当前位置: 首页 >  论文展示 >  正文

A Deep Learning Approach for Urban Underground Objects Detection from Vehicle-Borne Ground Penetrating Radar Data in Real-time

石莹 2021-08-08 浏览

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七类典型目标(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400MHZ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,共包含七类目标,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400MHZ波段采集的GPR数据进行实验验证。实验结果表明,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。
本文提出的基于深度学习的GPR图像地下目标探测方法的流程如图1所示。
D1CA  
图1 卷积神经网络GPR图像地下目标检测框架
为验证本文方法的有效性,分别利用SIR-30车载GPR系统采集的深圳市彩田路中往返两条路线的GPR数据进行实验验证(如图2)。GPR采集原理如图3左所示,本次实验数据样例如图3右所示,其中图右侧单点波形对应红线标注位置。
DE9D  
图2 SIR-30车载雷达深圳市测试路段(谷歌地球)
643F  
图 3 SIR-30车载雷达工作原理及样例
本文的测试数据为SIR-30车载探地雷达系统以400MHZ频率获取的深圳市数据。图4为训练后的神经网络识别GPR波形图像数据中雨水井、稀疏/密集钢筋网、桥梁、金属/非金属管道、电缆等目标的实验结果。深度学习预测结果表明,本文提出的方法能够根据GPR图像对地下目标的类型与位置进行准确地探测与定位。
69F3  
(a)雨水井识别结果
656C  
(b)稀疏钢筋网识别结果
68A5  
(c)金属/非金属管道识别结果
9B6F  
(d)桥梁识别结果
6886  
(e)电缆识别结果
图 4 GPR图像地下目标识别结果

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 400MHZ 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 darknet53 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.