Volume 9 | Issue 8

 Abstract

According to WHO, more than 1.35 million deaths occur each year in vehicle accidents, but they would have a 40-50% probability of survival if they used seat belts properly. So, ensuring that seat belts are worn by every driver is a vital component of active safety measures. Many nations, including India, make it illegal for drivers to drive without wearing a seat belt otherwise the drivers will be given an appropriate punishment. But currently check of this behavior is completely done manually, which not only increases the burden on the police but also has low efficiency, especially if there are a big number of vehicles traveling at a high rate. The main goal behind this research determines whether the seat belts in the vehicle are belted or unbelted. First, the driver area is located based on the vehicle outline. Then the potential seat belt edges are detected by an effective algorithm Hough Transform, and the result is finally obtained by further verification of the edges. After the detection of the seat belt if the seat belt has not been detected then the model will go for plate recognition. The area of the number plate is determined using automatic number plate recognition (ALPR). Therefore, we propose an approach that can detect the seat belt automatically in the images taken by the camera and recognize the plate number of the vehicle.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Vehicle Seat Belt Detection, Plate Number Recognition, Machine Learning, Safety belt detection and license plate recognition

  License

Creative Commons Attribution 4.0 and The Open Definition