基于改进simAM-YOLOv8的路面多病害识别方法

doi:10.13229/j.cnki.jdxbgxb.20240586

吉林大学学报(工学版) ›› 2026, Vol. 56 ›› Issue (1): 219-230.doi: 10.13229/j.cnki.jdxbgxb.20240586

• 交通运输工程·土木工程 • 上一篇下一篇

基于改进simAM-YOLOv8的路面多病害识别方法

单飞^1,²(),李辉¹(),孙浩²,聂世刚²,申忠虎²

^1.同济大学道路与交通工程教育部重点实验室，上海 201804
^2.河南交通发展研究院有限公司，郑州 450066

收稿日期:2024-05-26 出版日期:2026-01-01 发布日期:2026-02-03
通讯作者: 李辉 E-mail:shanfei@tongji.edu.cn;hli@tongji.edu.cn
作者简介:单飞（1983-），男，博士研究生，正高级工程师.研究方向：智能交通，交通大数据，交通规划与管理. E-mail： shanfei@tongji.edu.cn
基金资助:
交通运输行业重点科技项目(2022-MS1-019);河南省交通运输科技计划项目(2022-5-6);河南省交通运输科技计划项目(2023-4-2)

Pavement distress identification method based on improved simAM-YOLOv8

Fei SHAN^1,²(),Hui LI¹(),Hao SUN²,Shi-gang NIE²,Zhong-hu SHEN²

^1.Key Laboratory of Road and Traffic Engineering，Ministry of Education，Tongji University，Shanghai 201804，China
^2.Henan Transportation Development Research Institute Co. ，Ltd. ，Zhengzhou 450066，China

Received:2024-05-26 Online:2026-01-01 Published:2026-02-03
Contact: Hui LI E-mail:shanfei@tongji.edu.cn;hli@tongji.edu.cn

摘要/Abstract

摘要：

针对道路路面病害数据多模态和识别准确率低的问题，提出了一种基于无参数注意力机制simAM改进YOLOv8的路面多病害识别算法。利用自有路面病害数据集，在YOLOv8结构中嵌入Res2Net，在计算负载量相似的基础上增强多规模特征提取能力；采用simAM模块进一步调整不同尺度特征图的权重，实现对目标的检测改善；利用遗传算法提升模型自动寻参速度，使用HSV以及Mosaic等图像增强手段扩充小样本病害。实验结果表明：改进后的simAM-YOLOv8算法对沥青、水泥等不同类型路面的裂缝、破碎板、修补等病害识别结果相较原网络精确率整体提升了15.3%，召回率整体提升了13.1%，表现出了较好的智能识别效果，可在公路路况自动化检测方面发挥重要作用。

关键词: 智能交通, 路面病害, 识别算法, simAM, YOLOv8, Res2Net

Abstract:

To solve the problems of multi-modal data and low recognition accuracy in road pavement distress detection， an improved pavement multi-distress recognition algorithm based on the YOLOv8 model enhanced with the non-parametric attention mechanism simAM is proposed. Utilizing the self-owned pavement distress dataset， Res2Net is embedded into the YOLOv8 structure to enhance multi-scale feature extraction capabilities while maintaining similar computational loads. The simAM module is employed to further adjust the weights of feature maps at different scales， improving the detection of targets. Genetic algorithm is used to increase the speed of automatic parameter searching for the model， and image enhancement techniques such as HSV and Mosaic are employed to expand the small sample distresss. Experimental results show that the improved simAM-YOLOv8 algorithm significantly improves accuracy and recall rates for various pavement distresss such as cracks， broken panels， repairs， etc.， on asphalt， cement， and other road surfaces. Specifically， the precision rate has increased by 15.3% and the recall rate has increased by 13.1% compared to the original network， demonstrating excellent intelligent recognition performance， and playing an important role in automated detection of highway conditions.

Key words: intelligent transportation, pavement distress, recognition algorithm, simAM, YOLOv8, Res2Net

中图分类号:

TP391.4

单飞,李辉,孙浩,聂世刚,申忠虎. 基于改进simAM-YOLOv8的路面多病害识别方法[J]. 吉林大学学报(工学版), 2026, 56(1): 219-230.

Fei SHAN,Hui LI,Hao SUN,Shi-gang NIE,Zhong-hu SHEN. Pavement distress identification method based on improved simAM-YOLOv8[J]. Journal of Jilin University(Engineering and Technology Edition), 2026, 56(1): 219-230.

参考文献 20

[1]	罗晖, 余俊英, 涂所成. 基于深度学习的公路路面病害检测算法[J]. 科学技术与工程, 2022, 22(13):5329-5305.
	Luo Hui, Yu Jun-ying, Tu Suo-cheng. Pavement defect detection algorithm based on deep learning[J]. Science Technology and Engineering, 2022, 22(13): 5329-5305.
[2]	Hou Y, Li Q, Zhang C, et al. The state-of-the-art review on applications of intrusive sensing, image processing techniques, and machine learning methods in pavement monitoring and analysis[J]. Engineering, 2021, 7(6): 845-856.
[3]	Cheng H, Wan F, Lei G,et al.GCS-YOLO: a lightweight strawberry disease detection algorithm based on improved YOLOv8[C]∥The 5th International Conference on Frontiers Technology of Information and Computer(ICFTIC), Qiangdao, China, 2023:1071-1076.
[4]	章世祥, 张汉成, 李西芝, 等. 基于机器视觉的路面裂缝病害多目标识别研究[J]. 公路交通科技, 2021, 38(3): 30-39.
	Zhang Shi-xiang, Zhang Han-cheng, Li Xi-zi,et al.Study on multi-objective identification of pavement cracks based on machine vision[J].Journal of Highway and Transportation Rresearch and Development,2021,38(3):30-39.
[5]	陈涵深. 基于深度学习的路面破损检测研究[D]. 杭州: 浙江工业大学信息工程学院, 2020.
	Chen Han-shen.Deep learning for pavement distress detection[D]. Hangzhou: College of Information Engineering,Zhejiang University of Technology, 2020.
[6]	魏陈浩, 杨睿, 刘振丙, 等. 具有双层路由注意力的YOLOv8道路场景目标检测方法[J]. 图学学报, 2023, 44(6): 1104-1111.
	Wei Chen-hao, Yang Rui, Liu Zhen-bing, et al. YOLOv8 with bi-level routing attention for road scene object detection[J]. Journal of Graphics, 2023, 44(6): 1104-1111.
[7]	侯越, 张慧婷, 高智伟, 等. 基于数据深度增强的路面病害智能检测方法研究及比较[J]. 北京工业大学学报, 2022, 48(6): 622-634.
	Hou Yue, Zhang Hui-ting, Gao Zhi-wei,et al.Research and comparison of intelligent detection methods of pavement distress based on deep data augmentation[J].Journal of Beijing University of Technology, 2022, 48(6): 622-634.
[8]	倪昌双, 李林, 罗文婷, 等. 改进YOLOv7的沥青路面病害检测[J]. 计算机工程与应用, 2023, 59(13): 305-316.
	Ni Chang-shuang, Li Lin, Luo Wen-ting, et al. Disease detection of asphalt pavement based on improved YOLOv7[J]. Computer Engineering and Applications, 2023, 59(13): 305-316.
[9]	田鹏, 毛力. 改进YOLOv8的道路交通标志目标检测算法[J]. 计算机工程与应用, 2024, 60(8): 202-212.
	Tian Peng, Mao Li. Improved YOLOv8 object detection algorithm for traffic sign target[J]. Computer Engineering and Applications, 2024, 60(8): 202-212.
[10]	Yang L, Zhang R Y, Li L, et al. Simam: a simple, parameter-free attention module for convolutional neural networks[C]∥International Conference On Machine Learning, Vienna, Austria, 2021: 11863-11874.
[11]	Xie J, Wu Z, Zhu R, et al. Melanoma detection based on swin transformer and SimAM[C]∥IEEE 5th Information Technology, Networking, Electronic and Automation Control Conference(ITNEC), Xi'an, China, 2021: 1517-1521.
[12]	韩强. 面向小目标检测的改进YOLOv8算法研究[D].长春: 吉林大学数学学院, 2024.
	Han Qiang. Research on improved YOLOv8 algorithm for small object detection[D].Changchun:School of Mathematics, Jilin University, 2024.
[13]	Du Y, Pan N, Xu Z, et al. Pavement distress detection and classification based on YOLO network[J]. International Journal of Pavement Engineering, 2021, 22(13): 1659-1672.
[14]	Jiang P, Ergu D, Liu F, et al. A review of YOLO algorithm developments[J]. Procedia Computer Science, 2022, 199: 1066-1073.
[15]	邹彦艳, 曹衍芬, 张馨月, 等. 基于 YOLOv8-DSG 的钢铁表面缺陷检测算法[J]. 吉林大学学报: 信息科学版, 2025, 43(1): 116-125
	Zou Yan-yan, Cao Yan-fen, Zhang Xin-yue, et al. Steel surface defect detection algorithm based on YOLOv8-DSG[J]. Journal of Jilin University(Information Science Edition), 2025, 43(1): 116-125.
[16]	Gao S H, Cheng M M, Zhao K, et al. Res2Net: a new multi-scale backbone architecture[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 43(2): 652-662.
[17]	Zhou Z, Wang Y, Feng C, et al. A moving ferromagnetic target localization method based on YOLO-V3[C]∥The 4th International Conference on Intelligent Control, Measurement and Signal Processing (ICMSP),Hangzhou,China,2022: 205-212.
[18]	李志慧, 钟涛, 赵永华, 等. 面向车辆自主驾驶的行人跟踪算法[J]. 吉林大学学报: 工学版, 2019, 49(3):680-687.
	Li Zhi-hui, Zhong Tao, Zhao Yong-hua, et al. Pedestrian tracking algorithm for autonomous vehicle driving[J]. Journal of Jilin University(Engineering and Technology Edition), 2019, 49(3): 680-687.
[19]	宗芳, 齐厚成, 唐明, 等. 基于GPS数据的日出行模式-出行目的识别[J]. 吉林大学学报: 工学版, 2018, 48(5): 1374-1379.
	Zong Fang, Qi Hou-cheng, Tang Ming, et al. Daily travel mode based on GPS data - travel purpose recognition[J]. Journal of Jilin University(Engineering and Technology Edition),2018, 48(5):1374-1379..
[20]	Arya D, Maeda H, Ghosh S K, et al.Rdd2022: a multi-national image dataset for automatic road damage detection[DB/OL].[2024-04-26]..

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于改进simAM-YOLOv8的路面多病害识别方法

Pavement distress identification method based on improved simAM-YOLOv8

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献 20

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	吴德华,陈荣峰. 智能网联客货混合交通流特性及集聚换道策略[J]. 吉林大学学报(工学版), 2025, 55(8): 2588-2596.
[2]	侯越,郭劲松,林伟,张迪,武月,张鑫. 分割可跨越车道分界线的多视角视频车速提取方法[J]. 吉林大学学报(工学版), 2025, 55(5): 1692-1704.
[3]	郭宁,胡小晨,董德存. 基于改进YOLO算法的地铁车厢客流检测方法[J]. 吉林大学学报(工学版), 2025, 55(4): 1258-1265.
[4]	江晟,王祎笛,谢睿麟,夏淼磊. 基于门控循环网络时空关联的交通事故预测模型[J]. 吉林大学学报(工学版), 2025, 55(3): 954-962.
[5]	李立,鲍宇健,杨文臣,楚庆玲,汪贵平. 路侧多源感知数据集规范化构建方法[J]. 吉林大学学报(工学版), 2025, 55(2): 529-536.
[6]	王喆,范文波,刘昕,杨欢,宋现敏,杨柏婷. 基于改进开普勒优化算法的区域停车分配模型[J]. 吉林大学学报(工学版), 2025, 55(12): 3907-3917.
[7]	程国柱,陈永胜. 智能网联环境下高速公路异质交通流建模及仿真[J]. 吉林大学学报(工学版), 2025, 55(11): 3583-3592.
[8]	杨楠,肖军. 序列二次规划算法下城市智能交通运行节能优化控制[J]. 吉林大学学报(工学版), 2024, 54(8): 2223-2228.
[9]	李立,吴晓强,杨文臣,周瑞杰,汪贵平. 基于路侧毫米波雷达的群体车辆目标识别与跟踪[J]. 吉林大学学报(工学版), 2024, 54(7): 2104-2114.
[10]	杨秀建,贾晓寒,张生斌. 考虑汽车队列动态特性的混合交通流特性[J]. 吉林大学学报(工学版), 2024, 54(4): 947-958.
[11]	高海龙,徐一博,侯德藻,王雪松. 基于深度异步残差网络的路网短时交通流预测算法[J]. 吉林大学学报(工学版), 2023, 53(12): 3458-3464.
[12]	高明华,杨璨. 基于改进卷积神经网络的交通目标检测方法[J]. 吉林大学学报(工学版), 2022, 52(6): 1353-1361.
[13]	邝先验,罗会超,钟蕊,欧阳鹏. 基于天牛须小波神经网络的公交到站时间预测[J]. 吉林大学学报(工学版), 2022, 52(1): 110-117.
[14]	张健,吴坤润,杨敏,冉斌. 智能网联环境下交叉口双环自适应控制模型[J]. 吉林大学学报(工学版), 2021, 51(2): 541-548.
[15]	赵宏伟, 刘宇琦, 董立岩, 王玉, 刘陪. 智能交通混合动态路径优化算法[J]. 吉林大学学报(工学版), 2018, 48(4): 1214-1223.