UMBUMB

SINERGISINERGI

Seatbelt usage is essential for minimizing injury risk during vehicular accidents. The monitoring seatbelt system in modern vehicles can be easily tricked into not displaying the warning alert. Car seatbelt detection, utilising real-time object detection, is employed to monitor seatbelt usage. However, the accuracy of such systems needs to be further evaluated under low-light and bright-light conditions. This study aims to develop a car seatbelt monitoring system using a real-time object detection algorithm, which will be tested in low-light and bright-light scenarios. The system integrates a trained YOLOv5 model into embedded hardware, which interfaces directly with the vehicles ignition system, enabling or disabling engine start based on seatbelt usage. Notifications are also delivered through LEDs, a buzzer, and Telegram messages. This system has an accuracy of 95.75%, precision of 99.1%, recall of 96.2%, and an F1-score of 97.2%. The results show that the system can generate a better confidence score under bright-light conditions than under low-light conditions. This work offers tangible proof of the efficacy of applying intelligent object detection models for real-time driver monitoring, particularly in enhancing compliance through physical intervention and IoT-based alerts.

The study successfully developed a car seatbelt monitoring system utilizing the YOLOv5 algorithm for real-time seatbelt and face detection.The system achieved high accuracy with 95.Performance was observed to be better under bright-light conditions compared to low-light conditions, highlighting a potential area for future improvement.

Future research should focus on expanding the dataset to include more diverse scenarios and driver profiles, addressing the dataset imbalance to improve seatbelt detection accuracy, and integrating advanced image preprocessing techniques like low-light enhancement to improve performance in varying lighting conditions. Furthermore, exploring the integration of the system with law enforcement notification systems could enhance its impact on road safety. Finally, testing the system across a wider range of vehicle models and real-world driving conditions is crucial to validate its robustness and generalizability, potentially leading to a more effective and reliable driver monitoring solution for improved road safety and compliance.

  1. FAST DETECTION OF SEATBELT DRIVER BASED ON IMAGE CAPTURING | JURTEKSI (jurnal Teknologi dan Sistem Informasi).... jurnal.stmikroyal.ac.id/index.php/jurteksi/article/view/2276FAST DETECTION OF SEATBELT DRIVER BASED ON IMAGE CAPTURING JURTEKSI jurnal Teknologi dan Sistem Informasi jurnal stmikroyal ac index php jurteksi article view 2276
Read online
File size690.19 KB
Pages8
DMCAReport

Related /

ads-block-test