raulmur/ORB_SLAM2

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

10223 stars · 4749 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

ORB-SLAM2 is a real-time SLAM library for monocular, stereo, and RGB-D cameras that computes camera trajectories and sparse 3D reconstructions with loop detection and relocalization. It is a well-known research codebase from the University of Zaragoza, released under GPLv3 and usable with or without ROS.

Use cases

• run visual SLAM on a monocular camera feed
• estimate camera trajectory from stereo video
• build a sparse 3D map from an RGB-D camera
• detect loop closures and relocalize a camera in real time
• evaluate SLAM on KITTI, TUM, or EuRoC datasets
• integrate SLAM into a ROS robot

When to choose

• you need a proven, accurate feature-based visual SLAM system for research or benchmarking
• you work with monocular, stereo, or RGB-D cameras and want loop closure and relocalization
• you want a ROS node or standalone C++ SLAM library

When to avoid

• you need actively maintained code or modern dependency versions - the project is largely in maintenance mode
• you need dense mapping or visual-inertial SLAM - consider ORB-SLAM3 or alternatives
• your project is not GPLv3-compatible

Facets

library · maturity maintenance

computer-vision simulation graphics robotics computer-vision autonomous-vehicles cpp slam orb-features monocular stereo rgb-d loop-closure relocalization camera-tracking 3d-reconstruction ros algorithms linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="raulmur/ORB_SLAM2")