LiDAR-Driven Innovations in Pavement Distress Detection: A Review

The rapid advancement of light detection and ranging (LiDAR) technology has become essential in pavement distress detection, offering large-scale, high-resolution, georeferenced data to accurately capture road surface geometries while remaining robust to light variation. Unlike traditional image-based methods that rely on visual information and are sensitive to lighting conditions, LiDAR provides comprehensive 3D data, enabling the detection of surface and deformation-based distresses. This review systematically examines the development of LiDAR-based pavement distress detection from 2010 to 2024, highlighting its applications in intelligent pavement condition surveys. Key aspects of LiDAR data processing are discussed, including technical specifications and essential preprocessing techniques. Moreover, various algorithms for pavement distress detection, ranging from rule-based approaches to deep learning-based methods are reviewed. The authors then provide a comparative analysis of image- and point-based methods, emphasizing their respective advantages and limitations. Further, challenges in data processing and future research directions, such as the integration of deep learning and the optimization of real-time processing capabilities, are explored to further enhance LiDAR’s role in intelligent transportation systems.