6533b873fe1ef96bd12d4514

RESEARCH PRODUCT

Developing a framework for using structure-from-motion techniques for road distress applications

Gaetano Di MinoLaura InzerilloRonald Roberts

subject

050210 logistics & transportationComputer sciencebusiness.industryPavement Management System05 social sciences0211 other engineering and technologiesTransportation02 engineering and technologyPavement DistresseGeneralLiterature_MISCELLANEOUS3D ModellingDistress021105 building & construction0502 economics and businessAutomotive EngineeringStructure-from-MotionSettore ICAR/04 - Strade Ferrovie Ed AeroportiStructure from motionComputer visionArtificial intelligencebusiness

description

On Urban road networks, road agencies need to quickly identify road pavement distresses in order to identify appropriate maintenance and rehabilitation strategies. This is integral as agencies are plagued with financial and time constraint issues. There have been several attempts over the last few years to identify new solutions and techniques to solve these issues. Several of these have shown merit and accuracy in identifying distresses. However, the techniques in many instances are not correlated to available distress identification standards. One of the considered techniques is the use of Structure-from-Motion, which tries to recreate 3D distress models for identification and analysis. This paper considers this methodology and attempts to integrate it with measurement requirements used by distress manuals to illustrate how the technique can be used with real-world industry standards and practices. Case studies of different measurement types, on an urban road in Palermo, Italy, are considered. The results from these examples show that the technique replicates pavement distresses of varying measurement requirements and the paper presents a workflow of how it can be utilized to help optimize the pavement management system and their connections to different distress identification manuals worldwide.

http://www.scopus.com/inward/record.url?eid=2-s2.0-85087334227&partnerID=MN8TOARS