Blocked Traffic Sign Detection Algorithm Based on Improved YOLOv5s

doi:10.19678/j.issn.1000-3428.0069025

Abstract

Abstract:

The detection and recognition of road traffic signs are extremely important in intelligent driving. When traffic signs are obstructed, problems such as small targets and low detection accuracy occur. This paper proposes an improved model for obstructed traffic sign recognition based on YOLOv5s. To address the issue of a lack of dataset for traffic signs under occlusion, a self-made Chinese Occlusion Traffic Sign Dataset (COTSD) is developed. A backbone network based on MobileNetv2 improvement is proposed to extract rich discriminative features for fine-grained object detection. For small and obstructed traffic signs with low resolution, ordinary linear interpolation methods cannot capture higher-order and more detailed features; therefore, an improved Dynamic weight Upsampling Module (DEUM) is designed to integrate channel information weighted by channel attention for pixel rearrangement and generate high-resolution images. To address the sensitivity of loss functions such as CIoU (Complete IoU) to small target position changes, Normalized Gaussian Wasserstein Distance (NWD) is used to optimize the bounding box regression loss. For the self-made occluded COTSD dataset, the accuracy is 93.60%, recall is 72.50%, F1 value is 81.71%, and mAP@0.5 is 79%. For the publicly available CCTSDB dataset containing a small number of occluded traffic signs, the accuracy is 92.2%, recall is 78.8%, F1 value is 85%, and mAP@0.5 is 88.5%. The experimental results for the two datasets demonstrate that the improved algorithm can effectively improve the detection accuracy of traffic signs after occlusion.

Key words: traffic sign detection, occlusion conditions, MobileNetv2 model, Dynamic weight Upsampling Module (DEUM), Normalized Gaussian Wasserstein Distance (NWD)

摘要：

智能驾驶中道路交通标志的检测与识别极其重要, 针对交通标志被遮挡时存在目标小、检测精度低的问题, 提出一种基于改进YOLOv5s的被遮挡交通标志检测算法。通过自制中国遮挡交通标志数据集(COTSD), 解决交通标志在被遮挡情况下数据集缺乏的问题, 并根据细粒度物体检测需要模型提取丰富判别特征, 提出一种基于MobileNetv2改进的主干网络。针对交通标志较小、被遮挡且分辨率较低, 普通线性插值方式无法捕捉更高阶、更细节特征的问题, 设计一种改进的动态权重上采样模块(DEUM), 整合经过通道注意力加权之后的通道信息进行像素重排, 生成高分辨率图像; 针对综合交并比(CIoU)等损失函数对小目标位置变化敏感的问题, 使用归一化高斯Wassertein距离(NWD)来优化边界框回归损失。实验结果表明, 该算法在自制被遮挡COTSD上的准确率为93.60%, 召回率为72.50%, F1值为81.71%, mAP@0.5为79%;在包含少量被遮挡交通标志的公开CCTSDB上的准确率为92.2%, 召回率为78.8%, F1值为85%, mAP@0.5为88.5%。该算法有效提高了被遮挡后交通标志的检测精度。

关键词: 交通标志检测, 遮挡条件, MobileNetv2模型, 动态权重上采样模块, 归一化高斯Wassertein距离

LAN Zhangli, XING Caizhuo, ZHANG Hong. Blocked Traffic Sign Detection Algorithm Based on Improved YOLOv5s[J]. Computer Engineering, 2025, 51(5): 361-369.

蓝章礼, 邢彩卓, 张洪. 基于改进YOLOv5s的被遮挡交通标志检测算法[J]. 计算机工程, 2025, 51(5): 361-369.

/ Recommend / Download Citations

URL: https://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0069025

https://www.ecice06.com/EN/Y2025/V51/I5/361

Figures/Tables 15

Fig.1 The overall architecture of the network

Fig.2 Inverted residual structure

Fig.3 The schematic diagram of full dimensional dynamic convolution

Fig.4 DEUM module

Fig.5 Traffic sign categories

Fig.6 Dataset samples

Fig.7 Dataset sample distribution map

Fig.8 Target size distribution range map

Fig.9 Low, medium, and deep three-layer thermal maps

Fig.10 Visualization of detection results

Fig.11 Sample image of detection failure

References 27

1	刘振渤, 李慧, 刘桥缘, 等. 基于改进YOLOv5的交通标志小目标检测算法. 现代信息科技, 2024, 8(1): 94-98, 103.
	LIU Z B, LI H, LIU Q Y, et al. Traffic sign small target detection algorithm based on improved YOLOv5. Modern Information Technology, 2024, 8(1): 94-98, 103.
2	徐鑫, 方凯. 基于改进YOLOv5的小目标交通标志检测算法. 湖北汽车工业学院学报, 2023, 37(4): 17- 21.
	XU X, FANG K. Small target traffic sign detection algorithm based on improved YOLOv5. Journal of Hubei University of Automotive Industry, 2023, 37(4): 17- 21.
3	李孟歆, 李易营, 李松昂. 一种改进的YOLOv5小目标交通标志检测方法. 计算机仿真, 2023, 40(10): 152-156, 161.
	LI M X, LI Y Y, LI S A. Improved small target traffic sign detection algorithm based on YOLOv5. Computer Simulation, 2023, 40(10): 152-156, 161.
4	陈春辉, 马社祥. 基于新型算子采样优化的交通标志检测网络. 计算机工程, 2022, 48(10): 306- 312. doi: 10.19678/j.issn.1000-3428.0063188
	CHEN C H, MA S X. Traffic sign detection network based on new operator sampling optimization. Computer Engineering, 2022, 48(10): 306- 312. doi: 10.19678/j.issn.1000-3428.0063188
5	MANZARI O N, BOUDESH A, SHOKOUHI S B. Pyramid transformer for traffic sign detection[C]//Proceedings of the 12th International Conference on Computer and Knowledge Engineering. Washington D. C., USA: IEEE Press, 2022: 112-116.
6	张永亮, 陆阳, 朱芜强, 等. 基于多尺度特征提取与特征融合的交通标志检测. 计算机工程, 2022, 48(10): 270-278, 287. doi: 10.19678/j.issn.1000-3428.0062282
	ZHANG Y L, LU Y, ZHU W Q, et al. Traffic sign detection based on multi-scale feature extraction and feature fusion. Computer Engineering, 2022, 48(10): 270-278, 287. doi: 10.19678/j.issn.1000-3428.0062282
7	TABERNIK D, SKOCAJ D. Deep learning for large-scale traffic-sign detection and recognition. IEEE Transactions on Intelligent Transportation Systems, 2020, 21(4): 1427- 1440.
8	徐迪红. 复杂背景下的交通标志检测和分类算法研究[D]. 武汉: 武汉大学, 2010.
	XU D H. Research on traffic sign detection and classification algorithm under complex background[D]. Wuhan: Wuhan University, 2010. (in Chinese)
9	CHEN T Y, REN J T. MFL-YOLO: an object detection model for damaged traffic signs[EB/OL]. [2023-11-10]. https://arxiv.org/abs/2309.06750.
10	曾雷鸣, 侯进, 陈子锐, 等. 基于弱语义分割的轻量化交通标志检测网络. 计算机工程, 2022, 48(9): 269-276, 285. doi: 10.19678/j.issn.1000-3428.0062671
	ZENG L M, HOU J, CHEN Z R, et al. Lightweight traffic sign detection network based on weak semantic segmentation. Computer Engineering, 2022, 48(9): 269-276, 285. doi: 10.19678/j.issn.1000-3428.0062671
11	SANDLER M, HOWARD A, ZHU M L, et al. MobileNetV2: inverted residuals and linear bottlenecks[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2018: 3325-3336.
12	LI C, ZHOU A J, YAO A B. Omni-dimensional dynamic convolution[C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2022: 578-589.
13	WANG J W, XU C, YANG W, et al. A normalized Gaussian wasserstein distance for tiny object detection[EB/OL]. [2023-11-10]. https://arxiv.org/abs/2110.13389v1.
14	SANDLER M, HOWARD A, ZHU M L, et al. MobileNetV2: inverted residuals and linear bottlenecks[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2018: 4510-4520.
15	CHEN J R, KAO S H, HE H, et al. Run, don't walk: chasing higher FLOPs for faster neural networks[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2023: 12021-12031.
16	LI Y X, HOU Q B, ZHENG Z H, et al. Large selective kernel network for remote sensing object detection[EB/OL]. [2023-11-10]. https://arxiv.org/abs/2303.09030v2.
17	WANG A, CHEN H, LIN Z J, et al. RepViT: revisiting mobile CNN from ViT perspective[EB/OL]. [2023-11-10]. https://arxiv.org/abs/2307.09283v8.
18	LIU X Y, PENG H W, ZHENG N X, et al. EfficientViT: memory efficient vision transformer with cascaded group attention[C]//Proceedings of IEEE/CVF Conferenceon Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2023: 14420-14430.
19	WOO S, DEBNATH S, HU R H, et al. ConvNeXt V2: co-designing and scaling ConvNets with masked autoencoders[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2023: 16133-16142.
20	REDMON J, FARHADI A. YOLOv3: an incremental improvement[EB/OL]. [2023-11-10]. https://arxiv.org/abs/1804.02767.
21	WANG C Y, BOCHKOVSKIY A, LIAO H M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2023: 7464-7475.
22	LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector[C]//Proceedings of European Conference on Computer Vision. Berlin, Germany: Springer, 2016: 21-37.
23	LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//Proceedings of IEEE International Conference on Computer Vision. Washington D. C., USA: IEEE Press, 2017: 2980-2988.
24	REN S, HE K, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137- 1149. doi: 10.1109/TPAMI.2016.2577031
25	BOCHKOVSKIY A, WANG C Y, LIAO H M. YOLOv4: optimal speed and accuracy of object detection[EB/OL]. [2023-11-10]. https://arxiv.org/abs/2004.10934v1.
26	PANG J M, CHEN K, SHI J P, et al. Libra R-CNN: towards balanced learning for object detection[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2019: 821-830.
27	ZHANG H K, CHANG H, MA B P, et al. Dynamic R-CNN: towards high quality object detection via dynamic training[C]//Proceedings of European Conference on Computer Vision. Berlin, Germany: Springer, 2020: 260-275.

[1]	SUN Ting, YANG Jie, LI Jiaxuan, WANG Yaozong. Optimization of YOLOv7 Road Sign Detection Algorithm for Low-Light Traffic Scenes [J]. Computer Engineering, 2025, 51(3): 342-351.
[2]	YUAN Yajian, MAO Li. A Lightweight Traffic Sign Detection Model with Enhanced Foregrounds [J]. Computer Engineering, 2025, 51(3): 54-63.
[3]	XIE Jing, DENG Yueming, WANG Runmin. Improved Traffic Sign Detection Algorithm Based on YOLOv8s [J]. Computer Engineering, 2024, 50(11): 338-349.
[4]	WANG Hanwen, GE Qing, ZHU Ningke, YU Pengfei. Chinese Traffic Sign Detection Algorithm in Natural Scenes [J]. Computer Engineering, 2024, 50(11): 327-337.
[5]	Jiahao LI, Weidong MIN, Jiongjin CHEN, Meng ZHU, Guowei ZHAN. A High Precision Traffic Sign Detection Model in Complex Scenes [J]. Computer Engineering, 2023, 49(11): 311-320.
[6]	ZENG Leiming, HOU Jin, CHEN Zirui, ZHOU Haoran. Lightweight Traffic Sign Detection Network Based on Weak Semantic Segmentation [J]. Computer Engineering, 2022, 48(9): 269-276,285.
[7]	CHEN Chunhui, MA Shexiang. Traffic Sign Detection Network Based on New Operator Sampling Optimization [J]. Computer Engineering, 2022, 48(10): 306-312.
[8]	ZHANG Yongliang, LU Yang, ZHU Wuqiang, WEI Xing, WEI Zhen. Traffic Sign Detection Based on Multi-Scale Feature Extraction and Feature Fusion [J]. Computer Engineering, 2022, 48(10): 270-278,287.
[9]	YU Chaochao,HOU Jin,HOU Changzheng. Traffic Sign Detection Based on Saliency Map and Fourier Descriptor [J]. Computer Engineering, 2017, 43(5): 28-34.
[10]	SHA Sha; XIAO Xue-gang. Traffic Sign Detection Method with Multi-channel Integration [J]. Computer Engineering, 2009, 35(6): 202-204.

Please choose a citation manager

Content to export