Pavement asset management systems and technologies: A review
The shift from manual condition surveys to automated pavement condition surveys has profusely improved data collection rate and the wide-range of data collection methods, manual, automated vehicles, and cost-effective methods followed across the globe were reviewed.
Abstract
Pavement asset management system (PAMS) assists agencies and decision makers to maintain deteriorating pavement assets with optimized budget allocation. The recent developments in pavement condition data collection and processing have significant effect on estimating remaining service life and selecting optimum maintenance strategies. Further, image processing (IP) and artificial intelligence (AI) tools have improved the overall performance of PAMS by helping analyze big data emanating from distress surveys. The objective of this review paper was to collect and report several current state-of-the-art developments in PAMS and the associated embedded processes, majorly focused on data collection procedures, analytical techniques, decision making tools, and processing methods. The shift from manual condition surveys to automated pavement condition surveys has profusely improved data collection rate. The wide-range of data collection methods, manual, automated vehicles, and cost-effective methods followed across the globe were reviewed. Further, the chronological development in data analysis, specifically, distress evaluation, homogeneous sectioning for selection of maintenance strategies, and prioritization and optimization of maintenance strategies were discussed while emphasizing the application of IP and AI in enhancing the efficacy of PAMS. In addition, this paper provided a narrative account of the interdisciplinary research and multi-scale developments that recognize the value-addition of cutting-edge technologies in AI and computer vision.