基于改进卷积神经网络的交通标志识别方法

doi:10.16180/j.cnki.issn1007-7820.2019.11.006

电子科技 ›› 2019, Vol. 32 ›› Issue (11): 28-32.doi: 10.16180/j.cnki.issn1007-7820.2019.11.006

基于改进卷积神经网络的交通标志识别方法

袁小平,王岗,王晔枫,汪喆远,孙辉

中国矿业大学信息与控制工程学院,江苏徐州221000

收稿日期:2018-11-17 出版日期:2019-11-15 发布日期:2019-11-15
作者简介:袁小平(1966-),男,博士,教授。研究方向:模式识别与人工智能。|王岗(1994-),男,硕士研究生。研究方向:计算机视觉。
基金资助:
江苏省自然科学基金(BK20170278)

Traffic Sign Recognition Method Based on Improved Convolutional Neural Network

YUAN Xiaoping,WANG Gang,WANG Yefeng,WANG Zheyuan,SUN Hui

School of Information and Control Engineering,China University of Mining and Technology,Xuzhou 221000,China

Received:2018-11-17 Online:2019-11-15 Published:2019-11-15
Supported by:
Natural Science Foundation of Jiangsu(BK20170278)

摘要/Abstract

摘要：

针对智能交通系统中小尺度交通标志识别率低的问题,文中提出一种改进卷积神经网络的交通标志识别方法。该方法通过在Faster R-CNN算法的低层特征图上增加优化的RPN网络,提升了小尺度交通标志的检测率。该方法还利用Max Pooling方法实了现图像的局部细节特征与全局语义特征充分融合。在TT-100K数据集上稍微实验结果表明新方法可以明显提高小尺度交通标志的识别率。

关键词: 深度学习, 交通标志识别, 卷积神经网络, Faster R-CNN, RPN, 特征融合

Abstract:

Aiming at the low recognition rate of small scale traffic signs in intelligent transportation system, an improved convolution neural network method for traffic sign recognition was proposed in this paper.This method could improve the detection rate of small-scale traffic signs by adding an optimized RPN network to the low-level feature map of Faster R-CNN algorithm.In addition, Max Pooling method was used to fully fuse the local details and global semantic features of the image. The experimental results on TT-100K data set showed that the proposed method could significantly improve the recognition rate of small-scale traffic signs.

Key words: deep learning, trafficsign recognition, convolutional neural network, Faster R-CNN, RPN, feature fusion

中图分类号:

TP391.41

袁小平,王岗,王晔枫,汪喆远,孙辉. 基于改进卷积神经网络的交通标志识别方法[J]. 电子科技, 2019, 32(11): 28-32.

YUAN Xiaoping,WANG Gang,WANG Yefeng,WANG Zheyuan,SUN Hui. Traffic Sign Recognition Method Based on Improved Convolutional Neural Network[J]. Electronic Science and Technology, 2019, 32(11): 28-32.

图/表 7

图1

图2

图3

图4

图5

图6

图7

参考文献 16

[1]	张达峰, 刘宇红, 张荣芬 . 基于深度学习的智能辅助驾驶系统[J]. 电子科技, 2018,31(10):60-63.
	Zhang Dafeng, Liu Yuhong, Zhang Rongfen . Intelligent assistantdriving system based on deep learning[J]. Electronic Science and Technology, 2018,31(10):60-63.
[2]	Yao C, Wu F, Chen H J, et al. Traffic sign recognition using HOG-SVM and grid search [C].Hangzhou:International Conference on Signal Processing, 2015.
[3]	Gim J W, Hwang M C, Ko B C, et al. Real-time speed-limit sign detection and recognition using spatial pyramid feature and boosted random forest [C].Genoa: International Conference Image Analysis and Recognition, 2015.
[4]	Deng Zhijie, Wang Yong, Tao Xiaoling. Method of network traffic classification using Naïve Bayes based on FPGA [C].Chongqing:13^th IEEE Joint International Computer Science and Information Technology Conference , 2011.
[5]	Zhang Qi, He Ning, Chi Yue , et al. Traffic sign detection and recognition based on the improved SIFT algorithm[J]. Journal of Beijing Union University, 2017,31(2):59-65.
[6]	Abedin M Z, Dhar P, Deb K. Traffic sign recognition using SURF: Speeded up robust feature descriptor and artificial neural network classifier [C].Dhaka:International Conference on Electrical and Computer Engineering, 2016.
[7]	李盈盈, 李菲菲, 陈虬 . 基于改进HOG共生概率特征的行人检测算法[J]. 电子科技, 2018,31(9):4-8.
	Li Yingying, Li Feifei, Chen Qiu . Pedestrian detection algorithm using co-occurrence probability feature based on improved HOG[J]. Electronic Science and Technology, 2018,31(9):4-8.
[8]	Wu Yihui, Liu Yulong, Li Jianmin, et al. Traffic sign detection based on convolutional neural networks [C]. Dallas:International Joint Conference on Neural Networks, 2014.
[9]	Sermanet P, Lecun Y. Traffic sign recognition with multi-scale convolutional networks [C].San Jose: International Joint Conference on Neural Networks, 2011.
[10]	Jin J, Fu K, Zhang C . Traffic sign recognition with hinge loss trained convolutional neural networks[J]. IEEE Transactions on Intelligent Transportation Systems, 2014,15(5):1991-2000. doi: 10.1109/TITS.2014.2308281
[11]	Zhu Zhe, Liang Dun, Zhang Songhai, et al. Traffic-sign detection and classification in the wild [C].Las Vegas: IEEE Conference on Computer Vision and Pattern Recognition, 2016.
[12]	Ciresan D, Meier U, Masci J, et al. A committee of neural networks for traffic sign classification [C].San Jose: International Joint Conference on Neural Networks, 2011.
[13]	Sermanet P, Eigen D, Zhang Xiang, et al. Overfeat: integrated recognition, localization anddetection using convolutional networks [C].Vancouver:International Conference on Learning Representations, 2014.
[14]	Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation [C].Columbus:IEEE Conference on Computer Vision and Pattern Recognition, 2013.
[15]	Girshick R . Fast R-CNN[C].Santiago:IEEE International Conference on Computer Vision(ICCV) , 2015.
[16]	Ren S, He K, Girshick R , et al. Faster R-CNN:towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017,39(6):1137-1149.

基于改进卷积神经网络的交通标志识别方法

Traffic Sign Recognition Method Based on Improved Convolutional Neural Network

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献 16

相关文章 15

Metrics

本文评价

推荐阅读 10

[1]	李辉,王一丞. 基于CNNCIFG-Attention模型的文本情感分类[J]. 电子科技, 2022, 35(2): 46-51.
[2]	程晓雅,张雷. 基于深度学习的有遮挡人脸识别方法研究[J]. 电子科技, 2022, 35(1): 35-39.
[3]	赵崇,迟蒙蒙,储聪,张鹏. 导盲犬行走机构运动仿真及其视觉识别算法研究[J]. 电子科技, 2021, 34(9): 66-72.
[4]	战荫伟,朱百万,杨卓. 一种车脸识别算法的研究与应用[J]. 电子科技, 2021, 34(8): 1-7.
[5]	廖璐明,张伟. 基于改进VGG16网络的混合批量训练交通标志识别[J]. 电子科技, 2021, 34(8): 8-13.
[6]	马立新,豆晨飞,宋晨灿,杨天笑. 基于特征融合卷积神经网络的绝缘子无损检测[J]. 电子科技, 2021, 34(7): 26-30.
[7]	顾伟,李菲菲,陈虬. 基于多特征融合的行人检测方法[J]. 电子科技, 2021, 34(5): 29-34.
[8]	薛永杰,巨志勇. 基于改进AlexNet的鱼类识别算法[J]. 电子科技, 2021, 34(4): 12-17.
[9]	闫书豪,乔美英. 基于一维WConv-BiLSTM的轴承故障诊断算法[J]. 电子科技, 2021, 34(4): 75-82.
[10]	邵杭,王永雄,秦宇龙. 基于深度学习与显著性的数字图像构图优化[J]. 电子科技, 2021, 34(3): 36-42.
[11]	葛靖,刘子龙. 基于CNN和LSTM的睡眠呼吸暂停检测算法[J]. 电子科技, 2021, 34(2): 21-26.
[12]	朱斌,刘子龙. 基于新型初始模块的卷积神经网络图像分类方法[J]. 电子科技, 2021, 34(2): 52-56.
[13]	闫超,孙占全,田恩刚,赵杨洋,范小燕. 基于深度学习的医学图像分割技术研究进展[J]. 电子科技, 2021, 34(2): 7-11.
[14]	张灿,陈玮,尹钟. 基于弱监督宫颈细胞图像的语义分割方法[J]. 电子科技, 2021, 34(12): 68-74.
[15]	张莹,刘子龙,万伟. 基于Faster R-CNN的无人机车辆目标检测[J]. 电子科技, 2021, 34(11): 11-20.