Development of a Test Method to Determine the Source of Staining on Structures

The goal of this research is to develop a strategy and approach to determine whether existing staining on structures has originated from bats or other sources. The study will develop a vision-based approach that leverages advances in computer vision and machine learning techniques to formulate a classification model for the described staining. The vision-based approach relies on the collection and identification of a pool of images, which can then be used to formulate the classification model. If successful, it is expected that the trained model will be capable of classifying the origin of the staining without contact or use of any chemical testing. The model can be tailored for field deployment such that results or classifications can be determined in real-time during field inspections.

    Project

    • Status: Active
    • Funding: $100625
    • Contract Numbers:

      111999

    • Sponsor Organizations:

      Virginia Transportation Research Council

      530 Edgemont Road
      Charlottesville, VA  United States  22903
    • Managing Organizations:

      Virginia Transportation Research Council

      530 Edgemont Road
      Charlottesville, VA  United States  22903
    • Project Managers:

      Donaldson, Bridget

    • Performing Organizations:

      University of Virginia, Charlottesville

      P. O. Box 400195
      Charlottesville, VA  United States  22904
    • Principal Investigators:

      Harris, Devin

    • Start Date: 20181001
    • Expected Completion Date: 20200131
    • Actual Completion Date: 0

    Subject/Index Terms

    Filing Info

    • Accession Number: 01682231
    • Record Type: Research project
    • Source Agency: Virginia Department of Transportation
    • Contract Numbers: 111999
    • Files: RiP, STATEDOT
    • Created Date: Sep 28 2018 8:46AM