学术动态：Infrared Gas Detection Method Based on Non-Solid Characteristics and Spatiotemporal Information
MDPI Sensors 论文摘要：Infrared imaging technology has been widely adopted for industrial gas leak detection due to its capability for large field-of-view, long-range, and dynamic monitoring. However, in practical application
论文标题：Infrared Gas Detection Method Based on Non-Solid Characteristics and Spatiotemporal Information
发布日期：2026-05-22
作者：Xin Zhang, Shiwei Xu
DOI：10.3390/s26113284
论文摘要：Infrared imaging technology has been widely adopted for industrial gas leak detection due to its capability for large field-of-view, long-range, and dynamic monitoring. However, in practical applications, natural object interference within the scene, together with the blurred contours and low contrast of infrared images, severely degrades the performance of gas detection and leakage region segmentation. To address these challenges, this paper proposes a gas leak detection method that integrates gas characteristics with spatiotemporal information. Specifically, the non-solid characteristics of gas are incorporated to constrain the foreground extraction process of the Gaussian Mixture Model (GMM), thereby suppressing interfering moving objects. Furthermore, by exploiting the spatiotemporal information in infrared image sequences, a multi-scale cross-attention fusion model is designed to fuse multi-scale and global feature representations, improving the accuracy of foreground detection. Finally, density-based clustering is employed to achieve complete segmentation of gas regions with irregular shapes. Experimental results demonstrate that the proposed method effectively suppresses interference from solid objects, accurately detects gas leakage, and successfully segments the diffusion regions. Compared with existing approaches, the proposed method shows significant advantages and provides a valuable reference for research on infrared imaging-based gas leak detection.
元数据：Crossref 收录的 MDPI Sensors 论文。 DOI: 10.3390/s26113284. Vol. 26, Issue 11. Authors: Xin Zhang, Shiwei Xu.
开放许可： https://creativecommons.org/licenses/by/4.0/
原文链接： https://doi.org/10.3390/s26113284
PDF 链接： https://www.mdpi.com/1424-8220/26/11/3284/pdf
来源： MDPI Sensors via Crossref
