1,000 People-Driver Behavior Identification Data. The data includes multiple ages, multiple time periods and multiple lighting. The driver behaviors includes Dangerous behavior, fatigue behavior and visual movement behavior. 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.
For more details, please refer to the link: https://www.nexdata.ai/datasets/1277?source=Github
1,000 people
gender distribution: male, female; race distribution: Asian; 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 rear view mirror of the car, above the center console in the car, above the left A-pillar in the car, steering wheel position
day, evening, night
normal light, weak light, strong light
car, SUV, MVP, truck, coach
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