Ground Penetrating Radar Underground Target Detection Based on GPR-YOLOv5

doi:10.1109/ICICML60161.2023.10424750

	Ground Penetrating Radar Underground Target Detection Based on GPR-YOLOv5
	He, Yongqiang 1; Yang, Wanli 2; Luo, Jia 3; Li, Xiaojuan 1; Wang, Huiqing 3; Li, Jiahao 3
	2023
会议名称	2nd International Conference on Image Processing, Computer Vision and Machine Learning, ICICML 2023
会议录名称	2023 International Conference on Image Processing, Computer Vision and Machine Learning, ICICML 2023
页码	621-624
会议日期	November 3, 2023 - November 5, 2023
会议地点	Hybrid, Chengdu, China
会议录编者/会议主办者	IEEE
出版者	Institute of Electrical and Electronics Engineers Inc.
摘要	For the current Ground Penetrating Radar (GPR) image recognition problems such as low accuracy, this paper relies on the architecture of YOLOv5, ConvNeXt as the feature extraction network and proposes a new GPR image recognition network GPR-YOLOv5, and the common underground pipe corridors, underground cavities, galvanized water pipelines, PVC pipes and, etc were identified in the GPR images. The experimental results show that the recognition accuracy, average accuracy mean and F1 value of the GPR-YOLOv5 network are 93.21%, 92.46%, and 91.25%, respectively, when detecting and recognizing underground pipe corridors, underground voids, galvanized water transmission steel pipes and PVC pipes. Compared with YOLOv4 and YOLOv5 models, the proposed network has good recognition accuracy. © 2023 IEEE.
DOI	10.1109/ICICML60161.2023.10424750
收录类别	EI
语种	英语
EI入藏号	20241015683115
原始文献类型	Conference article (CA)
引用统计	无
文献类型	会议论文
条目标识符	https://ir.lut.edu.cn/handle/2XXMBERH/170014
专题	兰州理工大学
通讯作者	Wang, Huiqing
作者单位	1.Northwest Minzu University, School of Civil Engineering, Lanzhou; 730030, China; 2.Gansu Road and Bridge Highway Investment Co., Lanzhou; 730030, China; 3.Lanzhou University of Technology, School of Computing and Communications, Lanzhou; 730050, China
通讯作者单位	兰州理工大学
推荐引用方式 GB/T 7714	He, Yongqiang,Yang, Wanli,Luo, Jia,et al. Ground Penetrating Radar Underground Target Detection Based on GPR-YOLOv5[C]//IEEE:Institute of Electrical and Electronics Engineers Inc.,2023:621-624.