raulmur/ORB_SLAM

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1632 stars · 817 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

ORB-SLAM is a real-time monocular SLAM system written in C++ that computes camera trajectories and sparse 3D reconstructions from a single camera. It supports loop closing and global relocalization and is integrated with ROS for image input and visualization.

Use cases

• estimate camera trajectory from monocular video in real time
• build a sparse 3D map of an environment from a single camera
• perform loop closure and relocalization in SLAM pipelines
• run visual odometry on KITTI-style datasets
• localize a handheld camera or vehicle-mounted camera indoors and outdoors

When to choose

• you need a proven, accurate monocular SLAM solution with ROS integration
• you are doing robotics or SLAM research and want a well-cited reference implementation
• you work on Linux with C++ and can build against Boost and ROS

When to avoid

• you need stereo or RGB-D support (use ORB-SLAM2 or ORB-SLAM3 instead)
• you need a maintained project with recent updates or modern build tooling
• you need a permissively licensed library for closed-source commercial use (GPLv3)
• you target Windows or non-ROS platforms

Facets

library · maturity maintenance

computer-vision simulation graphics robotics autonomous-vehicles computer-vision cpp slam monocular-slam orb-features real-time 3d-reconstruction ros robotics computer-vision c-plus-plus algorithms linux

Member repositories

For agents

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