Optimization of Yolov5 Hyperparameter Using Adam Optimizer in Vehicle Object Detection
DOI:
https://doi.org/10.33633/jais.v9i1.9244Abstract
Utilization of computer vision can be applied in various aspects of daily life, reducing dependence on human labor. One of its implementations is in industry, such as in the production process of motorized vehicles, to sort or classify parts or goods. The computer vision process involves many stages, such as image capture, image processing, image analysis, image recognition, and decision-making. In the automotive industry, computer vision has been used in autonomous or driverless electric vehicles, as well as in creating intelligent transportation systems. To detect objects in real-time, one of the options that can be used is to use the YOLO algorithm, which can detect objects in one stage with predictions of bounding boxes and class probabilities simultaneously. However, although YOLO has good performance, the architecture has some drawbacks, such as complexity and complicated hyperparameter congurations. To remedy this, the Adam optimization algorithm was introduced, which combines the momentum and RMSprop algorithms to adjust the learning rate adaptively and provide faster convergence in model training. This is evidenced by an increase in the value of mAP on Yolov5. These results prove that the Yolov5 method with Adam`s optimization is better than the Yolov5 method without optimization.References
X. Jiang, K. Sun, L. Ma, Z. Qu, and C. Ren, “Vehicle Logo Detection Method Based on Improved YOLOv4,” Electron., vol. 11, no. 20, pp. 1–19, 2022, doi: 10.3390/electronics11203400.
G. Guo and Z. Zhang, “Road damage detection algorithm for improved YOLOv5,” Sci. Rep., vol. 12, no. 1, pp. 1–12, 2022, doi: 10.1038/s41598-022-19674-8.
I. A. Elaalami, S. O. Olatunji, and R. M. Zagrouba, “AT-BOD: An Adversarial Attack on Fool DNN-Based Blackbox Object Detection Models,” Appl. Sci., vol. 12, no. 4, 2022, doi: 10.3390/app12042003.
S. Sutriawan, A. Z. Fanani, F. Alzami, and R. S. Basuki, “Deep Learning Jaringan Saraf Tiruan Untuk Pemecahan Masalah Deteksi Penyakit Daun Apel,” J. Teknol. Inf. dan Komun., vol. 11, no. 1, p. 35, 2023, doi: 10.30646/tikomsin.v11i1.729.
Z. Ren, H. Zhang, and Z. Li, “Improved YOLOv5 Network for Real-Time Object Detection in Vehicle-Mounted Camera Capture Scenarios,” Sensors, vol. 23, no. 10, 2023, doi: 10.3390/s23104589.
A. Prof, A. Abdulazeez, M. Qazzaz, and E. Faculty, “Car Detection and Features Identification Based on,” vol. 7, no. 2, pp. 4049–4056, 2022.
N. Rochmawati, H. B. Hidayati, Y. Yamasari, H. P. A. Tjahyaningtijas, W. Yustanti, and A. Prihanto, “Analisa Learning Rate dan Batch Size pada Klasifikasi Covid Menggunakan Deep Learning dengan Optimizer Adam,” J. Inf. Eng. Educ. Technol., vol. 5, no. 2, pp. 44–48, 2021, doi: 10.26740/jieet.v5n2.p44-48.
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.
A. A. Hidayah, I. Firdauzi, and J. Prayogi, “Pelatihan Publish or Perish , Vosviewer , Dan Mendeley Pada Mahasiswa Mbkm Riset,” vol. 2, no. 1, pp. 8–12, 2023.
S. Mehta, C. Paunwala, and B. Vaidya, “CNN based traffic sign classification using adam optimizer,” 2019 Int. Conf. Intell. Comput. Control Syst. ICCS 2019, no. Iciccs, pp. 1293–1298, 2019, doi: 10.1109/ICCS45141.2019.9065537.
J. Ker, L. Wang, J. Rao, and T. Lim, “Deep Learning Applications in Medical Image Analysis,” IEEE Access, vol. 6, pp. 9375–9379, 2017, doi: 10.1109/ACCESS.2017.2788044.
C. Zhang, H. Ding, Q. Shi, and Y. Wang, “Grape Cluster Real-Time Detection in Complex Natural Scenes Based on YOLOv5s Deep Learning Network,” Agric., vol. 12, no. 8, 2022, doi: 10.3390/agriculture12081242.
B. Cortiñas-Lorenzo and F. Pérez-González, “Adam and the ants: On the influence of the optimization algorithm on the detectability of DNN watermarks,” Entropy, vol. 22, no. 12, pp. 1–39, 2020, doi: 10.3390/e22121379.
K. Khairunnas, E. M. Yuniarno, and A. Zaini, “Pembuatan Modul Deteksi Objek Manusia Menggunakan Metode YOLO untuk Mobile Robot,” J. Tek. ITS, vol. 10, no. 1, 2021, doi: 10.12962/j23373539.v10i1.61622.
Priyanto Hidayatullah,”Buku Sakti Deep Learning” – Stunning Vision AI Academy, Bandung 2021
Abdul Muiz Khalimi, 2018. Cara Menghitung Confusion Matrix 4 Kelas.[Online]. Available: https://www.pengalaman-edukasi.com/2020/01/confusion-matrix-multi-class-menghitung.html
S. Y. Sen and N. Ozkurt, “Convolutional Neural Network Hyperparameter Tuning with Adam Optimizer for ECG Classification,” Proc. - 2020 Innov. Intell. Syst. Appl. Conf. ASYU 2020, no. 978, 2020, doi: 10.1109/ASYU50717.2020.9259896.
Downloads
Published
Issue
Section
License
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution 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 (See The Effect of Open Access).
