Towards Robust Visual Odometry with a Multi-Camera System

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 on five datasets. The datasets were captured in different conditions: daytime, night-time with near-infrared (NIR) illumination and nighttime without NIR illumination. Experimental results show that a multi-camera setup makes the VO more robust to challenging environments, especially night-time conditions, in which a single stereo configuration fails easily due to the lack of features.

Authors

• Peidong Liu 0001
• Marcel Geppert
• Lionel Heng
• Torsten Sattler
• Andreas Geiger 0001
• Marc Pollefeys

Keywords

• Cameras
• Tracking
• Lighting
• Visual odometry
• Robot vision systems
• Robustness
• Simultaneous localization and mapping
• Multi-camera System
• Feature Points
• Local Map
• Lack Of Features
• Algorithmic Systems
• Current Frame
• Stereo Camera
• Robust Operation
• Current Pose
• Pose Tracking
• Jacobian Matrix
• Hessian Matrix
• Pose Estimation
• Joint Optimization
• Coordinate Frame
• High Dynamic Range
• Vehicle State
• Single Thread
• Sparse Feature
• Prior Term
• Stereo Pairs
• Stereo Matching
• Micro Air Vehicles
• Camera Pose
• Daylight Conditions
• Hardware Configuration
• Normal Plane
• Metric Scale
• Depth Planes