R. Damindarov, C. A. Fam, R. A. Boby, M. Fahim, A. Klimchik, T. Matsumaru
{"title":"A depth camera-based system to enable touch-less interaction using hand gestures","authors":"R. Damindarov, C. A. Fam, R. A. Boby, M. Fahim, A. Klimchik, T. Matsumaru","doi":"10.1109/NIR52917.2021.9666090","DOIUrl":null,"url":null,"abstract":"Touch-less interaction is an active area of research due to its numerous applications ranging from medical systems to gaming. In this paper we propose a novel interactive system based on RealSense camera to track the pose of hand and to recognize gestures. Our approach is based on MediaPipe model introduced by Google to detect the landmarks of the hand. The system utilizes the camera calibration information and user actions to get the geometry of the deployed environment, which shows high accuracy in measurement of hand position. The touch-less interaction is demonstrated using a graphical user interface for painting.","PeriodicalId":333109,"journal":{"name":"2021 International Conference \"Nonlinearity, Information and Robotics\" (NIR)","volume":"02 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 International Conference \"Nonlinearity, Information and Robotics\" (NIR)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/NIR52917.2021.9666090","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5
Abstract
Touch-less interaction is an active area of research due to its numerous applications ranging from medical systems to gaming. In this paper we propose a novel interactive system based on RealSense camera to track the pose of hand and to recognize gestures. Our approach is based on MediaPipe model introduced by Google to detect the landmarks of the hand. The system utilizes the camera calibration information and user actions to get the geometry of the deployed environment, which shows high accuracy in measurement of hand position. The touch-less interaction is demonstrated using a graphical user interface for painting.