NITYMED stands for Nighttime-Yawning-Microsleep-Eyeblink-Distraction. It is a dataset developed in the framework of CPSoSaware project by ESDA LAB of project partner University of Peloponnese (UoP).
130 videos have been capture in Patras, Greece, displaying drivers in real cars, moving under nighttime conditions where drowsiness detection is more important. The participating drivers are: 11 males and 10 females of Caucasoid race. The selected drivers have different features (hair color, beard, glasses, etc.). This dataset has been created for two purposes:
a) to train customized AI/ML models for facial shape alignment in videos or photographs displaying Caucasian drivers in nighttime conditions
b) to test the accuracy in drowsiness detection and compare more general AI/ML models trained both in daytime and nighttime, under various environmental conditions
This dataset has been used to detect yawnings and sleepy eye blinks. However, other face, mouth and eye tracking applications can also be tested using this dataset (driver distraction/microsleep, facial expressions, etc.).