Parallel, real-time visual SLAM

In this paper we present a novel system for real-time, six degree of freedom visual simultaneous localization and mapping using a stereo camera as the only sensor. The system makes extensive use of parallelism both on the graphics processor and through multiple CPU threads. Working together these threads achieve real-time feature tracking, visual odometry, loop detection and global map correction using bundle adjustment. The resulting corrections are fed back into to the visual odometry system to limit its drift over long sequences. We demonstrate our system on a series videos from challenging indoor environments with moving occluders, visually homogenous regions with few features, scene parts with large changes in lighting and fast camera motion. The total system performs its task of global map building in real time including loop detection and bundle adjustment on typical office building scale scenes.

Authors

• Brian Clipp
• Jongwoo Lim
• Jan-Michael Frahm
• Marc Pollefeys

Keywords

• Cameras
• Visualization
• Three dimensional displays
• Real time systems
• Feature extraction
• Tracking
• Simultaneous localization and mapping
• Graphics Processing Unit
• Indoor Environments
• Global Map
• Detection Function
• Feature Tracking
• Stereo Camera
• Camera Motion
• Bundle Adjustment
• Visual Odometry
• Loop Detection
• Real-Time System
• Ground Plane
• Image Distortion
• Visual Modality
• Optical Flow
• 3D Point
• Feature Matching
• 3D Features
• Repeat Structure
• SIFT Features
• Camera Pose
• Nonexpansive Mapping
• Global Module
• 2D Feature
• Stereo Images
• Global Consistency
• Query Image
• Reprojection Error
• Open-plan