Hostname: page-component-586b7cd67f-tf8b9 Total loading time: 0 Render date: 2024-11-28T17:09:55.886Z Has data issue: false hasContentIssue false
  • English
  • Français

Improving real-time drone detection for counter-drone systems

Published online by Cambridge University Press:  16 June 2021

E. Çetin Open the ORCID record for E. Çetin [Opens in a new window] ,
C. Barrado  and
E. Pastor
E. Çetin*
Affiliation:
Technical University of Catalonia UPC BarcelonaTech Computer Architecture Department BarcelonaSpain
C. Barrado
Affiliation:
Technical University of Catalonia UPC BarcelonaTech Computer Architecture Department BarcelonaSpain
E. Pastor
Affiliation:
Technical University of Catalonia UPC BarcelonaTech Computer Architecture Department BarcelonaSpain
*
[email protected]
Get access Rights & Permissions [Opens in a new window]

Abstract

The number of unmanned aerial vehicles (UAVs, also known as drones) has increased dramatically in the airspace worldwide for tasks such as surveillance, reconnaissance, shipping and delivery. However, a small number of them, acting maliciously, can raise many security risks. Recent Artificial Intelligence (AI) capabilities for object detection can be very useful for the identification and classification of drones flying in the airspace and, in particular, are a good solution against malicious drones. A number of counter-drone solutions are being developed, but the cost of drone detection ground systems can also be very high, depending on the number of sensors deployed and powerful fusion algorithms. We propose a low-cost counter-drone solution composed uniquely by a guard-drone that should be able to detect, locate and eliminate any malicious drone. In this paper, a state-of-the-art object detection algorithm is used to train the system to detect drones. Three existing object detection models are improved by transfer learning and tested for real-time drone detection. Training is done with a new dataset of drone images, constructed automatically from a very realistic flight simulator. While flying, the guard-drone captures random images of the area, while at the same time, a malicious drone is flying too. The drone images are auto-labelled using the location and attitude information available in the simulator for both drones. The world coordinates for the malicious drone position must then be projected into image pixel coordinates. The training and test results show a minimum accuracy improvement of 22% with respect to state-of-the-art object detection models, representing promising results that enable a step towards the construction of a fully autonomous counter-drone system.

Keywords

Counter-DroneUAVDronesObject DetectionYOLOEfficientNetdeep learningAirsim
Type
Research Article
Information
The Aeronautical Journal , Volume 125 , Issue 1292 , October 2021 , pp. 1871 - 1896
Check for updates
Copyright
© The Author(s), 2021. Published by Cambridge University Press on behalf of Royal Aeronautical Society

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Kratky, M. and Farlik, J. Countering UAVs–the mover of research in military technology, Defence Sci. J., 2018, 68, (5), pp 460–466.CrossRefGoogle Scholar
Choi, B., Oh, D., Kim, S., Chong, J.-W. and Li, Y.-C. Long-range drone detection of 24 g FMCW radar with e-plane sectoral horn array, Sensors, 2018, 18, (12), p 4171.CrossRefGoogle ScholarPubMed
Bernardini, A., Mangiatordi, F., Pallotti, E. and Capodiferro, L. Drone detection by acoustic signature identification, Electron. Imaging, 2017, 10, pp 60–64.CrossRefGoogle Scholar
de Haag, M.U., Bartone, C.G. and Braasch, M.S. Flight-test evaluation of small form-factor LiDAR and radar sensors for sUAS detect-and-avoid applications, 2016 IEEE/AIAA 35th Digital Avionics Systems Conference (DASC), IEEE, 2016, pp 1–11.Google Scholar
Samaras, S., Diamantidou, E., Ataloglou, D., Sakellariou, N., Vafeiadis, A., Magoulianitis, V., Lalas, A., Dimou, A., Zarpalas, D., Votis, K., Daras, P. and Tzovaras, D. Deep learning on multi sensor data for counter UAV applications–a systematic review, Sensors, 2019, 19, (22), p. 4837.CrossRefGoogle ScholarPubMed
Çetin, E., Barrado, C. and Pastor, E. Counter a drone in a complex neighborhood area by deep reinforcement learning, Sensors, 2020, 20, (8), p 2320.CrossRefGoogle Scholar
Girshick, R. Fast R-CNN, Proceedings of the IEEE International Conference on Computer vVision, 2015, pp 1440–1448.CrossRefGoogle Scholar
Ren, S., He, K., Girshick, R. and Sun, J. Faster R-CNN: Towards real-time object detection with region proposal networks, in Adv. Neural Inform. Process. Syst., 2015, pp 91–99.Google Scholar
Chollet, F. Xception: Deep learning with depthwise separable convolutions, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp 1251–1258.CrossRefGoogle Scholar
Redmon, J., Divvala, S., Girshick, R. and Farhadi, A. You only look once: Unified, real-time object detection, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp 779–788.CrossRefGoogle Scholar
Tan, M. and Le, Q. Efficientnet: Rethinking model scaling for convolutional neural networks, International Conference on Machine Learning, PMLR, 2019, pp 6105–6114.Google Scholar
Tan, M., Pang, R. and Le, Q.V. Efficientdet: Scalable and efficient object detection, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp 10781–10790.CrossRefGoogle Scholar
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D. Erhan, D., Vanhoucke, V. and Rabinovich, A. Going deeper with convolutions, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp 1–9.CrossRefGoogle Scholar
Redmon, J. and Farhadi, A. Yolo9000: Better, faster, stronger, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp 7263–7271.CrossRefGoogle Scholar
Bhattarai, N., Nakamura, T. and Mozumder, C. Real time human detection and localization using consumer grade camera and commercial UAV, 2018.CrossRefGoogle Scholar
Rudol, P. and Doherty, P. Human body detection and geolocalization for UAV search and rescue missions using color and thermal imagery, 2008 IEEE Aerospace Conference, IEEE, 2008, pp 1–8.CrossRefGoogle Scholar
Yang, D., Yurtsever, E., Renganathan, V., Redmill, K.A. and ÖzgÜner, Ü. A vision-based social distance and critical density detection system for covid-19, arXiv preprint arXiv:2007.03578, 2020.Google Scholar
Coronavirus disease (covid-19) pandemic. https://www.who.int/emergencies/diseases/novel-coronavirus-2019, last Accessed: 2021-01-10.Google Scholar
Craye, C. and Ardjoune, S. Spatio-temporal semantic segmentation for drone detection, 2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), IEEE, 2019, pp 1–5.CrossRefGoogle Scholar
Drone-net, https://github.com/chuanenlin/drone-net note = Last Accessed: 2020-06-02, 2020.Google Scholar
Xiaoping, L., Songze, L., Boxing, Z., Yanhong, W. and Feng, X. Fast aerial uav detection using improved inter-frame difference and svm, J. Phys. Conf. Ser., 1187, (3). IOP Publishing, 2019, p 032082.CrossRefGoogle Scholar
Hu, Q., Duan, Q., Mao, Y., Zhou, X. and Zhou, G. Diagonalnet: Confidence diagonal lines for the UAV detection, IEEJ Trans. Electr. Electron. Eng., 2019, 14, (9), pp 1364–1371.CrossRefGoogle Scholar
Jin, R., Jiang, J., Qi, Y., Lin, D. and Song, T. Drone detection and pose estimation using relational graph networks, Sensors, 2019, 19, (6), p 1479.CrossRefGoogle ScholarPubMed
Carrio, A., Tordesillas, J., Vemprala, S., Saripalli, S., Campoy, P. and How, J.P. “Onboard detection and localization of drones using depth maps,” IEEE Access, 2020, 8, pp 30480–30490.CrossRefGoogle Scholar
Wyder, P.M., Chen, Y.-S., Lasrado, A.J., Pelles, R.J., Kwiatkowski, R., Comas, E.O., Kennedy, R., Mangla, A., Huang, Z., Hu, X., Xiong, Z., Aharoni, T., Chuang, T.-C. and Lipson, H. Autonomous drone hunter operating by deep learning and all-onboard computations in gps-denied environments, PloS One, 2019, 14, (11).CrossRefGoogle ScholarPubMed
Çetin, E. Counter a drone, https://github.com/EnderUPC/CounterDrone.git note = Last Accessed: 2021-03-23, 2021.Google Scholar
Shah, S., Dey, D., Lovett, C. and Kapoor, A. Airsim: High-fidelity visual and physical simulation for autonomous vehicles, in Field and Service Robotics, 2017. [Online]. Available: https://arxiv.org/abs/1705.05065 CrossRefGoogle Scholar
Unreal engine 4, https://www.unrealengine.com/en-US/what-is-unreal-engine-4, last Accessed: 2019-01-29.Google Scholar
Redmon, J. Darknet: Open source neural networks in c. http, pjreddie. com/darknet, vol. 2016, 2013.Google Scholar
Yolo-v4 and yolo-v3/v2 for windows and linux. https://github.com/AlexeyAB/darknet note = Last Accessed: 2020-05-27, 2020.Google Scholar
Redmon, J. and Farhadi, A. Yolov3: An incremental improvement, arXiv, 2018.Google Scholar
Bisong, E. Google colaboratory, in Building Machine Learning and Deep Learning Models on Google Cloud Platform, Springer, 2019, pp 59–64.Google Scholar
Stevens, B.L., Lewis, F.L. and Johnson, E.N. Aircraft Control and Simulation: Dynamics, Controls Design, and Autonomous Systems, John Wiley & Sons, 2015.CrossRefGoogle Scholar
Taylor, M.E. and Stone, P. Transfer learning for reinforcement learning domains: A survey, J. Mach. Learn. Res., 2009, 10, pp 1633–1685.Google Scholar
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., DollÁr, P. and Zitnick, C.L. Microsoft coco: Common objects in context, European Conference on Computer Vision, Springer, 2014, pp 740–755.CrossRefGoogle Scholar