基于改进Tiny YOLOv3的交通标志检测方法

doi:10.19640/j.cnki.jtau.2023.02.013

天津农学院学报 ›› 2023, Vol. 30 ›› Issue (2): 62-68.doi: 10.19640/j.cnki.jtau.2023.02.013

基于改进Tiny YOLOv3的交通标志检测方法

郑海波, 宋爽, 刘同海^通信作者

天津农学院计算机与信息工程学院,天津 300392

收稿日期:2022-03-07 出版日期:2023-04-30 发布日期:2023-06-28
通讯作者: 刘同海（1977—）,男,教授,博士,主要从事农业人工智能方面研究。E-mail：tonghai_1227@126.com。
作者简介:郑海波（1996—）,男,硕士在读,主要从事基于深度学习的目标检测和智慧农业方面研究。E-mail：2009028125@stu.tjau.edu.cn。
基金资助:
天津市研究生科研创新项目人工智能专项（2020YJSZXS11）; 天津市重点研发计划科技支撑重点项目（20YFZCSN00220）; 中央引导地方科技发展专项（21ZYCGSN00590）; 内蒙古自治区科学技术厅项目（2020GG0068）

Traffic sign detection method based on improved Tiny YOLOv3

Zheng Haibo, Song Shuang, Liu Tonghai^{Corresponding Author}

College of Computer and Information Engineering, Tianjin Agricultural University, Tianjin 300392, China

Received:2022-03-07 Online:2023-04-30 Published:2023-06-28

摘要/Abstract

摘要： 针对智能驾驶场景下的小尺寸交通标志检测准确率不高的问题,提出一种基于Tiny YOLOv3网络的交通标志检测算法。通过使用深度可分离卷积重构特征提取网络和增加浅层与深层特征层之间的特征融合,提高模型对小目标的注意力;同时修改anchor boxes尺寸,提升预测框的准确度。在TT100K交通标志数据集上的试验结果表明,提出算法的平均精度均值（mAP）较Tiny YOLOv3提高了19.3%,对小尺寸交通标志检测具有更强的鲁棒性。

关键词: 交通标志检测, 深度可分离卷积, 特征融合, Tiny YOLOv3

Abstract: Aiming at the problem of low accuracy of small-size traffic sign detection in intelligent driving scenarios, a traffic sign detection algorithm based on Tiny YOLOv3 network was proposed. By using the depth separable convolutional reconstruction feature extraction network and increasing the feature fusion between the shallow and deep feature layers, the model's attention to small targets could be improved; at the same time, the accuracy of the prediction box was also improved by modifying the size of anchor boxes. The test results on the TT100K traffic sign data set showed that the mean average precision（mAP）of the proposed algorithm was 19.3% higher than that of Tiny YOLOv3, and it is more robust to the detection of small-size traffic signs.

Key words: traffic sign detection, depth separable convolution, feature fusion, Tiny YOLOv3

中图分类号:

TP391.41

郑海波, 宋爽, 刘同海. 基于改进Tiny YOLOv3的交通标志检测方法[J]. 天津农学院学报, 2023, 30(2): 62-68.

Zheng Haibo, Song Shuang, Liu Tonghai. Traffic sign detection method based on improved Tiny YOLOv3[J]. Journal of Tianjin Agricultural University, 2023, 30(2): 62-68.

导出引用管理器 EndNote|Reference Manager|ProCite|BibTeX|RefWorks

链接本文: http://xuebao.tjau.edu.cn/CN/10.19640/j.cnki.jtau.2023.02.013

http://xuebao.tjau.edu.cn/CN/Y2023/V30/I2/62

参考文献

[1] ZHU Z,LIANG D,ZHANG S,et al.Traffic-sign detection and classification in the wild[C]//IEEE. 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas:IEEE,2016:2110-2118.
[2] LILLO-CASTELLANO J M,MORA-JIMÉNEZ I,FIGUERA-POZUELO C,et al. Traffic sign segmentation and classification using statistical learning methods[J]. Neurocomputing,2015,153:286-299.
[3] XU Z,REN J,BAO C.A Traffic signs' detection method of contour approximation based on concave removal[C]// IEEE. 2016 Chinese Control and Decision Conference. Yinchuan:IEEE,2016:5199-5204.
[4] XU X,JIN J,ZHANG S,et al.Smart data driven traffic sign detection method based on adaptive color threshold and shape symmetry[J]. Future Generation Computer Systems,2019,94:381-391.
[5] 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 and Machine Intelligence,2017,39(6):1137-1149.
[6] REDMON J,DIVVALA S,GIRSHICK R, et al.You only look once:Unified,real-time object detection[C]//IEEE. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Los Alamitos:IEEE,2016:779-788.
[7] REDMON J,FARHADI A.YOLO9000:better,faster,stronger[C]//IEEE. 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu:IEEE,2017:6517-6525.
[8] REDMON J,FARHADI A. YOLOv3:An incremental improvement[EB/OL].(2018-04-08)[2022-02-07]. https:// arxiv.org/abs/1804.02767.
[9] YANG T,LONG X,SANGAIAH A K,et al.Deep detection network for real-life traffic sign in vehicular networks[J]. Computer Networks,2018,136:95-104.
[10] LI J,WANG Z.Real-time traffic sign recognition based on efficient CNNs in the wild[J]. IEEE Transactions on Intelligent Transportation Systems,2019,20(3):975-984.
[11] ZHANG H,QIN L,LI J,et al.Real-time detection method for small traffic signs based on Yolov3[J]. IEEE Access,2020,8:64145-64156.
[12] LIU S,HUANG D.Receptive field block net for accurate and fast object detection[C]//European Conference on Computer Vision. Proceedings of the European Conference on Computer Vision. Berlin:Springer,2018:404-419.
[13] ZHANG J,HUANG M,JIN X,et al.A real-time Chinese traffic sign detection algorithm based on modified YOLOv2[J]. Algorithms,2017,10(4):127.
[14] KISANTAL M,WOJNA Z,MURAWSKI J,et al.Augmentation for small object detection[J]. arXiv preprint arXiv,2019,21:47.
[15] 刘胜,马社祥,孟鑫,等. 基于U-Net定位优化的交通标志识别网络[J]. 重庆理工大学学报(自然科学版),2020,34(11):147-155.

基于改进Tiny YOLOv3的交通标志检测方法

Traffic sign detection method based on improved Tiny YOLOv3

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

本文评价

[1]	马含章, 王淼鑫, 钟拼扬, 刘华, 常若葵, 董晋峰. 视觉识别的生活垃圾分类系统设计[J]. 天津农学院学报, 2023, 30(4): 53-57.
[2]	马国强, 马吉飞, 郭鹏, 宋志恒, 于娜. 改进的医学CT图像K-均值聚类分割算法的实现[J]. 天津农学院学报, 2013, 20(4): 28-35.