测绘学报 ›› 2020, Vol. 49 ›› Issue (7): 874-882.doi: 10.11947/j.AGCS.2020.20190293

• 摄影测量学与遥感 • 上一篇    下一篇

车载探地雷达地下目标实时探测法

杨必胜1,2, 宗泽亮1,2, 陈驰1,2, 孙文鹿1,2, 米晓新1,2, 吴唯同1,2, 黄荣刚3   

  1. 1. 武汉大学测绘遥感信息工程国家重点实验室, 湖北 武汉 430079;
    2. 武汉大学时空数据智能获取技术与应用教育部工程研究中心, 湖北 武汉 430079;
    3. 中国科学院大地测量与地球物理研究所, 湖北 武汉 430079
  • 收稿日期:2019-07-09 修回日期:2020-05-07 发布日期:2020-07-14
  • 通讯作者: 陈驰 E-mail:chichen@whu.edu.cn
  • 作者简介:杨必胜(1974-),男,博士,教授,研究方向为摄影测量。E-mail:bsyang@whu.edu.cn
  • 基金资助:
    国家自然科学基金(41701530;41725005;41531177);中国博士后科学基金(2018T110802);中国南方电网公司科学技术项目(ZBKJXM20170229)

Real time approach for underground objects detection from vehicle-borne ground penetrating radar

YANG Bisheng1,2, ZONG Zeliang1,2, CHEN Chi1,2, SUN Wenlu1,2, MI Xiaoxin1,2, WU Weitong1,2, HUANG Ronggang3   

  1. 1. State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China;
    2. Engineering Research Center of Space-Time Data Capturing and Smart Application, the Ministry of Education of P. R. C., Wuhan University, Wuhan 430079, China;
    3. State Key Laboratory of Geodesy and Earth's Dynamics, Institute of Geodesy and Geophysics of CAS, Wuhan 430077, Chinat
  • Received:2019-07-09 Revised:2020-05-07 Published:2020-07-14
  • Supported by:
    The National Natural Science Foundation Project of China (Nos. 41701530;41725005;41531177);China Postdoctoral Science Found (No. 2018T110802);China Southern Power Grid Corporation Science and Technology Project (No. ZBKJXM20170229)

摘要: 中国的城镇化加快了地下空间大规模开发与利用的进程。摸清地下空间目标的分布状况,保障城市可持续发展和地下空间资源的永久利用,是维护未来城市安全中的重要任务。探地雷达(GPR)凭借其数据采集速度快、成像分辨率高、无损检测等优点在地下空间资源调查中得以广泛应用。但仍存在GPR数据地下目标识别不准确、自动化程度低等缺陷,自动检测GPR数据中的地下目标或目标缺陷仍然是一个亟待解决的难题。为此,本文分析并确定了GPR影像中可进行识别的城市道路地下空间的7类典型目标(如雨水井、电缆等)。并根据其反射信号特征,标记了GSSI SIR30设备以400 MHz波段采集的GPR数据中的典型地下目标,构建了GPR地下目标样本库,共包含7类总数为3033个。通过迁移学习的方法,精调预训练后的darknet53网络参数,通过端到端的YOLOV3检测方法完成地下目标的自动识别与定位。最后,利用深圳福田区彩田路GSSI SIR30装备以400 MHz波段采集的GPR数据进行试验验证。试验结果表明,本文提出的基于深度学习的地下目标探测方法对城市典型地下目标的检测精度和召回率达到85%以上,检测速度达到了16帧/秒,能够有效探测GPR数据中的城市地下目标。

关键词: 探地雷达, 地下目标探测, 卷积神经网络, 深度学习, 城市空间安全

Abstract: Urbanization has triggered great development and changes in underground space. Exploring the types and positions of underground targets is of vital importance to urban underground security and utilization. GPRs (ground penetrating radar) are widely used in exploring underground space because of its advantages of rapid data collection, convenience, high imaging resolution and non-destructive inspection. However, the heavy manual interpretation costs of object detection from GPR limit the GPR applications in large-scale urban underground objects detection. This paper analyzes and determines seven typical types of urban road underground target that can be detected in GPR images (e.g. rainwater wells, cables, etc.). According to the characteristics of its reflected signals, the underground target in the GPR data of the 400 MHz band acquired by GSSI SIR30 in a typical urban road environment are labeled to construct the training dataset with seven categories and 3033 training samples. With the transfer learning method, the pre-trained Darknet 53 network parameters are fine-tuned, and the end-to-end YOLOV3 detection method is used to automatically extract and locate the underground targets. Finally, the experimental verification was carried out using the GPR data of the 400 MHz band collected by GSSI SIR30 in Caitian Road, Futian District, Shenzhen. Experiments show that the proposed deep learning detection method detects the buried objects from GRP data effectively, in terms of 85% of recall and precision,and the detection speed of 16FPS.

Key words: ground penetrating radar, underground object detection, convolutional neural network, deep learning, urban space security

中图分类号: