Analisis Komputasi dan Waktu Inferensi Model YOLOv8 dan YOLOv11 pada Deteksi Kendaraan
DOI:
https://doi.org/10.29407/wvkzem06Abstract
Pemantauan lalu lintas cerdas memerlukan model deteksi objek yang akurat dan efisien secara komputasi untuk diimplementasikan pada perangkat tepi. Penelitian ini bertujuan membandingkan tolak tarik performa antara arsitektur YOLOv8 dan YOLOv11 berdasarkan stabilitas pelatihan, ukuran model, dan kecepatan inferensi. Pendekatan eksperimental kuantitatif digunakan dengan melatih kedua model selama 50 iterasi menggunakan dataset citra lalu lintas pada lingkungan komputasi awan. Hasil pengujian menunjukkan YOLOv11 lebih efisien dalam ruang penyimpanan (5,22 Megabyte) dan unggul pada akurasi keseluruhan dengan nilai 77,8 persen, khususnya pada deteksi kendaraan besar. Sebaliknya, YOLOv8 menunjukkan konvergensi pelatihan yang lebih stabil di fase awal dan kecepatan inferensi yang lebih unggul (7,31 milidetik per bingkai) dibandingkan YOLOv11 (9,25 milidetik). Disimpulkan bahwa YOLOv8 direkomendasikan untuk implementasi waktu nyata guna mencegah penundaan pemrosesan, sedangkan YOLOv11 ideal untuk perangkat dengan kapasitas memori terbatas yang menuntut presisi tinggi.
Keywords:
Deteksi Kendaraan, Kecepatan Inferensi, Komputasi, YOLOv11, YOLOv8##plugins.themes.default.displayStats.downloads##
References
[1] J. Jusnidar, R. Riskayanti, Y. Setiawan, K. Khomsiah, A. Diath Yogmar, dan D.
Tribuana, ―IMPLEMENTASI WEB-BASED TRANSPORTATION MANAGEMENT
SYSTEM DI INDUSTRI TRANSPORTASI: SEBUAH TINJAUAN SISTEMATIS
LITERATUR,‖ Jurnal Teknologi dan Bisnis Cerdas, vol. 1, no. 3, hlm. 194–209, Des
2025, doi: 10.64476/jtbc.v1i3.15.
[2] N. H. Setiyawan, A. Hariyadi, dan A. Kurniawan, ―Sistem Pengawasan CCTV Pada
ATM Secara Real-Time Berbasis Internet of Things,‖ Jurnal Janitra Informatika dan
Sistem Informasi, vol. 5, no. 1, Mei 2025, doi: 10.59395/k0e60m33.
[3] A. Saadeldin, M. M. Rashid, A. A. Shafie, dan T. F. Hasan, ―Real-time vehicle counting
using custom YOLOv8n and DeepSORT for resource-limited edge devices,‖
Telkomnika (Telecommunication Computing Electronics and Control), vol. 22, no. 1,
hlm. 104–112, Feb 2024, doi: 10.12928/TELKOMNIKA.v22i1.25096.
[4] K. D. Dharmasaputra dan B. P. Hartato, ―Evaluation of YOLOv8 and Centroid
Tracking in Vehicle Detection, Classification, and Counting System,‖ Journal of
Applied Informatics and Computing, vol. 9, no. 5, hlm. 2310–2319, Okt 2025, doi:
10.30871/jaic.v9i5.10873.
[5] Ms. Abirami S, Ajai B, Imran Hussain S, Kavin Ezhil Arasu S.U, dan Mohamed
Yasinkhan R, ―Real-Time Traffic Density Estimation Using Yolov8,‖ International
Research Journal on Advanced Engineering and Management (IRJAEM), vol. 4, no. 05,
hlm. 1962–1967, Mei 2026, doi: 10.47392/IRJAEM.2026.0287.
[6] Z. Zhang, Z. Zhang, G. Li, dan C. Xia, ―ZZ-YOLOv11: A Lightweight Vehicle
Detection Model Based on Improved YOLOv11,‖ Sensors, vol. 25, no. 11, 2025, doi:
10.3390/s25113399.
[7] ―YOLOv8 vs YOLO11: A Comprehensive Technical Comparison of Real-Time Vision
Models | Ultralytics Docs.‖ Diakses: 5 Juni 2026. [Daring]. Tersedia pada:
https://docs.ultralytics.com/compare/yolov8-vs-yolo11#architectural-andmethodological-differences
[8] J. Terven, D.-M. Córdova-Esparza, dan J.-A. Romero-González, ―A Comprehensive
Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and
YOLO-NAS,‖ Mach. Learn. Knowl. Extr., vol. 5, no. 4, hlm. 1680–1716, 2023, doi:
10.3390/make5040083.
[9] G. Wang, Y. Chen, P. An, H. Hong, J. Hu, dan T. Huang, ―UAV-YOLOv8: A SmallObject-Detection Model Based on Improved YOLOv8 for UAV Aerial Photography
Scenarios,‖ Sensors, vol. 23, no. 16, 2023, doi: 10.3390/s23167190.
[10] M. Sobirin dan P. Wijonarko, ―Pemantauan Keamanan Real-Time pada Base
Transceiver Station (BTS) Menggunakan YOLOv8 dan Integrasi Telegram: Optimasi
Model dan Evaluasi Performa,‖ ILKOMNIKA: Journal of Computer Science and
Applied Informatics E, vol. 7, no. 3, hlm. 533–547, 2025, doi:
10.28926/ilkomnika.v7i3.824.
[11] H. Sukron dan S. Arifin, ―Tinjauan Literatur tentang Perkembangan Wireless Sensor
Network dalam Berbagai Bidang Aplikasi,‖ Karapan Network Journal, vol. 1, no. 01,
2025, doi: 10.20473/KNJ.01.01.pp-pp.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- The author grants 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.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
