Comments (1)
Hi Stefan,
Are you trying to run the algorithm on a single 640x240 image with two eyes? If so, I recommend you split the image into two halves and run the algorithm separately for each eye. I think the 3D model is build on a one eye per camera basis.
Also, you are correct that the dark regions will interfere with the pupil finding process. I recommend cropping the image and passing the result as a new Mat to the algorithm. The pupil should be the darkest region in the image. Based on your images above, cropping should be fairly easy. You could alternatively just color all black border pixels white.
Lastly, there is a parameter for maximum possible pupil size called sizeIn in the pupilAreaFitRR method of pupilfitter.h. Set this to some value less than 240, ideally the maximum possible pupil size for any user for that particular camera. For example, if your cropped eye image is only 200 pixels high, I recommend setting sizeIn to somewhere around 60, maybe even smaller. This also significantly speeds up processing time as the pupil ellipse candidate points will be smaller.
Let me know if that works.
from 3d-eye-tracker.
Related Issues (20)
- MSBuild.exe
- Unable to connect to Pupil Cam HOT 11
- Debug Assertion Error in Visual Studio HOT 3
- Running in Visual Studio 2013 (vc120) HOT 1
- Theoretical problem HOT 1
- Not an issue, just a question regarding accuracy HOT 6
- algorithm of this project? HOT 1
- Error from pupilFitter.h HOT 10
- How to compile x86 HOT 1
- Is it possible to run the program in linux? HOT 3
- camera features HOT 2
- error C2440 HOT 5
- IR hardware HOT 1
- Non-Code Related: HMD Eyetracker Suggestion HOT 1
- When using a web camera to track my eyes, I can't always get the gaze vector, why? HOT 2
- Access is Denied HOT 3
- Unable to start program HOT 6
- Assertion failed
- Visual Studio 2017
- The program was stuck at the beginning HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
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.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from 3d-eye-tracker.