首页>
外文期刊>生産研究
>Detection of Subsurface Void from Radar Images by Three-dimensional Convolutional Neural Network and Finite Difference Time Domain Method
【24h】
Detection of Subsurface Void from Radar Images by Three-dimensional Convolutional Neural Network and Finite Difference Time Domain Method
展开▼
机译:Detection of Subsurface Void from Radar Images by Three-dimensional Convolutional Neural Network and Finite Difference Time Domain Method
Ground Penetrating Radar (GPR) mounted on a vehicle as shown in Fig. 1 is a promising tool for detecting subsurface anomalies under the road. Radar is multi-channel. Pairs of transmitting and receiving antennas are aligned in a lane width direction. Scanning speed is around 80 km/h. Measured data is three-dimensional (3D) with centimeter-order resolutions in scanning, transverse, and depth directions. In this article, subsurface void is the target considering a rapidly raising social demand and safety of the road users because it leads to devastating accidents of road collapse.
展开▼