首页 > 论文 > 激光与光电子学进展 > 56卷 > 7期(pp:71003--1)

基于改进卷积神经网络的实时交通标志检测方法

Real-Time Traffic Sign Detection Method Based on Improved Convolution Neural Network

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

提出了一种基于改进卷积神经网络的交通标志检测方法。预训练模型产生否定; 使用难分类负样本采集将负样本输入到网络中,提高模型的判别能力; 使用多尺度训练过程中的特征级联策略来进一步提升模型的性能。利用TensorFlow框架在德国交通标志检测数据集上对所提方法的有效性进行了仿真。研究结果表明,与现有技术相比,所提方法能够获得更快的检测速率,处理每幅图像仅需0.016 s。

Abstract

A detection method of traffic signs is proposed based on a modified convolutional neural network. The model is pre-trained to produce the negatives, and hard negative mining is used to add the negative samples into the network to improve the discriminating ability of the model. A feature concatenation strategy during the multi-scale training process is employed to further enhance the performance of the model. On the German traffic sign detection dataset, the effectiveness of the proposed method is simulated in the TensorFlow framework. The research results show that compared with the existing methods, the proposed method can be used to obtain a high detection rate and processing time of only 0.016 s for each image.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP181

DOI:10.3788/lop56.071003

所属栏目:图像处理

基金项目:安徽省高校自然科学研究重点项目(KJ2018A0122)

收稿日期:2018-09-25

修改稿日期:2018-10-17

网络出版日期:2018-10-22

作者单位    点击查看

童英:安徽工程大学电气工程学院, 安徽 芜湖 241000
杨会成:安徽工程大学电气工程学院, 安徽 芜湖 241000

联系人作者:童英(864844537@qq.com)

【1】Stewart B T, Yankson I K, Afukaar F, et al. Road traffic and other unintentional injuries among travelers to developing countries[J]. Medical Clinics of North America, 2016, 100(2): 331-343.

【2】Zhang S F, Zhu T. A method of traffic sign detection and recognition based on HDR technology[J]. Laser & Optoelectronics Progress, 2018, 55(9): 091006.
张淑芳, 朱彤. 一种基于HDR技术的交通标志牌检测和识别方法[J]. 激光与光电子学进展, 2018, 55(9): 091006.

【3】Hu C P, Bai X, Qi L, et al. Learning discriminative pattern for real-time car brand recognition[J]. IEEE Transactions on Intelligent Transportation Systems, 2015, 16(6): 3170-3181.

【4】Gao D D, Xu X T, Li B. Research on application of infrared and white light mixed supplemental lighting system in intelligent transportation[J]. Infrared and Laser Engineering, 2018, 47(9): 0918006.
高东东, 徐晓婷, 李博. 红外/白光混合补光系统在智能交通中的应用研究[J]. 红外与激光工程, 2018, 47(9): 0918006.

【5】Xu Y,Wei Z Y. An improved traffic sign image recognition algorithm[J]. Laser & Optoelectronics Progress, 2017, 54(2): 021001.
徐岩, 韦镇余. 一种改进的交通标志图像识别算法[J]. 激光与光电子学进展, 2017, 54(2): 021001.

【6】Fleyeh H, Davami E. Eigen-based traffic sign recognition[J]. IET Intelligent Transport Systems, 2011, 5(3): 190-196.

【7】Khan J F, Bhuiyan S M A, Adhami R R. Image segmentation and shape analysis for road-sign detection[J].IEEE Transactions on Intelligent Transportation Systems, 2011, 12(1): 83-96.

【8】Yang Y, Luo H L, Xu H R, et al. Towards real-time traffic sign detection and classification[C]∥Proceedings of 17th International IEEE Conference on Intelligent Transportation Systems, 2014: 87-92.

【9】Yang Y, Wu F C. Real-time traffic sign detection via color probability model and integral channel features[C]∥Proceedings of Chinese Conference on Pattern Recognition, 2014: 545-554.

【10】Liang M, Yuan M Y, Hu X L, et al. Traffic sign detection by ROI extraction and histogram features-based recognition[C]∥Proceedings of the 2013 International Joint Conference on Neural Networks, 2013: 1-8.

【11】Wang G Y, Ren G H, Wu Z L, et al. A hierarchical method for traffic sign classification with support vector machines[C]∥Proceedings of the 2013 International Joint Conference on Neural Networks, 2013: 1-6.

【12】Wang G Y, Jin Y S, Ren G H, et al. High-performance VLSI architecture for traffic sign detection[J]. Infrared and Laser Engineering, 2018, 47(9): 0926001.
王刚毅, 金炎胜, 任广辉, 等. 高性能交通标志检测模块的VLSI结构设计[J]. 红外与激光工程, 2018, 47(9): 0926001.

【13】Belaroussi R, Tarel J P. Angle vertex and bisector geometric model for triangular road sign detection[C]∥Proceedings of 2009 Workshop on Applications of Computer Vision, 2009: 1-7.

【14】Belaroussi R, Tarel J P. A real-time road sign detection using bilateral Chinese transform[C]∥Proceedings of International Symposium on Visual Computing, 2009: 1161-1170.

【15】Houben S. A single targetvoting scheme for traffic sign detection[C]∥Proceedings of 2011 IEEE Intelligent Vehicles Symposium, 2011: 124-129.

【16】Mammeri A, Khiari E H, Boukerche A. Road-sign text recognition architecture for intelligent transportation systems[C]∥Proceedings of 2014 IEEE 80th Vehicular Technology Conference, 2014: 1-5.

【17】Yin S Y, Ouyang P, Liu L B, et al. Fast traffic sign recognition with a rotation invariant binary pattern based feature[J]. Sensors, 2015, 15(1): 2161-2180.

【18】Mathias M, Timofte R, Benenson R, et al. Traffic sign recognition-how far are we from the solution[C]∥Proceedings of the 2013 International Joint Conference on Neural Networks, 2013: 1-8.

【19】Ruta A, Porikli F, Watanabe S, et al. In-vehicle camera traffic sign detection and recognition[J]. Machine Vision and Applications, 2011, 22(2): 359-375.

【20】He K M, Zhang X Y, Ren S Q, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1904-1916.

【21】Girshick R. Fast R-CNN[C]∥Proceedings of 2015 IEEE International Conference on Computer Vision, 2015: 1440-1448.

【22】Uijlings J R R, van de Sande K E A, Gevers T, et al. Selective search for object recognition[J]. International Journal of Computer Vision, 2013, 104(2): 154-171.

【23】Ren S Q, He K M, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.

【24】Zeiler M D, Fergus R. Visualizing and understanding convolutional networks[C]∥Proceedings of European Conference on Computer Vision, 2014: 818-833.

【25】Redmon J, Divvala S, Girshick R, et al. You only look once: unified, real-time object detection[C]∥Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016: 779-788.

【26】Sun X D, Wu P C, Hoi S C H. Face detection using deep learning: an improved faster RCNN approach[J]. Neurocomputing, 2018, 299: 42-50.

引用该论文

Tong Ying,Yang Huicheng. Real-Time Traffic Sign Detection Method Based on Improved Convolution Neural Network[J]. Laser & Optoelectronics Progress, 2019, 56(7): 071003

童英,杨会成. 基于改进卷积神经网络的实时交通标志检测方法[J]. 激光与光电子学进展, 2019, 56(7): 071003

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF