论文标题
对四个现成的专有视觉惯性循环系统的经验评估
An Empirical Evaluation of Four Off-the-Shelf Proprietary Visual-Inertial Odometry Systems
论文作者
论文摘要
商业视觉惯性进程（VIO）系统一直引起人们的关注，以成本效益，现成的六个自由度（6-DOF）自由度（6-DOF）自动运动跟踪方法，除了它们在没有外部定位或全球定位系统的情况下操作的能力，除了它们在没有外部定位或全球定位系统的情况下运行的能力外，还可以估算准确且一致的摄像头姿势数据。但是，从现有结果中尚不清楚，在哪些商业VIO平台对室内和室外机器人应用的状态估计方面是最稳定，一致和准确的。我们通过一系列室内和室外实验评估了四个受欢迎的专有VIO系统（Apple Arkit，Google Arcore，Intel Realsense T265和Stereolabs Zed 2），我们可以在其中显示其定位稳定性，一致性，准确性和准确性。我们将完整的结果作为研究界的基准比较。
Commercial visual-inertial odometry (VIO) systems have been gaining attention as cost-effective, off-the-shelf six degrees of freedom (6-DoF) ego-motion tracking methods for estimating accurate and consistent camera pose data, in addition to their ability to operate without external localization from motion capture or global positioning systems. It is unclear from existing results, however, which commercial VIO platforms are the most stable, consistent, and accurate in terms of state estimation for indoor and outdoor robotic applications. We assess four popular proprietary VIO systems (Apple ARKit, Google ARCore, Intel RealSense T265, and Stereolabs ZED 2) through a series of both indoor and outdoor experiments where we show their positioning stability, consistency, and accuracy. We present our complete results as a benchmark comparison for the research community.
