Towards Successful Implementation of Automated Raveling Detection: Effects of Training Data Size, Illumination Difference, and Spatial Shift

2026-04-14

AI Summary

This study addresses the performance degradation of asphalt pavement raveling detection models in real-world deployment due to domain shifts such as illumination variations and spatial misalignments. To this end, we propose RavelingArena, the first robustness evaluation benchmark specifically designed for raveling detection. Without requiring large-scale additional data, RavelingArena systematically quantifies the impact of training data volume, lighting conditions, and spatial shifts on model robustness by applying controlled perturbations to existing datasets to generate diverse test environments. Leveraging this framework alongside deep learning and targeted data augmentation strategies, our approach improves model accuracy by at least 9.2% under the most challenging perturbations and significantly enhances inter-annual consistency across multi-year road segments in Georgia, USA, thereby providing a reliable foundation for temporal deterioration modeling.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Machine Learning: Adversarial Learning & Robustness

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Raveling, the loss of aggregates, is a major form of asphalt pavement surface distress, especially on highways. While research has shown that machine learning and deep learning-based methods yield promising results for raveling detection by classification on range images, their performance often degrades in large-scale deployments where more diverse inference data may originate from different runs, sensors, and environmental conditions. This degradation highlights the need of a more generalizable and robust solution for real-world implementation. Thus, the objectives of this study are to 1) identify and assess potential variations that impact model robustness, such as the quantity of training data, illumination difference, and spatial shift; and 2) leverage findings to enhance model robustness under real-world conditions. To this end, we propose RavelingArena, a benchmark designed to evaluate model robustness to variations in raveling detection. Instead of collecting extensive new data, it is built by augmenting an existing dataset with diverse, controlled variations, thereby enabling variation-controlled experiments to quantify the impact of each variation. Results demonstrate that both the quantity and diversity of training data are critical to the accuracy of models, achieving at least a 9.2% gain in accuracy under the most diverse conditions in experiments. Additionally, a case study applying these findings to a multi-year test section in Georgia, U.S., shows significant improvements in year-to-year consistency, laying foundations for future studies on temporal deterioration modeling. These insights provide guidance for more reliable model deployment in raveling detection and other real-world tasks that require adaptability to diverse conditions.

Problem

• raveling detection
• model robustness
• illumination difference
• spatial shift
• training data size

Innovation

• Raveling detection
• model robustness
• data augmentation
• illumination variation
• spatial shift