探地雷达多属性融合的隧道衬砌多目标检测方法

doi:10.13474/j.cnki.11-2246.2025.1006

测绘通报 ›› 2025, Vol. 0 ›› Issue (10): 30-35.doi: 10.13474/j.cnki.11-2246.2025.1006

• 学术研究 • 上一篇

探地雷达多属性融合的隧道衬砌多目标检测方法

赵亮¹, 唐禄怡¹, 刘世鹏²

1. 西安建筑科技大学信息与控制工程学院, 陕西西安 710055;
2. 西安建筑科技大学机电工程学院, 陕西西安 710055

收稿日期:2025-03-31 发布日期:2025-10-31
作者简介:赵亮(1981-),男,博士,教授,主要从事模式识别及智能检测系统科研工作。E-mail:zhaoliang@xauat.edu.cn
基金资助:
国家自然科学基金(51209167;52178393;51578447);西安市科学家+工程师队伍建设项目(2024JH-KGDW-0112);重点项目-实验室重点项目(2025SYS-SYSZD-049)

Ground penetrating radar multi-attribute fusion for multi-target detection of tunnel lining

ZHAO Liang¹, TANG Luyi¹, LIU Shipeng²

1. College of Information and Control Engineering, Xi'an University of Architecture and Technology, Xi'an 710055, China;
2. College of Mechanical and Electrical Engineering, Xi'an University of Architecture and Technology, Xi'an 710055, China

Received:2025-03-31 Published:2025-10-31

摘要/Abstract

摘要： 本文针对探地雷达图像特征复杂、病害检测精度低的问题,提出了一种多属性融合的隧道衬砌病害检测方法。通过提取雷达信号的瞬时振幅、瞬时相位和瞬时频率属性,结合波粒二象性理论设计Wave模块作为骨干网络,构建多模态特征融合框架。该方法采用金字塔结构分层提取底层和高层语义特征,并引入轻量级MLP架构优化网络动态性与计算效率。试验结果表明,融合瞬时属性与Wave模块的模型在空洞、不密实和钢筋网检测任务中平均精度均值(mAP)达到91.7%,较基线模型YOLOv8提升3.8%。消融试验与对比分析验证了多属性融合策略及Wave模块在增强特征表达能力方面的有效性,为隧道衬砌病害的精准无损检测提供了新思路。

关键词: 多属性融合, 探地雷达, Wave模块, 金字塔架构, 无损检测

Abstract: This paper addresses the issues of complex ground penetrating radar (GPR)image features and low accuracy in defect detection by proposing a multi-attribute fusion method for tunnel lining defect detection.By extracting instantaneous amplitude, instantaneous phase, and instantaneous frequency attributes of radar signals, combined with wave-particle duality theory to design a Wave module as the backbone network, a multi-modal feature fusion framework is constructed.The method employs a pyramid structure to extract low-level and high-level semantic features in layers, and introduces a lightweight MLP architecture to optimize network dynamics and computational efficiency.Experimental results demonstrate that the model fusing instantaneous attributes with the Wave module achieves a mean average precision (mAP)of 91.7%in cavity, loose, and steel detection tasks, an improvement of 3.8%compared to the baseline YOLOv8 model.Ablation experiments and comparative analysis verify the effectiveness of the multi-attribute fusion strategy and the Wave module in enhancing feature expression capability, providing a new approach for precise non-destructive detection of tunnel lining defects.

Key words: multi-attribute fusion, GPR, Wave module, pyramid architecture, non-destructive defection

中图分类号:

P237

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, 0(10): 30-35.

ZHAO Liang, TANG Luyi, LIU Shipeng. Ground penetrating radar multi-attribute fusion for multi-target detection of tunnel lining[J]. Bulletin of Surveying and Mapping, 2025, 0(10): 30-35.

参考文献

[1] XU Tianjia,YUAN Da,YANG Gexing,et al. FM-GAN: forward modeling network for generating approaching-reality B-scans of GPR pipelines with transformer tuning[J]. IEEE Transactions on Geoscience and Remote Sensing,2024,62:5102513. [2] LIU Zhen,GU Xingyu,WU Wenxiu,et al. GPR-based detection of internal cracks in asphalt pavement:a combination method of DeepAugment data and object detection[J]. Measurement,2022,197:111281. [3] LIN Y D,HSU Y C. Multihop cellular:a new architecture for wireless communications[C]//Proceedings of 19th Annual Joint Conference of the IEEE Computer and Communications Societies. Tel Aviv:IEEE,2000:1273-1282. [4] YANG Kaifu,LI Hui,KUANG Hulin,et al. An adaptive method for image dynamic range adjustment[J]. IEEE Transactions on Circuits and Systems for Video Technology,2019,29(3):640-652. [5] PACHORI R B. Time-frequency analysis techniques and their applications[M]. Boca Raton:CRC Press,2023. [6] MILLER S D,BANKERT R L,SOLBRIG J E,et al. A dynamic enhancement with background reduction algorithm:overview and application to satellite-based dust storm detection[J]. Journal of Geophysical Research:Atmospheres,2017,122(23):12,938-12,959. [7] JEON J,PARK J H,JEONG Y S. Dynamic analysis for IoT malware detection with convolution neural network model[J]. IEEE Access,2020,8:96899-96911. [8] LU Guoze,ZHAO Wenke,FORTE E,et al. Multi-frequency and multi-attribute GPR data fusion based on 2D wavelet transform[J]. Measurement,2020,166:108243. [9] CORBEANU R,MCMECHAN G A,SZERBIAK R B,et al. Prediction of 3D fluid permeability and mudstone distributions from ground-penetrating radar (GPR)attributes:Example from the Cretaceous Ferron Sandstone Member,east-central Utah[J]. 2002,67(5):1495-1504. [10] YUE Guanghua,DU Yuchuan,LIU Chenglong,et al. Road subsurface distress recognition method using multiattribute feature fusion with ground penetrating radar[J]. International Journal of Pavement Engineering,2023,24(2):1-13. [11] SOHAN M,SAI RAM T,RAMI REDDY C V. A review on YOLOv8 and its advancements[M]//Data Intelligence and Cognitive Informatics. Singapore:Springer Nature Singapore,2024:529-545. [12] DANESHGAR RAHBAR M,MOUSAVI MOJAB S Z. Enhanced U-Net with GridMask (EUGNet):a novel approach for robotic surgical tool segmentation[J]. Journal of Imaging,2023,9(12):282. [13] YUN S,HAN D,CHUN S,et al. CutMix:regularization strategy to train strong classifiers with localizable features[C]//Proceedings of 2019 IEEE/CVF International Conference on Computer Vision. Seoul:IEEE,2019:6022-6031. [14] 张世文,周涛,王阳,等. 基于希尔伯特-黄变换的覆土层厚度动态探测[J]. 农业机械学报,2023,54(3):338-346. [15] FENG Zhipeng,LIN Xuefeng,ZUO M J. Joint amplitude and frequency demodulation analysis based on intrinsic time-scale decomposition for planetary gearbox fault diagnosis[J]. Mechanical Systems and Signal Processing,2016,72:223-240. [16] TANG Yehui,HAN Kai,GUO Jianyuan,et al. An image patch is a wave:phase-aware vision MLP[C]//Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans:IEEE,2022:10925-10934. [17] LIU Wei,ANGUELOV D,ERHAN D,et al. SSD:single shot MultiBox detector[M]//Computer Vision - ECCV 2016. Cham:Springer International Publishing,2016:21-37. [18] REN Shaoqing,HE Kaiming,GIRSHICK R,et al. Faster R-CNN:towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149. [19] 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 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver,BC:IEEE,2023:7464-7475.

探地雷达多属性融合的隧道衬砌多目标检测方法

Ground penetrating radar multi-attribute fusion for multi-target detection of tunnel lining

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 8

编辑推荐

Metrics

本文评价

[1]	尹晓敏, 冉一丁, 娄凤强, 李晓东, 汤晓先, 郭鸣锐, 葛峻恺, 王晓龙, 孙怀凤. 探地雷达干涉噪声定位方法在输电线路勘察中的应用[J]. 测绘通报, 2025, 0(9): 146-151,156.
[2]	陈登峰, 何拓航, 杨小燕, 刘世鹏, 孟屯良. 路基病害雷达图像多视图融合识别方法[J]. 测绘通报, 2025, 0(5): 66-73.
[3]	张广伟. 一种探地雷达与深度学习的隧道衬砌健康评价方法[J]. 测绘通报, 2025, 0(3): 122-126,149.
[4]	谢小国, 罗兵, 黄长兵, 张玉玲, 杨生博. 基于三维探地雷达和PSO-ELM的地下病害体识别方法——以成都市金牛区为例[J]. 测绘通报, 2024, 0(8): 54-59.
[5]	周命端, 覃钰涵, 张文尧, 徐翔, 周庆辉. 塔式起重机垂直度激光雷达无损检测算法[J]. 测绘通报, 2024, 0(2): 90-94.
[6]	赵镇, 黄勇, 冯昆. 三维探地雷达在道路检测中的研究与应用[J]. 测绘通报, 2024, 0(2): 148-152.
[7]	王文龙, 胡庆武, 张菊, 赵鹏程, 艾明耀. 三维探地雷达体素化局部熵特征提取地下目标[J]. 测绘通报, 2024, 0(12): 6-10.
[8]	胡荣明, 李鑫, 竞霞, 武建强, 魏青博. YOLOv7在探地雷达B-Scan图像解译中的应用[J]. 测绘通报, 2023, 0(8): 29-33.