Study of Indoor Visual SLAM System for Semi-autonomous Robot Platform

Camera Calibration, Feature Extraction, Odometry, Indoor Visual SLAM, Semi-autonomous Robot

Authors

  • Yeon Taek OH School of Mechanical Engineering, Tongmyung University, 428 Sinseon-ro, Nam-gu, Busan, 48520, Korea
November 23, 2021

Downloads

This study propose the use of heterogeneous visual landmarks, points and line segments, to achieve effective cooperation in indoor SLAM environments. In order to achieve un-delayed initialization required by the bearing-only observations, the well-known inverse-depth parameterization is adopted to estimate 3D points. Similarly, to estimate 3D line segments, we present a novel parameterization based on anchored Plücker coordinates, to which extensible endpoints are added