Git Product home page Git Product logo

Comments (6)

levexis avatar levexis commented on May 27, 2024 1

Sure, have ordered it and will submit a PR if I'm successful with it.

from jeelizpupillometry.

xavierjs avatar xavierjs commented on May 27, 2024

Hi,

It seems good (8MP, good zoom level), but I m not sure.
If you try it, I would be very interested by your feedback (either here or by submitting a PR to edit the README.md).

Best,
Xavier

from jeelizpupillometry.

levexis avatar levexis commented on May 27, 2024

FireShot Capture -  _ LIGHT INTENSITY PUPIL MEASUREMENT _ _ - https___127 0 0 1_levexis_jeelizPupi

I think it is working, here is example output from the light intensity test. Great little camera it seems to me. Let me know if you want me to run any other tests.

from jeelizpupillometry.

xavierjs avatar xavierjs commented on May 27, 2024

Hi @levexis

Thank you very much for your feedback.
What is the curve in the "Averaged results" tab ?
It should look like this one: https://github.com/jeeliz/jeelizPupillometry#light-intensity

The initial value is always 1, it is the pupil size at the beginning of each trial.
Then it should increase or decrease but not too abruptly.
If it is too abrupt, it may be due to a measurement problem.

Indeed, sometimes the tracking can be lost under some lighting conditions. For example if the screen is too bright, it can add a reflection point on the pupil which will disturb the measurement. It is important to check it in the "debug view" tab to see if the iris then the pupil are well segmented.

Best,
Xavier

from jeelizpupillometry.

levexis avatar levexis commented on May 27, 2024

I've been having a few problems so have a new graphics card coming for my PC. I get ok results but only for one eye and in debug mode it seems to be struggling. I never seem to get the red lines that I can see in the videos I've seen. If there is a good video/ article for getting going then please let me know.

Thanks,

Paul

from jeelizpupillometry.

xavierjs avatar xavierjs commented on May 27, 2024

Hi @levexis

The red lines are linked to the pupil detection.
In the debug view tab, they can be tweaked using the 2 first sliders (cf https://github.com/jeeliz/jeelizPupillometry#sliders-usage )
The first one should control their thickness and the second one their intensity.

The red lines are computed with edge detection.
So they depends a lot on the image quality around the pupil.
If it is a bit blurry (bad focus), it will be hard to detect edges.
Same if the image is too dark/too bright.
I had to tweak manually my camera settings because by default, the exposure is not set specifically for the eyes region but for the whole image. (on Linux, v4l2ucp then I put these settings: https://github.com/jeeliz/jeelizPupillometry/blob/master/images/screenshots/v4l2ucp.png )

For the graphic card, mine is a GTX960M.
I also tested it on Nvidia Jetson TX2 (about the same computing power than a GTX930M).

Best,
Xavier

from jeelizpupillometry.

Related Issues (10)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.