Deep learning-based system for automated damage detection and quantification in concrete pavement

Abstract

The increasing volume of vehicle traffic and climate change significantly impact the performance of road infrastructure, necessitating comprehensive analyses throughout the road lifecycle to ensure its resilience. While traditional visual inspections remain prevalent for road assessment, they are hampered by high costs and subjective biases. Additionally, concrete pavement presents specific evaluation challenges due to its high stiffness and susceptibility to cracking, spalling, and faulting, requiring precise detection techniques. In response to these challenges, deep data-based systems emerge as a promising solution. This research introduces a novel system for detecting, locating, and quantifying damages in concrete pavement by combining convolutional neural networks with classical computer vision techniques. The system studies various CNNs and ultimately selects UNet ResNext-101 for its superior performance. Additionally, the system applies perspective transformations, Hough Transform, and thresholding techniques to enhance feature extraction and improve damage quantification precision. This combination mitigates the high data requirements typically associated with neural networks alone. By limiting the inspection area to specific slabs, the system improves efficiency. It is trained and tested using high-resolution images from the LanammeUCR. This innovative approach could significantly transform the maintenance and monitoring processes of road infrastructure, leading to safer and more reliable transportation networks. • Automated damage inspection reduces time and costs: The proposed system automates the inspection process, significantly reducing the time required for analysis. This enables decision-makers to address pavement issues more promptly, preventing damage from worsening and thereby reducing maintenance costs. • Comprehensive system tailored to concrete pavement inspection standards: The system identifies and segments individual concrete slabs, aligning with established road inspection norms that use slabs as the primary evaluation unit. Damage quantification is then conducted at the slab level, ensuring a methodical and standardized approach. • Efficiency through advanced deep learning techniques: The system leverages state-of-the-art computer vision and deep neural networks to enhance data processing efficiency. By targeting relevant regions of interest, the approach minimizes computational overhead and maximizes the utility of training datasets. • Highly adaptable to diverse conditions: The system's models can be fine-tuned to accommodate varying camera angles, concrete pavement types, and road conditions, making it versatile and scalable for different contexts and regions. • Open data for reproducibility: The training datasets used in this research are publicly shared alongside the manuscript, promoting transparency, reproducibility, and further innovation in the field.

Topics & Concepts