Geodesic
UAV detection using neural networks
Modelirovanie i analiz informacionnyh sistem, Tome 31 (2024) no. 2, pp. 182-193.

Voir la notice de l'article provenant de la source Math-Net.Ru

The availability of unmanned aerial vehicles (UAVs) has led to a significant increase in the number of offenses involving their use. This makes the development of UAV detection systems relevant. Solutions based on deep neural networks show the best results in detecting UAVs on video. This article presents a study of various neural network detectors and focuses on identifying objects as small as possible, up to the size of 4$\times$4 and even 3$\times$3 pixels. The work investigates architectures SSD (VGG16) and YOLOv3 and it's modifications. Precision and recall metrics are calculated separately for different intervals of the object areas. The best result have been shown by YOLOv3 model with bbox parameters chosen as the result of object sizes clustering. Small (3$\times$3 px) drones have been successfully identified with 76% precision and a very small recall of 26%. For objects between 10 and 20 pixels in area, the recall is 64% with an accuracy of 75%. For objects with an area more than 20px the recall is about 90%, the precision is 89%, and the F1 score is 90%. These results show that it is possible to recognize even 4$\times$4 pixel drones, which can be used in video surveillance systems.
Keywords: UAV detection. 
@article{MAIS_2024_31_2_a4,
     author = {M. D. Averina and O. A. Levanova and D. V. Grushevskaya and K. A. Kukharev and D. M. Murin and M. A. Kalinin},
     title = {UAV detection using neural networks},
     journal = {Modelirovanie i analiz informacionnyh sistem},
     pages = {182--193},
     publisher = {mathdoc},
     volume = {31},
     number = {2},
     year = {2024},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/MAIS_2024_31_2_a4/}
}
TY  - JOUR
AU  - M. D. Averina
AU  - O. A. Levanova
AU  - D. V. Grushevskaya
AU  - K. A. Kukharev
AU  - D. M. Murin
AU  - M. A. Kalinin
TI  - UAV detection using neural networks
JO  - Modelirovanie i analiz informacionnyh sistem
PY  - 2024
SP  - 182
EP  - 193
VL  - 31
IS  - 2
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/MAIS_2024_31_2_a4/
LA  - ru
ID  - MAIS_2024_31_2_a4
ER  - 
%0 Journal Article
%A M. D. Averina
%A O. A. Levanova
%A D. V. Grushevskaya
%A K. A. Kukharev
%A D. M. Murin
%A M. A. Kalinin
%T UAV detection using neural networks
%J Modelirovanie i analiz informacionnyh sistem
%D 2024
%P 182-193
%V 31
%N 2
%I mathdoc
%U http://geodesic.mathdoc.fr/item/MAIS_2024_31_2_a4/
%G ru
%F MAIS_2024_31_2_a4
M. D. Averina; O. A. Levanova; D. V. Grushevskaya; K. A. Kukharev; D. M. Murin; M. A. Kalinin. UAV detection using neural networks. Modelirovanie i analiz informacionnyh sistem, Tome 31 (2024) no. 2, pp. 182-193. http://geodesic.mathdoc.fr/item/MAIS_2024_31_2_a4/

[1] European ATM master plan: Digitalising Europe's aviation infrastructure: Executive view, SESAR Joint Undertaking, 2020 | DOI

[2] N. Al-lQubaydhi et al, “Deep learning for unmanned aerial vehicles detection: A review”, Computer Science Review, 51 (2024), 100–614 | DOI | MR

[3] F. Mahdavi, R. Rajabi, “Drone detection using convolutional neural networks”, 2020 6th Iranian Conference on Signal Processing and Intelligent Systems (ICSPIS), 2020, 1–5 | DOI

[4] U. Seidaliyeva, D. Akhmetov, L. Ilipbayeva, E. Matson, “Real-time and accurate drone detection in a video with a static background”, Sensors, 20:14 (2020), 3856 | DOI

[5] A. Coluccia et al, “"Drone vs. bird detection: Deep learning algorithms and results from a grand challenge”, Sensors, 21:8 (2021), 2824 | DOI

[6] S. Jamil et al, “Malicious UAV detection using integrated audio and visual features for public safety applications”, Sensors, 20:14 (2020), 3923 | DOI

[7] E. Unlu, E. Zenou, N. Riviere, P. E. Dupouy, “Deep learning-based strategies for the detection and tracking of drones using several cameras”, IPSJ T Comput Vis Appl, 11:7 (2019), Unlu2019 | DOI

[8] Y. Shang, C. Liu, D. Qiu, Z. Zhao, R. Wu, S. Tang, “AD-YOLOv5s based UAV detection for low altitude security”, International Journal of Micro Air Vehicles, 15 (2023) | DOI

[9] X. Zhai, Z. Huang, T. Li, H. Liu, S. Wang, “YOLO-drone: An optimized YOLOv8 network for tiny UAV object detection”, Electronics, 12 (2023), 3664 | DOI

[10] J. Li, D. H. Ye, M. Kolsch, J. P. Wachs, C. A. Bouman, “Fast and robust UAV to UAV detection and tracking from video”, IEEE Transactions on Emerging Topics in Computing, 10:3 (2022), 1519–1531 | DOI

[11] A. Rozantsev, V. Lepetit, P. Fua, “Detecting flying objects using a single moving camera”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 39:5 (2017), 879–892 | DOI

[12] H. Sun, J. Yang, J. Shen, D. Liang, L. Ning-Zhong, H. Zhou, “Tib-net: Drone detection network with tiny iterative backbone”, IEEE Access, 8 (2020), 130-697–130-707

[13] O. A. Levanova, D. V. Grushevskaya, A. A. Britnev, M. D. Averina, D. M. Murin, Baza videodannyh s razmetkoj bespilotnyh letatel'nyh apparatov (kvadrokopterov), Svidetelstvo o gosudarstvennoy registratsii bazy dannyh No 2021620329, 2021-02-25