The 942 passenger behavior recognition dataset covers multiple ages, time periods and light exposure. Passenger behavior includes passenger normal behavior, passenger abnormal behavior (passenger motion sickness behavior, passenger sleepiness behavior, passenger lost children & items behaviors). In terms of acquisition equipment, visible and infrared binocular cameras are used. This dataset is suitable for passenger activity recognition, abnormal behavior detection and other tasks.
For more details, please refer to the link: https://www.nexdata.ai/datasets/computervision/1279?source=Github
942 people
gender distribution: 503 males, 439 females; race distribution: Asian; age distribution: 1845 years old, 4660 years old, over 60 years old
in-car Cameras
multiple age groups, multiple time periods, multiple lighting, multiple behaviors (normal behaviors, carsick behaviors, sleepy behaviors, lost children & items behaviors)
visible light and infrared binocular camera, resolution 1,920x1,080
the center of rear view mirror inside the car, above the right A-pillar in the car, front passenger position, above the left B-pillar in the car, above the right B-pillar in the car, 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