[1]张　蓓,徐　硕,钟燕辉,等.基于改进YOLOv8算法的半刚性基层松散病害识别方法[J].郑州大学学报(工学版),2025,46(05):122-129.[doi:10.13705/j.issn.1671-6833.2025.05.006]
　ZHANG Bei,XU Shuo,ZHONG Yanhui,et al.Detection Method of Loose Defects in Semi-rigid Base Based on Improved YOLOv8 Algorithm[J].Journal of Zhengzhou University (Engineering Science),2025,46(05):122-129.[doi:10.13705/j.issn.1671-6833.2025.05.006]
点击复制

基于改进YOLOv8算法的半刚性基层松散病害识别方法()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
46
期数:
2025年05期
页码:
122-129
栏目:
出版日期:
2025-08-10

文章信息/Info

Title:
Detection Method of Loose Defects in Semi-rigid Base Based on Improved YOLOv8 Algorithm
文章编号:
1671-6833(2025)05-0122-08
作者:
张　蓓;  徐　硕;  钟燕辉;  蔡鸿健;  臧全胜;  李晓龙
郑州大学 水利与交通学院,河南 郑州 450001
Author(s):
ZHANG Bei;  XU Shuo;  ZHONG Yanhui;  CAI Hongjian;  ZANG Quansheng;  LI Xiaolong
School of Water Conservaney and Transportation, Zhengzhou University, Zhengzhou 450001, China
关键词:
探地雷达;  改进YOLOv8;  松散病害;  深度学习;  目标检测
Keywords:
ground penetrating radar;  improved YOLOv8;  loose defects;  deep learning;  object detection
分类号:
TP391.41U416.217
DOI:
10.13705/j.issn.1671-6833.2025.05.006
文献标志码:
A
摘要:
针对目前复杂环境下探地雷达对路面松散病害的检测精度差、速度低等问题,提出了一种基于改进YOLOv8算法(YOLOv8-DN)的松散病害识别方法。所提方法针对性设计了DN模块替代C2f模块,该模块结合动态形变卷积模块和多尺度特征融合模块,使用动态形变卷积核的感受野以适应病害特征的形态复杂性,并利用多尺度特征融合路径提升模型对细小和模糊病害区域的捕捉能力。将原结构中的C2f模块替换为DN模块后,改进的YOLOv8-DN算法显著增强了对复杂病害的识别能力,且有效减少了计算开销。实验结果表明:相比原始YOLOv8算法,改进算法的mAP提升了5.29百分点,漏检率降低了5.2百分点,推理速度提高了4.9 帧/ms,且检测掩膜区域的完整性和准确性显著提高,证明了该算法的有效性和可行性,也为沥青路面半刚性基层松散病害的快速、精准检测提供了一种新的方法。
Abstract:
To address the issues of low detection accuracy and speed of ground-penetrating radar for loose defects under complex environmental conditions, a loose defect recognition method based on an improved YOLOv8 algorithm (YOLOv8-DN) was proposed. A DN module was designed and replaced C2f module, integrating a dynamic deformable convolution module and a multi-scale feature fusion module. The receptive fields of the dynamic deformable convolution kernels were adapted to accommodate the morphological complexity of defect features, while the multi-scale feature fusion path was employed to enhance the model′s ability to capture small and blurred defect regions. By replacing the original C2f module with the DN module, the recognition capability for complex defects was significantly improved, and computational overhead was effectively reduced. It was shown by experimental results that compared with the original YOLOv8 algorithm, the improved algorithm achieved a 5.29 percentage point increase in mAP, a 5.2 percentage point reduction in missed detection rate, and a 4.9 frame/ms improvement in inference speed. In addition, the integrity and accuracy of the detected mask regions were significantly enhanced, which validated the effectiveness and feasibility of the proposed algorithm and provided a novel solution for the rapid and precise detection of loose defects in the semi-rigid base layers of asphalt pavements.

参考文献/References:

[1]袁江, 程怀磊, 孙立军, 等. 基于温度应力分析的半刚性基层沥青路面拱胀病害成因[J]. 中国公路学报, 2024, 37(12): 182-196. 

YUAN J, CHENG H L, SUN L J, et al. Causes of arch expansion on semi-rigid base asphalt pavement based on temperature-stress analysis[J]. China Journal of Highway and Transport, 2024, 37(12): 182-196. 
[2]SUI X, LENG Z, WANG S Q, et al. In-situ grouting rate prediction of semi-flexible pavement based on a novel composite dielectric constant model and ground-penetrating radar[J]. Construction and Building Materials, 2024, 438: 137209.
[3]方宏远, 董智峰, 薛冰寒, 等. 高聚物注浆修复的面板堤坝探地雷达波场特征分析[J]. 郑州大学学报(工学版), 2024, 45(3): 1-6, 13. 
FANG H Y, DONG Z F, XUE B H, et al. Analysis of ground penetrating radar wave field characteristics of dam face disengaging repaired by polymer grouting[J]. Journal of Zhengzhou University (Engineering Science), 2024, 45(3): 1-6, 13. 
[4]GIRSHICK R. Fast R-CNN[EB/OL]. (2015-04-30) [2024-11-19]. https:∥doi. org/10. 48550/arXiv. 1504.08083. 
[5]REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]∥ 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2016: 779-788. 
[6]宋娟, 贺龙喜, 龙会平. 基于深度学习的隧道衬砌多病害检测算法[J]. 浙江大学学报(工学版), 2024, 58(6): 1161-1173. 
SONG J, HE L X, LONG H P. Deep learning-based algorithm for multi defect detection in tunnel lining[J]. Journal of Zhejiang University (Engineering Science), 2024, 58(6): 1161-1173. 
[7]叶发茂, 张立, 袁燎, 等. DB-YOLO: 特征增强融合的双骨干YOLOv8道路缺陷检测模型[J]. 计算机工程与应用, 2024, 60(24): 260-269. 
YE F M, ZHANG L, YUAN L, et al. DB-YOLO: dual backbone YOLOv8 model with feature enhancement fusion for road defect detection[J]. Computer Engineering and Applications, 2024, 60(24): 260-269. 
[8]申铉京, 李涵宇, 黄永平, 等. 基于自适应多尺度特征融合网络的车辆检测方法[J/OL]. 电子学报, 2023: 1-9(2023-03-31)[2024-11-19].:https:∥ kns.cnki.net/kcms/detail/11.2087. tn.20230330.1000. 056.html. 
SHEN X J, LI H Y, HUANG Y P, et al. Vehicle detection method based on adaptive multi-scale feature fusion network[J/OL]. China Industrial Economics, 2023: 19(2023-03-31)[2024-11-19].:https:∥kns. cnki. net/kcms/detail/11. 2087. tn. 20230330. 1000. 056. html. 
[9]赵平, 周永霞. 基于注意力机制的DA-YOLO缺陷检测算法[J]. 中国计量大学学报, 2024, 35(2): 326332, 348. 
ZHAO P, ZHOU Y X. A DA-YOLO defect detection algorithm based on the attention mechanism[J]. Journal of China University of Metrology, 2024, 35(2): 326332, 348. 
[10] SOHAN M, SAI RAM T, RAMI REDDY C V. A review on YOLOv8 and its advancements[C]∥Data Intelligence and Cognitive Informatics. New York: Springer, 2024: 529-545. 
[11] DING X H, ZHANG X Y, HAN J G, et al. Diverse branch block: building a convolution as an inception-like unit[C]∥2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2021: 10881-10890.
[12] YANG S M, CAO Z, LIU N B, et al. Maritime electrooptical image object matching based on improved YOLOv9 [J]. Electronics,2024, 13(14):2774. 
[13] LI X W, NI X B, CAO Z Y, et al. Detection method for power workers′ protection rope compliance based on improved YOLOv8[C]∥Advanced Intelligent Computing Technology and Applications. New York: Springer, 2024: 335-344. 
[14]郭士礼, 岳光华, 蔡文才, 等. 多相离散随机介质探地雷达波传输特性研究[J]. 地球物理学进展, 2021, 36(1): 351-360. 
GUO S L, YUE G H, CAI W C, et al. Study on transmission characteristics of GPR in multiphase discrete random medium[J]. Progress in Geophysics, 2021, 36 (1): 351-360. 
[15] ZHANG Y, GUO Z Y, WU J Q, et al. Real-time vehicle detection based on improved YOLO v5[J]. Sustainability, 2022, 14(19): 12274. 
[16]WANG C Y, BOCHKOVSKIY A, LIAO H M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for realtime object detectors[C]∥2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2023: 7464-7475.

相似文献/References:

[1]孟美丽,蔡迎春,高海彬..路用探地雷达的回波模拟[J].郑州大学学报(工学版),2002,23(02):44.[doi:10.3969/j.issn.1671-6833.2002.02.013]

更新日期/Last Update: 2025-09-19