Deteksi dan Klasifikasi Kendaraan Berbasis Algoritma You Only Look Once (Yolov7)
DOI:
https://doi.org/10.47065/bulletincsr.v5i3.509Keywords:
YOLOv7; Vehicle Detection; Traffic Classification; Deep Learning; Google Colab; Kaggle Dataset; Object DetectionAbstract
The increasing traffic density in Indonesia highlights the need for an accurate vehicle detection system to support infrastructure planning. This study aims to implement the YOLOv7 algorithm for detecting and classifying various types of vehicles in traffic images. The method involves training the model using Google Colab on a Kaggle dataset consisting of 6,633 images, with a batch size of 1, 19 training epochs, and optimization using the Stochastic Gradient Descent (SGD) algorithm. The training results show that the model achieved a precision of 93.22%, recall of 90.64%, mAP@0.5 of 94.27%, and mAP@0.5:0.95 of 69.19%, with a total training time of 1 hours. In conclusion, the YOLOv7 algorithm is effective for vehicle detection and classification, although increasing the number of training epochs is recommended to further enhance model performance.
Downloads
References
D. Iskandar Mulyana and M. A. Rofik, “Implementasi Deteksi Real Time Klasifikasi Jenis Kendaraan Di Indonesia Menggunakan Metode YOLOV5,” J. Pendidik. Tambusai, vol. 6, no. 3, pp. 13971–13982, 2022, doi: 10.31004/jptam.v6i3.4825.
Nurhawanti, “SISTEM PENDETEKSI SEPEDA MOTOR PELANGGAR MARKA JALAN MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORKS (CNNs),” Galang Tanjung, vol. 2, no. 2504, pp. 1–9, 2019.
M. Harahap, J. Elfrida, P. Agusman, M. Rafael, R. Abram, and K. Andrianto, “Sistem Cerdas Pemantauan Arus Lalu Lintas Dengan YOLO (You Only Look Once v3),” Semin. Nas. APTIKOM, pp. 367–376, 2019.
D. Alamsyah, S. Gi, and M. Palembang, “Pengenalan Mobil pada Citra Digital Menggunakan HOG-SVM” J. Informatika dan Sistem Informasi, Vol 3, No 2, 2017, 10.35957/jatisi.v3i2.79
A. Arinaldi, J. A. Pradana, and A. A. Gurusinga, “Detection and classification of vehicles for traffic video analytics,” Procedia Comput. Sci., vol. 144, pp. 259–268, 2018, doi: 10.1016/j.procs.2018.10.527.
N. Fadlia and R. Kosasih, “Klasifikasi Jenis Kendaraan Menggunakan Metode Convolutional Neural Network (Cnn),” J. Ilm. Teknol. dan Rekayasa, vol. 24, no. 3, pp. 207–215, 2019, doi: 10.35760/tr.2019.v24i3.2397.
M. Fachrie, “A Simple Vehicle Counting System Using Deep Learning with YOLOv3 Model,” J. RESTI (Rekayasa Sist. dan Teknol. Informasi), vol. 4, no. 3, pp. 462–468, 2020, doi: 10.29207/resti.v4i3.1871.
Z. A. Fikriya, M. I. Irawan, and S. Soetrisno., “Implementasi Extreme Learning Machine untuk Pengenalan Objek Citra Digital,” J. Sains dan Seni ITS, vol. 6, no. 1, 2017, doi: 10.12962/j23373520.v6i1.21754.
N. K. Negoro, E. Utami, and A. Yaqin, “Klasifikasi Deteksi Penggunaan Masker Menggunakan Metode Convolutional Neural Network,” JIPI (Jurnal Ilm. Penelit. dan Pembelajaran Inform., vol. 8, no. 2, pp. 664–674, 2023, doi: 10.29100/jipi.v8i2.3748.
S. R. Dewi, “Deep Learning Object Detection Pada Video,” Deep Learn. Object Detect. Pada Video Menggunakan Tensorflow Dan Convolutional Neural Netw., pp. 1–60, 2018, [Online]. Available: https://dspace.uii.ac.id/bitstream/handle/123456789/7762/14611242_Syarifah Rosita Dewi_Statistika.pdf?sequence=1
S. Indolia, A. K. Goswami, S. P. Mishra, and P. Asopa, “Conceptual Understanding of Convolutional Neural Network- A Deep Learning Approach,” Procedia Comput. Sci., vol. 132, pp. 679–688, 2018, doi: 10.1016/j.procs.2018.05.069.
G. Plastiras, C. Kyrkou, and T. Theocharides, “Efficient convnet-based object detection for unmanned aerial vehicles by selective tile processing,” ACM Int. Conf. Proceeding Ser., 2018, doi: 10.1145/3243394.3243692.
M. G. A. Binuri, T. Haryanti, and M. A. Haq, “Penerapan Algoritma YOLO v7 Sebagai Deteksi Kecelakaan Kendaraan Pada Lalu Lintas,” Comput. Insight J. Comput. Sci., vol. 4, no. 2, pp. 7–14, 2022.
L. Rahmawati and K. Adi, “Rancang bangun penghitung dan pengidentifikasi kendaraan menggunakan Multiple Object Tracking,” Youngster Phys. J., vol. 6, no. 1, pp. 70–75, 2017.
R. F. Waliulu, “Deteksi dan Penggolongan Kendaraan dengan Kalman Filter dan Model Gaussian di Jalan Tol,” J. Sist. Inf. Bisnis, vol. 8, no. 1, p. 1, 2018, doi: 10.21456/vol8iss1pp1-8.
L. Da Van, L. Y. Zhang, C. H. Chang, K. L. Tong, K. R. Wu, and Y. C. Tseng, “Things in the air: tagging wearable IoT information on drone videos,” Discov. Internet Things, vol. 1, no. 1, 2021, doi: 10.1007/s43926-021-00005-8.
Y. Song, H. Yang, L. Huang, and S. Huang, “YOLOv7-b: An Enhanced Object Detection Model for Multi-Scale and Dense Target Recognition in Remote Sensing Images,” Int. J. Adv. Comput. Sci. Appl., vol. 16, no. 2, pp. 233–248, 2025, doi: 10.14569/IJACSA.2025.0160225.
Z. Bowen, L. Huacai, Z. Shengbo, C. Xinqiang, and X. Hongwei, “Night target detection algorithm based on improved YOLOv7,” Sci. Rep., vol. 14, no. 1, pp. 1–10, 2024, doi: 10.1038/s41598-024-66842-z.
J. Yu, H. Zheng, L. Xie, L. Zhang, M. Yu, and J. Han, “Enhanced YOLOv7 integrated with small target enhancement for rapid detection of objects on water surfaces,” Front. Neurorobot., vol. 17, 2023, doi: 10.3389/fnbot.2023.1315251.
K. Li, Y. Wang, and Z. Hu, “Improved YOLOv7 for Small Object Detection Algorithm Based on Attention and Dynamic Convolution,” Appl. Sci., vol. 13, no. 16, 2023, doi: 10.3390/app13169316.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Deteksi dan Klasifikasi Kendaraan Berbasis Algoritma You Only Look Once (Yolov7)
ARTICLE HISTORY
How to Cite
Issue
Section
Copyright (c) 2025 Yusuf Kautsar Rohiman, Bulkis Kanata, L Ahmad S Irfan Akbar
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
