GPR Pipeline Target Detection Based on Improved Cascade R-CNN
CSTR:
Author:
  • Article
  • | |
  • Metrics
  • |
  • Reference [22]
  • |
  • Related [20]
  • | | |
  • Comments
    Abstract:

    As manual identification of ground-penetrating radar (GPR) pipeline images faces the problems of low efficiency, large errors, and high costs, this study proposes an intelligent pipeline target detection method based on improved Cascade R-CNN. First, the GPR pipeline image data set is preprocessed to improve data quality. ResNeXt is used instead of ResNet as the backbone network to extract target feature information, and a multi-scale feature fusion module FPN is added to fuse high-level features to low-level features to enhance the expressiveness of low-level features. Secondly, the Gaussian non-maximum suppression (NMS) method Soft-NMS is used to obtain more accurate candidate boxes, and Smooth_L1 is taken as the loss function, which accelerates model convergence and reduces the probability of gradient explosion during training. Finally, for the special shape features of the pipeline target, the appropriate aspect ratio and size of the anchor boxes are set to improve the quality of generated anchor boxes. The experimental results demonstrate that the proposed method achieves the intelligent detection of underground pipeline targets with complex features, and the average accuracy of target detection reaches 94.7%, which is 10.1% higher than that of the Cascade R-CNN method.

    Reference
    [1] 刘勇. 城市管理中地下管线检测的运用研究. 工程技术研究, 2020, 5(24): 172–173
    [2] 王建. 城市地下管网信息系统建设管理研究. 四川建材, 2018, 44(5): 253–254
    [3] 刘明珠. 关于混凝土钻芯取样的一些问题的探讨. 黑龙江科技信息, 2013, (7): 251
    [4] 刘永义, 杨磊, 王瑞芳. 探地雷达在地下管线探测中的应用. 全球定位系统, 2015, 40(3): 73–76. [doi: 10.13442/j.gnss.1008-9268.2015.03.019
    [5] Li TJ, Zhou ZO. Fast extraction of hyperbolic signatures in GPR. Proceedings of 2007 International Conference on Microwave and Millimeter Wave Technology. Guilin: IEEE, 2007. 1–3.
    [6] Liu YY, Wang MQ, Cai QR. The target detection for GPR images based on curve fitting. Proceedings of the 3rd International Congress on Image and Signal Processing. Yantai: IEEE, 2010. 2876–2879.
    [7] Pasolli E, Melgani F, Donelli M. Automatic analysis of GPR images: A pattern-recognition approach. IEEE Transactions on Geoscience and Remote Sensing, 2009, 47(7): 2206–2217. [doi: 10.1109/TGRS.2009.2012701
    [8] Delbo S, Gamba P, Roccato D. A fuzzy shell clustering approach to recognize hyperbolic signatures in subsurface radar images. IEEE Transactions on Geoscience and Remote Sensing, 2000, 38(3): 1447–1451. [doi: 10.1109/36.843039
    [9] Yang J, Wang LQ. Feature fusion and enhancement for single shot multibox detector. Proceedings of 2019 Chinese Automation Congress. Hangzhou: IEEE, 2019. 2766–2770.
    [10] Redmon J, Farhadi A. YOLOv3: An incremental improvement. arXiv: 1804.02767, 2018.
    [11] Zhao T, Liu JY, Duan ZQ. UAV target detection based on RetinaNet. Proceedings of 2019 Chinese Control and Decision Conference. Nanchang: IEEE, 2019. 3342–3346.
    [12] Ma L, Xu CF, Zuo GY, et al. Detection method of insulator based on Faster R-CNN. Proceedings of the 2017 IEEE 7th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems. Honolulu: IEEE, 2017. 1410–1414.
    [13] Jiang AF, Yan NN, Wang F. Visible image recognition of power transformer equipment based on mask R-CNN. Proceedings of 2019 IEEE Sustainable Power and Energy Conference. Beijing: IEEE, 2019. 657–661.
    [14] Bai RX, Cao H, Yu YJ, et al. Insulator fault recognition based on spatial pyramid pooling networks with transfer learning (Match 2018). Proceedings of the 3rd International Conference on Advanced Robotics and Mechatronics. Singapore: IEEE, 2018. 824–828.
    [15] 米宏涛. 基于探地雷达的地下管线正演模拟及探测研究[硕士学位论文]. 哈尔滨: 哈尔滨工业大学, 2020.
    [16] 胡浩帮, 方宏远, 王复明, 等. 基于Faster R-CNN算法的探地雷达管线目标智能识别. 城市勘测, 2020, (3): 203–208
    [17] 杨坤. 基于深度学习的地下管道雷达探测识别与检测研究[硕士学位论文]. 成都: 电子科技大学, 2022.
    [18] 胡浩帮, 方宏远, 王念念, 等. 基于Mobilenet-SSD的探地雷达管线目标智能识别研究. 城市勘测, 2022, (2): 164–167
    [19] Howard AG, Zhu ML, Chen B, et al. MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv: 1704.04861, 2017.
    [20] He KM, Zhang XY, Ren SQ, et al. Deep residual learning for image recognition. Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016. 770–778.
    [21] Szegedy C, Liu W, Jia YQ, et al. Going deeper with convolutions. Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston: IEEE, 2015. 1–9.
    [22] Szegedy C, Ioffe S, Vanhoucke V, et al. Inception-v4, inception-ResNet and the impact of residual connections on learning. Proceedings of the 31st AAAI Conference on Artificial Intelligence. San Francisco: AAAI, 2017. 4278–4284.
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation

来鹏飞,李伟,高尧,丁健刚,袁博,杨明.基于改进Cascade R-CNN的探地雷达管线目标检测.计算机系统应用,2023,32(2):102-110

Copy
Share
Article Metrics
  • Abstract:708
  • PDF: 1547
  • HTML: 1901
  • Cited by: 0
History
  • Received:July 04,2022
  • Revised:August 09,2022
  • Online: December 23,2022
Article QR Code
You are the first987196Visitors
Copyright: Institute of Software, Chinese Academy of Sciences Beijing ICP No. 05046678-3
Address:4# South Fourth Street, Zhongguancun,Haidian, Beijing,Postal Code:100190
Phone:010-62661041 Fax: Email:csa (a) iscas.ac.cn
Technical Support:Beijing Qinyun Technology Development Co., Ltd.

Beijing Public Network Security No. 11040202500063