Annotated Drowsiness Detection Dataset Captured via Raspberry Pi 5

All recordings were captured at a consistent frame rate of 30 frames per second (FPS), with a resolution of 640x480 pixels, utilizing H.264 compression for video encoding. The recordings cover various lighting conditions, characterized by differing lux levels, to simulate real-world scenarios ranging from low-light (e.g., nighttime conditions) to bright daylight settings.Additionally, the dataset includes labeled categories essential for training and testing machine learning models.

Labeling was performed using Edge Impulse. These categories include:Open Eyes: 968 training samples, 225 testing samples (Total 1193)Closed Eyes: 158 training samples, 49 testing samples (Total 207)No Yawning: 496 training samples, 124 testing samples (Total 620)Yawning: 60 training samples, 12 testing samples (Total 72)The dataset further contains detailed video-wise annotations for testing, such as:Open Eyes (mata_terbuka): 30,922 testing samplesClosed Eyes (mata_tertutup): 4,662 testing samplesNo Yawning (tidak_menguap): 16,877 testing samplesYawning (menguap): 1,019 testing samples