基于快速区域卷积神经网络的交通标志识别算法研究
详细信息 查看官网全文
- 英文论文题名：Traffic Sign Recognition Based on Fast Region-based Convolutional Neural Networks
- 论文作者：钟晓明 ; 余贵珍 ; 马亚龙 ; 任毅龙
- 英文论文作者：Zhong Xiaoming ; Yu Guizhen ; Ma Yalong ; Ren Yilong ; School of Transportation Science and Engineering ; Beihang University
- 年：2016
- 作者机构：北京航空航天大学交通科学与工程学院;
- 论文关键词：交通标志识别 ; 快速区域卷积神经网络 ; 候选区域网络
- 英文论文关键词：traffic sign recognition ; fast R-CNN ; region proposal network
- 会议召开时间：2016-10-26
- 会议录名称：2016中国汽车工程学会年会论文集
- 英文会议录名称：Proceedings of 2016 SAE-China Congress
- 语种：中文
- 分类号：TP391.41;TP183
- 学会代码：QCGC
- 会议名称：2016中国汽车工程学会年会暨展览会
- 会议地点：中国上海
- 主办单位：中国汽车工程学会
- 学会名称：中国汽车工程学会
- 页数：4
- 文件大小：685k
- 原文格式：O
- 会议级别：全国
摘要
复杂城市道路环境下的交通标志识别作为智能车辆以及高级驾驶辅助系统的重要感知技术正逐步受到研究者的关注。本文提出一种基于快速区域卷积神经网络的交通标志识别方法,包括交通标志候选区域提取与分类。通过对输入图片进行卷积及池化操作,提取交通标志特征,然后利用候选区域网络产生候选区域,最后利用快速区域卷积神经网络来完成交通标志的识别。实验结果表明该方法能够自动地提取交通标志的特征,有效地提高了复杂背景下的交通标志识别的准确率,具有良好的泛化能力和适应范围。
As an important perception technology of intelligent vehicles and advanced driving assistant system,traffic sign recognition in the complex urban environment has obtained more and more attention of researchers.In this paper,we propose a traffic sign recognition method based on the fast region- based convolutional neural networks(Fast R- CNN) including extraction and classification of traffic signs candidate regions.The feature of traffic signs are extracted by convolution and pooling operating,then region proposals are generated through region proposal networks.Finally,traffic signs can be recognized with Fast R- CNN.The experiment results demonstrate that the proposed method can extract feature of traffic signs automatically and improve the recognition accuracy.In addition,the proposed method has strong generalization ability and wide adapting range.
As an important perception technology of intelligent vehicles and advanced driving assistant system,traffic sign recognition in the complex urban environment has obtained more and more attention of researchers.In this paper,we propose a traffic sign recognition method based on the fast region- based convolutional neural networks(Fast R- CNN) including extraction and classification of traffic signs candidate regions.The feature of traffic signs are extracted by convolution and pooling operating,then region proposals are generated through region proposal networks.Finally,traffic signs can be recognized with Fast R- CNN.The experiment results demonstrate that the proposed method can extract feature of traffic signs automatically and improve the recognition accuracy.In addition,the proposed method has strong generalization ability and wide adapting range.
引文
[1]Viola P,Jones M.Robust real-time object detection[J].International Journal of Computer Vision,2001,4:34-47.
[2]Wang G,Ren G,Wu Z,et al.A robust,coarse-tofine traffic sign detection method[C]//Neural Networks(UCNN),The 2013 International Joint Conference on.IEEE,2013,Dallas,TX,USA.
[3]Prieto M S,Allen A R.Using self-organising maps in the detection and recognition of road signs[J].Image and Vision Computing,2009,27(6):673-683.
[4]Kuo W J,Lin C C.Two-stage road sign detection and recognition[C]//2007 IEEE International Conference on Multimedia and Expo.IEEE,2007;1427-1430.
[5]王雁,穆春阳,马行.基于Zemike不变矩与SVM的交通标志的识别[J].公路交通科技,2015,12:128-132.
[6]SERMANET P,LECUN Y.Traffic sign recognition with multi-scale convolutional networks[C]//Neural Networks(UCNN),The 2011 International Joint Conference on.IEEE,2011:2809-2813.
[7]CIRESAN D,MEIER U,MASCI J,et al.A committee of neural networks for traffic sign classification[C]//Neural Networks(UCNN),The 2011 International Joint Conference on.IEEE,2011:1918—1921.
[8]Ren S,He K,Girshick R,et al.Faster R-CNN;Towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems.2015,Montreal,Canada.
[9]Girshick R.Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision.2015,Santiago,Chile.
[10]Zeiler M D,Fergus R.Visualizing and understanding convolutional networks[M].Computer vision-ECCV2014.Springer International Publishing,2014:818-833.
[2]Wang G,Ren G,Wu Z,et al.A robust,coarse-tofine traffic sign detection method[C]//Neural Networks(UCNN),The 2013 International Joint Conference on.IEEE,2013,Dallas,TX,USA.
[3]Prieto M S,Allen A R.Using self-organising maps in the detection and recognition of road signs[J].Image and Vision Computing,2009,27(6):673-683.
[4]Kuo W J,Lin C C.Two-stage road sign detection and recognition[C]//2007 IEEE International Conference on Multimedia and Expo.IEEE,2007;1427-1430.
[5]王雁,穆春阳,马行.基于Zemike不变矩与SVM的交通标志的识别[J].公路交通科技,2015,12:128-132.
[6]SERMANET P,LECUN Y.Traffic sign recognition with multi-scale convolutional networks[C]//Neural Networks(UCNN),The 2011 International Joint Conference on.IEEE,2011:2809-2813.
[7]CIRESAN D,MEIER U,MASCI J,et al.A committee of neural networks for traffic sign classification[C]//Neural Networks(UCNN),The 2011 International Joint Conference on.IEEE,2011:1918—1921.
[8]Ren S,He K,Girshick R,et al.Faster R-CNN;Towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems.2015,Montreal,Canada.
[9]Girshick R.Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision.2015,Santiago,Chile.
[10]Zeiler M D,Fergus R.Visualizing and understanding convolutional networks[M].Computer vision-ECCV2014.Springer International Publishing,2014:818-833.