U-Net Inspired Deep Neural Network-Based Smoke Plume Detection in Satellite Images  

作　　者：Ananthakrishnan Balasundaram Ayesha Shaik Japmann Kaur Banga Aman Kumar Singh 

机构地区：[1]Centre for Cyber Physical Systems,Vellore Institute of Technology(VIT),Chennai,Tamil Nadu,600127,India [2]School of Computer Science and Engineering,Vellore Institute of Technology(VIT),Chennai,Tamil Nadu,600127,India

出　　处：《Computers, Materials & Continua》2024年第4期779-799,共21页计算机、材料和连续体（英文）

摘　　要：Industrial activities, through the human-induced release of Green House Gas (GHG) emissions, have beenidentified as the primary cause of global warming. Accurate and quantitative monitoring of these emissions isessential for a comprehensive understanding of their impact on the Earth’s climate and for effectively enforcingemission regulations at a large scale. This work examines the feasibility of detecting and quantifying industrialsmoke plumes using freely accessible geo-satellite imagery. The existing systemhas so many lagging factors such aslimitations in accuracy, robustness, and efficiency and these factors hinder the effectiveness in supporting timelyresponse to industrial fires. In this work, the utilization of grayscale images is done instead of traditional colorimages for smoke plume detection. The dataset was trained through a ResNet-50 model for classification and aU-Net model for segmentation. The dataset consists of images gathered by European Space Agency’s Sentinel-2 satellite constellation from a selection of industrial sites. The acquired images predominantly capture scenesof industrial locations, some of which exhibit active smoke plume emissions. The performance of the abovementionedtechniques and models is represented by their accuracy and IOU (Intersection-over-Union) metric.The images are first trained on the basic RGB images where their respective classification using the ResNet-50model results in an accuracy of 94.4% and segmentation using the U-Net Model with an IOU metric of 0.5 andaccuracy of 94% which leads to the detection of exact patches where the smoke plume has occurred. This work hastrained the classification model on grayscale images achieving a good increase in accuracy of 96.4%.

关 键 词：Smoke plume ResNet-50 U-Net geo satellite images early warning global monitoring 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP391.41[自动化与计算机技术—控制科学与工程]