# lessthanoptimal/BoofCV

Fast computer vision library for SFM, calibration, fiducials, tracking,  image processing, and more.

Repository: https://github.com/lessthanoptimal/BoofCV
Canonical: https://ross.abutalabs.com/products/boofcv
Homepage: http://boofcv.org
Language: Java
License Family: other
Topics: camera-calibration, computer-vision, 3d-vision, structure-from-motion, android, stereo-vision, photogrammetry, image-processing, qrcode-scanner, 3d-reconstruction, java, qr-code, qrcode-generator, qrcode, micro-qrcode, micro-qr-code, aztec-code
Last push: 2026-08-24T16:25:19+00:00

## Health v2 (maintenance only)
Score: 86/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 61, longevity 100
- inputs: {"age_days": 5615, "days_push": 9, "days_rel": 100, "gap_med": 157.0, "n_releases_24m": 5}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1192, forks 270 (observed 2026-08-28T04:03:56.354064+00:00)

## What it is
BoofCV is an open-source, real-time computer vision library written entirely in Java, covering image processing, camera calibration, feature detection and tracking, structure-from-motion, fiducial detection, and QR/barcode scanning. It is available on Maven Central and runs on any JVM platform, including Android.

## Use cases
- calibrate camera intrinsics from images
- detect and track fiducial markers for AR or robotics
- scan and generate QR codes in Java
- reconstruct 3D scenes with structure-from-motion
- track features across video frames in real time
- process and filter images on Android
- compute stereo depth maps from image pairs

## When to choose
- you need a pure-Java, dependency-light computer vision library on the JVM or Android
- you need camera calibration, SFM, or fiducial detection without native OpenCV bindings
- you want real-time QR/barcode scanning including Micro QR and Aztec codes
- you prefer an Apache 2.0 license usable in commercial products

## When to avoid
- you need deep-learning-based vision models (detection, segmentation) - use OpenCV with DNN or PyTorch instead
- you work primarily in Python or C++ and want the broadest algorithm ecosystem
- you need GPU-accelerated vision pipelines
- you need a GUI-heavy interactive vision tool rather than a library

## Facets
- artifact type: library
- maturity: active
- function: computer-vision, image-processing, ocr
- domain: computer-vision, image-processing, robotics, photography
- platform: jvm, cross-platform
- tags: structure-from-motion, camera-calibration, fiducial-detection, qr-code, stereo-vision, feature-tracking, photogrammetry, real-time, android

## Member repositories
- lessthanoptimal/BoofCV (main) score 86

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:56.354064+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:22:30.543050+00:00, confidence not recorded.
  - readme: https://github.com/lessthanoptimal/BoofCV (fetched 2026-08-28T04:03:56.354064+00:00, sha 74f2b2d21e67)
  - homepage: http://boofcv.org (fetched 2026-08-29T12:29:40.142998+00:00, sha 9a4d56f7bfd6)
  - site_page: http://boofcv.org/index.php?title=BoofCV%3AAbout (fetched 2026-08-29T12:29:40.148439+00:00, sha ddc589f6dfe2)
  - site_page: http://boofcv.org/index.php?title=FAQ (fetched 2026-08-29T12:29:40.146375+00:00, sha 3cf6a0b2f162)
- Data as of 2026-08-30T08:39:29.467469+00:00.