6533b82afe1ef96bd128c2e7

RESEARCH PRODUCT

Image-based 3D reconstruction using traditional and UAV datasets for analysis of road pavement distress

Gaetano Di MinoLaura InzerilloRonald Roberts

subject

Computer science0211 other engineering and technologies02 engineering and technologyRoad pavement distresseTransport engineering021105 building & construction11. Sustainability0202 electrical engineering electronic engineering information engineeringStructure from motionSettore ICAR/04 - Strade Ferrovie Ed AeroportiReliability (statistics)Civil and Structural Engineeringbusiness.industryStructure from motion3D reconstructionLow-cost technologiePavement managementBuilding and ConstructionAutomationDistress3D modelsPavement managementControl and Systems Engineering020201 artificial intelligence & image processingMetric (unit)businessImage based

description

Abstract On local and urban networks, the enduring issue of scarce resources for Maintenance, Rehabilitation, and Reconstruction strategies (MR&R) has led, in many cases, to using unadjusted or poor techniques for road pavement distress detection and analysis, yielding ineffective or even counterproductive results. Therefore, it is necessary to have tools that can carry out quick, reliable and low-cost assessment surveys. This paper aims at validating the use of innovative and low-cost technologies for road pavement analysis, assessing their potentialities for improving the automation and reliability of distress detection. A Structure from Motion (SfM) technique is analyzed at different altitudes. The technique was applied on a distressed road pavement inside the University Campus in Palermo. The models obtained were compared with a terrestrial laser scanned 3D model to analyze the technique's metric accuracy and reliability. The results have shown that the technique accurately replicates pavement distresses, inciting an integrated approach to optimize pavement management strategies.

10.1016/j.autcon.2018.10.010http://dx.doi.org/10.1016/j.autcon.2018.10.010