Enhanced Scoring Instance Segmentation Network for Subsurface Targets Recognition from GPR B-Scans

Abstract

Abstract Ground Penetrating Radar (GPR) is a non-destructive technique used for detecting subsurface structure and space. However, the interpretation of field GPR data is quite labour-intensive and time-consuming. This paper develops a deep learning-based approach for the detection and segmentation of subsurface targets based on GPR data. Since existing deep learning methods do not always accurately reflect the true quality of segmentation masks and exhibit locality when handling details in complex scenes, the proposed method employs the Mask Scoring R-CNN (MS R-CNN) framework as its primary framework and makes additional modifications to its backbone and neck architecture. Experimental results on GPR bridge dataset show notable improvements in loss metrics, segmentation accuracy, and bounding box precision. These enhancements have effectively reduced overall losses and enhanced the performance of Average Precision index of the enhanced MS R-CNN, demonstrating the effectiveness of our approach in the accurate identification of underground objects under complex environments.