pupil-apriltags
Python bindings for apriltags v3
Decision gist · record as of 2026-08-14
Yes. The package is production-stable, actively maintained, carries no known vulnerabilities, and offers pre-built wheels for broad platform coverage. Install it if you need AprilTag detection in Python and are comfortable with the pupil-labs variant of the AprilTags3 library; verify that its adjustments align with your specific accuracy or performance requirements if migrating from another AprilTag binding.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires numpy and a compatible Python version (3.6+); on Windows, pupil-pthreads-win is an additional runtime dependency.
- Pre-built wheels available for multiple Python versions on macOS (ARM64), Linux (x86_64), and Windows, reducing compile friction.
- Repository is actively maintained with recent commits and stable production status.
License · maintenance · safety
MIT (permissive) — MIT license permits commercial and private use with minimal restrictions; you may use, modify, and distribute this package freely provided you include the license notice.
last release 2025-04-22 (479 days) · last repo commit 2026-07-06 · 163 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 95,777 downloads/mo, #13,249 on PyPI
Alternatives
Verify before relying
pip install pupil-apriltags
from pupil_apriltags import Detector
at_detector = Detector(families="tag36h11", nthreads=1)
detections = at_detector.detect(img)- Performance characteristics (detection speed, accuracy) relative to other AprilTag implementations.
- Whether the pupil-labs adjustments to the original AprilTags3 library introduce behavioral differences relevant to your use case.
What it is and what it does
pupil-apriltags wraps the AprilTags3 library from AprilRobotics, providing a Python interface to detect and localize fiducial markers (AprilTags) in images. It is commonly used in robotics, augmented reality, and computer vision systems where visual markers serve as reference points for pose estimation, localization, or object tracking. The package ships with pre-built wheels for common platforms, reducing installation friction compared to compiling from source.
The core API centers on the Detector class, which you configure with tag family, threading, and image processing parameters, then call with image data to retrieve detections. The library depends on numpy for array handling and includes platform-specific threading support via pupil-pthreads-win on Windows. It is actively maintained, supports modern Python versions, and carries no known security vulnerabilities.
Use it for
- Robotics: localize robots in indoor environments using AprilTag markers placed on walls or floors.
- Augmented reality: anchor virtual content to physical AprilTag markers in real-world scenes.
- Camera calibration and pose estimation: use tags as known reference points to compute camera position and orientation.
- Multi-agent tracking: coordinate multiple robots or objects by detecting shared AprilTag landmarks.
- Visual SLAM: integrate tag detections as loop-closure constraints in simultaneous localization and mapping.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
The package is production-stable, actively maintained, carries no known vulnerabilities, and offers pre-built wheels for broad platform coverage. Install it if you need AprilTag detection in Python and are comfortable with the pupil-labs variant of the AprilTags3 library; verify that its adjustments align with your specific accuracy or performance requirements if migrating from another AprilTag binding.
Install
pupil-apriltags on PyPI
Before you install
Pre-built wheels available for multiple Python versions on macOS (ARM64), Linux (x86_64), and Windows, reducing compile friction. Repository is actively maintained with recent commits and stable production status.
Requires numpy and a compatible Python version (3.6+); on Windows, pupil-pthreads-win is an additional runtime dependency.
License in practice
MIT license permits commercial and private use with minimal restrictions; you may use, modify, and distribute this package freely provided you include the license notice.
Quickstart
pip install pupil-apriltags
from pupil_apriltags import Detector
at_detector = Detector(families="tag36h11", nthreads=1)
detections = at_detector.detect(img)Verify before relying
- Performance characteristics (detection speed, accuracy) relative to other AprilTag implementations.
- Whether the pupil-labs adjustments to the original AprilTags3 library introduce behavioral differences relevant to your use case.
Package facts
| License | MIT permissive |
| Python support | Supports the current Python release >=3.6 |
| Install friction | Medium. Platform-specific wheel |
| Runtime dependencies | 3 packagesnumpyimportlib-metadatapupil-pthreads-win |
| Maintenance | Actively maintained 479 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 95,777 / month, #13,249 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 5 - Production/StableIntended Audience :: DevelopersLicense :: OSI Approved :: MIT LicenseProgramming Language :: Python :: 3Programming Language :: Python :: 3 :: Only |
Evidence: pupil_apriltags-1.0.4.post11-cp310-cp310-macosx_11_0_arm64.whl; pupil_apriltags-1.0.4.post11-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; pupil_apriltags-1.0.4.post11-cp310-cp310-win_amd64.whl; pupil_apriltags-1.0.4.post11-cp311-cp311-macosx_11_0_arm64.whl; pupil_apriltags-1.0.4.post11-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; pupil_apriltags-1.0.4.post11-cp311-cp311-win_amd64.whl; pupil_apriltags-1.0.4.post11-cp312-cp312-macosx_11_0_arm64.whl; pupil_apriltags-1.0.4.post11-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; pupil_apriltags-1.0.4.post11-cp312-cp312-win_amd64.whl; pupil_apriltags-1.0.4.post11-cp313-cp313-macosx_11_0_arm64.whl; pupil_apriltags-1.0.4.post11-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; pupil_apriltags-1.0.4.post11-cp313-cp313-win_amd64.whl; pupil_apriltags-1.0.4.post11-cp36-cp36m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; pupil_apriltags-1.0.4.post11-cp36-cp36m-win_amd64.whl; pupil_apriltags-1.0.4.post11-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; pupil_apriltags-1.0.4.post11-cp37-cp37m-win_amd64.whl; pupil_apriltags-1.0.4.post11-cp38-cp38-macosx_11_0_arm64.whl; pupil_apriltags-1.0.4.post11-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl; pupil_apriltags-1.0.4.post11-cp38-cp38-win_amd64.whl; pupil_apriltags-1.0.4.post11-cp39-cp39-macosx_11_0_arm64.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “apriltag detection python”
- pupil-apriltagsPython bindings for the AprilTags v3 library, enabling detection and…
- pyodPyOD detects anomalies and outliers across tabular, time series,…
- yolov5YOLOv5 is a packaged object detection model that runs inference on…
Give your agent the search over MCP, or paste the wish link into any chat.
More Scientific/Engineering packages
NumPy provides an N-dimensional array object and a comprehensive suite of mathematical, linear algebra, Fourier transform, and random number functions for scientific computing in Python.
pandas provides fast, flexible data structures (Series and DataFrame) for loading, cleaning, transforming, and analyzing labeled or relational data in Python.
scipy provides numerical algorithms for mathematics, science, and engineering—including optimization, integration, linear algebra, Fourier transforms, signal and image processing, and ODE solvers—built on numpy arrays.
scikit-learn provides a comprehensive Python library for supervised and unsupervised machine learning, including classification, regression, clustering, dimensionality reduction, and model evaluation tools built on NumPy and SciPy.
Install it if you need to train, evaluate, or deploy supervised or unsupervised learning models.
dill extends Python's pickle module to serialize and deserialize a much wider range of Python objects, including functions, lambdas, classes, and interpreter sessions, to byte streams for storage or network transmission.
Multiprocess is an enhanced fork of Python's standard multiprocessing library that uses dill for better serialization, allowing you to spawn processes with a threading-like API and share complex objects between them.
Install it if you use multiprocessing and encounter pickle serialization limits with lambdas or complex objects.
See also pyPPG · norfair · pycolmap · pyobjc-framework-Vision · dlib · ultralytics · azure-ai-vision-imageanalysis · gtsam · voxel51-eta · mtcnn