🤖 AI Summary
To address key bottlenecks in UAV-based infrastructure inspection—namely, complex structural damage imagery, high label noise, and strong reliance on manual assessment—this paper proposes Guided-DetNet, a unified framework for damage detection, severity grading, and 3D quantitative evaluation. Methodologically, it introduces three novel components: a Generative Attention Module (GAM), a Hierarchical Disambiguation Algorithm (HEA), and Voxelized Contour Visualization Assessment (VCVA). It is the first to model damage severity as a continuous probability distribution using the Dirac delta function, and integrates cross-orientation patch aggregation, foreground-background feature fusion, hierarchical class-relation modeling, and voxelized contour representation. Evaluated on the PEER Hub dataset, Guided-DetNet achieves 96% accuracy in three-class severity classification, 94% detection accuracy and 79% mAP in dual-task detection, and an inference speed of 57.04 fps. Robustness tests yield 79–91% accuracy, and the framework has been successfully deployed in real-world UAV inspection systems.
📝 Abstract
Structural health monitoring (SHM) is essential for ensuring the safety and longevity of infrastructure, but complex image environments, noisy labels, and reliance on manual damage assessments often hinder its effectiveness. This study introduces the Guided Detection Network (Guided-DetNet), a framework designed to address these challenges. Guided-DetNet is characterized by a Generative Attention Module (GAM), Hierarchical Elimination Algorithm (HEA), and Volumetric Contour Visual Assessment (VCVA). GAM leverages cross-horizontal and cross-vertical patch merging and cross-foreground-background feature fusion to generate varied features to mitigate complex image environments. HEA addresses noisy labeling using hierarchical relationships among classes to refine instances given an image by eliminating unlikely class instances. VCVA assesses the severity of detected damages via volumetric representation and quantification leveraging the Dirac delta distribution. A comprehensive quantitative study and two robustness tests were conducted using the PEER Hub dataset, and a drone-based application, which involved a field experiment, was conducted to substantiate Guided-DetNet's promising performances. In triple classification tasks, the framework achieved 96% accuracy, surpassing state-of-the-art classifiers by up to 3%. In dual detection tasks, it outperformed competitive detectors with a precision of 94% and a mean average precision (mAP) of 79% while maintaining a frame rate of 57.04fps, suitable for real-time applications. Additionally, robustness tests demonstrated resilience under adverse conditions, with precision scores ranging from 79% to 91%. Guided-DetNet is established as a robust and efficient framework for SHM, offering advancements in automation and precision, with the potential for widespread application in drone-based infrastructure inspections.