This dataset includes diverse drivers across multiple ages, time periods, and lighting conditions, with annotated behaviors including dangerous driving, fatigue, and visual movement behaviors. In terms of device, binocular cameras of RGB and infrared channels were applied. This data can be used for tasks such as driver behavior analysis, fatigue and drowsiness detection, dangerous driving recognition and driver attention and visual movement monitoring.
For more details, please refer to the link: https://www.nexdata.ai/datasets/computervision/1277?source=Github
844 people
gender distribution: 421 males, 423 females; race distribution: Vietnam, Indonesia; age distribution: 1845 years old, 4660 years old, over 60 years old
in-car Cameras
multiple age periods, multiple time periods, multiple lighting and behaviors (Dangerous behavior, Fatigue behavior, Visual movement behavior)
visible light and infrared binocular camera, resolution 1,920x1,080
the center of the inside rearview mirror of the car, above the center console in the car, above the left A-pillar in the car, steering wheel position, rearview mirror wide angle lens position
day, evening, night
normal light, weak light, strong light
car, SUV, MVP, truck, bus
the video data format is .mp4
according to the accuracy of each person's acquisition action, the accuracy exceeds 95%;the accuracy of label annotation is not less than 95%
Commercial License