An Interactive System For Training And Assisting Bridge Inspectors In Inspection Video Data Analytics (WD-4)

University:

Missouri University of Science and Technology (Missouri S&T)

Principal Investigator:

Ruwen Qin, Missouri S&T

PI Contact Information:

Phone: (573) 341-4493 | Email: qinr@mst.edu

Co-Principal Investigators: 

Funding Source(s) and Amounts Provided:
Missouri S&T: $160,000
INSPIRE UTC: $160,000

Total Project Cost: $320,000

Match Agency ID or Contract Number:
Missouri S&T: In-Kind Match | INSPIRE UTC: 00069372

INSPIRE Grant Award Number: 69A3551747126

Start Date: January 1, 2020
End Date: December 31, 2020

Brief Description of Research Project:

The project will develop the prototype of an interactive system that guides and assists users to learn fundamentals of inspection video data analytics; contribute their expertise to the development of the deep neural network (DNN) for detecting and segmenting bridge elements from inspection videos; and analyze inspection videos to assess the condition of bridges. To deliver the proposed system prototype, the project will perform the following tasks: creating web-based learning modules for training learners to master cross-disciplinary knowledge and fundamental skills of analytics; developing an inspection data analytic tool to assist inspectors in processing and analyzing inspection video data for the bridge condition assessment; creating a Graphical User Interface (GUI) to enable the interaction between users and the three major functions (i.e., learning, developing, and implementing video data analytics), developing a system central controller that integrates all developed components at a system’s level; and testing the viability and usability of the system prototype to identify the room of system improvement.

Approach and Methodology: The proposed approach is to develop the porotype of an interactive system that helps users develop the capability of inspection video data analytics for the robotic platform empowered bridge inspection. Specifically, the system guides and assists users to (i) learn and master cross-disciplinary knowledge such as deep learning and fundamental skills of analytics; (ii) contribute their expertise to the development of the deep neural network (DNN) for detecting and segmenting bridge elements from inspection videos; and (iii) analyze inspection videos to assess the condition of bridges.

Overall Objectives: The overall goal of the project is to help users build the capability of inspection video data analytics for the robotic platform empowered bridge inspection. Specifically, the project will develop the prototype of an interactive system that guides and assists users to (i) learn fundamentals of inspection video data analytics; (ii) contribute their expertise to the development of the deep neural network (DNN) for detecting and segmenting bridge elements from inspection videos; and (iii) analyze inspection videos to assess the condition of bridges.

Scope of Work in Year 1: (1) Create Learning Modules, (2) Develop the Inspection Video Analytic Tool, (3) Create the Graphical User Interface, (4) Build the Central Controller, (5) Test the Developed System.

Describe Implementation of Research Outcomes:

Research outcomes and implementation plan will be described towards the end of this project.

Impacts/Benefits of Implementation:

Impact/Benefits of Implementation will be summarized at the end of this project.

 Web Links:

Project Website:
Progress Reports: