ETH Zurich - D-INFK - IVC - CVG - Research - Multi-Camera VO

Towards Robust Visual Odometry with a Multi-Camera System

Peidong Liu (1)      Marcel Geppert (1)      Lionel Heng (2)      Torsten Sattler (1)     
Andreas Geiger (1,3)      Marc Pollefeys(1,4)

(1) CVG ETH Zurich, Switzerland
(2) Robotics Autonomy Lab, DSO National Laboratories, Singapore
(3) Autonomous Vision Group, MPI for Intelligent Systems Tübingen
(4) Microsoft, Redmond, USA



We present a visual odometry (VO) algorithm for a multi-camera system and robust operation in challenging environments. Our algorithm consists of a pose tracker and a local mapper. The tracker estimates the current pose by minimizing photometric errors between the most recent keyframe and the current frame. The mapper initializes the depths of all sampled feature points using plane-sweeping stereo. To reduce pose drift, a sliding window optimizer is used to refine poses and structure jointly. Our formulation is flexible enough to support an arbitrary number of stereo cameras. We evaluate our algorithm thoroughly with five datasets. The datasets were captured in different conditions: daytime, night-time with near-infrared (NIR) illumination and night-time without NIR illumination. Experimental results show that a multi-camera setup makes the VO more robust in challenging environments, especially night-time conditions, in which a single stereo configuration fails easily due to the lack of features.


  • Towards Robust Visual Odometry with a Multi-Camera System
    Peidong Liu, Marcel Geppert, Lionel Heng, Torsten Sattler, Andreas Geiger and Marc Pollefeys
    submitted to IROS 2018.

© CVG, ETH Zürich