Skip to content

Latest commit

 

History

4 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

942-People-Passenger-Behavior-Recognition-Data

Description

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

Data size

942 people

Population distribution

gender distribution: 503 males, 439 females; race distribution: Asian; age distribution: 1845 years old, 4660 years old, over 60 years old

Collecting environment

in-car Cameras

Data diversity

multiple age groups, multiple time periods, multiple lighting, multiple behaviors (normal behaviors, carsick behaviors, sleepy behaviors, lost children & items behaviors)

Device

visible light and infrared binocular camera, resolution 1,920x1,080

Shooting position

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

Collecting time

day, evening, night

Collecting light

normal light, weak light, strong light

Vehicle Type

Car, SUV, MVP, Truck, Bus

Data Format

the video data format is .mp4

Accuracy

according to the accuracy of each person's acquisition action, the accuracy exceeds 95%;the accuracy of label annotation is not less than 95%

Licensing Information

Commercial License

Releases

Packages

Used by

Contributors