Buried target detection method for ground penetrating radar based on deep learning

Abstract

Deep learning method has been extensively applied to ground penetrating radar twodimensional profile (GPR B-SCAN) hyperbola detection recently. We propose a B-SCAN image feature extraction method based on the constraints of the GPR physical model, and further detect the weak boundary feature curve of the target in the local space. A deep convolutional neural network (DCNN) is first designed to extract high-level semantic features from B-SCAN images to remove direct wave. Next, a multiscale feature fusion DCNN is used to extract the features of the B-SCAN image with the direct wave removed, and the classifier network is used to identify the hyperbola of the upper boundary feature of the target. Finally, according to the hyperbola, the local space corresponding to the target in the B-SCAN image is determined. On this basis, the amplitude and phase information of the scattered electric field are used to segment the lower boundary characteristic curve of the target through convolution operation. Experimental results on simulation and field data show that feature information of the buried target in the GPR B-SCAN image can be efficiently extracted when the proposed method is adopted. © The Authors. Published by SPIE under a Creative Commons Attribution 4.0 International License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

Buried object characterization by data-driven surrogates and regression-enabled hyperbolic signature extraction

“…In general form of relation between travelling time and the distance 8 , 18 , 20 , 40 is given in Eq. ( 1 ) indicating two-way travel time.…”

“…The response features extracted from the peaks and their locations within the subsequent 1D time-varying amplitude signals by means of principle component analysis (PCA), are employed to classify the material type into three groups by using k-nearest neighbor supervised learning classification algorithm 26 . Other Artificial Intelligence (AI) algorithms have been successfully used for buried target recognition in GPR images include Deep Learning (DL), especially Convolutional Neural Network (CNN) frameworks 14 – 16 , 18 , 19 , 21 . 3D GPR data generated along longitudinal and cross axes is analyzed in CNN and LSTM (Long Short-Term Memory) units combined into a framework of a cascaded structure for the detection of buried explosive objects and discrimination targets or non-target alarms 15 .…”

Buried Object Characterization Using Ground Penetrating Radar Assisted by Data-Driven Surrogate-Models

“…In this study, for the purpose of further verification of the proposed surrogate model, new data sets are generated by random noise addition [15,[22][23][24][25][26][27][28] to the generated raw Ascans. The literature offers different approaches to noise incorporation and for different purposes such as data augmentation [14,23,24,29], being closer to realistic scenarios [14,22,24,29,30] and obtaining further verification to test the sensitivity and stability of the considered models [15,[25][26][27][28]. The cases studied in [22,23] are arranged to bring the models closer to the real-time applications, specifically by considering noisy data sets.…”

“…Another technique is used as integration of the real background reflections with B-scans in order to generalize on realistic scenarios [14] as well as for data augmentation purpose. Application of a similar technique is explained in the study of buried target detection with deep learning [29] by using real background without targets and removed air-soil boundary reflections. Another approach is to replace randomly chosen pixels (typically, from 0.3% to 25% of the overall number of pixels) with white and black pixels to obtain noisy data and for further verification of their model in realistic scenarios by using noisy data [30].…”

“…The last state-of-the-art benchmark surrogate model is CNN, which is a technique derived from deep learning [6,12,13,29,33]. It takes its name from the convolutional layer, which is one of the main elements in the network, and has the ability to automatically extract the features owing to the convolution filter in this layer.…”