Detection of drones with YOLOv4 deep learning algorithm

Document Type : Research Paper

Authors

Computer Science Department, College of Science, University of Baghdad, Baghdad, Iraq

Abstract

Drones or unmanned aerial vehicles (UAVs) have rapidly spread all over the world and are becoming widely popular in major cities for personal and commercial use. It has also been widely used for military purposes in the last decade. Thus, it has become difficult to maintain control over them and the risks they pose to privacy and security. In this paper, we present a solution to detect drones before they can reach a sensitive area or residence using the latest YOLOv4 deep learning algorithm while using Darknet as a backbone. We trained our model on different images at different distances and climatic conditions and trained our model to detect birds and aircraft that are very similar to drones at higher distances that may cause confusion, and also train the system at close distances and at very low and high image quality. For all available cases, our dataset was collected from three global and certified datasets in aircraft detection systems and the result was a dataset containing all cases. However, the collection of drones, birds and aircraft datasets is not easy to obtain. The proposed method achieved an accuracy of 98.3\% with the main challenge of detecting similar small objects near and far in all conditions.

Keywords

[1] K. Abbasi, A. Batool, M.A. Asghar, A. Saeed, M.J. Khan and M. ur Rehman, A vision-based amateur drone detection algorithm for public safety applications, 2019 UK/China Emerg. Technol. UCET 2019 (2019), 1–5.
[2] Y. He, I. Ahmad, L. Shi and KH. Chang, SVM-based drone sound recognition using the combination of HLA and WPT techniques in practical noisy environment, KSII Trans. Internet Inf. Syst. 13 (2019), no. 10, 5078–5094.
[3] M.A. Akhloufi, S. Arola and A. Bonnet, Drones chasing drones: reinforcement learning and deep search area proposal, Drones 3 (2019), no. 3, 1–14.
[4] M.S. Allahham, M.F. Al-Sa’d, A. Al-Ali, A. Mohamed, T. Khattab and A. Erbad, DroneRF dataset: a dataset of drones for RF-based detection, classification and identification, Data Br. 26 (2019).
[5] A. Bochkovskiy, C.-Y. Wang and H.-Y.M. Liao, YOLOv4: optimal speed and accuracy of object detection, arXiv preprint arXiv:2004.10934. (2020).
[6] E. Burger and G. Bordacchini, Global space policies and programmes, In Yearbook on Space Policy, Springer, Cham. 2019.
[7] Caltech Vision Lab, C.-U. Birds-200-2011, http://www.vision.caltech.edu/visipedia/CUB-200-2011.html, (2011).
[8] A. Coates, H. Lee and A.Y. Ng, An analysis of single layer networks in unsupervised feature learning, Proc. 14th Int. Conf. Artific. Intell. Statist. (AISTATS), Fort Lauderdale, FL, USA, 2011.
[9] A. Coluccia, A. Fascista, A. Schumann, L. Sommer, A. Dimou, D. Zarpalas, F.C. Akyon, O. Eryuksel, K.A. Ozfuttu, S.O. Altinuc and F. Dadboud, Drone-vs-bird detection challenge at IEEE AVSS2019, 16th IEEE Int. Conf. Adv. Video Signal Based Surveillance, AVSS, 2019, pp. 1–8.
[10] A.R. Eldosouky, A. Ferdowsi and W. Saad, Drones in distress: A game-theoretic countermeasure for protecting UAVs against GPS spoofing, IEEE Internet Things J. 7 (2020), no. 4, 2840–2854.
[11] J. Gao, C.-D. L¨u, Y.-L. Shen, Y.-M. Wang and Y.-B. Wei, Precision calculations of B −→ V form factors in QCD, arXiv preprint arXiv:1907.11092. (2019).
[12] S. Grac, P. Beno, F. Duchon, M. Dekan and M. Tolgyessy, Automated detection of multi-rotor UAVs using a machine-learning approach, Appl. Syst. Innov. 3 (2020), no. 3, 1–23.
[13] D. Kinaneva, G. Hristov, J. Raychev and P. Zahariev, Early forest fire detection using drones and artificial intelligence, 42nd Int. Conv. Inf. Commun. Technol. Electron. Microelectron. MIPRO 2019 Proc., 2019, pp. 1060–1065.
[14] S. Marathe, Leveraging drone based imaging technology for pipeline and RoU monitoring survey, Soc. Pet. Eng. -SPE Symp. Asia Pacific Heal. Safety, Secur. Environ. Soc. Responsib. 2019 (2019).
[15] S. Mayer, L. Lischke and P.W. Wo´zniak, Drones for search and rescue, 1st Int. Workshop on Human-Drone Interaction, 2019.
[16] D. Misra, Mish: a self regularized non-monotonic activation function, arXiv preprint arXiv:1908.08681. (2019).
[17] PASCAL 2, Visual Object Classes Challenge 2011 (VOC2011), http://host.robots.ox.ac.uk:8080/pascal/VOC/voc2011/inde2011.
[18] M. Pawe lczyk and M. Wojtyra, Real world object detection dataset for quadcopter unmanned aerial vehicle detection, IEEE Access 8 (2020), 174394–174409.
[19] T. Preethi Latha, K. Naga Sundari, S. Cherukuri and M.V.V.S.V. Prasad, Remote sensing uav/drone technology as a tool for urban development measures in apcrda, Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. ISPRS Arch. 42 (2019), no. 2/W13, 525–529.
[20] J. Redmon and A. Farhadi, YOLOv3: an incremental improvement, arXiv preprint arXiv:1804.02767. (2018).
[21] Q Shi and, J Li, Object detection of UAV for anti-UAV based on YOLOv4, IEEE 2nd Int. Conf. Civil Aviation Safety Inf. Technol.(ICCASIT. IEEE, 2020, pp. 1048–1052.
[22] S. Singha and B. Aydin, Automated drone detection using YOLOv4, Drones 5 (2021), no. 3.
[23] D. Tezza and M. Andujar, The state-of-the-art of human-drone interaction: A survey, IEEE Access 7 (2019), 167438–167454.
[24] E. Unlu, E. Zenou, N. Riviere and P.E. Dupouy, Deep learning-based strategies for the detection and tracking of drones using several cameras, IPSJ Trans. Comput. Vis. Appl. 11 (2019), no. 1.
[25] E. Unlu, E. Zenou, N. Riviere and P.E. Dupouy, An autonomous drone surveillance and tracking architecture, Electronic Imag. 2019 (2019), no. 15, 1–35.
[26] J.P. Winkler, J. Gr¨onberg and A. Vogelsang, Optimizing for recall in automatic requirements classification: an empirical study, IEEE 27th Int. Requir. Engin. Conf., IEEE, 2019, pp. 40–50.
[27] M. Wu, W. Xie, X. Shi, P. Shao and Z. Shi, Real-time drone detection using deep learning approach, Lect. Notes Inst. Comput. Sci. Soc. Telecommun. Eng. LNICST 251 (2018), 22–32.
[28] J. Xu, L. Guo, J. Jiang, B. Ge and M. Li, A deep learning methodology for automatic extraction and discovery of technical intelligence, Technol. Forecast. Soc. Change 146 (2019), 339–351.
[29] Z. Zhang, T. He, H. Zhang, Z. Zhang, J. Xie and M. Li, Bag of freebies for training object detection neural networks, arXiv preprint arXiv:1902.04103. (2019).
Volume 13, Issue 2
July 2022
Pages 2709-2722
  • Receive Date: 16 November 2021
  • Revise Date: 19 December 2021
  • Accept Date: 15 January 2022