Y
Yawn Detection Module
A Computer Vision project that detects the yawn using the 468 face landmarks obtained using the Mediapipe Library.
61
Created on 13th March 2022
•
Y
Yawn Detection Module
A Computer Vision project that detects the yawn using the 468 face landmarks obtained using the Mediapipe Library.
The problem Yawn Detection Module solves
I was able to successfully:
- Differentiate between a normal yawn and a tired yawn by keeping a note of the frequency and duration of these yawns.
- Find an optimal value for the number and duration of these yawns which helps us to have an accurate measure of when the person starts feeling tired/sleepy.
PS: This module can also be integrated into several large-scale projects with small changes as per the requirements.
Challenges I ran into
The major challenge was actually to have an accurate measure of the number of yawns and the frequency of these yawns which would help me differentiate between a normal yawn and a sleepy yawn.
This challenge was overcome with continuous trial and error of the yawn detection module on a group of people. The threshold value for each one of them was recorded and a cumulative measure suggested to me the value which should be finally taken for this module.
Discussion
Builders also viewed
See more projects on Devfolio