Ainvestigation of computer vision capabilities in autonomous unmanned aerial vehicles control systems

封面

如何引用文章

全文:

详细

The development of modern hardware and software has led to a rapid increase in the use of unmanned aerial vehicles, primarily aircraft. One of the promising areas for improving the efficiency of such platforms is the development of autonomous control systems, eliminating the need for human operators. The article presents the results of a study on the possibility of constructing elements of an automatic motion control system based on computer vision for unmanned aerial vehicles. The authors used comparative analysis to evaluate the advantages of two popular instruments: YOLO and SSD. They have also collected data for training the chosen model and tested it in various conditions, described the methodology for creating a training set and presented the model testing results on video images captured by a UAV's camera. The test results confirm that the YOLOv8n model is suitable for object detection on the UAV board using a Raspberry Pi 4 Model B as the single-board hardware platform. The object detection accuracy was from 80% to 90%, with the power consumption of 15-25 watts.

作者简介

Е. Karelin

Bonch-Bruevich Saint Petersburg State University of Telecommunications

编辑信件的主要联系方式.
Email: evgeniikarelin01@mail.ru

Student of Software Engineering and Computer Engineering Department

俄罗斯联邦, Saint Petersburg

T. Lyubashenko

Bonch-Bruevich Saint Petersburg State University of Telecommunications

Email: tima50879@gmail.com

Student of Secure Communication Systems Department

俄罗斯联邦, Saint Petersburg

M. Palilov

Bonch-Bruevich Saint Petersburg State University of Telecommunications

Email: palilovfox@gmail.com

Student of Secure Communication Systems Department

俄罗斯联邦, Saint Petersburg

N. Zhiglova

Bonch-Bruevich Saint Petersburg State University of Telecommunications

Email: zhiglova.natalia@yandex.ru

Student of Secure Communication Systems Department

俄罗斯联邦, Saint Petersburg

A. Pachin

Bonch-Bruevich Saint Petersburg State University of Telecommunications

Email: pachin.andrej@bk.ru

Associate Professor of Software Engineering and Computer Engineering Department, PhD in Technical Science

俄罗斯联邦, Saint Petersburg

参考

  1. Alkentar S.M. et al. Practical comparation of the accuracy and speed of YOLO, SSD and Faster RCNN for drone detection. Journal of Engineering, 2021, vol. 27, no. 8, pp. 19–31. doi: 10.31026/j.eng.2021.08.02
  2. Choudhari V. et al. Comparison between YOLO and SSD MobileNet for object detection in a surveillance drone. URL: https://www.researchgate.net/publication/355336797_Comparison_between_YOLO_and_SSD_MobileNet_for_Object_Detection_in_a_Surveillance_Drone (accessed: 01.06.2024).
  3. Li M. et al. Agricultural greenhouses detection in high-resolution satellite images based on convolutional neural networks: comparison of faster R-CNN, YOLO v3 and SSD. Sensors, 2020, vol. 20, no. 17. URL: https://www.sci-hub.ru/10.3390/s20174938 (accessed: 01.06.2024).
  4. Soylu E., Soylu T. A performance comparison of YOLOv8 models for traffic sign detection in the Robotaxi-full scale autonomous vehicle competition. Multimedia Tools and Applications, 2024, vol. 83, pp. 25005–25035. doi: 10.1007/s11042-023-16451-1
  5. Long X. et al. PP-YOLO: an effective and efficient implementation of object detector. URL: https://www.researchgate.net/publication/343178810_PP-YOLO_An_Effective_and_Efficient_Implementation_of_Object_Detector (accessed: 05.06.2024).
  6. Osco L.P. et al. A review on deep learning in UAV remote sensing. International Journal of Applied Earth Observation and Geoinformation. URL: https://www.sci-hub.ru/10.1016/j.jag.2021.102456 (accessed: 05.06.2024).
  7. Joseph R. et al. You only look once: unified, real-time object detection. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, 2015, pp. 779–788.
  8. Selcuk B., Serif T. A comparison of YOLOV5 and YOLOV8 in the context of mobile UI detection. Lecture Notes in Computer Science, 2023, vol. 13977, pp. 161–174. doi: 10.1007/978-3-031-39764-6_11
  9. Zagitov A. et al. Comparative analysis of neural network models performance on low-power devices for a real-time object detection task. Journal Computer Optics, 2024, vol. 48, no. 2, pp. 242–252. doi: 10.18287/2412-6179-CO-1343
  10. Zhang H. et al. A review of unmanned aerial vehicle low-altitude remote sensing (UAV-LARS) use in agricultural monitoring in China. Remote Sensing, 2021, vol. 13, no. 6, pp. 1221. URL: https://doi.org/10.3390/rs13061221 (accessed: 05.06.2024).
  11. COCO – Common Objects in context. URL: https://cocodataset.org/#home (accessed: 18.02.2024).
  12. Quadrocopters for schools «Pioneer Mini» – GC «Geoscan». URL: https://www.geoscan.ru/ru/products/pioneer/mini. (accessed: 18.02.2024). (In Russ.)
  13. Set: F450 (E305) ARF KIT+NAZA-M V2+GPS+Landing Skid+PMU v2+LED. URL: https://www.djimsk.ru/catalog/products/components/flame_wheel_arf_kit/komplekt_f450_e305_arf_kit_naza_m_v2_gps_landing_skid_pmu_v2_led.html (accessed: 18.02.2024). (In Russ.)
  14. GitHub – opencv/opencv: Open Source Computer Vision Library. URL: https://github.com/opencv/opencv?ysclid=lsqmv32jem25767816 (accessed: 18.02.2024).
  15. GitHub – pytorch/ pytorch: Tensors and Dinamic Neural Networks in Python. URL: https://github.com/pytorch/pytorch?ysclid=lsqmug3hgs789690537 (accessed: 20.04.2024).
  16. Buy a Raspberry Pi 4 Model B – Raspberry Pi. URL: https://www.raspberrypi.com/products/raspberry-pi-4-model-b/?parent-baobab-id=lsqmt1h7lk (accessed: 20.04.2024).
  17. Raspberry Pi OS – Raspberry Pi. URL: https://www.raspberrypi.com/software/ (accessed: 25.05.2024).
  18. Overview of datasets – Ultralytics YOLO Docs. URL: https://docs.ultralytics.com/ru/datasets/ (accessed: 25.05.2024). (In Russ.)
  19. GitHub – Ultralytics. URL: https://github.com/ultralytics/ultralytics (accessed: 28.05.2024).

补充文件

附件文件
动作
1. JATS XML
下载

版权所有 © Karelin Е.А., Lyubashenko T.D., Palilov M.R., Zhiglova N.S., Pachin A.V., 2025

Creative Commons License
此作品已接受知识共享署名-非商业性使用-禁止演绎 4.0国际许可协议的许可。