Open Collections

Bin, Junchi

University of British Columbia

Natural gas is a key component of the global energy system and the manufacturing industries, with ethane being the main flammable chemical compound. Unfortunately, ethane leaks from pipelines and facilities can cause economic losses, environmental damage, and public safety issues. Currently, infrared (IR) imaging is the most common method for manual surveillance of ethane leaks. However, it is difficult for humans to accurately detect ethane leaks in IR imaging. This research seeks to create an automated framework to help engineers detect ethane leaks from surveillance cameras. First, a motion-aware ethane leak detection framework is proposed to detect ethane leaks from streaming videos of surveillance IR cameras. Specifically, the framework first applies a background subtraction to extract motion information from video frames. Then, an object detection framework, foreground fusion-based gas detection (FFBGD), is proposed to combine the motion information from motion and IR frames to accurately detect the ethane leaks. The experimental results indicate a significant improvement over the contemporary frameworks. Second, the observation unveils that the visible (VI) camera can also help to visualize the ethane leaks. Integration of VI and IR cameras as multimodal imaging may also enhance ethane leak detection. Thus, at first, an image registration algorithm is developed to align VI and IR images. Then, a vision Fourier transformer-based ethane detection (VFTED) is proposed to detect the ethane leaks by fusing the VI and IR images. Third, a motion-aware multimodal ethane leak detection (MMELD) framework is proposed to integrate the advantages of these frameworks. The experimental results indicate that the proposed MMELD can further improve the detection accuracy and sensitivity in contemporary industrial frameworks. In summary, the outcome of this thesis contributes to the visual surveillance process in the petrochemical industries. The proposed frameworks achieve precise detection and aid in the decision-making process of leak repairs. Meanwhile, the research is a pioneering effort to improve current ethane leak detection from surveillance cameras through two perspectives, that is motion information and multimodal imaging, which may also inspire academic researchers for future developments.

Text

2023-09-26

Attribution-NonCommercial-NoDerivatives 4.0 International

http://hdl.handle.net/2429/86022

Electrical Engineering

University of British Columbia

UBCO

http://creativecommons.org/licenses/by-nc-nd/4.0/