一种增强前景的轻量级交通标志检测模型

doi:10.19678/j.issn.1000-3428.0069042

摘要/Abstract

摘要：

交通标志检测在辅助驾驶中扮演着不可或缺的角色, 为安全驾驶提供了至关重要的支持。在实际交通环境中, 在黑夜或雨天产生的背景噪声会加大交通标志检测的难度。现有模型往往难以有效检出远处的小目标交通标志, 此外, 在设计交通标志检测模型时应当考虑到实际部署对模型体积的要求。为此, 在YOLOv8的基础上提出一种增强前景的轻量级交通标志目标检测模型。首先, 设计了1个轻量级的PC2f模块替换掉原本Backbone中的部分C2f模块, 该模块降低了模型的参数量和计算量, 在保留更多浅层信息的同时进一步丰富了梯度流信息, 同时实现了模型轻量化和提升检测性能; 其次, 设计了前景增强模块(FEM)并将其引入Neck位置, 该模块能够有效放大前景信息并减弱背景噪声; 最后, 增加了一层小目标检测层, 用于在高分辨率的图像上提取浅层特征, 加强模型对小目标交通标志的检测性能。实验结果表明, 优化后的模型在数据集CCTSDB 2021和GTSDB上的mAP₅₀分别达到了82.5%和95.3%, 相较于原模型分别提升了3.6和1百分点, 并且模型权重大小减小了0.22×10⁶。这些结果验证了所提模型在实际应用中的有效性。

关键词: 交通标志检测, 轻量化网络, 前景增强模块, 小目标检测, 黑夜场景目标检测

Abstract:

Traffic sign detection is crucial for assisted driving and plays a vital role in ensuring driving safety. However, in real-world traffic environments, factors such as darkness and rain create background noise that complicates the detection process. In addition, existing models often struggle to effectively detect small traffic signs from a distance. Furthermore, when a traffic sign detection model is designed, the model size must be considered for practical deployment. To address these challenges, this study proposes a lightweight traffic sign detection model based on YOLOv8 with enhanced foregrounds. First, a lightweight PC2f module is designed to replace a part of the C2f module in the original Backbone. This modification reduces the number of parameters and computational load, enriches the gradient flow, retains more shallow information, and ultimately enhances detection performance while maintaining a lightweight design. Next, the study designs a Foreground Enhancement Module (FEM) and incorporates it into the Neck position to effectively amplify the foreground information and reduce background noise. Finally, the study adds a small-target detection layer to extract shallow features from high-resolution images, thereby improving the ability of the model to detect small-target traffic signs. Experimental results show that the optimized model achieves a mAP₅₀ of 82.5% and 95.3% on the CCTSDB 2021 and GTSDB datasets, which is an improvement of 3.6 and 1 percentage points over the original model, respectively, with a reduction in model weight size by 0.22×10⁶. These results confirm the effectiveness of the proposed model for practical applications.

Key words: traffic sign detection, lightweight network, Foreground Enhancement Module (FEM), small target detection, dark scene target detection

袁亚剑, 毛力. 一种增强前景的轻量级交通标志检测模型[J]. 计算机工程, 2025, 51(3): 54-63.

YUAN Yajian, MAO Li. A Lightweight Traffic Sign Detection Model with Enhanced Foregrounds[J]. Computer Engineering, 2025, 51(3): 54-63.

https://www.ecice06.com/CN/Y2025/V51/I3/54

图/表 18

图1 模型结构示意图

Fig.1 Schematic diagram of model structure

图2 部分卷积结构示意图

Fig.2 Schematic diagram of the partial convolution structure

图3 PC2f结构示意图

Fig.3 Schematic diagram of PC2f structure

图4 FEM结构示意图

Fig.4 Schematic diagram of FEM structure

图5 交通场景

Fig.5 Traffic scenario

图6 交通标志示例

Fig.6 Example of traffic signs

图7 改进前后的模型在小目标中的检测结果对比

Fig.7 Comparison of detection results in small targets before and after model improvement

图8 模型改进前后在黑夜环境下的检测结果对比

Fig.8 Comparison of detection results in night environment before and after model improvement

图9 模型改进前后在雨天条件下的检测结果对比

Fig.9 Comparison of detection results under rainy conditions before and after model improvement

图10 各模型的检测结果对比

Fig.10 Comparison of detection results of each model

参考文献 31

1	BENALLAL M, MEUNIER J. Real-time color segmentation of road signs[C]//Proceedings of Canadian Conference on Electrical and Computer Engineering. Washington D. C., USA: IEEE Press, 2003: 1823-1826.
2	MALIK R, KHURSHID J, AHMAD S N. Road sign detection and recognition using color segmentation, shape analysis and template matching[C]//Proceedings of International Conference on Machine Learning and Cybernetics. Washington D. C., USA: IEEE Press, 2007: 3556-3560.
3	JEON W J, SANCHEZ G A R, LEE T, et al. Real-time detection of speed-limit traffic signs on the real road using Haar-like features and boosted cascade[C]//Proceedings of the 8th International Conference on Ubiquitous Information Management and Communication. Washington D. C., USA: IEEE Press, 2014: 1-5.
4	BOUJEMAA K S, BERRADA I, BOUBOUH A, et al. Traffic sign recognition using convolutional neural networks[C]//Proceedings of 2017 International Conference on Wireless Networks and Mobile Communications. Washington D. C., USA: IEEE Press, 2017: 1-6.
5	WANG F, LI Y D, WEI Y C, et al. Improved Faster RCNN for traffic sign detection[C]//Proceedings of the 23rd International Conference on Intelligent Transportation Systems (ITSC). Washington D. C., USA: IEEE Press, 2020: 1-6.
6	WEI H Y , ZHANG Q Q , QIAN Y R , et al. MTSDet: multi-scale traffic sign detection with attention and path aggregation. Applied Intelligence, 2023, 53, 238- 250. doi: 10.1007/s10489-022-03459-7
7	李嘉豪, 闵卫东, 陈炯缙, 等. 一种复杂场景下高精度交通标志检测模型. 计算机工程, 2023, 49 (11): 311- 320. doi: 10.19678/j.issn.1000-3428.0066372
	LI J H , MIN W D , CHEN J J , et al. A high precision traffic sign detection model in complex scense. Computer Engineering, 2023, 49 (11): 311- 320. doi: 10.19678/j.issn.1000-3428.0066372
8	HOU Q B, ZHOU D Q, FENG J S. Coordinate attention for efficient mobile network design[C]//Proceedings of Conference on Computer Vision and Pattern Recognition (CVPR). Washington D. C., USA: IEEE Press, 2021: 13708-13717.
9	GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2014: 580-587.
10	GIRSHICK R. Fast R-CNN[C]//Proceedings of 2015 IEEE International Conference on Computer Vision (ICCV). Washington D. C., USA: IEEE Press, 2015: 1440-1448.
11	REN S Q , HE K M , 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
12	REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Washington D. C., USA: IEEE Press, 2017: 6517-6525.
13	REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Washington D. C., USA: IEEE Press, 2017: 6517-6525.
14	REDMON J, FARHADI A. YOLOv3: an incremental improvement. [EB/OL]. [2023-11-12]. https://arxiv.org/pdf/1804.02767.
15	BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4: optimal speed and accuracy of object detection. [EB/OL]. [2023-11-12]. https://arxiv.org/abs/2004.10934.
16	LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[EB/OL]. [2023-11-12]. https://link.springer.com/content/pdf/10.1007/978-3-319-46448-0_2.pdf.
17	王朕, 李豪, 严冬梅, 等. 基于改进YOLOv5的路面病害检测模型. 计算机工程, 2023, 49 (2): 15- 23. doi: 10.19678/j.issn.1000-3428.0064924
	WANG Z , LI H , YAN D M , et al. Pavement disease detection model based on improved YOLOv5. Computer Engineering, 2023, 49 (2): 15- 23. doi: 10.19678/j.issn.1000-3428.0064924
18	李松江, 耿兰兰, 王鹏. 基于改进Yolov4的车辆目标检测. 计算机工程, 2023, 49 (4): 272- 280. doi: 10.13364/j.issn.1672-6510.20220180
	LI S J , GENG LL , WANG P . Vehicle target detection based on improved Yolov4. Computer Engineering, 2023, 49 (4): 272- 280. doi: 10.13364/j.issn.1672-6510.20220180
19	贵向泉, 刘世清, 李立, 等. 基于改进YOLOv8的景区行人检测算法. 计算机工程, 2024, 50 (7): 342- 351. doi: 10.19678/j.issn.1000-3428.0068125
	GUI X Q , LIU S Q , LI l , et al. Pedestrian detection algorithm for scenic spots based on improved YOLOv8. Computer Engineering, 2024, 50 (7): 342- 351. doi: 10.19678/j.issn.1000-3428.0068125
20	WANG G , CHEN Y F , AN P , et al. UAV-YOLOv8: a small-object-detection model based of improved YOLOv8 for UAV aerial photography scenarios. Sensors, 2023, 23 (16): 7190. doi: 10.3390/s23167190
21	LIN T Y, DOLLÁR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Washington D. C., USA: IEEE Press, 2017: 2117-2125.
22	LIU S, QI L, QIN H, et al. Path aggregation network for instance segmentation[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2018: 8759-8768.
23	HAN K, WANG Y, TIAN Q, et al. GhostNet: more features from cheap operations[C]//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D. C., USA: IEEE Press, 2020: 1577-1586.
24	CHEN J R, KAO S H, HE H, et al. Run, don't walk: chasing higher FLOPS for faster neural networks[C]//Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Washington D. C., USA: IEEE Press, 2023: 12021-12031.
25	ZHU X K, LYU S C, WANG X, et al. TPH ‐YOLOv5: improved YOLOv5 based on transformer prediction head for object detection on drone‐captured scenarios[C]//Proceedings of IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). Washington D. C., USA: IEEE Press, 2021: 2778-2788.
26	ZHANG J M , ZOU X , KUANG Y , et al. CCTSDB 2021: a more comprehensive traffic sign detection benchmark. Human-centric Computing and Information Sciences, 2022, 12 (23): 11- 19.
27	LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[C]//Proceedings of 2017 IEEE International Conference on Computer Vision(ICCV). Washington D. C., USA: IEEE Press, 2017: 2999-3007.
28	PANG J M, CHEN K, SHI J P, et al. Libra R-CNN: towards balanced learning for object detection[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Washington D. C., USA: IEEE Press, 2019: 821-830.
29	SUN P, ZHANG R, JIANG Y, et al. Sparse R-CNN: end-to-end object detection with learnable proposals[C]//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR). Washington D. C., USA: IEEE Press, 2021: 14449-14458.
30	CAI Z, VASCONCELOS N. Cascade R-CNN: delving into high quality object detection[C]//Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington D. C., USA: IEEE Press, 2018: 6154-6162.
31	REN K , HUANG L , FAN C Q , et al. Real-time traffic sign detection network using DS-DetNet and lite fusion FPN. Journal of Real-Time Image Processing, 2021, 18 (6): 2181- 2191. doi: 10.1007/s11554-021-01102-1

[1]	孙亭, 杨洁, 李家璇, 王耀宗. 面向弱光交通场景的YOLOv7道路标志检测算法优化[J]. 计算机工程, 2025, 51(3): 342-351.
[2]	刘圣杰, 何宁, 王鑫, 于海港, 韩文静. 基于轻量级高分辨率网络的人体姿态估计算法[J]. 计算机工程, 2025, 51(2): 278-288.
[3]	孙浩淼, 李宗民, 肖倩, 孙文洁, 张雯欣. AI-Curling: 一种冰壶现场分析与决策方法[J]. 计算机工程, 2025, 51(2): 102-110.
[4]	火久元, 苏泓瑞, 武泽宇, 王婷娟. 基于改进YOLOv8的道路交通小目标车辆检测算法[J]. 计算机工程, 2025, 51(1): 246-257.
[5]	张倡倡, 吕卫东, 蔡子杰, 刘炎奎. 基于域泛化的轻量化图像分类算法[J]. 计算机工程, 2025, 51(1): 182-189.
[6]	张天鹏, 韩晶, 吕学强. 基于多任务学习的超分辨率辅助小目标检测[J]. 计算机工程, 2024, 50(9): 304-312.
[7]	贵向泉, 刘世清, 李立, 秦庆松, 李唐艳. 基于改进YOLOv8的景区行人检测算法[J]. 计算机工程, 2024, 50(7): 342-351.
[8]	谭若琦, 董明刚, 赵唯肖, 武天昊. 基于语义对齐和层次优化的非机动车车牌识别定位方法[J]. 计算机工程, 2024, 50(11): 142-151.
[9]	谢竞, 邓月明, 王润民. 改进YOLOv8s的交通标志检测算法[J]. 计算机工程, 2024, 50(11): 338-349.
[10]	王翰文, 葛青, 朱宁可, 余鹏飞. 自然场景下的中国交通标志检测算法[J]. 计算机工程, 2024, 50(11): 327-337.
[11]	圣文顺, 余熊峰, 林佳燕, 陈欣. 融合注意力与特征金字塔的小尺度目标检测算法[J]. 计算机工程, 2024, 50(1): 242-250.
[12]	蒋心璐, 陈天恩, 王聪, 赵春江. 大田环境下的农业害虫图像小目标检测算法[J]. 计算机工程, 2024, 50(1): 232-241.
[13]	李嘉新, 侯进, 盛博莹, 周宇航. 基于改进YOLOv5的遥感小目标检测网络[J]. 计算机工程, 2023, 49(9): 256-264.
[14]	吴珊, 周凤. 基于改进SSD算法的小目标检测[J]. 计算机工程, 2023, 49(7): 179-188.
[15]	谌雨章, 黄逸姿, 张钧涵. 基于多速率空洞卷积的多尺度水下小目标检测[J]. 计算机工程, 2023, 49(6): 257-264.

选择文件类型/文献管理软件名称

选择包含的内容