With the development of neural networks, there is a need for real-time detection. In these tasks, accuracy and speed are important. This article provides a comparative analysis of YOLO and SSD - two key architectures that are actively used today.
real time, YOLO, SSD, single pass detectors, machine learning, computer vision
1. Makarov, M.A. Iskusstvennyy intellekt v promyshlennoy informatike : uchebnoe posobie / M.A. Makarov, I.Yu. Zaycev. – M. : MIREA – RTU, 2024. – 118 s.
2. Vision-basedapproachforhumanmotiondetectionandsmartappliancecontrol / S. Swami [etal.] // IAES International Journal of Robotics and Automation. – 2024. – Vol. 13, № 4. – Pp. 445-451.
3. Howard, A. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications / A. Howard, M. Zhu, B. Chen [et al.] – arXiv:1704.04861, 2017. – 9 c.
4. Tan, M. EfficientDet: Scalable and Efficient Object Detection / M. Tan, R. Pang, Q. V. Le // CVPR. – 2020. – P. 10781-10790.
5. Redmon, J. You Only Look Once: Unified, Real-Time Object Detection / J. Redmon, S. Divvala, R. Girshick, A. Farhadi. – arXiv:1506.02640, 2015. – 10 p.
6. Redmon, J. YOLO9000: Better, Faster, Stronger / J. Redmon, A. Far-hadi. – URL: https://arxiv.org/pdf/1612.08242 (data obrascheniya: 16.03.2025).
7. Istoriya YOLO – samoy izvestnoy arhitektury komp'yuternogo zreniya. – URL: https://datasecrets.ru/articles/20 (data obrascheniya: 16.03.2025).
8. Chzhu, I. Issledovanie neyronnyh setey YOLO / I. Chzhu, T.P. Novikova // Modelirovanie informacionnyh sistem i tehnologiy : sbornik materialov mezhdunarodnoy nauchno-prakticheskoy konferencii. – Voronezh, 2022. – S. 338-342.
9. Bochkovskiy, A. YOLOv4: Optimal Speed and Accuracy of Object De-tection / A. Bochkovskiy, C.-Y. Wang, H.-Y. M. Liao // arXiv preprint. – 2020. – arXiv:2004.10934.
10. Liu, W.SSD: Single Shot MultiBox Detector / W. Liu, D. Anguelov, D. Erhan [et al.] –ECCV 2016. – Springer, 2016. – C. 21-37.
