J. R. Smit, Hugh G. P. Hunt, C. Schumann, T. Warner
{"title":"Metric collection on semantically segmented highspeed lightning footage with machine learning","authors":"J. R. Smit, Hugh G. P. Hunt, C. Schumann, T. Warner","doi":"10.1109/ICLPandSIPDA54065.2021.9627429","DOIUrl":null,"url":null,"abstract":"An investigation of the accuracy of a system using semantic segmentation in determining the number of individual strokes, direction of leaders and strike points for high-speed lightning footage. The paper uses a pre-trained DeepLabv3+ network, chosen to allow for the lowest computer requirements, where the last layers of the model are retrained on lightning footage. The network produces semantic segmented images where each pixel has a numerical label which are evaluated to count strokes. Regions of interest are created per strike and used to reduce noise. The system has a stroke detection efficiency of 70.1%, direction accuracy of 80% and a strike point accuracy of 89.5% when evaluated on 15 videos.","PeriodicalId":70714,"journal":{"name":"中国防雷","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2021-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"中国防雷","FirstCategoryId":"1089","ListUrlMain":"https://doi.org/10.1109/ICLPandSIPDA54065.2021.9627429","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
An investigation of the accuracy of a system using semantic segmentation in determining the number of individual strokes, direction of leaders and strike points for high-speed lightning footage. The paper uses a pre-trained DeepLabv3+ network, chosen to allow for the lowest computer requirements, where the last layers of the model are retrained on lightning footage. The network produces semantic segmented images where each pixel has a numerical label which are evaluated to count strokes. Regions of interest are created per strike and used to reduce noise. The system has a stroke detection efficiency of 70.1%, direction accuracy of 80% and a strike point accuracy of 89.5% when evaluated on 15 videos.