SISTEM SMART TRAFFIC LIGHT MENGGUNAKAN ALGORITMA YOLOv8

Dewi Primasari, Ghifari Ferdian R, Zakiah Aulia R, Ulfiya Tussyifaa, Arrobi Rot Wiranto

Abstract


Traffic jams have become a serious problem in many countries, including Indonesia. Traffic management is a challenging task, especially in developing countries. One of the causes of traffic jams is long lines of vehicles at intersections because the traffic light signals are on at the same time without paying attention to the number of vehicles queuing. The computer vision approach can be applied as a solution by minimizing waiting time for drivers by adjusting the length of time the green light signal is on based on the number of vehicles in each lane. To carry out this approach, a vehicle detection system was built using the YOLOv8 (You Only Look Once 8th version) algorithm, which operates in real-time. The data used comes from CCTV installed at every traffic light at intersection four. The YOLOv8 algorithm shows high accuracy and efficiency in object detection in various studies. To find out to what extent the YOLO model that has been built can predict the data correctly, it is necessary to evaluate the model by calculating accuracy, recall and mAP50 score. This research aims to build an intelligent traffic light management system using YOLOv8, based on computer vision and the OpenCV library. The results obtained from this system calculation are an accuracy value of 0.689, a recall value of 0.578, and an mAP50 score of 0.65.

Full Text:

PDF

References


Al Mudawi, N., Qureshi, A.M., Abdelhaq, M., Alshahrani, A., Alazeb, A., Alonazi, M., & Algarni, A. (2023). Vehicle Detection and Classification via YOLOv8 and Deep Belief Network over Aerial Image Sequences. Sustainability 2023, 15, 14597. https://doi.org/10.3390/su151914597

Amwin, A. (2021). Deteksi Dan Klasifikasi Kendaraan Berbasis Algoritma You Only Look Once (YOLO). Universitas Islam Indonesia. Https://Dspace.Uii.Ac.Id/Handle/123456789/34154

Ardiansyah, M. R., Supit, Y., & Said, M. S. (2022). Sistem Visi Komputer Untuk Kalkulasi Kepadatan Kendaraan Menggunakan Algoritma Yolo. Simtek : Jurnal Sistem Informasi Dan Teknik Komputer, 7(1), 52–59. Https://Doi.Org/10.51876/Simtek.V7i1.123

Cholissodin, I., & Soebroto, A. A. (2021). Buku Ajar AI , Machine Learning & Deep Learning ( Teori & Implementasi ) (1.01, Issue July 2019). Https://Www.Researchgate.Net/Publication/348003841

Dian Maniswari, S., Rusdinar, A., & Purnama, B. (2015). Smart Traffic Light Using Image Processing And Fuzzy Logic Method. E-Proceeding Of Engineering, 2(2), 2166.

Fali Oklilas, A., Dwinta, D., Shofi, G., Putri Mariza, N., Arum Kinanti, S., & Amanda Sari, Y. (2023). Akurasi Pengujian Model Hasil Training Menggunakan Yolov4 Untuk Pengenalan Kendaraan Di Jalan Raya. Jurnal JUPITER, 15(1), 799–806.

Gibran, H, Purnama, B., & Kosala, G. (2023). Object Tracking Menggunakan Algoritma You Only Look Once (Yolo)v8 Untuk Menghitung Kendaraan. Jurnal Komputa, 12(2), 31–45.

Harahap, E., Suryadi, A., Ridwan, R., Darmawan, D., & Ceha, R. (2017). Efektifitas Load Balancing Dalam Mengatasi Kemacetan Lalu Lintas. Matematika, 16(2), 1–7. Https://Doi.Org/10.29313/Jmtm.V16i2.3665

Harahap, M., Elfrida, J., Agusman, P., Rafael, M., Abram, R., Andrianto, K., Kunci-Visi Komputer, K., Arus Lalu Lintas, P., & Kendaraan, D. (2019). Sistem Cerdas Pemantauan Arus Lalu Lintas Dengan YOLO (You Only Look Once V3). In Seminar Nasional APTIKOM.

Hayati, N. J., Singasatia, D., & Muttaqin, M. R. (2023). Object Tracking Menggunakan Algoritma You Only Look Once (YOLO)v8 Untuk Menghitung Kendaraan. Komputa : Jurnal Ilmiah Komputer Dan Informatika, 12(2), 91–99. Https://Doi.Org/10.34010/Komputa.V12i2.10654

Hidayati, Q. (2017). Kendali Lampu Lalu Lintas Dengan Deteksi Kendaraan Menggunakan Metode Blob Detection. Jurnal Nasional Teknik Elektro Dan Teknologi Informasi (JNTETI), 6(2). Https://Doi.Org/10.22146/Jnteti.V6i2.318

Kandir, N. (2018). Opencv Dengan Python. Https://Doi.Org/10.1128/AAC.03728-14

Lin, C. J., Jeng, S. Y., & Lioa, H. W. (2021). A Real-Time Vehicle Counting, Speed Estimation, And Classification System Based On Virtual Detection Zone And YOLO. Mathematical Problems In Engineering, 2021. Https://Doi.Org/10.1155/2021/1577614

Rachmawati, F., & Widhyaestoeti, D. (2020). Deteksi Jumlah Kendaraan Di Jalur SSA Kota Bogor Menggunakan Algoritma Deep Learning YOLO. In Prosiding LPPM UIKA Bogor. Http://Pkm.Uika-Bogor.Ac.Id/Index.Php/Prosiding/Index

Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You Only Look Once: Unified, Real-Time Object Detection. Proceedings Of The IEEE Computer Society Conference On Computer Vision And Pattern Recognition, 2016-Decem, 779–788. Https://Doi.Org/10.1109/CVPR.2016.91

Reis, D., Kupec, J., Hong, J., & Daoudi, A. (2023). Real-Time Flying Object Detection With Yolov8. Georgia Institute Of Technology. Http://Arxiv.Org/Abs/2305.09972

Santoso, J. T. (2022). Proyek Coding Dengan Python (M. K. Muhammad Sholikan (Ed.)). Yayasan Prima Agus Bekerja Sama Denganuniversitas Sains & Teknologi Komputer (Universitas STEKOM).

Saputra, B. M., Ilman, M. Z., Audina, M., & Jepri, M. (2023). Sistem Pengenalan Tanda Lalu Lintas Menggunakan Algoritma YOLO. Jurnal Inovasi Dan Humaniora, 1(1), 161–164.

Setianingsih, C., & Paryasto, M. W. (2022). Sistem Deteksi Pelanggaran Zebra Cross Pada Kendaraan Sepeda Motor Menggunakan Algoritma Yolov4 Cross Zebra Violation Detection System On Motorcycle Vehicles Using The Yolov4 Algorithm. E-Proceeding Of Engineering, 9(5), 5038–5045.

Sunaryo, & Kusumawati, Natalia Reza. (2020). Evaluasi Pembangunan Median Jalan. Jurnalteknologi Transportasi Dan Logistik, 1(1), 11–14.

Y. E. K. Ignasius Widira Kristianto. (2022). Pendeteksian Sepeda Motor di Jalur Khusus Sepeda Menggunakan Algoritma Pendeteksi Objek YOLO. Kalbisiana: Jurnal Mahasiswa Institut Teknologi Dan Bisnis Kalbis, 8(1), 275–281.




DOI: https://doi.org/10.31884/jtt.v10i1.622

Refbacks

  • There are currently no refbacks.


Copyright (c) 2024 JTT (Jurnal Teknologi Terapan)

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

View Stats

 

 Creative Common Attribution-ShareAlike 4.0 International (CC BY-SA 4.0)