Back to search

University of British Columbia

Design of deep learning models for real-time gas leak monitoring

Abstract

dc:description

Nowadays, more and more people are concerned about the threats to human health and atmospheric pollution caused by gas leaks. The lack of efficient gas leak monitoring methods makes it difficult to address the problem effectively. Although some vision-based approaches attempt to monitor gas leaks in infrared videos, the transparent and non-rigid nature of gases often poses a challenge to these techniques. To address these problems, the thesis explores several feasible approaches and first proposes a Fine-Grained Spatial-Temporal Perception (FGSTP) algorithm for gas leak monitoring. FGSTP captures critical motion clues across frames and integrates them with refined object features. A correlation volume is first used to capture motion information between consecutive frames. Then, the spatial perception progressively refines the object-level features using previous outputs. Experiments demonstrate that the proposed model excels in segmenting non-rigid objects like gas leaks, generating the most accurate mask compared to other state-of-the-art (SOTA) models. However, sometimes the FGSTP is misled by objects that have similar motion or appearance, and it may also generate false positives on non-leak frames in a video because of the strong noise disturbance. Therefore, we modify FGSTP and design a novel model to solve those problems. The new network, Vision-Language Joint Gas Leak Segmentation (VLJGS), integrates the complementary strengths of video and text modalities to enhance the representation and detection of gas leaks. Additionally, the model employs a post-processing step to eliminate the false positives, ensuring that the model is not disturbed by non-target objects. Experiments demonstrate that the proposed model outperforms SOTA models. We evaluate the model using both supervised and few-shot training approaches, and the proposed model achieves excellent results in both cases, whereas existing models either perform well only in one scenario or poorly in both. In summary, this thesis presents two novel methods for gas leak monitoring, demonstrating the importance of multi-modality fusion. The findings of the thesis establish a foundation for future research on quantifying volumes or identifying types of gas leaks.

Degree

thesis:*
Name thesis:degree_name
Master of Science - MSc
Level thesis:degree_level
master's
Discipline thesis:degree_discipline
Computer Science
Grantor dc:publisher
University of British Columbia
Year dc:date
2025

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Zhao, Xinlong
Contributors dc:contributor
  • Du, Shan

Rights

dc:rights
Statement dc:rights
  • Attribution-NonCommercial-NoDerivatives 4.0 International
Language dc:language
eng

Identifiers

dc:identifier.*
Handle dc:identifier
http://hdl.handle.net/2429/91936

Chain of custody

source
Harvested from
University of British Columbia
Base URL
circle.library.ubc.ca/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Zhao, Xinlong. Design of deep learning models for real-time gas leak monitoring. master's thesis, University of British Columbia, 2025. http://hdl.handle.net/2429/91936