{"title":"Perancangan Aplikasi Pengumpulan Data Statistik Penguasaan Bola Berbasis Background Subtraction","authors":"M. Fadhlan, Hertog Nugroho, L. Maldini","doi":"10.31544/jtera.v6.i2.2021.329-340","DOIUrl":null,"url":null,"abstract":"In football matches, possession of the ball becomes an assessment and evaluation material that shows opportunities to score. Calculation of ball possession is done by calculating the time of the total game time manually. Even though it is only an outline of the assessment of football matches, there are still many errors in writing match statistics due to human error, especially in Indonesia. To overcome this problem, in this study an application was made to collect ball possession statistical data using background subtraction. Several frames on the recording of a football match are taken to make a reference background and then a subtraction process is carried out with the frame during the match. The result of the subtraction will then form a rectangular border whose sides indicate the outermost object detected. The rectangular position will be divided into five conditions that determine ball possession statistics. The detection results are compared with human judgments to assess the detection accuracy. The result of this research is a prototype in the form of an application as the application of the background subtraction method. Based on the results of the research that has been done, the detection accuracy is 91%. Most of the errors occur because the object is idle for too long which makes the object in the background and is not detected by the system.","PeriodicalId":17680,"journal":{"name":"JTERA (Jurnal Teknologi Rekayasa)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2021-12-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"JTERA (Jurnal Teknologi Rekayasa)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.31544/jtera.v6.i2.2021.329-340","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
In football matches, possession of the ball becomes an assessment and evaluation material that shows opportunities to score. Calculation of ball possession is done by calculating the time of the total game time manually. Even though it is only an outline of the assessment of football matches, there are still many errors in writing match statistics due to human error, especially in Indonesia. To overcome this problem, in this study an application was made to collect ball possession statistical data using background subtraction. Several frames on the recording of a football match are taken to make a reference background and then a subtraction process is carried out with the frame during the match. The result of the subtraction will then form a rectangular border whose sides indicate the outermost object detected. The rectangular position will be divided into five conditions that determine ball possession statistics. The detection results are compared with human judgments to assess the detection accuracy. The result of this research is a prototype in the form of an application as the application of the background subtraction method. Based on the results of the research that has been done, the detection accuracy is 91%. Most of the errors occur because the object is idle for too long which makes the object in the background and is not detected by the system.