A Novel Shape-Aware Topological Representation for GPR Data with DNN Integration

2025-05-26

AI Summary

Traditional GPR data interpretation methods suffer from high noise sensitivity and weak structural awareness, leading to low accuracy in underground utility detection. To address this, we propose a shape-aware GPR image representation framework integrating Topological Data Analysis (TDA) with YOLOv5. Our approach introduces a novel topological representation mechanism grounded in persistent homology, explicitly encoding target geometric structures. It further incorporates B-scan feature enhancement and a Sim2Real synthetic data strategy to mitigate scarcity of annotated real-world data and domain shift. Experiments demonstrate substantial improvements in detection robustness and accuracy: mean Average Precision (mAP) increases by 12.6% under complex noise conditions. The framework enables high-precision, near-real-time pipeline localization while offering interpretability and cross-domain generalizability—establishing a new paradigm for intelligent urban subsurface infrastructure sensing.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

Ground Penetrating Radar (GPR) is a widely used Non-Destructive Testing (NDT) technique for subsurface exploration, particularly in infrastructure inspection and maintenance. However, conventional interpretation methods are often limited by noise sensitivity and a lack of structural awareness. This study presents a novel framework that enhances the detection of underground utilities, especially pipelines, by integrating shape-aware topological features derived from B-scan GPR images using Topological Data Analysis (TDA), with the spatial detection capabilities of the YOLOv5 deep neural network (DNN). We propose a novel shape-aware topological representation that amplifies structural features in the input data, thereby improving the model's responsiveness to the geometrical features of buried objects. To address the scarcity of annotated real-world data, we employ a Sim2Real strategy that generates diverse and realistic synthetic datasets, effectively bridging the gap between simulated and real-world domains. Experimental results demonstrate significant improvements in mean Average Precision (mAP), validating the robustness and efficacy of our approach. This approach underscores the potential of TDA-enhanced learning in achieving reliable, real-time subsurface object detection, with broad applications in urban planning, safety inspection, and infrastructure management.

Problem

• Enhances underground utility detection using shape-aware topological features
• Integrates Topological Data Analysis with YOLOv5 for structural awareness
• Addresses data scarcity via Sim2Real synthetic dataset generation

Innovation

• Shape-aware topological features with TDA
• YOLOv5 DNN for spatial detection
• Sim2Real strategy for synthetic datasets