A method for training a vehicular occupant monitoring system includes accessing a frame image data captured by a camera disposed at a vehicle and viewing an occupant present in the vehicle. A first artificial visual characteristic for the occupant is generated. A first modified frame of image data is generated that includes the accessed frame with the first artificial visual characteristic overlaying a first portion of the occupant. A second artificial visual characteristic is generated for the occupant. The second artificial visual characteristic is different than the first artificial visual characteristic. A second modified frame of image data is generated that includes the accessed frame with the second v artificial visual characteristic overlaying a second portion of the occupant. The vehicular occupant monitoring system is trained using the first modified frame of image data and the second modified frame of image data.