Description

Robots such as drones have been leveraged to perform structure health inspection such as bridge inspection. Big data of inspection videos can be collected by cameras mounted on drones. In this project, we develop image analysis algorithms to support bridge engineers to analyze the big video data. Bridge engineers define the region of interest initially, then the algorithm retrieves all related regions in the video, which facilitates the engineers to inspect the bridge rather than exhaustively check every frame of the video. To perform this task, we propose a Multi-scale Siamese Neural Network. The network is initially trained by one-shot learning and is fine-tuned iteratively with human in the loop. Our neural network is evaluated on three bridge inspection videos with promising performances.

Location

St. Louis, Missouri

Start Date

8-7-2019 9:00 AM

End Date

8-7-2019 9:20 AM

Meeting Name

INSPIRE-UTC 2019 Annual Meeting

Department(s)

Computer Science

Second Department

Engineering Management and Systems Engineering

Third Department

Civil, Architectural and Environmental Engineering

Document Type

Article - Conference proceedings

Document Version

Final Version

File Type

text

Language(s)

English

Source Publication Title

Proceedings of the 9th International Conference on Structural Health Monitoring of Intelligent Infrastructure (2019: Aug. 4-7, St. Louis, MO)

Share

COinS
 
Aug 7th, 9:00 AM Aug 7th, 9:20 AM

Image Data Analytics to Support Engineers’ Decision-Making

St. Louis, Missouri

Robots such as drones have been leveraged to perform structure health inspection such as bridge inspection. Big data of inspection videos can be collected by cameras mounted on drones. In this project, we develop image analysis algorithms to support bridge engineers to analyze the big video data. Bridge engineers define the region of interest initially, then the algorithm retrieves all related regions in the video, which facilitates the engineers to inspect the bridge rather than exhaustively check every frame of the video. To perform this task, we propose a Multi-scale Siamese Neural Network. The network is initially trained by one-shot learning and is fine-tuned iteratively with human in the loop. Our neural network is evaluated on three bridge inspection videos with promising performances.