Deep learning based automatic vertical height adjustment of incorrectly fastened seat belts for driver and passenger safety in fleet vehicles
| Autor: | Husnu Baris Baydargil, Ibrahim Furkan Ince, Ilhan Garip, Arif Senol Sener, Oktay Ozturk |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
050210 logistics & transportation
business.industry Computer science Mechanical Engineering Deep learning 05 social sciences Automotive industry Aerospace Engineering 030230 surgery Convolutional neural network Driver safety 03 medical and health sciences 0302 clinical medicine Aeronautics 0502 economics and business Artificial intelligence business |
| Zdroj: | Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering. 236:639-654 |
| ISSN: | 2041-2991 0954-4070 |
| Popis: | The recognition of incorrect fastening of seat belts is significant in passenger and driver safety for the automotive industry and public health. It should be made sure that the passenger’s seat belt is not only fastened but also correctly fastened across the body so that the passenger is adequately protected in the event of an accident. Current technology employs the buckle effect sensor, which merely solves the buckling detection problem, but there is no reliable solution for the correct positioning of the seat belt. Additionally, computer vision-based systems are still incapable of recognizing the incorrect positioning of seat belts when the training is performed by employing the subjects out of the fleet. Considering this fact, in this study, we propose a novel solution that employs a vision-based incorrect fastening seat belt detector to perform automatic vertical height adjustment independent from drivers and passengers for the fleet vehicles. We recognize the incorrect positioning of the seat belt inside the car by the acceptable distance of the seat belt from the neck of drivers or passengers to avoid neck injuries and the deaths caused by neck cuts. An extensive benchmarking is performed by comparing the three CNN architectures such as; DenseNet121, GoogLeNet (Inception-v3), ResNet50 with respect to sensitivity, specificity, precision, false-positive rate, false-negative rate, F1 score, and accuracy. Additionally, training and validation loss curves and accuracy curves are plotted for all the models. Later, the three models are evaluated with a precision-recall (PR) curve at the end. According to the results, the DenseNet121 achieved the highest classification accuracy among the tested models with 99.95%. This paper includes information about the proposed system elements, registration of data, elaboration of data, program algorithm, testing the system in the lab, and on the vehicle. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|