EyeTrack2Fixation 👁

📝 Table of Contents

1. 📚 What is EyeTrack2Fixation?
2. 🔧 How to install EyeTrack2Fixation?
3. 🚀 How to use EyeTrack2Fixation?
4. 📦 Dependencies
5. 📧 Contact

📚 What is EyeTrack2Fixation?

Pipeline to derive fixation features from eye-tracking records. A fixation is a stable gaze on a point of interest.

Input

The system automatically scans a list of potential column names (case-insensitive) for the features and assigns the values accordingly (see in src/constants.py).

Supported input data formats:

Example:

Time Left_X Left_Y Right_X Right_Y
0 554262330 92.60 648.54 79.27 648.36

💡 "At timestamp 554262330 the left eye is at coordinates (92.60, 648.54) (in px) and the right eye is at coordinates (79.27, 648.36) (in px)."

or

Time X Y
0 554262330 92.60 648.54

💡 "At timestamp 554262330 the eyes are at coordinates (92.60, 648.54) (in px)."

Output

Output data format:

Example:

starttime endtime duration endx endy
0 554264326 555036492 772166 84.680000 647.890000

💡"At timestamp 554264326 the fixation starts and ends at timestamp 555036492 with a duration of 772166 nanoseconds. The fixation ends at coordinates (84.680000, 647.890000) (in px)."

🔧 How to install EyeTrack2Fixation?

If you don't yet have Python installed, you can download it from Python Official Website!

If you don't yet have Git installed, you can download it from Git Official Website!

1. Clone the repository by running following command in your terminal:

   git clone https://github.com/hubii-world/EyeTrack2Fixation-01.git

2. Navigate to the project root directory by running the following command in your terminal:

   cd EyeTrack2Fixation

3. Create a virtual environment and activate it (Python Version 3.10 or higher):

   python3 -m venv venv
   source venv/bin/activate

4. Install the required packages by running the following command in your terminal:

   pip install -r requirements.txt

🚀 How to use EyeTrack2Fixation?

1. Via file path:
   • _Example .txt-file available in repository 'data/raw/eyetracker_freeviewing.txt'!_

from src.feature_extraction import Eye2FixExtractor

ffe = Eye2FixExtractor(data='../data/raw/eyetracker_freeviewing.txt')
efix = ffe.extract_features()

1. Via pandas DataFrame:
   • If you have left and right eye coordinates:

import pandas as pd
from src.feature_extraction import Eye2FixExtractor

df = pd.DataFrame({
'Time': [554262330, 554264326 , 554266315],
'Left_X': [92.60, 185.06, 190.84],
'Left_Y': [648.54, 647.05, 637.12],
'Right_X': [79.27, 84.30, 84.77],
'Right_Y': [648.36, 648.73, 649.84]
})

ffe = Eye2FixExtractor(data=df)
efix = ffe.extract_features()

• If you only have x and y coordinates:

import pandas as pd
from src.feature_extraction import Eye2FixExtractor

df = pd.DataFrame({
'Time': [554262330, 554264326 , 554266315],
'X': [85.935, 84.680, 87.805],
'Y': [648.450, 647.890, 643.480]
})

ffe = Eye2FixExtractor(data=df)
efix = ffe.extract_features()

📦 Dependencies

• pandas
• numpy
• pygaze analyser

📧 Contact

HUman BIosignal Intelligence Hub (HUBII)

• Website
• GitHub
• Hugging Face