On Choosing Training and Testing Data for Supervised Algorithms in Ground Penetrating Radar Data for Buried Threat Detection

TL;DR

This paper evaluates various strategies for selecting training and testing data in supervised GPR-based buried threat detection, introduces a taxonomy of these strategies, and proposes a new, superior method called PatchSelect.

Contribution

It provides a comprehensive taxonomy of keypoint utilization strategies and introduces PatchSelect, a new method that consistently improves classifier performance in GPR threat detection.

Findings

PatchSelect outperforms existing strategies across all experiments

Keypoint utilization strategy significantly impacts classifier accuracy

A detailed taxonomy of utilization strategies is established

Abstract

Ground penetrating radar (GPR) is one of the most popular and successful sensing modalities that has been investigated for landmine and subsurface threat detection. Many of the detection algorithms applied to this task are supervised and therefore require labeled examples of target and non-target data for training. Training data most often consists of 2-dimensional images (or patches) of GPR data, from which features are extracted, and provided to the classifier during training and testing. Identifying desirable training and testing locations to extract patches, which we term "keypoints", is well established in the literature. In contrast however, a large variety of strategies have been proposed regarding keypoint utilization (e.g., how many of the identified keypoints should be used at targets, or non-target, locations). Given the variety keypoint utilization strategies that are available, it is very unclear (i) which strategies are best, or (ii) whether the choice of strategy has a large impact on classifier performance. We address these questions by presenting a taxonomy of existing utilization strategies, and then evaluating their effectiveness on a large dataset using many different classifiers and features. We analyze the results and propose a new strategy, called PatchSelect, which outperforms other strategies across all experiments.