Abstract
Abstract
The petrochemical industry faces frequent hazardous gas leaks, which demand precise and timely detection to avert severe consequences. Existing computer vision approaches encounter challenges due to limitations in gas characteristics and scene features. To address these issues, we propose a multiscale receptive field grouped and split attention network, GAS-YOLO, that integrates infrared imaging technology. Within GAS-YOLO, we design a novel module, multi-scale receptive field grouped convolution (MRFGConv), to preserve fine-grained information, preventing detail loss and addressing spatial attention feature-sharing issues. An innovative split convolution attention (SCA) mechanism in the C2f module effectively couples multi-scale features, balancing performance and efficiency. Additionally, the asymptotic feature pyramid network (AFPN) facilitates the mutual interaction of information between non-adjacent levels, enabling advanced feature fusion. Using benchmark InfraGasLeakDataset, GAS-YOLO surpasses YOLOv8-n by 5.8% mAP50, with SCA outperforming state-of-the-art attention models. Experiment results validate the effectiveness and feasibility of our proposed approaches, providing valuable insights into hazardous chemical gas leak detection.
Funder
Key Scientific Research Foundation of the Education Department of Province Anhui
National Natural Science Foundation of China
Program for Scientific Research Innovation Team in Colleges and Universities of Anhui Province
Hefei University Talent Research Funding
Hefei University Scientific Research Development Funding
University Natural Sciences Research Project of Province Anhui
Anhui Province Graduate Student Quality Engineering Project