Automatic Boundary Detection and Change Analysis Using Static and Dynamic Imagery

This project aims to develop an automated segmentation and boundary detection system capable of identifying geometric features and changes in river boundaries using advanced image processing techniques on satellite imagery, digital photographs, and videos. Current aerial remote sensing and data collection techniques use LiDAR, photogrammetry, or other methods that require significant time and computational power to assess and identify key features of interest. Therefore, rapid or real-time monitoring of dynamic conditions such as flooding is difficult or impossible. By combining a fast segmentation algorithm with novel edge detection and artificial intelligence (AI)-based classification methods to analyze boundary changes, the proposed system will allow for temporal monitoring of river conditions and adjacent infrastructure, and aid in the detection of any deviations from established boundary norms. While this system has numerous potential use cases, the main focus of this research will be the creation and training of a system that can identify and quantify a number of key features used for asset management, flood monitoring, and disaster response associated with levees and adjacent transportation infrastructure.

Language

• English

Project

• Status: Active
• Funding: $300,664.00
• Contract Numbers:

  69A3552348331

• Sponsor Organizations:

  Office of the Assistant Secretary for Research and Technology

  University Transportation Centers Program
  Department of Transportation
  Washington, DC  United States  20590
• Managing Organizations:

  Maritime Transportation Research and Education Center (MarTREC)

  University of Arkansas
  4190 Bell Engineering Center
  Fayetteville, AR  United States  72701
• Performing Organizations:

  University of Arkansas, Fayetteville

  4190 Bell Engineering
  Civil Engineering
  Fayetteville, Arkansas  United States  72701
• Principal Investigators:

  Barry, Michelle

• Start Date: 20250701
• Expected Completion Date: 20270630
• Actual Completion Date: 0
• USDOT Program: University Transportation Centers Program

Subject/Index Terms

• TRT Terms: Artificial intelligence; Floods; Image processing; Monitoring; Rivers
• Subject Areas: Data and Information Technology; Hydraulics and Hydrology; Marine Transportation; Planning and Forecasting;

Filing Info

• Accession Number: 01970157
• Record Type: Research project
• Source Agency: Maritime Transportation Research and Education Center (MarTREC)
• Contract Numbers: 69A3552348331
• Files: UTC, RIP
• Created Date: Oct 30 2025 2:39PM