Enhancing 3D Visual Odometry with Single-Camera Stereo Omnidirectional Systems

We explore low-cost solutions for efficiently improving the 3D pose estimation problem of a single omnidirectional camera moving in an unfamiliar environment.

GUMS: A Generalized Unified Model for Stereo Omnidirectional Vision (Demonstrated Via a Folded Catadioptric System)

GUMS is a complete projection model for omnidirectional stereo vision systems. GUMS is based on the existing generalized unified model (GUM), which we extend for fixed baseline sensors.