GPR B scan image analysis with deep learning methods. (1st December 2020)

• Record Type: Journal Article
• Authors: Ozkaya, Umut; Melgani, Farid; Belete Bejiga, Mesay; Seyfi, Levent; Donelli, Massimo
• Is Part Of: Measurement. Volume 165(2020)
• Publication Date: 2020-12-01
• Subjects: Buried object detection -- Convolutional Neural Network (CNN) -- Convolutional Support Vector Machine (CSVM) -- Ground Penetrating Radar B Scan (GPR B Scan); Weights and measures -- Periodicals; Measurement -- Periodicals; Measurement; Weights and measures; Periodicals; 530.8
• DOI: 10.1016/j.measurement.2020.107770
• Languages: English
• ISSNs: 0263-2241

Abstract

Highlights: GPR data is analyzed with deep neural network structure. Proposed CSVM models have higher performance than other deep learning methods. As seen in comparative results, proposed CSVM models have low computation time in training and testing process. In testing phase, simulation and real data were evaluated in proposed method. Machine learning algorithms have no enough performance to analyze GPR data. Abstract: In this paper, we propose a Convolutional Support Vector Machine (CSVM) network for the analysis of Ground Penetrating Radar B Scan (GPR B Scan) images. Similar to a Convolutional Neural Network (CNN) architecture, a CSVM is also a cascade of convolution and pooling layers. However, the main difference is that it utilizes linear Support Vector Machine (SVM) based filters to generate feature maps and follows a forward learning strategy. We applied proposed method for the classification of buried objects, shape type and soil type. We used simulated GPR B scan images to train the networks. Proposed method was tested on both simulated and real GPR B scan images. In addition, we conducted a comparative study of the CSVM method with the classical machine learning approaches and pre-trained CNN models. Experimental results show that the proposed method provides an improved classification performance while the computational complexity is low.