文献类型：会议论文

英文题名：Gas Leakage Segmentation in Industrial Plants

作者：Lin, Haoqi[1];Gu, Xiaojing[1];Hu, Jingyu[1];Gu, Xingsheng[1]

机构：[1]East China Univ Sci & Technol, Key Lab Adv Control & Optimizat Chem Proc, Minist Educ, Shanghai 200237, Peoples R China

会议论文集：Chinese Automation Congress (CAC)

会议日期：NOV 06-08, 2020

会议地点：Shanghai, PEOPLES R CHINA

语种：英文

外文关键词：infrared; gas; video; segmentation; 2.5D-Unet

摘要：Industrial gas leakage in chemical plants presents a high risk to health and safety, also makes a huge waste of production materials. In this paper, we propose an automatic gas segmentation method for optical gas imaging (OGI) videos, which can not only indicate the existence of leakage in frames but also show the precise locations and shapes of gas plumes. Specifically, we propose a novel video segmentation network that stacks 21) spatial convolutions, ID temporal convolutions and 31) spatial-temporal convolutions together within an encoder-decoder structure, termed 2.5D-Unet. Stacking mixed convolutions increases the representation ability of network for leakage's appearance and motion. More importantly, stacking mixed convolutions facilitates pre-training of model using still images of smoke, which is especially useful when lacking of labeled videos of leaked gas. Experimental results show, for OGI video-based gas leakage segmentation, our method outperforms existing video segmentation methods.