Proceedings of TUSUR University / Archive / Issue of Journal № 4, t. 27, 2024 / Detection and classification of small-size flying objects in images using convolutional neural networks from the YOLOv5 family

Detection and classification of small-size flying objects in images using convolutional neural networks from the YOLOv5 family

DOI: 10.21293/1818-0442-2024-27-4-103-110

Download article in PDF format

JATS xml

Abstract: The effectiveness of two models of convolutional neural networks, YOLOv5s and YOLOv5x of the YOLOv5 family, selected as a result of the analysis of the main known models of such networks for solving the problem of detection and classification of small-sized flying objects in images, was studied. Two datasets were formed with labeled RGB images of flying objects for three classes: birds, rotary-wing unmanned aerial vehicles (UAVs), and fixed-wing aircraft. The first dataset contains images with small-size objects (up to 32x32 pixels in area), and the second dataset, used for comparative studies, contains images with objects of different size. The network models were trained using each of the datasets and then studied using their test samples. It was found that both network models, regardless of the object size category, show a computation speed significantly exceeding the threshold value of the FPS metric equal to 25. It was shown that in the case of small-size flying objects, the YOLOv5s model does not reach the required threshold value of 0.9 in terms of classification accuracy according to the AP0.5 metric for objects of the «Bird» class, while the YOLOv5x model exceeds it and can be used in computer vision systems. For flying objects of different size, both models meet the formulated requirements for the accuracy of object classification in images and for the speed of their computation and are recommended for use in real-time computer vision systems.

Keywords: computer vision system, YOLOv5 convolutional neural network, detection and classification of flying objects, helicopter and airplane type unmanned aerial vehicles, bird

For citation:
Klekovkin V. A., Markov N. G., Nebaba S. G. Detection and classification of small-size flying objects in images using convolutional neural networks from the YOLOv5 family. Doklady Tomskogo gosudarstvennogo universiteta sistem upravleniya i radioelektroniki, 2024, vol. 27, no. 4, pp. 103–110. DOI: 10.21293/1818-0442-2024-27-4-103-110

Authors and copyright holders:

Klekovkin V. A. , National Research Tomsk Polytechnic University (Tomsk, Russia)
Markov N. G. , National Research Tomsk Polytechnic University (Tomsk, Russia)
Nebaba S. G. , National Research Tomsk Polytechnic University (Tomsk, Russia)

1. Zoev I.V., Markov N.G., Ryzhova S.E. Intelligent computer vision system for unmanned aerial vehicles for monitoring technological objects of oil and gas industry. Bulletin of the Tomsk Polytechnic University. Geo Assets Engineering, 2019, vol. 330, no. 11, pp. 34–49 (in Russ.). DOI: 10.18799/24131830/2019/11/2346.
2. Alzubaidi L., Zhang J., Humaidi A.J., Al-Dujaili A., Duan Y., Al-Shamma O., Santamaría J., Fadhel M.A., AlAmidie M., Farhan L. Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. Journal of Big Data, 2021, vol. 8, no. 53, pp. 1–77. DOI: 10.1186/s40537-021-00444-8.
3. Klekovkin V.A., Markov N.G. Model svertochnoj nejronnoj seti LeNet5 dlya obnaruzheniya i klassifikacii objektov vozdushnogo prostranstva na izobrazheniyah [Model of convolutional neural network LeNet5 for detection and classification of air space objects in images]. Bulletin of the Tomsk Polytechnic University. Industrial Cybernetics, 2023, vol. 1, no. 2, pp. 11–16 (in Russ.). DOI: 10.18799/29495407/2023/2/17.
4. Markov N.G., Zoev I.V., Mytsko E.A. FPGA hardware implementation of the YOLO subclass convolutional neural network model in computer vision systems. Proceedings of the 2022 International Siberian Conference on Control and Communication (SIBCON 2022), 2022, pp. 1–5 (in Russ.).
5. Nebaba S.G., Markov N.G. Svertochnye nejronnye seti semejstva YOLO dlya mobilnyh sistem kompyuternogo zreniya [Convolutional neural networks of YOLO family for mobile computer vision systems]. Computer Research and Modeling, 2024, vol. 16, no. 3, pp. 615–631 (in Russ.). DOI: 10.20537/2076-7633-2024-16-3-615-631.
6. Wu S., Lu X., Guo C., Guo H. Accurate UAV Small Object Detection Based on HRFPN and EfficentVMamba. Sensors, 2024, vol. 24, no. 15, p. 4966. DOI: 10.3390/s24154966.
7. Girshick R., Donahue J., Darrell T., Malik J. Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2014, pp. 580–587. DOI: 10.48550/arXiv.1311.2524.
8. Lin T.Y., Maire M., Belongie S., Hays J., Perona P., Ramanan D., Zitnick C.L. Microsoft COCO: Common objects in context. Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6–12, 2014, Proceedings, Part V 13. Springer International Publishing, 2014. pp. 740–755. DOI: 10.48550/arXiv.1405.0312.
9. Kisantal М., Wojna Z., Murawski J., Naruniec J., Cho K. Augmentation for small object detection. CVPR 2019, 2019. Available at: https://arxiv.org/abs/1902.07296, free (accessed: June 19, 2024).
10. Roboflow. Available at: https://roboflow.com, free (Accessed: June 15, 2024).
11. He K., Gkioxari G., Dollár P., Girshick R. Mask R-CNN. Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 2980–2988.
12. Bochkovskiy A., Wang C.Y., Liao H.Y.M. YOLOv4: Optimal Speed and Accuracy of Object Detection. Journal arXiv, preprint arXiv: 2004.10934v1, 2020, pp. 1–17. DOI: 10.48550/arXiv.2004.10934.
13. Olorunshola O.E., Irhebhude M.E., Evwiekpaefe A.E. A Comparative Study of YOLOv5 and YOLOv7 Object Detection Algorithms. Journal of Computing and Social Informatics, 2023, vol. 2, pp. 1–12. DOI: 10.33736/jcsi.5070.2023.
14. Wang C.Y., Bochkovskiy A., Liao H.Y.M. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for realtime object detectors. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 7464–7475.
15. Filichkin C.A., Vologdin S.V. Sravnenie effektivnosti algoritmov YOLOv5 i YOLOv8 dlya obnaruzheniya sredstv individual'noy zashchity cheloveka [Comparison of the Effectiveness of YOLOv5 and YOLOv8 Algorithms for Detecting Human Personal Protective Equipment]. Intelligent Systems in Manufacturing, 2023, vol. 21, no. 3. pp. 124–131 (in Russ.). DOI: 10.22213/2410-9304-2023-3-124-131.
16. Afonso M., Teixeira E., Cruz M., Aquino G., Vilas Boas E. Vehicle and Plate Detection for Intelligent Transport Systems: Performance Evaluation of Models YOLOv5 and YOLOv8. International Conference on Computing (ICOCO), IEEE, 2023, pp. 1–6. DOI: 10.1109/ICOCO59262.2023.10397996.
17. Horvat M., Gledec G. A comparative study of YOLOv5 models performance for image localization and classification. Proceedings of the 33rd Central European Conference on Information and Intelligent Systems (CECIIS), 2022, pp. 349–356.