A Real-time Method For Landmine Detection Using Vehicle Array GPR

Ground Penetrating Radar (GPR) is an effective method to identify subsurface target. Using vehicle array GPR can quickly detect landmine targets. At the same time, it means processing data will need more quickly and more accurately. Here, we present a real-time landmine detection method used on a 3-dimensional (3-D) dataset of vehicle array GPR. Firstly, the preprocessing is operated in each channel (down-track direction) to prominent the abnormality. Then, the Histogram of Oriented Gradient (HOG) method and Support Vector Machine (SVM) are performed to flag potential locations of interest among the separated 2-dimensional (2-D) GPR image in the cross-track direction. Energy feature method is used to exclude non-mine targets. Thirdly, we use the weight judgment method to confirm targets. Finally, the location of the landmine is shown on the time slice. Experimental results show that the approach we presented can detect the landmine targets in real-time at 5km/h with a low false alarm rate.