YOLOv8-Seg with Dynamic Multi-Kernel Learning for Infrared Gas Leak Segmentation: A Weakly Supervised Approach
Sensors · 10.08.2025 · 25 (16) · 4939
DOI: 10.3390/s25164939 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 10.08.2025. Verfasst von Haoyang Shen und 6 weiteren Autor:innen. Beteiligte Einrichtung: College of Carbon Neutral Energy, China University of Petroleum, Beijing 102249, China. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: CNPC and CUPB, CNPC.
Abstract (Originalsprache)
Gas leak detection in oil and gas processing facilities is a critical component of the safety production monitoring system. Non-contact detection technology based on infrared imaging has emerged as a vital real-time monitoring method due to its rapid response and extensive coverage. However, existing pixel-level segmentation networks face challenges such as insufficient segmentation accuracy, rough gas edges, and jagged boundaries. To address these issues, this study proposes a novel pixel-level segmentation network training framework based on anchor box annotation and enhances the segmentation performance of the YOLOv8-seg network for gas detection applications. First, a dynamic threshold is introduced using the Visual Background Extractor (ViBe) method, which, in combination with the YOLOv8-det network, generates binary masks to serve as training masks. Next, a segmentation head architecture is designed, incorporating dynamic kernels and multi-branch collaboration. This architecture utilizes feature concatenation under deformable convolution and attention mechanisms to replace parts of the original segmentation head, thereby enhancing the extraction of detailed gas features and reducing dependency on anchor boxes during segmentation. Finally, a joint Dice-BCE (Binary Cross-Entropy) loss, weighted by ViBe-CRF (Conditional Random Fields) confidence, is employed to replace the original Seg_loss. This effectively reduces roughness and jaggedness at gas edges, significantly improving segmentation accuracy. Experimental results indicate that the improved network achieves a 6.4% increase in F1 score and a 7.6% improvement in the mIoU (mean Intersection over Union) metric. This advancement provides a new, real-time, and efficient detection algorithm for infrared imaging of gas leaks in oil and gas processing facilities. Furthermore, it introduces a low-cost weakly supervised learning approach for training pixel-level segmentation networks.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Carbon Neutral Energy, China University of Petroleum, Beijing 102249, China.
- College of Artificial Intelligence, China University of Petroleum, Beijing 102249, China.
- Key Laboratory of Oil and Gas Safety and Emergency Technology, Ministry of Emergency Management, Beijing 102249, China.
- School of Engineering, China University of Petroleum-Beijing at Karamay, Karamay 834000, China.
- College of Safety and Ocean Engineering, China University of Petroleum, Beijing 102249, China.
- Petrochina Beijing Gas Pipeline Co., Ltd., Beijing 100101, China.
ORCID-Profile: Haoyang Shen, Mingyue Wang, Qingqing Xu
Förderung
- CNPC and CUPB
- CNPC
Zitieren
APA
Shen, H., Xu, L., Wang, M., Dong, S., Xu, Q., Li, F., & Yu, H. (2025). YOLOv8-Seg with Dynamic Multi-Kernel Learning for Infrared Gas Leak Segmentation: A Weakly Supervised Approach. Sensors, 25(16), 4939. https://doi.org/10.3390/s25164939
Vancouver
Shen H, Xu L, Wang M, Dong S, Xu Q, Li F, et al. YOLOv8-Seg with Dynamic Multi-Kernel Learning for Infrared Gas Leak Segmentation: A Weakly Supervised Approach. Sensors. 2025;25(16):4939. doi:10.3390/s25164939
BibTeX
@article{Shen2025,
author = {Shen, Haoyang and Xu, Lushuai and Wang, Mingyue and Dong, Shaohua and Xu, Qingqing and Li, Feng and Yu, Haiyang},
title = {YOLOv8-Seg with Dynamic Multi-Kernel Learning for Infrared Gas Leak Segmentation: A Weakly Supervised Approach},
journal = {Sensors},
year = {2025},
volume = {25},
number = {16},
pages = {4939},
doi = {10.3390/s25164939}
}
EUVIMED