AI-based Bridge and Road Inspection Framework using Drones

There are over 590,000 bridges dispersed across the roadway network that stretches across the United States alone. Each bridge with a length of 20 feet or greater must be inspected at least once every 24 months, according to the Federal Highway Act (FHWA) of 1968. Each inspection must adhere to the National Bridge Inspection Standards' requirements (NBIS). A bridge inspection will also uncover severe structural flaws that need to be addressed, quantify the overall state of the bridge in order to prioritize capital needs, identify routine maintenance, and keep track of the bridge's history. Inspecting bridges is a time-consuming and expensive task. Traditional inspection methods necessitate a lot of coordination, such as traffic control, and they put personnel in danger. Drones on the other hand can readily access regions that humans find difficult or dangerous, such as under bridges or along train tracks. They allow workers to keep a longer standoff distance while still collecting the data required for inspections. In comparison to traditional inspection equipment like snoopers, drones can capture significantly more thorough inspection data. They make collecting high-definition photos from limited and inaccessible areas, such as beneath bridges and along beams and girders, simple.

Principal Investigator: 
Hovannes Kulhandjian
PI Contact Information: 

hkulhandjian@csufresno.edu

California State University, Fresno

Impacts/Benefits of Implementation: 

During bridge inspections, drones have the potential to save costs, deliver better data, and increase worker safety. Drone inspections of bridges will considerably reduce inspection expenses as noted by the Minnesota Department of Transportation which was involved in research focusing on using drones as a tool for increasing the quality of bridge inspections. A normal bridge inspection requires three snooper inspection vehicles and eight inspection days on average which can cost $59,000. According to a report published by the United States Department of Transportation, Office of the Assistant Secretary for Research and Technology, “The use of drones for bridge inspections can create an overall average cost savings of 40 percent without a reduction in inspection quality”. Recently, on Jan. 28, 2022, the Fern Hollow Bridge Collapsed in Pittsburgh. The National Transportation Safety Board (NTSB) reported that there might have been some structural damages that were not detected In this research work, we propose to develop artificial intelligence (AI)-based framework for bridge and road inspection using drones with multiple sensors collecting capabilities. It is not sufficient to conduct inspection using cameras alone, we plan to utilize an infrared (IR) camera along with a high-resolution optical camera. The IR camera in many instances can provide more details on the interior structural damages of a bridge compared to an optical camera which is more suitable for inspecting damages on the surface of a bridge. In addition to that our drone inspection system will be equipped with a minicomputer that runs Machine Learning algorithms to enable autonomous drone navigation and taking images of the bridge or the road structure whenever it detects any damages. Instead of having a person operate the drone it will self-operate and carry out the inspection process on its own using advanced AI algorithms we plan to develop.

Project Number: 
2226

-

MCTM
CSUTC
NTSC
NTFC

Contact Us

SJSU Research Foundation   210 N. 4th Street, 4th Floor, San Jose, CA 95112    Phone: 408-924-7560   Email: mineta-institute@sjsu.edu