Intelligent traffic sign recognition method based on capsule network

doi:10.11772/j.issn.1001-9081.2019091610

Journal of Computer Applications ›› 2020, Vol. 40 ›› Issue (4): 1045-1049.DOI: 10.11772/j.issn.1001-9081.2019091610

• Artificial intelligence • Previous Articles Next Articles

Intelligent traffic sign recognition method based on capsule network

CHEN Lichao¹, ZHENG Jiamin¹, CAO Jianfang^1,2, PAN Lihu¹, ZHANG Rui¹

1. College of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan Shanxi 030024, China;
2. Computer Department, Xinzhou Teachers University, Xinzhou Shanxi 034000, China

Received:2019-09-23 Revised:2019-11-04 Online:2020-04-10 Published:2020-04-17
Supported by:
This work is partially supported by the Applied Basic Research Project of Shanxi Province(201801D221179).

基于胶囊网络的智能交通标志识别方法

陈立潮¹, 郑佳敏¹, 曹建芳^1,2, 潘理虎¹, 张睿¹

1. 太原科技大学计算机科学与技术学院, 太原 030024;
2. 忻州师范学院计算机系, 山西忻州 034000

通讯作者: 曹建芳
作者简介:陈立潮(1961-),男,山西万荣人,教授,博士,CCF高级会员,主要研究方向:大数据软件工程、智能图像信息处理;郑佳敏(1994-),男,山西晋中人,硕士研究生,主要研究方向:图像处理、深度学习;曹建芳(1976-),女,山西忻州人,教授,博士,CCF高级会员,主要研究方向:数字图像理解、大数据;潘理虎(1974-),男,河南上蔡人,副教授,博士,CCF高级会员,主要研究方向:智能信息处理;张睿(1987-),男,山西太原人,讲师,博士,CCF会员,主要研究方向:智能信息处理。
基金资助:
山西省应用基础研究项目（201801D221179）。

Abstract

Abstract: The scalar neurons of convolutional neural networks cannot express the feature location information,and have poor adaptability to the complex vehicle driving environment,resulting in low traffic sign recognition rate. Therefore,an intelligent traffic sign recognition method based on capsule network was proposed. Firstly,the very deep convolutional neural network was used to improve the feature extraction part. Then,a pooling layer was introduced in the main capsule layer. Finally,the movement index average method was used for improving the dynamic routing algorithm. The test results on the GTSRB dataset show that the improved capsule network method improves the recognition accuracy in special scenes by 10. 02 percentage points. Compared with the traditional convolutional neural network,the proposed method has the recognition time for single image decreased by 2. 09 ms. Experimental results show that the improved capsule network method can meet the requirement of accurate and real-time traffic sign recognition.

Key words: traffic sign recognition, capsule network, very deep convolution, dynamic routing algorithm, deep learning

摘要： 针对卷积神经网络的标量神经元无法表达特征位置信息，对复杂的车辆行驶环境适应性差，导致交通标志识别率低的问题，提出一种基于胶囊网络的智能交通标志识别方法。首先采用超深度卷积神经网络改进特征提取部分，然后在主胶囊层引入池化层，最后采用移动指数平均法改进了动态路由算法。在GTSRB数据集上的测试结果表明，改进后的胶囊网络方法在特殊场景下的识别精度提高了10.02个百分点，相对于传统的卷积神经网络，该方法的单张图片的识别时间缩短了2.09 ms。实验结果表明，改进后的胶囊网络方法能满足准确、实时的交通标志识别要求。

关键词: 交通标志识别, 胶囊网络, 超深度卷积, 动态路由算法, 深度学习

CLC Number:

TP391.3

CHEN Lichao, ZHENG Jiamin, CAO Jianfang, PAN Lihu, ZHANG Rui. Intelligent traffic sign recognition method based on capsule network[J]. Journal of Computer Applications, 2020, 40(4): 1045-1049.

陈立潮, 郑佳敏, 曹建芳, 潘理虎, 张睿. 基于胶囊网络的智能交通标志识别方法[J]. 计算机应用, 2020, 40(4): 1045-1049.

References

[1] BISWAS R,TORA M R,BHUIYAN F H. LVQ and HOG based speed limit traffic signs detection and categorization[C]//Proceedings of the 2014 International Conference on Informatics, Electronics and Vision. Piscataway:IEEE,2014:1-6.
[2] HOU Y,HAO X,CHEN H. A cognitively motivated method for classification of occluded traffic signs[J]. IEEE Transactions on Systems,Man,and Cybernetics:Systems,2016,47(2):255-262.
[3] 张邯, 罗晓曙, 袁荣尚. 基于优化的卷积神经网络在交通标志识别中的应用[J]. 现代电子技术,2018,41(21):132-136. (ZHANG H,LUO X S,YUAN R S. Application of optimized convolutional neural network in traffic sign recognition[J]. Modern Electronics Technique,2018,41(21):132-136.)
[4] 汪贵平, 盛广峰, 黄鹤, 等. 基于改进LeNet-5网络的交通标志识别方法[J]. 科学技术与工程,2018,18(34):78-84.(WANG G P,SHENG G F,HUANG H,et al. Traffic sign recognition method based on improved LeNet-5 network[J]. Science Technology and Engineering,2018,18(34):78-84.)
[5] SABOUR S,FROSST N,HINTON G E. Dynamic routing between capsules[C]//Proceedings of the 31st Conference on Neural Information Processing Systems. New York:Curran Associates Inc., 2017:3859-3869.
[6] 洪瑞, 康旭东, 郭军, 等, 基于复杂网络描述的图像深度卷积分类方法[J]. 计算机应用,2018,38(12):3399-3402.(HONG R, KANG X D,GUO J,et al. Image deep convolution classification method based on complex network description[J]. Journal of Computer Applications,2018,38(12):3399-3402.)
[7] SIMONYAN K,ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[EB/OL].[2019-07-20]. https://arxiv.org/pdf/1409.1556.pdf.
[8] GLOROT X,BORDES A,BENGIO Y. Deep sparse rectifier neural networks[C]//Proceedings of the 14th International Conference on Artificial Intelligence and Statistics. New York:JMLR. org,2011:315-323.
[9] 周飞燕, 金林鹏, 董军. 卷积神经网络研究综述[J]. 计算机学报,2017,40(6):1229-1251. (ZHOU F Y,JIN L P,DONG J. Review of convolutional neural network[J]. Chinese Journal of Computers,2017,40(6):1229-1251.)
[10] 曹荣川. 图像分类中基于显著关系的改进特征编码与池化算法研究[D]. 长春:吉林大学,2017:34-41. (CAO R C. Research on improved feature coding and pooling algorithm based on saliency relationship in image classification[D]. Changchun:Jilin University,2017:34-41.)
[11] 付家慧, 吴晓富, 张索非. 基于仿射变换的胶囊网络特征研究[J]. 信号处理,2018,34(12):1508-1516. (FU J H,WU X F, ZHANG S F. Study on characteristics of capsule network based on affine transformation[J]. Journal of Signal Processing,2018,34(12):1508-1516.)
[12] 胡聪, 屈瑾瑾, 许川佩, 等. 基于自适应池化的神经网络的服装图像识别[J]. 计算机应用,2018,38(8):2211-2217.(HU C, QU J J,XU C P,et al. Garment image recognition based on adaptive pooling neural network[J]. Journal of Computer Applications, 2018,38(8):2211-2217.)
[13] KINGMA D P,BA J L. Adam:a method for stochastic optimization[EB/OL].[2019-07-20]. https://arxiv.org/pdf/1412.6980.pdf.

[1]	CHEN Chengrui, SUN Ning, HE Shibiao, LIAO Yong. Deep learning-based joint channel estimation and equalization algorithm for C-V2X communications [J]. Journal of Computer Applications, 2021, 41(9): 2687-2693.
[2]	ZHAO Hong, KONG Dongyi. Chinese description of image content based on fusion of image feature attention and adaptive attention [J]. Journal of Computer Applications, 2021, 41(9): 2496-2503.
[3]	XU Jianglang, LI Linyan, WAN Xinjun, HU Fuyuan. Indoor scene recognition method combined with object detection [J]. Journal of Computer Applications, 2021, 41(9): 2720-2725.
[4]	ZHENG Zhiqiang, HU Xin, WENG Zhi, WANG Yuhe, CHENG Xi. Cattle eye image feature extraction method based on improved DenseNet [J]. Journal of Computer Applications, 2021, 41(9): 2780-2784.
[5]	XIE Defeng, JI Jianmin. Syntax-enhanced semantic parsing with syntax-aware representation [J]. Journal of Computer Applications, 2021, 41(9): 2489-2495.
[6]	DAI Yurou, YANG Qing, ZHANG Fengli, ZHOU Fan. Trajectory prediction model of social network users based on self-supervised learning [J]. Journal of Computer Applications, 2021, 41(9): 2545-2551.
[7]	HE Zhenghai, XIAN Yantuan, WANG Meng, YU Zhengtao. Case reading comprehension method combining syntactic guidance and character attention mechanism [J]. Journal of Computer Applications, 2021, 41(8): 2427-2431.
[8]	CAO Yuhong, XU Hai, LIU Sun'ao, WANG Zixiao, LI Hongliang. Review of deep learning-based medical image segmentation [J]. Journal of Computer Applications, 2021, 41(8): 2273-2287.
[9]	QIN Binbin, PENG Liangkang, LU Xiangming, QIAN Jiangbo. Research progress on driver distracted driving detection [J]. Journal of Computer Applications, 2021, 41(8): 2330-2337.
[10]	LI Yafang, LIANG Ye, FENG Weiwei, ZU Baokai, KANG Yujian. Deep network embedding method based on community optimization [J]. Journal of Computer Applications, 2021, 41(7): 1956-1963.
[11]	DU Yan, LYU Liangfu, JIAO Yichen. Fuzzy prototype network based on fuzzy reasoning [J]. Journal of Computer Applications, 2021, 41(7): 1885-1890.
[12]	WANG Yue, JIANG Yiming, LAN Julong. Intrusion detection based on improved triplet network and K-nearest neighbor algorithm [J]. Journal of Computer Applications, 2021, 41(7): 1996-2002.
[13]	GAO Qinquan, HUANG Bingcheng, LIU Wenzhe, TONG Tong. Bamboo strip surface defect detection method based on improved CenterNet [J]. Journal of Computer Applications, 2021, 41(7): 1933-1938.
[14]	HOU Xiaohan, JIN Guodong, TAN Lining, XUE Yuanliang. Synthetic aperture radar ship detection method based on self-adaptive and optimal features [J]. Journal of Computer Applications, 2021, 41(7): 2150-2155.
[15]	LIU Shize, ZHU Yida, CHEN Runze, LUO Haiyong, ZHAO Fang, SUN Yi, WANG Baohui. Traffic mode recognition algorithm based on residual temporal attention neural network [J]. Journal of Computer Applications, 2021, 41(6): 1557-1565.

Intelligent traffic sign recognition method based on capsule network

基于胶囊网络的智能交通标志识别方法

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics