UZ-SLAMLab/ORB_SLAM3
ORB SLAM3
ORB_SLAM3 is a visual-inertial SLAM library designed for real-time simultaneous localization and mapping. It provides a framework for tracking camera movement and building 3D maps of environments using monocular, stereo, or RGB-D cameras combined with inertial sensors.
The system features a multi-map fusion engine capable of merging separate spatial sessions into a single seamless representation of an environment. It includes specialized processing for wide-angle and fisheye lenses to expand the visual field of view for spatial tracking.
The library covers a broad range of spatial intelligence capabilities, including visual odometry, loop closure, and map optimization. It supports the integration of inertial data to estimate scale and velocity, as well as integration with the Robot Operating System for robotic spatial mapping and localization.
The project includes tools for execution performance analysis to measure processing time and system latency.
Features
- Simultaneous Localization and Mapping - Implements a real-time framework for tracking camera movement and building 3D maps of environments using visual and inertial sensors.
- Visual SLAM Implementations - Provides a real-time visual SLAM implementation for tracking camera movement and building 3D maps.
- Loop Closure Detection - Implements a Bag-of-Words system to detect revisited locations and correct spatial drift during mapping.
- Visual Odometry Systems - Implements feature-based visual odometry using FAST and BRIEF descriptors to track camera motion.
- Visual-Inertial SLAM Implementations - A complete library for real-time simultaneous localization and mapping using cameras and inertial sensors.
- Inertial Environmental Tracking - Integrates IMU data to estimate scale and velocity, maintaining stable tracking during camera occlusions.
- Map Fusion - Features a multi-map fusion engine capable of merging separate spatial sessions into a single seamless representation of an environment.
- Visual-Inertial Odometry Frameworks - Fuses high-frequency IMU measurements with visual tracking in a tightly-coupled sliding-window filter.
- Bundle Adjustment Algorithms - Provides graph-based bundle adjustment to optimize camera poses and 3D points by minimizing reprojection error.
- Diverse Camera Input Processing - Provides the ability to calculate spatial positioning using monocular, stereo, or depth sensor data across various lens models.
- Fisheye Lens Processing - Processes wide-angle and fisheye lens inputs to ensure accurate spatial positioning.
- Wide-Angle Lens Processing - Supports wide-angle and fisheye lens models to expand the visual field of view for tracking.
- Spatial Map Fusion - Includes a multi-map fusion engine that merges separate spatial sessions into a seamless environment representation.
- Robotics And Autonomous Systems - Integrates visual-inertial SLAM capabilities within the Robot Operating System for autonomous navigation.
- Covisibility Graphs - Organizes map keyframes into covisibility graphs to efficiently manage search spaces for visual landmarks.
- Motion Models - Uses a constant-velocity motion model to predict camera positions and optimize feature matching search areas.
Star history
How this analysis was created: This summary and feature list were written by an AI model that read the project's README and public documentation pages. Each feature links to the documentation it came from; stars, license and language come straight from the GitHub API. The model does not read the source code, and the analysis is refreshed when the project is re-analysed. Learn more on our About page.
