Intelligent Traffic Monitoring: Detection of Helmetless Riders and Motorcycle License Plate Recognition Using YOLOv8

Authors

  • Dimas Rossiawan Hendra Putra
  • Hendro Darmono Digital Telecommunication Networks Study Program, Department of Electrical Engineering, State Polytechnic of Malang, Indonesia
  • Delila Cahya Permatasari Electronics Engineering Study Program, Department of Electrical Engineering, State Polytechnic of Malang, Indonesia
  • Adi Candra Kusuma Electronics Engineering Study Program, Department of Electrical Engineering, State Polytechnic of Malang, Indonesia

DOI:

https://doi.org/10.26905/jeemecs.v8i2.16092

Keywords:

Helmet Detection, Lisence Plate Detection, Optical Character Recognition, YoloV8

Abstract

Traffic accidents involving motorcycle riders are often caused by a lack of education on road safety. One of the primary factors contributing to traffic accidents is rider negligence, which accounts for the largest percentage at 61%. Traffic accidents can result in severe injuries. One way to prevent severe injuries during an accident is by using safety riding equipment, such as helmets, while riding. Therefore, this study proposes a system for detecting helmet violations and recognizing license plates, which can facilitate the communication of information to the authorities. The detection system utilizes a CNN algorithm with the YOLO model to detect riders, helmets, no-helmets, and vehicle license plates. This research will implement a violation detection and license plate recognition system by deploying an IP Camera to record objects in real-time using dummy violation data. The system also employs Optical Character Recognition (OCR) to extract text from detected license plates, which will then be sent as notifications via the Telegram application. The YOLOv8 model training achieved an mAP score of 84.2%, with the accuracy for each class as follows: rider accuracy at 94%, no-helmet accuracy at 93%, license plate accuracy at 93%, and helmet accuracy at 87%. The license plate recognition system operates optimally at a distance of 1 to 5 meters, with an accuracy of 93.7% at 1 meter, 65% at 2 meters, 90% at 3 meters, 62.5% at 4 meters, and 51.7% at 5 meters.

Downloads

Download data is not yet available.

References

[1] Badan Pusat Statistik, "Statistik Indonesia 2023". accessed on January 14, 2024 from: https://www.bps.go.id/id/publication/2023/ 02/28/18018f9896f09f03580a614b/statistik-indonesia-2023.html.

[2] Ahdiat, Adi. "Ini Pertumbuhan Jumlah Motor di Indonesia 10 Tahun Terakhir". accessed on January 14, 2024 from : https:// databoks.katadata.co.id/datapublish/2023/03/ 16/ini-pertumbuhan-jumlah-motor-di-indonesia-10-tahun-terakhir.

[3] Biro Komunikasi dan Informasi Publik, "Tekan Angka Kecelakaan Lalu Lintas, Kemenhub Ajak Masyarakat Beralih ke Transportasi Umum dan Utamakan Keselamatan Berkendara" accessed on January 14, 2024 from: https://dephub.go.id/post/read/%E2%80%8B tekan-angka-kecelakaan-lalu-lintas,-kemenhub-ajak-masyarakat-beralih-ke-transportasi-umum-dan-utamakan-keselamatan-berkendara.

[4] Muhammad, Daafa Alhaqqy. Maulana, Aditya. "Fenomena Rider Motor Tidak Pakai Helmet Kian Marak, Banyak yang Cuek," accessed on January 14, 2024 from: https://otomotif.kompas.com/read/2023/12/06/ 125209915/ fenomena-rider-motor-tidak-pakai- helmet-kian-marak-banyak-yang-cuek?page=all.

[5] Febryanti, Kartika. "Undang-undang yang mewajibkan penggunaan helmet standar," accessed on January 14, 2024 from: https://www.hukumonline.com/klinik/a/ undang--undang-yang-mengatur-penggunaan-helmet-standar-kendaraan-roda-dua-cl4957.

[6] Albert. Gunandi, Kartika. Setyati, Endang. "Deteksi Helmet Pada Pengguna Sepeda Motor Dengan Metode Convolutional Neural Network" Jurnal Infra, vol. 8, no. 1, hal. 295-301, 2020.

[7] Aldhiyatika, Amwin. "Deteksi Dan Klasifikasi Kendaraan Berbasis Algoritma You Only Look Once (YOLO)" DuraSPace UII, hal.1-44, Agustus 2021.

[8] Jaya, I Gusti Alit Wiraguna. Swardika, I Ketut. Sugirianta, Ida BAgus Ketut "Sistem Deteksi Pelanggaran Pengendara Motor Dengan Computer Vision Sesi Pelanggaran Pelindung Kepala" Repositori Politeknik Negeri Bali, hal. 1-8, September 2022.

[9] Lou, H., Duan, X., Guo, J., Liu, H., Gu, J., Bi, L., & Chen, H. (2023). DC-YOLOv8: Small-Size Object Detection Algorithm Based on Camera Sensor. Electronics (Switzerland), 12(10). https://doi.org/10.3390/electronics12102323

[10] Hanif, Ahmad Rizalul Hanif. Nasrullah, Emir. Setyawan, Arinto "Deteksi Karakter Plat Nomor Kendaraan Dengan Menggunakan Metode Optical Character Recognition (OCR)," JITET Jurnal Informatika dan Teknik Elektro, vol. 11, no. 1, hal. 109-117, 2023.

Downloads

Published

2025-08-26

Issue

Section

Articles