Embedded Files
Sponsors:
Sponsors:
Alaska Department of Transportation & Public Facilities, and the National Center for Transportation Infrastructure Durability and Life-Extension (TriDurLE) – University Transportation Center (UTC)
Project Funds: $365,867 ($192,500 from Alaska DOT&PF, $101,717 from TriDurLE, and $71,650 from CTIPS)
Year: 2022-2025
Personnel:
Personnel:
PI: Mostafa Tazarv, PhD, PE
Co-PI: Kwanghee Won, PhD, Electrical Eng. & Computer Science
Graduate Research Assistants: Ammad Khan (CEE), and Abir Hadi (EE&CS)
Project Technical Panel: Ben Fetterhoff, Jesse Escamilla, David McAdoo, and Jared Jones
Project Summary:
Project Summary:
The Alaska Department of Transportation & Public Facilities (DOT&PF) is responsible for condition assessment of approximately 1000 bridges in the state. Each year, Alaska DOT&PF engineers inspect about 500 bridges. Per the Alaska Bridge Inspection Program, the inspector must complete both a National Bridge Inventory (NBI) inspection (following the FHWA Recording and Coding Guide) and an element level inspection (following the AASHTO Manual for Bridge Element Inspection, MBEI) for each bridge. Using either NBI or MBEI, a significant amount of data must be collected and reported. However, the data collection/reporting is usually done manually, which is time consuming, error prone, and sometimes not consistent when repeated. For example, the deck defect mapping requires manual detection and measurement of delaminated concrete, patch repairs, exposed reinforcing steel, and spalling. Computer vision, a type of image processing that incorporates artificial intelligence (AI) for analyzing the surroundings, can significantly expedite the process of damage/defect identification and measurement only using photographs of bridge deck and other elements. Furthermore, this and other AI tools can be utilized to expedite and unify reporting.
The Alaska Department of Transportation & Public Facilities (DOT&PF) is responsible for condition assessment of approximately 1000 bridges in the state. Each year, Alaska DOT&PF engineers inspect about 500 bridges. Per the Alaska Bridge Inspection Program, the inspector must complete both a National Bridge Inventory (NBI) inspection (following the FHWA Recording and Coding Guide) and an element level inspection (following the AASHTO Manual for Bridge Element Inspection, MBEI) for each bridge. Using either NBI or MBEI, a significant amount of data must be collected and reported. However, the data collection/reporting is usually done manually, which is time consuming, error prone, and sometimes not consistent when repeated. For example, the deck defect mapping requires manual detection and measurement of delaminated concrete, patch repairs, exposed reinforcing steel, and spalling. Computer vision, a type of image processing that incorporates artificial intelligence (AI) for analyzing the surroundings, can significantly expedite the process of damage/defect identification and measurement only using photographs of bridge deck and other elements. Furthermore, this and other AI tools can be utilized to expedite and unify reporting.
The main goal of the present study is to develop practical AI tools that help inspectors with measurements and reporting of bridge defects following NBI and MBEI requirements. To achieve this goal, a few bridge elements (e.g., decks and girders) will be targeted for further investigation, inspection database including photographs of the selected elements with/without damage will be compiled, and computer vision tools will be developed for the selected elements to recognize the element defects, quantify the defect per NBI/MBEI, and produce a report following the DOT&PF standard practice. The tools, which can be standard software or web-based, will incorporate mobile devices for the ease of data collection, access, sharing, and reuse in future inspections.
The main goal of the present study is to develop practical AI tools that help inspectors with measurements and reporting of bridge defects following NBI and MBEI requirements. To achieve this goal, a few bridge elements (e.g., decks and girders) will be targeted for further investigation, inspection database including photographs of the selected elements with/without damage will be compiled, and computer vision tools will be developed for the selected elements to recognize the element defects, quantify the defect per NBI/MBEI, and produce a report following the DOT&PF standard practice. The tools, which can be standard software or web-based, will incorporate mobile devices for the ease of data collection, access, sharing, and reuse in future inspections.
Project Work Plan:
Project Work Plan:
Task 1: Literature Review,
Task 1: Literature Review,
Task 2: Selection of Bridge Elements for Computer Vision Condition Assessment,
Task 2: Selection of Bridge Elements for Computer Vision Condition Assessment,
Task 3: Data Collection,
Task 3: Data Collection,
Task 4: Definition of Damage Conditions Suitable for Computer Programming,
Task 4: Definition of Damage Conditions Suitable for Computer Programming,
Task 5: Development of Computer Vision Condition Assessment Tools,
Task 5: Development of Computer Vision Condition Assessment Tools,
Task 6: Field Validation of Computer Vision Condition Assessment Tools,
Task 7: Project Deliverables.
Publications:
Publications:
Khan, A., Hadi, A.M., Tazarv, M., Won, K. (2024). “Deep Learning Based Methods for Detecting Delamination of Concrete Bridge Decks,” Canadian Journal of Civil Engineering, Under Review.
Sample Presentation:
Sample Presentation:
Khan, A., Hadi, A.M., Tazarv, M., Won, K. (2024). “Use Thermal Images for Bridge Deck Inspection,” The 2024 World Bridge Engineering Conference, Miami, FL, Dec. 11-13.
Tazarv, M., Khan, A., Hadi, A.M., and Won, K. (2024). “Use of Lidar and Thermal Images for Bridge Deck Inspection,” Intelligent Transportation Society of Alaska, Sept. 17.
Khan, A., Hadi, A.M., Tazarv, M., Won, K. (2024). “Use of Lidar and Thermal Images for Bridge Deck Inspection,” The USDOT Future of Transportation Summit, Washington, DC, Aug. 13-15.
Khan, A., Hadi, A.M., Tazarv, M., Won, K. (2024). “AI for Bridge Deck Inspections,” The USDOT Future of Transportation Summit, Washington, DC, Aug. 13-15, 2024.
AI-iPhone-Lidar Based Deck Damage Assessment
AI-iPhone-Lidar Based Deck Damage Assessment
AI-Drone-Thermal Based Deck Damage Assessment
AI-Drone-Thermal Based Deck Damage Assessment
Google Sites
Report abuse