计算机科学 ›› 2014, Vol. 41 ›› Issue (7): 313-317.doi: 10.11896/j.issn.1002-137X.2014.07.065

• 图形图像与模式识别 • 上一篇    下一篇

基于HOG特征的交通信号灯实时识别算法研究

周宣汝,袁家政,刘宏哲,杨睿   

  1. 北京市信息服务工程重点实验室 北京联合大学 北京100101;北京市信息服务工程重点实验室 北京联合大学 北京100101;北京市信息服务工程重点实验室 北京联合大学 北京100101;北京市信息服务工程重点实验室 北京联合大学 北京100101
  • 出版日期:2018-11-14 发布日期:2018-11-14
  • 基金资助:
    本文受国家自然基金:基于超图形XGML的图像半结构化研究(61271369),国家自然基金:跨媒体社群图像语义理解(61372148),北京市教育委员会创新团队项目(IDHT20140508,CIT&TCD20130513),北京市教育委员会科技面上项目:智能车实时交通标志识别关键技术研究(SQKM201411417004)资助

Research on Algorithm for Real-time Recognition of Traffic Light Based on HOG Features

ZHOU Xuan-ru,YUAN Jia-zheng,LIU Hong-zhe and YANG Rui   

  • Online:2018-11-14 Published:2018-11-14

摘要: 针对无人驾驶汽车的交通信号灯识别,提出了一种基于HOG特征和SVM的交通信号灯实时识别算法。该算法首先提取视频中的红绿色区域,筛选出符合条件的区域,提取各类信号灯的HOG特征,然后运用SVM构建对应类别信号灯的分类器,之后依据判决函数对当前信号进行实时判决,从而得到准确的信号灯信息。实验结果表明该算法有良好的准确率和实时性。

关键词: HOG特征,SVM,交通信号灯识别 中图法分类号TP391文献标识码A

Abstract: For the recognition of traffic lights in driverless cars,this paper proposed a real-time traffic lights detection and recognition algorithm based on HOG features and SVM.This algorithm extracts red and green areas in the video preciously,and then the eligible area will be screened.Hereafter the HOG features of all kinds of lights will be extracted.Finally this work use SVM to build the classifier of corresponding category lights.We can get the accurate real-time information based on the judgment of the decision function.The experimental results show that the algorithm has good accuracy and real-time performance.

Key words: HOG features,SVM,Traffic lights recognition

[1] 武莹,张小宁,何斌.基于图像处理的交通信号灯识别方法[J].交通信息与安全,2011,9(3):51-54
[2] 赵志帅.基于彩色图像处理的铁路信号灯识别及其测距技术研究[D].武汉:武汉理工大学,2010
[3] Choi J,Ahn B T,Kweon I S.Crosswalk and traffic light detection via integral framework[C]∥201319th Korea-Japan Joint Workshop on Frontiers of Computer Vision.IEEE,2013:309-312
[4] Yu C,Huang C,Lang Y.Traffic Light Detection During Day and Night Conditions by a Camera[C]∥2010IEEE 10th International Conference on Signal Processing.2010:821-824
[5] Diaz-Cabrera M,Cerri P,Sanchez-Medina J.Suspended Traffic Lights Detection and Distance Estimation Using Color Features[C]∥201215th International IEEE Conference on Intelligent Transportation Systems.2012:1315-1320
[6] 王鹏,郑光字,宋开亮.一种新的基于图像识别技术的信号灯识别算法[J].兵工自动化,2009,8(3):73-75
[7] Yelal M R,Sasi S,Shaffer G R,et al.Color-based signal light tracking in real-time video[C]∥Proceedings of the IEEE International Conference on Video and Signal Based Surveillance.2006:67-67
[8] 谷明琴,蔡自兴,李仪.应用圆形度和颜色直方图的交通信号灯识别[J].计算机工程与设计,2012,1(33):243-247
[9] Shen Y,Ozguner U,Redmill K,et al.A robust video based traffic light detection algorithm for intelligent vehicles[C]∥Intelligent Vehicles Symposium.IEEE,2009:521-526
[10] Jie Y,Xiaomin C,Pengfei G,et al.A new traffic light detection and recognition algorithm for electronic travel aid[C]∥2013Fourth International Conference on Intelligent Control and Information Processing(ICICIP).Beijing,China,2013:644-648
[11] Park J H,Jeong C.Real-time signal light detection[C]∥2008Second International Conference on Future Generation Communication and Networking Symposia.IEEE,2008,3:139-142
[12] Lindner F,Kressel U,Kaelberer S.Robust recognition of traffic signals[C]∥2004IEEE International Vehicle Symposium.Parma,Italy,2004,6:49-53
[13] Omachi M,Omachi S.Traffic Light Dttection with Color andEdge Information[C]∥2009IEEE 10th International Confe-rence on Signal Processing(ICSP).2009:284-287
[14] Omachi M,Omachi S.Detection of traffic light using structural information[C]∥2010IEEE 10th International Conference on Signal Processing(ICSP).2010:809-812
[15] 王厅列,徐红霞,郑龙.一种基于机器视觉识别交通灯的方法[J].福建电脑,2010,6(3):12-13
[16] 徐成,谭乃强,刘彦.基于Lab色彩空间和模板匹配的实时交通灯识别算法[J].计算机应用,2010,0(5):1251-1254
[17] de Charette R,Nashashibi F.Real time visual traffic lights reco-gnition based on spot light detection and adaptive traffic lights templates[C]∥Intelligent Vehicles Symposium.IEEE,2009:358-363
[18] Chiang C C,Ho M C,Liao H S,et al.Detecting and recognizing traffic lights by genetic approximate ellipse detection and spatial texture layouts[J].International Journal of Innovative Computing,Information and Control,2011,7(12):6919-6934
[19] 谷明琴,蔡自兴,黄振威,等.城市环境中箭头型交通信号灯的实时识别算法[J].中南大学学报:自然科学版,2013,4(4):1403-1408
[20] Fairfield N,Urmson C.Traffic light mapping and detection[C]∥2011IEEE International Conference on Robotics and Automation(ICRA).Shanghai,China,IEEE,2011:5421-5426
[21] Levinson J,Askeland J,Dolson J,et al.Traffic light mapping,localization,and state detection for autonomous vehicles[C]∥2011IEEE International Conference on Robotics and Automation(ICRA).Shanghai,China,IEEE,2011:5784-5791
[22] 彭祖胜,房斌,吴琪.交通标志和信号灯实时检测与识别技术研究[D].重庆:重庆大学,2012

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!