AprilTag
- Software
- Perception
- Library
A visual fiducial marker system for robotics: a small C library that detects tags in images and estimates their pose, with Python and other bindings.
Made by AprilRobotics.
Source on GitHub: github.com/AprilRobotics/apriltag (opens in a new tab). Facts read at commit b7c0ebe (opens in a new tab).
Licenses
- Code
- BSD-2-Clause (opens in a new tab)
Read by Robotheca from LICENSE.md (opens in a new tab) (BSD-2-Clause) at commit b7c0ebe (opens in a new tab), on 16 Oct 2026.
- Commercial use
- Yes
What it does
- Detects AprilTag fiducial markers in images, with a detector more than twice as fast as AprilTag 2.
- Improves detection rate on small tags and supports flexible tag layouts, including circular and hole-containing designs.
- Provides pose estimation of a detected tag relative to the camera, given tag size and camera intrinsics.
- Offers a C library with minimal dependencies, plus Python usage and wrappers for OpenCV, Matlab, Julia and WebAssembly.
- Recommends the tagStandard41h12 family for most applications, with other families for more tags, circular objects or ArUco support.
- Includes helper functions for deep-copying detector configurations and detection results for multi-threaded use.
Written by Robotheca from the project's README (opens in a new tab) at commit b7c0ebe.
Getting started
- Difficulty
- Intermediate
- Hardware it needs, as the project states it
- Officially only Linux is supported, though installation on Windows has worked for some users. Needs CMake to build; no external dependencies are required.
- How to start
- The project's website (opens in a new tab)
Maintenance
- Status
- Active: a commit in the last 90 days
- Newest commit
- 7 Aug 2026 on master
- Latest release
- v3.4.5 (29 Aug 2025)
Checked on GitHub on 16 Oct 2026.
Links
Robots on Robotheca that use it
No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.
Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.