Noncentral 3D pose registration for the single-camera SOS

Visual Odometry with a Single-Camera Stereo Omnidirectional System

Abstract

This paper presents the advantages of a single-camera stereo omnidirectional system (SOS) in estimating egomotion in real-world environments. Dynamic conditions and the lack of features to track in the observable scene affect the pose estimation of all narrow-view systems. We compare the tracking accuracy and stability of the single-camera SOS versus an RGB-D device under various real circumstances. Our numerical evaluation is performed with respect to ground truth 3D data obtained from a motion capture system. The datasets and experimental results we provide are unique due to the nature of our catadioptric omnistereo rig, and the situations in which we captured these motion sequences. We have implemented a tracking system with proven correctness for both synthetic and real scenes. This implementation does not make any motion model assumptions, and it maintains a consistent configuration among the compared sensors. Our experimental outcomes confer the robustness in 3D metric visual odometry estimation that the single-camera SOS can achieve under normal and special conditions in which other perspective view systems such as RGB-D cameras would fail.

Publication
Pending.
Date