{"title":"A Fast Visual Odometry and Mapping System for RGB-D Cameras","authors":"Bruno M. F. Silva, L. Gonçalves","doi":"10.1109/SBR.LARS.ROBOCONTROL.2014.35","DOIUrl":null,"url":null,"abstract":"The introduction of low cost range sensing devices such as RGB-D cameras allows applications for Robotics to exploit novel and real-time capabilities. One such application is Visual Odometry, a module responsible to use the synchronized color/depth streams captured by this class of sensors to estimate the position and orientation of a robot at the same time that a map representation of the environment is built. Aiming to localize robots in a fast and efficient way, we design a Visual Odometry system for RGB-D sensors that allows real-time (approximately 25 Hz) camera pose estimation despite the fact that no specialized hardware (such as modern GPUs) is employed. Experiments carried out on publicly available benchmark and datasets demonstrate the usefulness of the method, which achieved localization accuracy superior to the state-of-the-art RGB-D SLAM algorithm.","PeriodicalId":264928,"journal":{"name":"2014 Joint Conference on Robotics: SBR-LARS Robotics Symposium and Robocontrol","volume":"68 12","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2014-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2014 Joint Conference on Robotics: SBR-LARS Robotics Symposium and Robocontrol","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SBR.LARS.ROBOCONTROL.2014.35","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
The introduction of low cost range sensing devices such as RGB-D cameras allows applications for Robotics to exploit novel and real-time capabilities. One such application is Visual Odometry, a module responsible to use the synchronized color/depth streams captured by this class of sensors to estimate the position and orientation of a robot at the same time that a map representation of the environment is built. Aiming to localize robots in a fast and efficient way, we design a Visual Odometry system for RGB-D sensors that allows real-time (approximately 25 Hz) camera pose estimation despite the fact that no specialized hardware (such as modern GPUs) is employed. Experiments carried out on publicly available benchmark and datasets demonstrate the usefulness of the method, which achieved localization accuracy superior to the state-of-the-art RGB-D SLAM algorithm.