Infrastructure-Guided Connectivity-Enhanced Road Crack Detection and Estimation
This work addresses the problem of real-time road crack detection for autonomous vehicles by leveraging infrastructure communication, but the results are preliminary and incremental.
The paper presents the first infrastructure-guided communication-enhanced road crack detection pipeline for passenger vehicles, achieving effective detection by transmitting region-of-interest data from infrastructure to vehicle and using a trained model on a forward-facing crack dataset.
In this paper, we report the world's first infrastructure-guided communication-enhanced road crack detection pipeline that is effective and implementable on passenger vehicles. We first design a customized communication protocol to transmit the region of interest from the infrastructure to the vehicle. With proper camera image processing (e.g., dynamic cropping and frame selection), the focused images are provided to the crack detection model. Leveraging state-of-the-art crack detection model backbones and a carefully prepared dataset comprising a forward-facing view with a crack, we train the model to improve crack-detection performance. We demonstrate the full detection pipeline on an experimental vehicle platform, showcase the detection effectiveness, and project future research directions.