Improving the Anomaly Detection in GPR Images by Fine-Tuning CNNs with Synthetic Data

TL;DR

This paper introduces a novel approach to improve GPR subsurface anomaly detection by fine-tuning CNNs with synthetic data generated from normal and simulated GPR images, enhancing feature extraction without prior anomaly knowledge.

Contribution

The method leverages synthetic data fusion and fine-tuning of pre-trained CNNs to improve anomaly detection in GPR images, requiring only normal data from the detection area.

Findings

Fine-tuning CNNs with synthetic data enhances feature extraction accuracy.

The approach effectively detects anomalies without predefined types or quantities.

Requires only normal GPR data, ensuring practical applicability.

Abstract

Ground Penetrating Radar (GPR) has been widely used to estimate the healthy operation of some urban roads and underground facilities. When identifying subsurface anomalies by GPR in an area, the obtained data could be unbalanced, and the numbers and types of possible underground anomalies could not be acknowledged in advance. In this paper, a novel method is proposed to improve the subsurface anomaly detection from GPR B-scan images. A normal (i.e. without subsurface objects) GPR image section is firstly collected in the detected area. Concerning that the GPR image is essentially the representation of electromagnetic (EM) wave and propagation time, and to preserve both the subsurface background and objects' details, the normal GPR image is segmented and then fused with simulated GPR images that contain different kinds of objects to generate the synthetic data for the detection area based on the wavelet decompositions. Pre-trained CNNs could then be fine-tuned with the synthetic data, and utilized to extract features of segmented GPR images subsequently obtained in the detection area. The extracted features could be classified by the one-class learning algorithm in the feature space without pre-set anomaly types or numbers. The conducted experiments demonstrate that fine-tuning the pre-trained CNN with the proposed synthetic data could effectively improve the feature extraction of the network for the objects in the detection area. Besides, the proposed method requires only a section of normal data that could be easily obtained in the detection area, and could also meet the timeliness requirements in practical applications.