{"title":"Ellipses Ring Marker for High-speed Finger Tracking","authors":"Tomohiro Sueishi, M. Ishikawa","doi":"10.1145/3489849.3489856","DOIUrl":null,"url":null,"abstract":"High-speed finger tracking is necessary for augmented reality and operation in human-machine cooperation without latency discomfort, but conventional markerless finger tracking methods are not fast enough and the marker-based methods have low wearability. In this paper, we propose an ellipses ring marker (ERM), a finger-ring marker consisting of multiple ellipses and its high-speed image recognition algorithm. The finger-ring shape has highly wearing continuity, and the surface shape is suitable for various viewing angle observation. The invariance of the ellipse in the perspective projection enables accurate and low-latency posture estimation. We have experimentally investigated the advantage in normal distribution, validated the sufficient accuracy and computational cost in the marker tracking, and showed a demonstration of dynamic projection mapping on a palm.","PeriodicalId":345527,"journal":{"name":"Proceedings of the 27th ACM Symposium on Virtual Reality Software and Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 27th ACM Symposium on Virtual Reality Software and Technology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3489849.3489856","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
High-speed finger tracking is necessary for augmented reality and operation in human-machine cooperation without latency discomfort, but conventional markerless finger tracking methods are not fast enough and the marker-based methods have low wearability. In this paper, we propose an ellipses ring marker (ERM), a finger-ring marker consisting of multiple ellipses and its high-speed image recognition algorithm. The finger-ring shape has highly wearing continuity, and the surface shape is suitable for various viewing angle observation. The invariance of the ellipse in the perspective projection enables accurate and low-latency posture estimation. We have experimentally investigated the advantage in normal distribution, validated the sufficient accuracy and computational cost in the marker tracking, and showed a demonstration of dynamic projection mapping on a palm.