Detection of Motorcycle Headlights Using YOLOv5 and HSV

Vessa Rizky Oktavia; Ahmad Wali Satria Bahari Johan; Whisnumurty Galih Ananta; Fahril Refiandi; Muhammad Khuluqil Karim

doi:10.34148/teknika.v12i3.682

Vessa Rizky Oktavia Informatics Department, Institut Teknologi Telkom Surabaya, Surabaya, East Java, Indonesia
Ahmad Wali Satria Bahari Johan Informatics Department, Institut Teknologi Telkom Surabaya, Surabaya, East Java, Indonesia
Whisnumurty Galih Ananta Informatics Department, Institut Teknologi Telkom Surabaya, Surabaya, East Java, Indonesia
Fahril Refiandi Informatics Department, Institut Teknologi Telkom Surabaya, Surabaya, East Java, Indonesia
Muhammad Khuluqil Karim Informatics Department, Institut Teknologi Telkom Surabaya, Surabaya, East Java, Indonesia

DOI: https://doi.org/10.34148/teknika.v12i3.682

Keywords: Digital Image Processing, Deep Learning, YOLOv5, HSV, ETLE

Abstract

"Electronic Traffic Law Enforcement" (ETLE) denotes a mechanism that employs electronic technologies to implement traffic regulations. This commonly entails utilizing a range of electronic apparatuses like cameras, sensors, and automated setups to oversee and uphold traffic protocols, administer fines, and enhance road security. ETLE systems are frequently utilized for identifying and sanctioning infractions like exceeding speed limits, disregarding red lights, and turning off the headlights. In Indonesia, there is currently no dedicated system designed to detect traffic violation, especially regarding vehicle headlights. Therefore, this research was conducted to detect vehicle headlights using digital images. With the results of this study, it will be possible to develop a system capable of classifying whether vehicle headlights are on or off. This research employed the deep learning method in the form of the YOLOv5 model, which achieved an accuracy of 94.12% in detecting vehicle images. Furthermore, the white color extraction method was performed by projecting the RGB space to HSV to detect the Region of Interest (ROI) of the vehicle headlights, achieving an accuracy of 73.76%. The results of this vehicle headlight detection are influenced by factors such as lighting, image capture angle, and vehicle type.

Downloads

Download data is not yet available.

References

D. Perhubungan R.I. Ditjen Perhubungan Darat, Buku Petunjuk Tata Cara Bersepeda Motor Di Indonesia. 2008.

J. E. Espinosa, S. A. Velastin, and J. W. Branch, “Motorcycle detection and classification in urban Scenarios using a model based on Faster R-CNN,” in 9th International Conference on Pattern Recognition Systems, Valparaiso: IET Digital Library, May 2018, pp. 91—96.

Sutikno, H. Arif Wibawa, and R. Saputra, “Automatic Detection of Motorcycle on the Road using Digital Image Processing,” Scientific Journal of Informatics, vol. 6, no. 2, pp. 203—212, Nov. 2019, [Online]. Available: http://journal.unnes.ac.id/nju/index.php/sji

J. H. Sri Wisna et al., “Deteksi Kendaraan Secara Real Time Menggunakan Metode YOLO Berbasis Android,” Jurnal Sustainable: Jurnal Hasil Penelitian dan Industri Terapan, vol. 09, no. 01, pp. 8—14, 2020.

D. J. P. Manajang, S. Sompie R.U.A, and A. Jacobus, “Implementasi Framework Tensorflow Object Detection Dalam Mengklasifikasi Jenis Kendaraan Bermotor,” Jurnal Teknik Informatika, vol. 15, pp. 171—178, 2020.

Asni B A, Amin, and Waruni K M, “Penerapan Metode Yolo Object Detection V1 Terhadap Proses Pendeteksian Jenis Kendaraan Di Parkiran,” Jurnal Teknik Elektro UNIBA (JTE), vol. 6, no. 1, pp. 194—199, 2021.

R. A. Utama and L. ETP, “Implementasi Metode Yolo Object Detector untuk Klasifikasi Jenis Kendaraan yang Melintas di Ruas Jalan,” Jurnal Ilmiah Komputasi, vol. 20, no. 4, pp. 601—608, 2021.

Q. Wang, Q. Zhang, X. Liang, Y. Wang, C. Zhou, and V. I. Mikulovich, “Traffic lights detection and recognition method based on the improved yolov4 algorithm,” Sensors, vol. 22, no. 1, Jan. 2022, doi: 10.3390/s22010200.

P. GarcÃa-SÃ¡nchez, Merelo J.J, Calandria D., Pelegrina A. B., Palacio R. Morcillo F., and Garcia-Ortega R.H., “Testing the Differences of using RGB and HSV Histograms during Evolution in Evolutionary Art,” in Conference: 5th International Joint Conference on Computational Intelligence, 2013. [Online]. Available: http://www.processing.org/

E. Prasetyo, R. Dimas Adityo, N. Suciati, and C. Fatichah, “Deteksi Wilayah Cahaya Intensitas Tinggi Citra Daun Mangga untuk Ekstraksi Fitur Warna dan Tekstur Pada Klasifikasi Jenis Pohon Mangga,” in Seminar Nasional Teknologi Informasi, Komunikasi dan Industri (SNTIKI) 9, Pekanbaru: Fakultas Sains dan Teknologi, UIN Sultan Syarif Kasim Riau, May 2017, pp. 21—31.

E. K. Kim, H. Lee, J. Y. Kim, and S. Kim, “Data Augmentation Method by Applying Color Perturbation of Inverse PSNR and Geometric Transformations for Object Recognition Based on Deep Learning,” Applied Sciences (Switzerland), vol. 10, no. 11, Jun. 2020, doi: 10.3390/app10113755.

R. Antika and M. Iqbal, “Using the Matlab App to Detect Objects By Color With Hsv Color Segmentation,” Jurnal Mantik, vol. 5, no. 4, pp. 2702—2710, 2022.

H. C. Kang, H. N. Han, H. C. Bae, M. G. Kim, J. Y. Son, and Y. K. Kim, “HSV Color-Space-Based Automated Object Localization for Robot Grasping without Prior Knowledge,” Applied Sciences (Switzerland), vol. 11, no. 16, Aug. 2021, doi: 10.3390/app11167593.

D. Iskandar and Marjuki, “Classification Of Melinjo Fruit Levels Using Skin Color Detection With RGB And HSV,” Journal of Applied Engineering and Technological Science, vol. 4, no. 1, pp. 123—130, 2022.

F. Rofii, G. Priyandoko, M. I. Fanani, and A. Suraji, “Vehicle Counting Accuracy Improvement By Identity Sequences Detection Based on Yolov4 Deep Neural Networks,” TEKNIK, vol. 42, no. 2, pp. 169—177, Aug. 2021, doi: 10.14710/teknik.v42i2.37019.

D. I. Mulyana and M. A. Rofik, “Implementasi Deteksi Real Time Klasifikasi Jenis Kendaraan Di Indonesia Menggunakan Metode YOLOV5,” Jurnal Pendidikan Tambusai, vol. 6, no. 3, pp. 13972—13982, 2022.

R. B. S, A. Marium, G. N. Srinivasan, and S. A. Shetty, “Literature Survey on Object Detection using YOLO,” International Research Journal of Engineering and Technology, vol. 7, no. 6, pp. 3082—3088, 2020, [Online]. Available: www.irjet.net

T. Diwan, G. Anirudh, and J. V. Tembhurne, “Object detection using YOLO: challenges, architectural successors, datasets and applications,” Multimed Tools Appl, vol. 82, no. 6, pp. 9243—9275, Mar. 2023, doi: 10.1007/s11042-022-13644-y.

A. Mashudi, F. Rofii, and M. Mukhsim, “Sistem Kamera Cerdas Untuk Deteksi Pelanggaran Marka Jalan,” JASEE Journal of Application and Science on Electrical Engineering, vol. 1, no. 1, pp. 15—25, Feb. 2020, doi: 10.31328/jasee.v1i01.4.

M. Iqbal, Karmilasari, Y. Karyanti, and dan Yulia Chalri, “Rancang Bangun Sistem Deteksi Pelanggaran Lalu Lintas dalam Simulator Mengemudi menggunakan Unity Game Engine,” Jurnal Format, vol. 1, pp. 38—49, 2021.

R. H. S., A. Rabi’, and E. Sonalitha, “Sistem Pendeteksi Pelanggar Traffic Light pada Zebra Cross Menggunakan Raspberry Pi Berbasis Pengolahan Citra Digital,” Journal of Electrical Electronic Control and Automotive Engineering (JEECAE), vol. 5, no. 1, May 2020.

Suhartono, S. G. Zain, and Sugiawan, “Sistem Object Recognition Plat Nomor Kendaraan Untuk Sistem Parkir Bandara,” Journal of Embedded System Security and Intelligent System, vol. 3, no. 2, pp. 127—134, Nov. 2022, [Online]. Available: https://ojs.unm.ac.id/JESSI/index