A Weak-Signal-Aware Framework for Subsurface Defect Detection: Mechanisms for Enhancing Low-SCR Hyperbolic Signatures

TL;DR

This paper introduces WSA-Net, a framework that enhances weak hyperbolic signals in subsurface defect detection by integrating physical-feature reconstruction mechanisms, significantly improving detection sensitivity and efficiency.

Contribution

The paper presents WSA-Net, a novel lightweight framework that incorporates four mechanisms to enhance faint signals and suppress clutter in GPR-based subsurface defect detection.

Findings

WSA-Net achieves 0.6958 mAP@0.5 on RTSTdataset.

WSA-Net runs at 164 FPS with only 2.412 million parameters.

Signal-centric awareness reduces false negatives in defect detection.

Abstract

Subsurface defect detection via Ground Penetrating Radar is challenged by "weak signals" faint diffraction hyperbolas with low signal-to-clutter ratios, high wavefield similarity, and geometric degradation. Existing lightweight detectors prioritize efficiency over sensitivity, failing to preserve low-frequency structures or decouple heterogeneous clutter. We propose WSA-Net, a framework designed to enhance faint signatures through physical-feature reconstruction. Moving beyond simple parameter reduction, WSA-Net integrates four mechanisms: Signal preservation using partial convolutions; Clutter suppression via heterogeneous grouping attention; Geometric reconstruction to sharpen hyperbolic arcs; Context anchoring to resolve semantic ambiguities. Evaluations on the RTSTdataset show WSA-Net achieves 0.6958 mAP@0.5 and 164 FPS with only 2.412 M parameters. Results prove that signal-centric awareness in lightweight architectures effectively reduces false negatives in infrastructure inspection.