集成多维度注意力的地下病害图像分类网络

doi:10.3778/j.issn.1002-8331.2304-0175

摘要/Abstract

摘要： 探地雷达技术（ground penetrating radar，GPR）是一种利用高频超宽带信号探测地下目标和介质分布的勘探技术。具有无损、高效、高分辨率等优点，被广泛运用于城市道路的地下病害探测任务。GPR的B-scan图像反映地下结构的回波信息，是判定地下病害的主要依据；但相对于自然图像，除噪声较大外，其中同物异谱、异物同谱情况也十分普遍，导致人工解译困难。针对目前基于B-scan数据的地下病害自动分类方法精度较低，基于ResNeXt50结合多维度注意力机制和空洞空间金字塔池化，提出了MA-ResNeXt网络以实现地下病害的自动分类。模型训练、测试数据使用空洞（void）、脱空（cavity underneath pavement，CUP）和疏松（loosely infilled void，LIV）三种常见道路地下病害的真实探地雷达数据，分类准确率到达98.2%，实现了道路地下病害的自动识别。

关键词: 深度学习, 探地雷达, 地下病害

Abstract: Ground penetrating radar (GPR) is a non-destructive exploration technology that utilizes high-frequency ultra-wideband signals to detect the distribution of subsurface objects and media. Benefiting from the advantages of non-destructiveness, high efficiency, and high resolution, GPR has been widely applied in underground defect detection task of urban roads. Illustrating the radar echo wave of subsurface structure, GPR B-scan images are a main means to detect underground disaster; however, compared to natural images, automatic interpretation of GPR B-scan ones is a more challenging task because of same objects with different spectra, different objects with same spectrum as well as heavy noise pollution. Aiming to improve the accuracy of subsurface disasters detection methods, a disasters classification network, i.e., MA-ResNeXt, based on ResNetXt50 is proposed by combining multi-dimensional attention mechanism, atrous space pyramid pool and multi-scale feature extraction structure. The proposed network is trained and tested on real GPR B-scan images of three common subsurface disasters, e.g., void, cavity underneath pavement (CUP) and loosely infilled void (LIV). The comparison results show that classification accuracy of the proposed network approaches 98.2%, and illustrate that the network can effectively realize accurate classification of underground disasters.

Key words: deep learning, ground penetrating radar, underground disaster

张弓, 许明, 李开鹏, 王斌. 集成多维度注意力的地下病害图像分类网络[J]. 计算机工程与应用, 2024, 60(14): 105-113.

ZHANG Gong, XU Ming, LI Kaipeng, WANG Bin. Classification Network Integrated with Multidimensional Attention Strategy of Underground Disaster Images[J]. Computer Engineering and Applications, 2024, 60(14): 105-113.

参考文献

[1] DUDA R O, HART P E. Use of the Hough transformation to detect lines and curves in pictures[J]. Communications of the ACM, 1972, 15(1): 11-15.
[2] CORTES C, VAPNIK V. Support-vector networks[J]. Machine Learning, 1995, 20(3): 273-297.
[3] HOWARD A G, ZHU M, CHEN B, et al. MobileNets: efficient convolutional neural networks for mobile vision applications[J]. arXiv:1704.04861, 2017.
[4] SANDLER M, HOWARD A, ZHU M, et al. MobileNetV2: inverted residuals and linear bottlenecks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 4510-4520.
[5] HOWARD A, SANDLER M, CHU G, et al. Searching for MobileNetv3[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019: 1314-1324.
[6] ZHANG X, ZHOU X, LIN M, et al. ShuffleNet: an extremely efficient convolutional neural network for mobile devices[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018: 6848-6856.
[7] MA N N, ZHANG X, ZHENG H T, et al. ShuffleNet v2: practical guidelines for efficient CNN architecture design[C]//Proceedings of the 15th European Conference on Computer Vision, 2018: 116-131.
[8] 张宸嘉, 朱磊, 俞璐. 卷积神经网络中的注意力机制综述[J]. 计算机工程与应用, 2021, 57(20): 64-72.
ZHANG C J, ZHU L, YU L. Review of attention mechanism in convolutional neural networks[J]. Computer Engineering and Applications, 2021, 57(20): 64-72.
[9] 付国栋, 黄进, 杨涛, 等. 改进CBAM的轻量级注意力模型[J]. 计算机工程与应用, 2021, 57(20): 150-156.
FU G D, HUANG J, YANG T, et al. Improved lightweight attention model based on CBAM[J]. Computer Engineering and Applications, 2021, 57(20): 150-156.
[10] 孙萍, 胡旭东, 张永军. 结合注意力机制的深度学习图像目标检测[J]. 计算机工程与应用, 2019, 55(17): 180-184.
SUN P， HU X D， ZHANG Y J. Object detection based on deep learning and attention mechanism[J]. Computer Engineering and Applications, 2019, 55(17): 180-184.
[11] 李婕, 周顺, 朱鑫潮, 等. 结合多通道注意力的遥感图像飞机目标检测[J]. 计算机工程与应用, 2022, 58(1): 209-217.
LI J, ZHOU S, ZHU X C, et al. Remote sensing image aircraft target detection combined with multiple channel attention[J]. Computer Engineering and Applications, 2022, 58(1): 209-217.
[12] 徐诚极, 王晓峰, 杨亚东. Attention-YOLO: 引入注意力机制的YOLO检测算法[J]. 计算机工程与应用, 2019, 55(6): 13-23.
XU C J, WANG X F, YANG Y D. Attention-YOLO：YOLO detection algorithm that introduces attention mechanism[J]. Computer Engineering and Applications, 2019, 55(6): 13-23.
[13] 杨斌, 梁婧, 周佳薇, 等. 基于注意力机制的可解释点击率预估模型研究[J]. 计算机科学, 2023, 50(5): 12-20.
YANG B, LIANG J, ZHOU J W, et al. Study on interpreable click-through rate prediction based on attention mechanism[J]. Computer Science, 2023, 50(5): 12-20.
[14] 赵乐乐, 张丽萍, 赵凤荣. 基于注意力机制的Tree2Seq代码注释自动生成[J]. 计算机工程与科学, 2023, 45(4): 638-645.
ZHAO L L, ZHANG L P, ZHAO F R. Automatic code comment generation of Tree2Seq based on attention mechanism[J]. Computer Engineering & Science, 2023, 45(4): 638-645.
[15] 姜文涛, 赵琳琳, 涂潮. 双分支多注意力机制的锐度感知分类网络[J]. 模式识别与人工智能, 2023, 36(3): 252-267.
JIANG W T, ZHAO L L, XU C. Double-branch multi-attention mechanism based sharpness-aware classification network[J]. Pattern Recognition and Artificial Intelligence, 2023, 36(3): 252-267.
[16] BESAW L E, STIMAC P J. Deep convolutional neural networks for classifying GPR B-scans[C]//Proceedings of the International Society for Optical Engineering, 2015: 385-394.
[17] YAMASHITA R, NISHIIO M, DO R K G, et al. Convolutional neural networks: an overview and application in radiology[J]. Insights into Imaging, 2018, 9(4): 611-629.
[18] 张天助. 基于卷积神经网络的地下目标定位与介电常数估计研究[D]. 南昌: 南昌大学, 2019.
ZHANG T Z. Research on underground target location and dielectric constant estimation based on convolutional neural network[D]. Nanchang: Nanchang University, 2019.
[19] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.
[20] 赵迪, 叶盛波, 周斌. 基于 Grad-CAM 的探地雷达公路地下目标检测算法[J]. 电子测量技术, 2020(10): 113-118.
ZHAO D, YE S B, ZHOU B. Ground penetrating radar anomaly detection based on convolution Grad-CAM[J]. Electronic Measurement Technology, 2020(10): 113-118.
[21] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. arXiv:1409. 1556, 2014.
[22] 李姝凡. 基于探地雷达的混凝土内钢筋下病害识别方法研究[D]. 济南: 山东大学, 2020.
LI S F. Research on the identification method of diseases in concrete under reinforcement using GPR[D]. Jinan: Shandong University, 2020.
[23] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 770-778.
[24] LEI W, HOU F, XI J, et al. Automatic hyperbola detection and fitting in GPR B-scan image[J]. Automation in Construction, 2019, 106: 102839.
[25] LING J, QIAN R, SHANG K, et al. Research on the dynamic monitoring technology of road subgrades with time-lapse full-coverage 3D ground penetrating radar (GPR)[J]. Remote Sensing, 2022, 14(7): 1593.
[26] LI F, YANG F, YAN R, et al. Study on significance enhancement algorithm of abnormal features of urban road ground penetrating radar images[J]. Remote Sensing, 2022, 14(7): 1546.
[27] LI H, LI N, WU R, et al. GPR-RCNN: an algorithm of subsurface defect detection for airport runway based on GRP[J]. IEEE Robotics and Automation Letters, 2021, 6(2): 3001-3008.
[28] LIU Z, WU W, GU X, et al. Application of combining YOLO models and 3D GPR images in road detection and maintenance[J]. Remote Sensing, 2021, 13(6): 1081.
[29] SU Q, BI B, ZHANG P, et al. GPR image clutter suppression using Gaussian curvature decomposition in the PCA domain[J]. Remote Sensing, 2022, 14(19): 4879.
[30] KANG M S, KIM N, IM S B, et al. 3D GPR image-based UcNet for enhancing underground cavity detectability[J]. Remote Sensing, 2019, 11(21): 2545.
[31] LI S, GU X, XU X, et al. Detection of concealed cracks from ground penetrating radar images based on deep learning algorithm[J]. Construction and Building Materials, 2021, 273: 121949.
[32] REDMON J, FARHADI A. YOLOv3: an incremental improvement[J]. arXiv:1804.02767, 2018.
[33] BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4: optimal speed and accuracy of object detection[J]. arXiv:2004.10934, 2020.
[34] XIE S, GIRSHICK R, DOLLAR P, et al. Aggregated residual transformations for deep neural networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 1492-1500.
[35] WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision, 2018: 3-19.
[36] HOU Q, ZHOU D, FENG J. Coordinate attention for efficient mobile network design[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 13708-13717.
[37] CHEN L C, PAPANDREOU G, SCHROFF F, et al. Rethinking atrous convolution for semantic image segmentation[J]. arXiv:1706.05587, 2017.