Real-time traffic sign detection algorithm based on improved YOLOv3

doi:10.11772/j.issn.1001-9081.2021050731

Journal of Computer Applications ›› 2022, Vol. 42 ›› Issue (7): 2219-2226.DOI: 10.11772/j.issn.1001-9081.2021050731

• Multimedia computing and computer simulation • Previous Articles Next Articles

Real-time traffic sign detection algorithm based on improved YOLOv3

Dawei ZHANG¹(), Xuchong LIU², Wei ZHOU¹, Zhuhui CHEN¹, Yao YU³

^1.School of Computer Science & School of Cyberspace Science，Xiangtan University，Xiangtan Hunan 411105，China
^2.Hunan Academy of Public Security Science and Technology，Hunan Police Academy，Changsha Hunan 410138，China
^3.School of Public Administration，Xiangtan University，Xiangtan Hunan 411105，China

Received:2021-05-10 Revised:2021-10-31 Accepted:2021-11-08 Online:2022-07-15 Published:2022-07-10
Contact: Dawei ZHANG
About author:LIU Xuchong， born in 1973， Ph. D.， professor. His research interests include big data analysis， information network security.
ZHOU Wei， born in 1978， Ph. D.， associate professor. His research interests include computer vision， intelligent systems.
CHEN Zhuhui， born in 1996， M. S. candidate. His research interests include natural language processing.
YU Yao， born in 1995， M. S. candidate. Her research interests include public opinion analysis.
Supported by:
Hunan Provincial Natural Science Foundation(2018JJ2107);Major Science and Technology Project of Hunan Province(2017SK1040);Project of Hunan Province High-tech Industry Science and Technology Innovation Leading Plan(2020GK2029)

基于改进YOLOv3的实时交通标志检测算法

张达为¹(), 刘绪崇², 周维¹, 陈柱辉¹, 余瑶³

^1.湘潭大学计算机学院·网络空间安全学院, 湘潭湖南, 411105
^2.湖南警察学院湖南公安科学技术研究院, 长沙 410138
^3.湘潭大学公共管理学院, 湘潭湖南, 411105

通讯作者: 张达为
作者简介:刘绪崇（1973—），男，湖南桑植人，教授，博士，CCF会员，主要研究方向：大数据分析、信息网络安全
周维（1978—），男，湖南湘潭人，副教授，博士，CCF会员，主要研究方向：计算机视觉、智能系统
陈柱辉（1996—），男，湖南永州人，硕士研究生，CCF会员，主要研究方向：自然语言处理
余瑶（1995—），女，江西上饶人，硕士研究生，主要研究方向：公共舆论分析。
基金资助:
湖南省自然科学基金资助项目(2018JJ2107);湖南省科技重大专项(2017SK1040);湖南省高新技术产业科技创新引领计划项目(2020GK2029)

Abstract

Abstract:

Aiming at the problems of slow detection and low recognition accuracy of road traffic signs in Chinese intelligent driving assistance system， an improved road traffic sign detection algorithm based on YOLOv3 （You Only Look Once version 3） was proposed. Firstly， MobileNetv2 was introduced into YOLOv3 as the basic feature extraction network to construct an object detection network module MN-YOLOv3 （MobileNetv2-YOLOv3）. And two Down-up links were added to the backbone network of MN-YOLOv3 for feature fusion， thereby reducing the model parameters， and improving the running speed of the detection module as well as information fusion performance of the multi-scale feature maps. Then， according to the shape characteristics of traffic sign objects， K-Means++ algorithm was used to generate the initial cluster center of the anchor， and the DIOU （Distance Intersection Over Union） loss function was introduced to combine DIOU and Non-Maximum Suppression （NMS） for the bounding box regression. Finally， the Region Of Interest （ROI） and the context information were unified by ROI Align and merged to enhance the object feature expression. Experimental results show that the proposed algorithm has better performance， and the mean Average Precision （mAP） of the algorithm on the dataset CSUST （ChangSha University of Science and Technology） Chinese Traffic Sign Detection Benchmark （CCTSDB） can reach 96.20%. Compared with Faster R-CNN （Region Convolutional Neural Network）， YOLOv3 and Cascaded R-CNN detection algorithms， the proposed algorithm has better real-time performance， higher detection accuracy， and is more robustness to various environmental changes.

Key words: object detection, feature fusion, You Only Look Once version 3 (YOLOv3), DIOU (Distance Intersection Over Union), MobileNetv2, K-Means++

摘要：

针对目前我国智能驾驶辅助系统识别道路交通标志检测速度慢、识别精度低等问题，提出一种基于YOLOv3的改进的道路交通标志检测算法。首先，将MobileNetv2作为基础特征提取网络引入YOLOv3以形成目标检测网络模块MN-YOLOv3，在MN-YOLOv3主干网络中引入两条Down-up连接进行特征融合，从而减少检测算法的模型参数，提高了检测模块的运行速度，增强了多尺度特征图之间的信息融合；然后，根据交通标志目标形状的特点，使用K-Means++算法产生先验框的初始聚类中心，并在边界框回归中引入距离交并比（DIOU）损失函数来将DIOU与非极大值抑制（NMS）结合；最后，将感兴趣区域（ROI）与上下文信息通过ROI Align统一尺寸后融合，从而增强目标特征表达。实验结果表明，所提算法性能更好，在长沙理工大学中国交通标志检测（CCTSDB）数据集上的平均准确率均值（mAP）可达96.20%。相较于Faster R-CNN、YOLOv3、Cascaded R-CNN检测算法，所提算法拥有具有更好的实时性和更高的检测精度，对各种环境变化具有更好的鲁棒性。

关键词: 目标检测, 特征融合, YOLOv3, 距离交并比, MobileNetv2, K-Means++

CLC Number:

TP391.4

Dawei ZHANG, Xuchong LIU, Wei ZHOU, Zhuhui CHEN, Yao YU. Real-time traffic sign detection algorithm based on improved YOLOv3[J]. Journal of Computer Applications, 2022, 42(7): 2219-2226.

张达为, 刘绪崇, 周维, 陈柱辉, 余瑶. 基于改进YOLOv3的实时交通标志检测算法[J]. 《计算机应用》唯一官方网站, 2022, 42(7): 2219-2226.

Figures/Tables 13

Fig.1 Bounding box coordinate transformation

Fig.2 Comparison of traditional convolution with depthwise separable convolution

Fig.3 Inverted residual structure

Fig.4 MN-YOLOv3 network structure

Fig. 5 GIOU loss bounding box regression effect

Fig.6 DIOU loss bounding box regression effect

Fig.7 Structure of adaptive feature fusion

Fig.8 CCTSDB dataset

Fig.9 Anchor box distribution

Fig.10 Data randomization

Tab.1 Results of ablation experiment on CCTSDB dataset

算法	Down-up	ASFF	DIOU	P/%	R/%	mAP@0.5/%
baseline				93.2	92.5	92.2
A	√			93.0	92.6	92.3
B		√		93.5	93.4	92.8
C			√	93.1	93.2	92.3
D	√	√		93.8	93.2	93.4
E	√		√	94.3	92.5	93.2
F		√	√	94.6	93.4	94.1
MN-YOLOv3	√	√	√	96.3	95.1	96.2

Tab.2 Comparison of experimental results on CCTSDB dataset

算法	P/%	R/%	mAP@0.5/%	FPS/（frame·s^-1）
YOLOv3	94.2	93.7	93.5	26.4
Faster R-CNN	94.5	95.2	94.6	14.5
Cascaded R-CNN	97.3	94.8	95.3	9.2
MN-YOLOv3	96.3	95.1	96.2	35.3

Fig.11 MN-YOLOv3 algorithm detection effects

References 21

1	REDMON J， FARHADI A. YOLOv3： an incremental improvement［EB/OL］. （2018-04-08）［2021-03-10］..
2	LI H J， QIU T S， SONG H Y， et al. A fast traffic signs detection method based on color segmentation and improved radial symmetry［J］. ICIC Express Letters， 2014， 8（8）： 2175-2180.
3	KAPLAN B， SELCAN G， HUSEYIN O， et al. On circular traffic sign detection and recognition［J］. Expert Systems with Applications， 2016， 48：67-75. 10.1016/j.eswa.2015.11.018
4	WANG J G， ZHOU L B. Traffic light recognition with high dynamic range imaging and deep learning［J］. IEEE Transactions on Intelligent Transportation Systems， 2019， 20（4）：1341-1352. 10.1109/tits.2018.2849505
5	ZHANG J M， XIE Z P， SUN J， et al. A cascaded R-CNN with multiscale attention and imbalanced samples for traffic sign detection［J］. IEEE Access， 2020， 8： 29742-29754. 10.1109/access.2020.2972338
6	GARCÍA-GARRIDO M Á， SOTELO M Á， MARTIN-GOROSTIZA E. Fast road sign detection using Hough transform for assisted driving of road vehicles［C］// Proceedings of the 2015 International Conference on Computer Aided Systems Theory， LNCS 3643. Berlin： Springer， 2005： 543-548.
7	REDMON J， DIVVALA S， GIRSHICK R， et al. You only look once： unified， real-time object detection［C］// Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2016： 779-788. 10.1109/cvpr.2016.91
8	REDMON J， FARHADI A. YOLO9000： better， faster， stronger［C］// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2017：6517-6525. 10.1109/cvpr.2017.690
9	SANDLER M， HOWARD A， ZHU M L， et al. MobileNetv2： inverted residuals and linear bottlenecks［C］// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2018：4510-4520. 10.1109/cvpr.2018.00474
10	任坤，黄泷，范春奇，等. 基于多尺度像素特征融合的实时小交通标志检测算法［J］. 信号处理， 2020， 36（9）：1457-1463 .
	REN K， HUANG L， FAN C Q， et al. Real-time small traffic sign detection algorithm based on multi-scale pixel feature fusion［J］. Journal of Signal Processing， 2020， 36（9）：1457-1463.
11	ZHENG Z H， WANG P， LIU W， et al. Distance-IoU loss： faster and better learning for bounding box regression［C］// Proceedings of the 34th AAAI Conference on Artificial Intelligence. Palo Alto， CA： AAAI Press， 2020：12993-13000. 10.1609/aaai.v34i07.6999
12	李震霄，孙伟，刘明明，等. 交通监控场景中的车辆检测与跟踪算法研究［J］. 计算机工程与应用， 2021， 57（8）：103-111.
	LI Z X， SUN W， LIU M M， et al. Research on vehicle detection and tracking algorithm in traffic monitoring scenes［J］. Computer Engineering and Applications， 2021， 57（8）：103-111.
13	蒋丽，薛善良.优化初始聚类中心及确定K值的K-means算法［J］. 计算机与数字工程， 2018， 46（1）：21-24， 113. 10.3969/j.issn.1672-9722.2018.01.006
	JIANG L， XUE S L. A K-means algorithm based on optimizing the initial clustering center and determining the K value ［J］. Computer and Digital Engineering， 2018， 46（1）： 21-24， 113. 10.3969/j.issn.1672-9722.2018.01.006
14	邓天民，周臻浩，方芳，等. 改进YOLOv3的交通标志检测方法研究［J］. 计算机工程与应用， 2020， 56（20）：28-35.
	DENG T M， ZHOU Z H， FANG F， et al. Research on improved YOLOV3 traffic sign detection method［J］. Computer Engineering and Applications， 2020， 56（20）： 28-35.
15	REZATOFIGHI H， TSOI N， GWAK J， et al. Generalized intersection over union： a metric and a loss for bounding box regression ［C］// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2019：658-666. 10.1109/cvpr.2019.00075
16	REN S Q， HE K M， GIRSHICK R， et al. Faster R-CNN： towards real-time object detection with region proposal networks［C］// Proceedings of the 28th International Conference on Neural Information Processing Systems. Cambridge： MIT Press， 2015：91-99.
17	LIU W， ANGUELOV D， ERHAN D， et al. SSD： single shot multiBox detector ［C］// Proceedings of the 2016 European Conference on Computer Vision， LNCS 9905. Cham： Springer， 2016： 21-37.
18	刘革，郑叶龙，赵美蓉. 基于RetinaNet改进的车辆信息检测［J］. 计算机应用， 2020， 40（3）：854-858.
	LIU G， ZHENG Y L， ZHAO M R. Vehicle information detection based on improved RetinaNet［J］. Journal of Computer Applications， 2020， 40（3）： 854-858.
19	候瑞环，杨喜旺，王智超，等. 一种基于YOLOv4-TIA的林业害虫实时检测方法［J］. 计算机工程， 2022， 48（4）：255-261.
	HOU R H， YANG X W， WANG Z C， et al. A real-time detection method of forestry pests based on YOLOV4-TIA［J］. Computer Engineering， 2022， 48（4）：255-261.
20	LIU S T， HUANG D， WANG Y H. Learning spatial fusion for single shot object detection［EB/OL］. （2019-11-21）［2021-03-10］..
21	CAI Z W， NUNO V. Cascade R-CNN： delving into high quality object detection［EB/OL］.［2017-12-03］.. 10.1109/cvpr.2018.00644

[1]	Yexin PAN, Zhe YANG. Optimization model for small object detection based on multi-level feature bidirectional fusion [J]. Journal of Computer Applications, 2024, 44(9): 2871-2877.
[2]	Yingjun ZHANG, Niuniu LI, Binhong XIE, Rui ZHANG, Wangdong LU. Semi-supervised object detection framework guided by curriculum learning [J]. Journal of Computer Applications, 2024, 44(8): 2326-2333.
[3]	Yeheng LI, Guangsheng LUO, Qianmin SU. Logo detection algorithm based on improved YOLOv5 [J]. Journal of Computer Applications, 2024, 44(8): 2580-2587.
[4]	Song XU, Wenbo ZHANG, Yifan WANG. Lightweight video salient object detection network based on spatiotemporal information [J]. Journal of Computer Applications, 2024, 44(7): 2192-2199.
[5]	Ruihua LIU, Zihe HAO, Yangyang ZOU. Gait recognition algorithm based on multi-layer refined feature fusion [J]. Journal of Computer Applications, 2024, 44(7): 2250-2257.
[6]	Xun SUN, Ruifeng FENG, Yanru CHEN. Monocular 3D object detection method integrating depth and instance segmentation [J]. Journal of Computer Applications, 2024, 44(7): 2208-2215.
[7]	Mengyuan HUANG, Kan CHANG, Mingyang LING, Xinjie WEI, Tuanfa QIN. Progressive enhancement algorithm for low-light images based on layer guidance [J]. Journal of Computer Applications, 2024, 44(6): 1911-1919.
[8]	Yue LIU, Fang LIU, Aoyun WU, Qiuyue CHAI, Tianxiao WANG. 3D object detection network based on self-attention mechanism and graph convolution [J]. Journal of Computer Applications, 2024, 44(6): 1972-1977.
[9]	Yaping DENG, Yingjiang LI. Review of YOLO algorithm and its applications to object detection in autonomous driving scenes [J]. Journal of Computer Applications, 2024, 44(6): 1949-1958.
[10]	Huantong GENG, Zhenyu LIU, Jun JIANG, Zichen FAN, Jiaxing LI. Embedded road crack detection algorithm based on improved YOLOv8 [J]. Journal of Computer Applications, 2024, 44(5): 1613-1618.
[11]	Xiaogang SONG, Dongdong ZHANG, Pengfei ZHANG, Li LIANG, Xinhong HEI. Real-time object detection algorithm for complex construction environments [J]. Journal of Computer Applications, 2024, 44(5): 1605-1612.
[12]	Xin LI, Qiao MENG, Junyi HUANGFU, Lingchen MENG. YOLOv5 multi-attribute classification based on separable label collaborative learning [J]. Journal of Computer Applications, 2024, 44(5): 1619-1628.
[13]	Guijin HAN, Xinyuan ZHANG, Wentao ZHANG, Ya HUANG. Self-supervised image registration algorithm based on multi-feature fusion [J]. Journal of Computer Applications, 2024, 44(5): 1597-1604.
[14]	Hongtian LI, Xinhao SHI, Weiguo PAN, Cheng XU, Bingxin XU, Jiazheng YUAN. Few-shot object detection via fusing multi-scale and attention mechanism [J]. Journal of Computer Applications, 2024, 44(5): 1437-1444.
[15]	Zhanjun JIANG, Baijing WU, Long MA, Jing LIAN. Faster-RCNN water-floating garbage recognition based on multi-scale feature and polarized self-attention [J]. Journal of Computer Applications, 2024, 44(3): 938-944.

Real-time traffic sign detection algorithm based on improved YOLOv3

基于改进YOLOv3的实时交通标志检测算法

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 13

References 21

Related Articles 15

Recommended Articles

Metrics