摘要：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. ? 2025 by the authors.

ISSN号：1424-8220

卷、期、页：卷25期16

发表日期：2025-08-01

影响因子：0.000000

期刊分区（SCI为中科院分区）：三区

收录情况：SCI（科学引文索引印刷版）,EI（工程索引）,SCIE（科学引文索引网络版）

发表期刊名称：Sensors

参与作者：Li, Feng

通讯作者：沈昊旸,徐鲁帅

第一作者：王明月,董绍华,徐晴晴,于海洋

论文类型：期刊论文

论文概要：沈昊旸,徐鲁帅,王明月,董绍华,徐晴晴,Li, Feng,于海洋，YOLOv8-Seg with Dynamic Multi-Kernel Learning for Infrared Gas Leak Segmentation: A Weakly Supervised Approach，Sensors，2025，卷25期16

论文题目：YOLOv8-Seg with Dynamic Multi-Kernel Learning for Infrared Gas Leak Segmentation: A Weakly Supervised Approach