AI-Driven Road Maintenance Inspection v2: Reducing Data Dependency & Quantifying Road Damage
This work addresses the labor-intensive and costly task of road maintenance inspection for infrastructure managers, though it appears incremental by building on existing AI techniques.
The paper tackles the problem of high annotation costs for road damage detection by proposing an automated labeling pipeline using few-shot learning and out-of-distribution detection, which reduces human annotation needs and includes risk assessment to prioritize repairs, leading to safer roads.
Road infrastructure maintenance inspection is typically a labor-intensive and critical task to ensure the safety of all road users. Existing state-of-the-art techniques in Artificial Intelligence (AI) for object detection and segmentation help automate a huge chunk of this task given adequate annotated data. However, annotating videos from scratch is cost-prohibitive. For instance, it can take an annotator several days to annotate a 5-minute video recorded at 30 FPS. Hence, we propose an automated labelling pipeline by leveraging techniques like few-shot learning and out-of-distribution detection to generate labels for road damage detection. In addition, our pipeline includes a risk factor assessment for each damage by instance quantification to prioritize locations for repairs which can lead to optimal deployment of road maintenance machinery. We show that the AI models trained with these techniques can not only generalize better to unseen real-world data with reduced requirement for human annotation but also provide an estimate of maintenance urgency, thereby leading to safer roads.