Visual odometry using a homography formulation with decoupled rotation and translation estimation using minimal solutions

Banglei Guan (1) , Pascal Vasseur (2) , Cédric Demonceaux (3, 4) , Friedrich Fraundorfer (5, 6)

1 Department of Computer Science and Technology [National University of Defense Technology]
2 LITIS - Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes
3 Le2i - Laboratoire d'Electronique, d'Informatique et d'Image [EA 7508]
4 VIBOT - VIsion pour la roBOTique [VIBOT CNRS ERL 6000]
5 Institute of Computer Graphics and Vision [Graz]
6 IMF - DLR Institut für Methodik der Fernerkundung / DLR Remote Sensing Technology Institute

In this paper we present minimal solutions for two-view relative motion estimation based on a homography formulation. By assuming a known vertical direction (e.g. from an IMU) and assuming a dominant ground plane we demonstrate that rotation and translation estimation can be decoupled. This result allows us to reduce the number of point matches needed to compute a motion hypothesis. We then derive different algorithms based on this decoupling that allow an efficient estimation. We also demonstrate how these algorithms can be used efficiently to compute an optimal inlier set using exhaustive search or histogram voting instead of a traditional RANSAC step. Our methods are evaluated on synthetic data and on the KITTI data set, demonstrating that our methods are well suited for visual odometry in road driving scenarios.

Domaines: Robotique [cs.RO]; Vision par ordinateur et reconnaissance de formes [cs.CV]

Banglei Guan, Pascal Vasseur, Cédric Demonceaux, Friedrich Fraundorfer. Visual odometry using a homography formulation with decoupled rotation and translation estimation using minimal solutions. International Conference on Robotics and Automation - ICRA, May 2018, Brisbane, Australia. ⟨10.1109/ICRA.2018.8460747⟩. ⟨hal-01756773⟩