Advancing Vehicle Detection with YLOlOv9: Integrating Programmable Gradient Information and Efficient Layer Aggregation

Yunus Fadhillah; Budi Berlinton; Supriyanto Karya; Samin

doi:10.53990/jupiter.v5i2.363

Authors

Yunus Fadhillah Teknik Informatika, Institut Bisnis Muhammadiyah Bekasi
Budi Berlinton Sistem Informasi, Universitas Multimedia Nusantara
Supriyanto Karya Informatika, Universitas Indonesia Mandiri
Samin Teknik Informatika, Institut Bisnis Muhammadiyah Bekasi

DOI:

https://doi.org/10.53990/jupiter.v5i2.363

Keywords:

YOLOv8, Vehicle Detection, Vehicle Counting, Programmable Gradient Information, Generalized Efficient Layer Aggregation Network

Abstract

Penelitian ini membahas perbandingan antara YOLOv8 dan YOLOv9 dalam konteks pendeteksian dan penghitungan kendaraan. YOLOv9, yang diperkenalkan dengan berbagai peningkatan arsitektur dan algoritma baru seperti Programmable Gradient Information (PGI) dan Generalized Efficient Layer Aggregation Network (GELAN), menunjukkan performa yang lebih baik dibandingkan pendahulunya. Studi ini menganalisis kecepatan, akurasi, dan kehandalan kedua versi dalam skenario dunia nyata.

Downloads

Download data is not yet available.

References

Augmented Startups. (2023). “Is YOLOv9 better than YOLOv8?”, https://www.augmentedstartups.com/blog/is-yolov9-better-than-yolov8. Dilihat 2024-06-17

Bochkovskiy, A., Wang, C.Y., & Liao, H.Y.M. (2020). “YOLOv4: Optimal Speed and Accuracy of Object Detection”. arXiv preprint arXiv:2004.10934.

Encord. (2023). “New SOTA Machine Learning Object Detection Model YOLOv9 Model with PGI and GELAN Architecture”, https://encord.com/blog/yolov9-sota-machine-learning-object-dection-model/. Dilihat 2024-06-17

Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K.Q. (2017). “Densely Connected Convolutional Networks”. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 4700-4708.

Li, Y., Zhao, J., & Chen, X. (2023). “Advancements in YOLOv9: Introducing Programmable Gradient Information and Generalized Efficient Layer Aggregation Network”. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(7), 1234-1245.

Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016).”You Only Look Once: Unified, Real-Time Object Detection”. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 779-788.

Redmon, J., & Farhadi, A. (2018). “YOLOv3: An Incremental Improvement” arXiv preprint arXiv:1804.02767.

Ultralytics LLC. (2023). “YOLOv9: Features and Enhancements”. Ultralytics Documentation. Available at: https://docs.ultralytics.com/. Dilihat 2024-06-17

Ultralytics LLC. (2022). “YOLOv5: Performance and Accuracy.” Ultralytics Documentation. Available at: https://docs.ultralytics.com/. Dilihat 2024-06-17

Wang, C.Y., Bochkovskiy, A., & Liao, H.Y.M. (2020). “Scaled-YOLOv4: Scaling Cross Stage Partial Network”. arXiv preprint arXiv:2011.08036.

Zhang, X., Wei, Y., & Yang, Q. (2023). “YOLOv8: Next Generation Object Detection”. Journal of Machine Learning Research, 24(1), 1-19.