Implementation of and Experimentation with Ground-Penetrating Radar for Real-Time Automatic Detection of Buried Improvised Explosive Devices

Abstract

This paper proposes the implementation of and experimentation with GPR for real-time automatic detection of buried IEDs. GPR, consisting of hardware and software, was implemented. A UWB antenna was designed and implemented, particularly for the operation of the GPR. The experiments were conducted in order to demonstrate the real-time automatic detection of buried IEDs using GPR with an R-CNN algorithm. In the experiments, the GPR was mounted on a pickup truck and a maintenance train in order to find the IEDs buried under a road and a railway, respectively. B-scan images were collected using the implemented GPR. R-CNN-based detection for the hyperbolic pattern, which indicates the buried IED, was performed along with pre-processing, for example, using zero offset removal, and background removal and filtering. Experimental results in terms of detecting the hyperbolic pattern in B-scan images were shown and verified that the proposed GPR system is superior to the conventional one using region analysis processing-based detection. Results also showed that pre-processing is required in order to improve and/or clean the hyperbolic pattern before detection. The GPR can automatically detect IEDs buried under roads and railways in real time by detecting the hyperbolic pattern appearing in the collected B-scan image.

A Radar Echo Simulator for the Synthesis of Randomized Training Data Sets in the Context of AI-Based Applications

“…However, following the approach of transfer learning in the introduction, it is not of central importance to exactly recreate the overall structure of all possible objects exactly but to present the classifier training data with a certain variance, since machine learning models are typically able to transfer knowledge from one problem to another. For instance, the R-CNN in [14] was trained to classify the hyperbolic pattern of IEDs while being partially trained with hand-drawn hyperbolas. Furthermore, in [12], it was shown that a classifier trained for detection in a certain environment can be transferred to another environment with only a few new training samples.…”

“…The use of robots [10] and handheld sensors [11] is particularly important here. In the context of humanitarian demining, a landmine leads to specific spatial reflection signatures in the GPR raw data, as shown in [12][13][14]. A system that applies a similar measurement method is ground-penetrating synthetic aperture radar (GPSAR), which uses a more advanced signal processing procedure following a synthetic aperture radar (SAR) approach.…”

“…Aside from these examples, there are also publications that explicitly deal with modeling IEDs in simulations. In [14], an R-CNN was trained with real and simulated data to detect the characteristic hyperbolic patterns of IEDs. Here, the simulated data consisted of simulations with gprMax as well as hand-drawn hyperbolas, while the accuracy was evaluated with the intersection over union (IoU) metric.…”

Characterization of Antenna Radiation Pattern and Penetration Depth in Ground Penetrating Radar Field Missions

“…Ground penetrating radar (GPR, georadar) [1][2][3] is widely used in archeology, geology, civil engineering, and security issues [4][5][6]. The problem of GPR radiation directivity plays an important role in planning the measurement paths in rural and urban conditions.…”