Intelligent detection of subsurface defects in ground penetrating radar images based on an improved YOLO11 network

doi:10.13474/j.cnki.11-2246.2026.0822

Abstract

Abstract: [Purposes] This paper aims to address the strong noise interference，blurred target edges，and high model complexity in the intelligent detection of ground penetrating radar (GPR)B-scan images. [Methods] This work proposed a lightweight underground defect detection method based on an improved YOLO11 framework.This approach integrates a dynamic convolution and adaptive down-sampling modules into the network architecture of YOLO11 to enhance feature extraction capability while preserving critical low-frequency information. [Findings] The experimental results demonstrate that the improved model of YOLO11_DA achieves a precision of 91.3%，recall of 86.1%，mAP_0.5 of 87.7%，and mAP_0.5：0.95 of 58.8%，while reducing parameters to 2.61×10⁶ and achieving an inference speed of 429.56 frames per second. [Conclusions] Compared to benchmark models including YOLOv5，YOLOv8，YOLOv10，and the original YOLO11，the proposed method maintains lightweight characteristics while exhibiting superior robustness and generalization capability in complex noise environments，weak echo conditions，and multi-scale target scenarios，which has provided an effective technical solution for intelligent detection of underground road defects．

Key words: underground road detection, ground penetrating radar, deep learning, YOLO11, C3k2_DynamicConv, ADown

CLC Number:

P25
P237

Huang Bin, Shi Guojie, Du Li, Wang Linke, Han Muyang, Peng Hongwei, Li Kefan, Li Jiaxi, Wang Jinguo, Hou Zhaoyang. Intelligent detection of subsurface defects in ground penetrating radar images based on an improved YOLO11 network[J]. Bulletin of Surveying and Mapping, 2026, 0(8): 154-160,173.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

URL: http://tb.chinasmp.com/EN/10.13474/j.cnki.11-2246.2026.0822

http://tb.chinasmp.com/EN/Y2026/V0/I8/154

References

[1] 交通运输部.2024年交通运输行业发展统计公报[EB/OL].[2025-06-12].https：//www.mot.gov.cn．
[2] Alani A M，Tosti F.GPR applications in structural detailing of a major tunnel using different frequency antenna systems[J].Construction and Building Materials，2018，158： 1111-1122．
[3] 赵亮，唐禄怡，刘世鹏.探地雷达多属性融合的隧道衬砌多目标检测方法[J].测绘通报，2025(10)： 30-35．
[4] Hou Feifei，Fang Mengqi，Xianghuan Luo T，et al.Dual-task GPR method： improved generative adversarial clutter suppression network and adaptive target localization algorithm in GPR image[J].IEEE Transactions on Geoscience and Remote Sensing，2024，62： 5108313．
[5] 范攀峰，黄日华，李绍建，等.基于探地雷达城市给排水管线渗漏及病害探测研究[J].测绘通报，2025(S1)： 97-103．
[6] Hou Feifei，Rui Xiyue，Fan Xinyu，et al.Review of GPR activities in civil infrastructures： data analysis and applications[J].Remote Sensing，2022，14(23)： 5972.
[7] Qin Hui，Xie Xiongyao，Vrugt J A，et al.Underground structure defect detection and reconstruction using crosshole GPR and Bayesian waveform inversion[J].Automation in Construction，2016，68： 156-169．
[8] 胡荣明，李鑫，竞霞，等.YOLOv7在探地雷达B-Scan图像解译中的应用[J].测绘通报，2023(8)： 29-33．
[9] 杨豪，郭凯丽，张军辉，等.基于YOLO11-L算法的道路内部空洞定量识别[J/OL].中国公路学报，1-18[2026-03-10].https：//link.cnki.net/urlid/61.1313.U.20250818.1134.002．
[10] 白桃，安奕铭，金光来，等.道路隐性病害三维探地雷达图谱轻量化识别改进算法[J].交通运输工程学报，2025，25(4)： 42-57．
[11] 王艾迪，彭一川，郎洪，等.基于YOLOX-Transformer两步模型的路面坑槽提取方法[J].中国公路学报，2023，36(12)： 304-317．
[12] 周中，周诗荣，李世帅，等.基于改进YOLOv7的隧道衬砌内部缺陷智能识别[J].铁道学报，2025，47(9)： 201-211．
[13] Yamaguchi T，Mizutani T，Meguro K，et al.Detecting subsurface voids from GPR images by 3D convolutional neural network using 2D finite difference time domain method[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing，2022，15： 3061-3073．
[14] Liu Bin，Ren Yuxiao，Liu Hanchi，et al.GPRInvNet： deep learning-based ground-penetrating radar data inversion for tunnel linings[J].IEEE Transactions on Geoscience and Remote Sensing，2021，59(10)： 8305-8325．
[15] 王惠琴，杨发东，何永强，等.面向探地雷达常见地下目标的GDS-YOLOv8n检测方法[J].雷达学报，2024，13(6)： 1170-1183．
[16] Han K，Wang Y，Guo J，et al.ParameterNet： parameters are all you need[C]//Proceedings of 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).Seattle：IEEE，2024．
[17] Wang C Y，Yeh I H，Mark Liao H Y.YOLOv9： learning what you want toLearn using programmable gradient information[C]//Proceedings of 2024 Computer Vision-ECCV.Cham：Springer，2025：1-21.