DEVELOPMENT OF A Ψ-DESCRIPTOR FOR THE COMPUTER VISION SYSTEM OF A TETHERED MULTICOPTER BASED ON THE KEYPOINT METHOD
DOI:
https://doi.org/10.56132/2791-3368-2026-2-66-124-153Keywords:
tethered UAV, descriptor, autonomous navigation, keypoint, computer vision, artificial intelligenceAbstract
The article provides a general overview of tethered multicopters, describes their main functional capabilities, and formulates the task of developing an autonomous navigation system for use in one of the most challenging operational processes of tethered unmanned aerial vehicles (UAVs) - their landing on the ground. The use of keypoint technology is proposed for the development of the autonomous navigation system. A brief review of keypoint detectors and descriptors is presented. It is shown that the FAST detector can be used as a keypoint detector. However, for descriptor construction, a mathematical model based on the Ψ-transformation method used in nonlinear function optimization problems was employed, forming the basis for the development of a proprietary keypoint descriptor - the Ψ-descriptor. The results of the practical application of the developed Ψ-descriptor for solving UAV autonomous navigation tasks are presented. The proposed new method for keypoint determination can be used in the computer vision systems of tethered unmanned aerial vehicles to solve landing tasks as an alternative to conventional GPS-based systems.
Downloads
References
1. Leading Global Suppliers. Tethered Drones. [Электронный ресурс]: https://www.unmannedsystemstechnology.com/expo/tethered-drones-uavs/ (дата обращения: 01.06.2026).
2. Kai Zhang, Wangmeng Zuo, Yunjin Chen, Deyu Meng, Lei Zhang. Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising. IEEE Transactions on Image Processing, Vol. 26, No. 7, pp. 3142-3155. 2017. 10.1109/TIP.2017.2662206
3. Chao Dong, Chen Change Loy, Kaiming He, Xiaoou Tang. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 38, No. 2, pp. 295-307. 20016. 10.1109/TPAMI.2015.2439281.
4. Olaf Ronneberger, Philipp Fischer, Thomas Brox. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015, Lecture Notes in Computer Science, Vol. 9351, pp. 234-241. Springer, Cham. 10.1007/978-3-319-24574-4_28
5. Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770-778. 2016. 10.1109/CVPR.2016.90
6. R. Archana, P. S. Eliahim Jeevaraj. Deep learning models for digital image processing: a review. Artificial Intelligence Review, Vol. 57, Article number 11. 2024. 10.1007/s10462-023-10631-z
7. Milos Radovic, Offir Adato, Natan S. Kopeika, Roman Bligh. Object Recognition in Aerial Images Using Convolutional Neural Networks. Journal of Imaging, Vol. 3, No. 2, Article 21. 2017. 10.3390/jimaging3020021
8. Andy Couturier, Moulay A. Akhloufi. Convolutional neural networks and particle filter for UAV localization. Proceedings of SPIE 11758, Real-Time Image Processing and Deep Learning 2021, 117580G. 2021. 10.1117/12.2585986
9. Gengyu Wang, Xianping Fu. A Convolutional Neural Network Image Compression Algorithm for UAVs. Journal of Circuits, Systems and Computers, Vol. 33, No. 12, Article 2450211. 2024. 10.1142/S0218126624502116.
10. Radoki S. M. M., Akhloufi M. A., Couturier A. Drone Model Classification Using Convolutional Neural Network Trained on Synthetic Data. Journal of Imaging, Vol. 8, No. 8, Article 218. 2022. 10.3390/jimaging8080218.
11. (5) Gabriel Silva de Oliveira, José Marcato Junior, Caio Polidoro, Wesley Gonçalves, Mateus Santos, Edson Matsubara, et al. Convolutional Neural Networks to Estimate Dry Matter Yield in a Guineagrass Breeding Program Using UAV Remote Sensing. Sensors, Vol. 21, No. 12, Article 3971. 2021. 10.3390/s21123971.
12. Chunyuan Cui, Juntong Fan, Xuanyao Zhao, Jianing Song, Leyuan Sun. An Improved ORB-SLAM3 System for UAV Localization and Mapping in GPS-Denied Environments. Drones, Vol. 8, No. 4, Article 132. 2024. 10.3390/drones8040132.
13. Muhammad Aamir, Zhao Jianqiang, Muhammad Ali, Saeed Ahmed, Muhammad Irfan. An Automated UAV Image Stitching Approach Based on Improved SIFT Features. IEEE Access, Vol. 9, pp. 62451-62461. 2021. 10.1109/ACCESS.2021.3073981.
14. Runwei Guan, Jinrong Hu, Yifei Huang, Liting Sun, Paolo Santi, Carlo Ratti. Deep Learning-Based Keypoint Detection and Matching for UAV Thermal Images. Remote Sensing, Vol. 15, No. 18, Article 4429. 2023. 10.3390/rs15184429
15. Rodehorst V., Koschan A. Comparison and evaluation of feature point detectors, 2006
16. Tinne Tuytelaars, Krystian Mikolajczyk. Local Invariant Feature Detectors: A Survey, 2008
17. Детектор Kitchen-Rosenfeld. L. Kitchen and A. Rosenfeld. Gray Level Corner Detection. Pattern Recognition Letters, pp. 95-102, 1982
18. Moravec, H. Rover visual obstacle avoidance // In International Joint Conference on Artificial Intelligence, Vancouver, Canada, 1981, pp. 785-790.
19. Детектор COP (Crosses as Oriented Pair). S.C. Bae, I.S. Kweon and C.D. Yoo. COP: a new corner detector. Pattern Recogn. Lett. 2002
20. E. R. a. T. Drummond. Fusing Points and Lines for High Performance Tracking, 2005
21. David G. Lowe. Distinctive Image Features from Scale-Invariant Keypoints, 2004
22. Шакенов А.К. Сравнение детекторов особых точек изображений и оценка их статистических характеристик. Журнал “Автометрия”, 2021. Т.57, №1
23. Клейнберг Дж., Тардос Е. Алгоритмы: разработка и применение. Классика Computers Science / Пер. с англ. Е. Матвеева. – СПб.: Питер, 2016. – 800 с
24. Системы компьютерного зрения: современные задачи и методы [Электронный ресурс]/Режим доступа: http://controleng.ru/innovatsii/sistemy-komp-yuternogo-zreniya-sovremenny-e-zadachi-metody/(дата обращения: 01.06.2025)
25. Паттерн посредник [Электронный ресурс]/Режим доступа: https://refactoring.guru/ru/design-patterns/mediator; A tutorial on binary descriptors [Электронный ресурс]/Режим доступа: https://gilscvblog.com/2013/10/04/a-tutorial-on-binary-descriptors-part-3-the-orb-descriptor/ (дата обращения: 01.06.2025)
26. Just look at the image: viewpoint-specific surface normal prediction for improved multi-view reconstruction [Электронный ресурс]/Режим доступа: https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Galliani_Just_Look_at_CVPR_2016_paper.pdf (дата обращения: 16.04.2025)
27. James L. Pro JavaFX 2/ L. James, G. Weiqi, C. Stephen, I. Dean, V. Johan. – Apress, 2012. – 641 p.
28. Feature detection and description [Электронный ресурс]/Режим доступа: https://docs.opencv.org/3.0-beta/doc/py_tutorials/py_feature2d/py_table_of_contents_feature2d/py_table_of_contents_feature2d.html (дата обращения: 16.04.2025)
29. ORB: Oriented FAST and Rotated BRIEF [Электронный ресурс]/Режим доступа: http://www.willowgarage.com/sites/default/files/orb_final.pdf (дата обращения: 16.04.2025)
30. Introduction to SURF [Электронный ресурс]/Режим доступа: https://docs.opencv.org/3.0-beta/doc/py_tutorials/py_feature2d/py_surf_intro/py_surf_intro.html (дата обращения: 16.04.2025)
31. What is KeyPoint Detection? [Электронный ресурс]/Режим доступа: https://translated.turbopages.org/proxy_u/en-ru.ru.ead253e4-67ff9724-ab1a850e-74722d776562/https/www.geeksforgeeks.org/what-is-keypoint-detection/ (дата обращения: 16.04.2025)
32. Чичинадзе В.К. Решение невыпуклых нелинейных задач оптимизации. - М.: Наука. Главная редакция физико-математической литературы. 1983. – 256 с.
33. Кадиркулов Ш.К., Оспанов Ж.Ш., Бекмурзаев Б.Ж., Бекмухамедов Б.Э., Анетбаев А.А. Объектно-ориентированное моделирование с использованием диаграмм UML для разработки имитационной модели автономной системы навигации БПЛА. Научные труды военно-инженерного института радиоэлектроники и связи. Военный научно-технический журнал. №3 (65), 2026 г.
