Skip to main content

A compact GUI application for optical distortion calibration of endoscopes

Project description

endocal is a compact GUI application for optical distortion calibration of endoscopes.

endocal was developed as part of the [GIFT-Surg project](http://www.gift-surg.ac.uk/). It uses the [OpenCV camera calibration module](http://docs.opencv.org/2.4/doc/tutorials/calib3d/camera_calibration/camera_calibration.html) under the hood, and was developed by Dzhoshkun I. Shakir at the [Translational Imaging Group](http://cmictig.cs.ucl.ac.uk/) in the [Centre for Medical Image Computing](http://www.ucl.ac.uk/cmic/homepage) at [University College London (UCL)](http://www.ucl.ac.uk/).

# System requirements
* [OpenCV 2.4](http://docs.opencv.org/2.4/doc/tutorials/introduction/table_of_content_introduction/table_of_content_introduction.html)
* [pip](https://pip.pypa.io/en/stable/installing/)
* For online calibration, frame-grabber hardware supported by [OpenCV](http://docs.opencv.org/2.4/modules/highgui/doc/reading_and_writing_images_and_video.html#videocapture)

# Installation
1. Install endocal by running `pip install endocal`.
1. Test your installation by running `endocal-test`:
* See [this screenshot](endocal/res/screenshot-start.png) for what to expect on launching the application.
* To perform an optical distortion calibration, follow the instructions shown in red on top of the window. While acquiring calibration data, detected calibration pattern blobs will be emphasized with a virtual overlay as in [this screenshot](endocal/res/screenshot-detection.png).
* All data for each calibration will be saved in the sub-folder of a folder called `tmp-sample_001`, created within the current folder. These include:
* Calibration parameters saved as `calibration.yml`
* Frames used for calibration saved as indexed image files, e.g. `frame_009.jpg`
* After performing a calibration, the application will automatically show the undistorted images to the right as shown in [this screenshot](endocal/res/screenshot-undistort.png).

# How to use
`endocal --help` will show details of what input parameters are expected. Examples include:

* Using all frames stored as indexed files e.g. `frame_009.jpg`:
```
endocal --pattern-specs 3 11 3 1 --output-folder ./calibration-results --input /home/dzhoshkun/offline-calibration-data/frame_%3d.jpg
```

* Using online video stream from a frame-grabber (attached to an endoscope) that is mounted as `/dev/video0` on Linux:
```
endocal --input 0 --pattern-specs 3 11 3 1 --output-folder ./calibration-results
```

* Using a `700 x 700` sub-frame of the whole endoscopic video frame (`1920 x 1080`):
```
endocal --input 0 --pattern-specs 3 11 3 1 --output-folder ./calibration-results --roi 620 200 700 700
```

# Supported platforms
endocal was tested only on Linux (Ubuntu 14.04 LTS) so far. However it is highly likely that it will work on other platforms as well, due to the small number of dependencies.

# License
Copyright (c) 2016, [University College London](http://www.ucl.ac.uk/). endocal is available as free open-source software under a BSD 3-Clause Licence.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

endocal-16.7rc1.tar.gz (1.4 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

endocal-16.7rc1-py2-none-any.whl (2.9 MB view details)

Uploaded Python 2

File details

Details for the file endocal-16.7rc1.tar.gz.

File metadata

  • Download URL: endocal-16.7rc1.tar.gz
  • Upload date:
  • Size: 1.4 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No

File hashes

Hashes for endocal-16.7rc1.tar.gz
Algorithm Hash digest
SHA256 5333e984841236db700bd48139d494b121f3280a2f68a70bcd4d9b5c3e3082a9
MD5 7939f3ae1faf07a1cb3264c026ea0464
BLAKE2b-256 b914a1c5b463b768968e895538fc115d294e7374757f13fa6d4bc30a88744256

See more details on using hashes here.

File details

Details for the file endocal-16.7rc1-py2-none-any.whl.

File metadata

File hashes

Hashes for endocal-16.7rc1-py2-none-any.whl
Algorithm Hash digest
SHA256 734c5c7f398c4aae7ec2f9fa2472985516dbe374185076b5c4760f802868ff11
MD5 e53f54383aaa02137fbcd0cac4b73217
BLAKE2b-256 c99130b7df8bb900f46cb2fce1b7e826bab086561bf3c777584bd7dbd7b3849b

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page