Efficient multi-camera visual-inertial SLAM for micro aerial vehicles

Visual SLAM is an area of vivid research and bears countless applications for moving robots. In particular, micro aerial vehicles benefit from visual sensors due to their low weight. Their motion is, however, often faster and more complex than that of ground-based robots which is why systems with multiple cameras are currently evaluated and deployed. This, in turn, drives the computational demand for visual SLAM algorithms.

Authors

• Sebastian Houben
• Jan Quenzel
• Nicola Krombach
• Sven Behnke

Keywords

• Cameras
• Simultaneous localization and mapping
• Robot vision systems
• Visualization
• Optimization
• Feature extraction
• Aerial Vehicles
• Micro Air Vehicles
• Optimization Problem
• Local Map
• Inertial Measurement Unit
• Multiple Cameras
• Accurate Mapping
• Nonlinear Programming
• Path Planning
• Corresponding Points
• Consecutive Frames
• Tracking Accuracy
• Feature Matching
• Pose Estimation
• Current Frame
• Map Points
• Previous Frame
• Camera Frame
• Reprojection
• Relative Pose
• Feature-based Approaches
• Part Of The Scene
• Loop Closure
• Stereo Pairs
• Graph Optimization
• Stereo Camera
• Bundle Adjustment