could adapt to different light conditions robustly．Specially,the proposed method has a recognition rate of 96.52percent and a false rate of 3.59percent in normal light condition.

Key words: Histogram of gradient,Support vector machine,Vehicle classifier,Forward vehicle recognition,Automotive safety driver assistant system

李星,郭晓松,郭君斌. 基于HOG特征和SVM的前向车辆识别方法[J]. 计算机科学, 2013, 40(Z11): 329-332. https://doi.org/

LI Xing,GUO Xiao-song and GUO Jun-bin. HOG-Feature and SVM Based Method for Forward Vehicle Recognition[J]. Computer Science, 2013, 40(Z11): 329-332. https://doi.org/

参考文献

[1] 公安部交通管理局． 2010年中华人民共和国道路交通事故统计年报[M]．北京,2011
[2] Sun Ze-hang,Bebis G,Miller R．On-road Vehicle Detection:A Review[J]．IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(5):694-711
[3] Bertozzi M,Broggi A,Fascioli A．Vision-Based intelligent Vehicles:State of the Art and Perspectives[J]．Robotics and Autonomous Systems,2000,32:1-16
[4] Guo D,Fraichard T,Xie M,et al．Color Modeling by Spherical Influence Field in Sensing Driving Environment[C]∥Procee-dings IEEE Intelligent Vehicle Symposium．2000:249-254
[5] Han S,Han Y,Hahn H．Vehicle Detection Method using Haar-like Feature on Real Time System[J]．Engineering and Techno-logy,2009,59:455-459
[6] Bertozzi M,Broggi A,Castelluccio S．A Real-Time Oriented System for Vehicle Detection[M]．Systems Architecture,1997:317-325
[7] Kalinke T,Tzomakas C,von Seelen W．A Texture-Based Object Detection and an Adaptive Model-Based Classification [C]∥Proceedings IEEE International Conference Intelligent Vehicles．1998:143-148
[8] Handmann U,Kalinke T,Tzomakas C,et al．An Image Processing System for Driver Assistance[J]．Image and Vision Computing,2000,18(5):367-376
[9] Wu Jun-wen,Zhang Xue-gong．A PCA Classifier and Its Application in Vehicle Detection[C]∥Proceedings IEEE International Joint Conference on Neural Networks．2001:600-604
[10] Sun Ze-hang,Bebis G,Miller R．On-Road Vehicle Detection Using Gabor Filters and Support Vector Machines[C]∥Procee-dings IEEE International Conference on Digital Signal Proces-sing．2002:1019-1022
[11] Sun Ze-hang,Bebis G,Miller R．Quantized Wavelet Features and Support Vector Machines for On-Road Vehicle Detection[C]∥Proceedings IEEE International Conference on Control．Automation,Robotics,and Vision,2002
[12] Song G Y,Lee K Y,Woong Lee J．Vehicle Detection by Edge-Based Candidate Generation and Appearance-based Classification[C]∥Proceedings IEEE Intelligent Vehicles Symposium．Eindhoven,Netherlands,2008:428-433
[13] Dalai N,Triggs B．Histograms of Oriented Gradients for Human Detection[C]∥Proceeding of IEEE International Conference on Computer Vision & Pattern Recognition．2005,1:886-893
[14] Zhu Qiang,Yeh Mei-chen,Cheng K-T．Fast Human Detection Using a Cascade of Histograms of Oriented Gradients[C]∥Proceedings IEEE International Conference on Computer Vision & Pattern Recognition．2006,2:1491-1498
[15] Suard F,Akotomamonjy A R,Bensrhair A,et al．Pedestrian Detection Using Infrared Images and Histograms of Oriented Gradients[C]∥Proceedings Intelligent Vehicle Symposium．2006:206-212
[16] Sidla O,Paletta L,Lypetskyy Y,et al．Vehicle Recognition for Highway Lane Survey[C]∥The 7^th International IEEE Confe-rence on Intelligent Transportation Systems．Washington,D.C.,USA,2004:531-536
[17] Henry S,Takeo K．A Statistical Approach to 3D Object Detection Applied to Faces and Cars[C]∥Proceedings IEEE Conference on Computer Vision and Pattern Recognition．Hilton Head,SC,USA,2000,1:746:751
[18] Chang Wen-chung,Cho C-W．Online Boosting for vehicle detection[J]．IEEE Transactions on Systems,Man,and Cybernetics,2010,40(3):892-902

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed