Cameras are widely used for localization and navigation in GNSS-denied environments. By exploiting VSLAM (Visual Simultaneous Localization and Mapping) techniques, vehicles equipped with cameras are capable of estimating their own trajectories and simultaneously building a map of the surrounding environment. Due to constraints on payload size, weight, and costs, many VSLAM applications must be based on a single camera. However, the associated monocular estimation of the vehicle trajectory and the map is ambiguous by a scale factor. The purpose of this work is to show how the correct scale factor can be estimated in planar motion cases by exploiting range measurements from a single station. The proposed method is independent of the VSLAM algorithm used for ego-motion estimation of the vehicle.
Planar Pose Estimation using a Camera and Single-Station Ranging Measurements
2017 ; Portland, Oregon, USA
2017
Conference paper
Electronic Resource
English
Multi-camera head pose estimation
British Library Online Contents | 2012
|Single-Camera Stereometric Laser Ranging System
Online Contents | 1997