Khairurizal Alfathdyanto, M. S. Febrianti, A. Prihatmanto, C. Machbub
{"title":"Creating Database for Traditional Dance Categorization using CSV File Format","authors":"Khairurizal Alfathdyanto, M. S. Febrianti, A. Prihatmanto, C. Machbub","doi":"10.1109/ICSENGT.2018.8606387","DOIUrl":null,"url":null,"abstract":"Categorizing dance requires an enormous amount of data storage which usually uses video as storage file. Joint position values from body movement mainly become base in categorizing dance. Author proposes an offline database system for traditional dance categorization system which utilizes CSV file format storing those numerical values. The method provides an easily accessible and sufficient database system that serves as training dataset and avatar reconstruction data. Meanwhile, the dance categorization system utilizes hidden Markov model. Recorded file consumes 40% less storage space compared to Brekel Pro Body v2 CSV outputs and differentiates two sequence correctly.","PeriodicalId":111551,"journal":{"name":"2018 IEEE 8th International Conference on System Engineering and Technology (ICSET)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2018 IEEE 8th International Conference on System Engineering and Technology (ICSET)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICSENGT.2018.8606387","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2
Abstract
Categorizing dance requires an enormous amount of data storage which usually uses video as storage file. Joint position values from body movement mainly become base in categorizing dance. Author proposes an offline database system for traditional dance categorization system which utilizes CSV file format storing those numerical values. The method provides an easily accessible and sufficient database system that serves as training dataset and avatar reconstruction data. Meanwhile, the dance categorization system utilizes hidden Markov model. Recorded file consumes 40% less storage space compared to Brekel Pro Body v2 CSV outputs and differentiates two sequence correctly.
舞蹈分类需要大量的数据存储,通常使用视频作为存储文件。肢体动作的关节位置值主要成为对舞蹈进行分类的依据。针对传统的舞蹈分类系统,作者提出了一种离线数据库系统,该系统利用CSV文件格式存储这些数值。该方法提供了一个易于访问和充分的数据库系统,作为训练数据集和化身重建数据。同时,舞蹈分类系统采用隐马尔可夫模型。与Brekel Pro Body v2 CSV输出相比,录制文件消耗的存储空间减少了40%,并正确区分了两个序列。