Loading...

Media is loading
 

Description

The objective of this research is to provide a basis for gas leakage detection with hyperspectral cameras. The gas leakage attacks vegetations, which yields some spectral signature changes. As the vegetation under different stressors may induce similar effect. The spectral signature changes can be similar. A lab test was arranged to test three kinds of plants under four common natural stressors with a reference. All plants are routinely scanned with hyperspectral cameras every three days to obtain every developmental stage. Linear discriminant analysis (LDR) was applied in the data analysis to discriminate the plant with gas leakage treatment from the other stressors. The result shows that there is a more than 80 percent possibility that gas leakage can be distinguished from the other stressors.

Presentation Date

10 Aug 2021, 1:20-3:00 pm

Meeting Name

INSPIRE-UTC 2021 Annual Meeting

Department(s)

Civil, Architectural and Environmental Engineering

Comments

Financial support for this study was provided in part by the USDOT Pipeline and Hazardous Materials Safety Administration (PHMSA), and by the U.S. department of Transportation under the auspices of the Center for Transportation Infrastructure and Safety at Missouri S&T.

Document Type

Poster

Document Version

Final Version

File Type

text

Language(s)

English

Share

COinS
 
Aug 10th, 1:20 PM Aug 10th, 1:30 PM

Gas Leakage Detection with Hyperspectral Imagery-Based Vegetation Stress Indices

The objective of this research is to provide a basis for gas leakage detection with hyperspectral cameras. The gas leakage attacks vegetations, which yields some spectral signature changes. As the vegetation under different stressors may induce similar effect. The spectral signature changes can be similar. A lab test was arranged to test three kinds of plants under four common natural stressors with a reference. All plants are routinely scanned with hyperspectral cameras every three days to obtain every developmental stage. Linear discriminant analysis (LDR) was applied in the data analysis to discriminate the plant with gas leakage treatment from the other stressors. The result shows that there is a more than 80 percent possibility that gas leakage can be distinguished from the other stressors.