Machine Learning and Artificial Intelligence Approaches for Drone Detection Using YOLOv11 Algorithm

Abstract

The rapid development of artificial intelligence (AI) and machine learning (ML) has significantly transformed the capabilities of unmanned aerial vehicle (UAV) detection systems. This study presents an AI- and ML-based approach for drone detection using the YOLOv11 algorithm, a state-of-the-art deep learning model designed for real-time object recognition. A custom dataset, consisting of 1450 drone images collected under diverse environmental and lighting conditions, was used to train and evaluate the model. The training process employed the YOLOv11 variants (n, s, m, l, x) on the PyTorch framework, with performance metrics including Precision, Recall, F1-Score, and mAP50–95. The results demonstrated exceptional detection accuracy, achieving up to 99% precision and 98% recall, with an overall mAP50 of 0.99 and mAP50–95 of 0.70. Loss function analyses indicated consistent convergence, while confusion matrix and confidence curve evaluations confirmed the model’s robustness in differentiating drone objects from background scenes. This research highlights the effectiveness of integrating deep learning architectures within AI-driven vision systems for UAV detection. The findings confirm that YOLOv11 offers a highly reliable and efficient solution for real-time drone identification, with strong potential for implementation in security, surveillance, and autonomous navigation applications.

Keywords

• Artificial intelligence
• deep learning
• machine learning
• image processing
• object detection

YOLOv11 Algoritması Kullanılarak Drone Tespiti için Makine Öğrenmesi ve Yapay Zeka Yaklaşımları

Abstract

The rapid development of artificial intelligence (AI) and machine learning (ML) has significantly transformed the capabilities of unmanned aerial vehicle (UAV) detection systems. This study presents an AI- and ML-based approach for drone detection using the YOLOv11 algorithm, a state-of-the-art deep learning model designed for real-time object recognition. A custom dataset, consisting of 1450 drone images collected under diverse environmental and lighting conditions, was used to train and evaluate the model. The training process employed the YOLOv11 variants (n, s, m, l, x) on the PyTorch framework, with performance metrics including Precision, Recall, F1-Score, and mAP50–95. The results demonstrated exceptional detection accuracy, achieving up to 99% precision and 98% recall, with an overall mAP50 of 0.99 and mAP50–95 of 0.70. 1.404 / 5.000 Yapay zekâ (YZ) ve makine öğreniminin (ML) hızlı gelişimi, insansız hava aracı (İHA) tespit sistemlerinin yeteneklerini önemli ölçüde dönüştürmüştür. Bu çalışma, gerçek zamanlı nesne tanıma için tasarlanmış son teknoloji derin öğrenme modeli olan YOLOv11 algoritmasını kullanarak drone tespiti için YZ ve ML tabanlı bir yaklaşım sunmaktadır. Modeli eğitmek ve değerlendirmek için çeşitli çevre ve ışık koşulları altında toplanan 1450 drone görüntüsünden oluşan özel bir veri kümesi kullanılmıştır. Eğitim sürecinde PyTorch çerçevesinde Hassasiyet, Geri Çağırma, F1 Puanı ve mAP50–95 gibi performans ölçütleriyle YOLOv11 varyantları (n, s, m, l, x) kullanılmıştır. Sonuçlar, %99'a varan hassasiyet ve %98'e varan geri çağırma ile 0,99'luk genel mAP50 ve 0,70'lik mAP50–95 değerlerine ulaşan olağanüstü tespit doğruluğu göstermiştir. Kayıp fonksiyonu analizleri tutarlı bir yakınsama gösterirken, karışıklık matrisi ve güven eğrisi değerlendirmeleri, modelin drone nesnelerini arka plan sahnelerinden ayırt etmedeki sağlamlığını doğruladı. Bu araştırma, derin öğrenme mimarilerinin İHA tespiti için yapay zeka destekli görüş sistemlerine entegre edilmesinin etkinliğini vurgulamaktadır. Bulgular, YOLOv11'in güvenlik, gözetleme ve otonom navigasyon uygulamalarında güçlü bir uygulama potansiyeline sahip, gerçek zamanlı drone tanımlama için son derece güvenilir ve verimli bir çözüm sunduğunu doğrulamaktadır.

Keywords

• Yapay zeka
• derin öğrenme
• makine öğrenmesi
• görüntü işleme
• nesne algılama

References

1. Wu, C., Ju, B., Wu, Y., Lin, X., Xiong, N., Xu, G., … & Liang, X. (2019). Uav autonomous target search based on deep reinforcement learning in complex disaster scene. IEEE Access, 7, 117227-117245. https://doi.org/10.1109/access.2019.2933002.
2. Wang, C., Wang, J., Zhang, X., & Zhang, X. (2017). Autonomous navigation of uav in large-scale unknown complex environment with deep reinforcement learning. 2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP), 858-862. https://doi.org/10.1109/globalsip.2017.8309082.
3. Azar, A. T., Koubâa, A., Mohamed, N. A., Ibrahim, H. A., Ibrahim, Z. F., Kazim, M., … & Casalino, G. (2021). Drone deep reinforcement learning: a review. Electronics, 10(9), 999. https://doi.org/10.3390/electronics10090999
4. Rohan, A., Rabah, M., & Kim, S. (2019). Convolutional neural network-based real-time object detection and tracking for parrot ar drone 2. IEEE Access, 7, 69575-69584. https://doi.org/10.1109/access.2019.2919332
5. Palossi, D., Loquercio, A., Conti, F., Flamand, É., Scaramuzza, D., & Benini, L. (2019). A 64-mw dnn-based visual navigation engine for autonomous nano-drones. IEEE Internet of Things Journal, 6(5), 8357-8371. https://doi.org/10.1109/jiot.2019.2917066
6. Tanveer, J., Haider, A., Ali, R., & Kim, A. (2021). Reinforcement learning-based optimization for drone mobility in 5g and beyond ultra-dense networks. Computers, Materials & Continua, 68(3), 3807-3823. https://doi.org/10.32604/cmc.2021.016087
7. Bithas, P. S., Michailidis, E. T., Νομικός, Ν., Vouyioukas, D., & Kanatas, Α. G. (2019). A survey on machine-learning techniques for uav-based communications. Sensors, 19(23), 5170. https://doi.org/10.3390/s19235170
8. Liu, L., Wu, Y., Fu, G., & Zhou, C. (2022). An improved four‐rotor uav autonomous navigation multisensor fusion depth learning. Wireless Communications and Mobile Computing, 2022(1). https://doi.org/10.1155/2022/2701359

9. Navardi, M., Shiri, A., Humes, E., Waytowich, N. R., & Mohsenin, T. (2022). An optimization framework for efficient vision-based autonomous drone navigation. 2022 IEEE 4th International Conference on Artificial Intelligence Circuits and Systems (AICAS), 304-307. https://doi.org/10.1109/aicas54282.2022.9869975
10. Baig, Z., Syed, N., & Mohammad, N. (2022). Securing the smart city airspace: drone cyber attack detection through machine learning. Future Internet, 14(7), 205. https://doi.org/10.3390/fi14070205
11. Ke, L., Zhang, K., Zhang, Z., Liu, Z., Hua, S., & He, J. (2021). A uav maneuver decision-making algorithm for autonomous airdrop based on deep reinforcement learning. Sensors, 21(6), 2233. https://doi.org/10.3390/s21062233
12. Akhloufi, M. A., Arola, S., & Bonnet, A. (2019). Drones chasing drones: reinforcement learning and deep search area proposal. Drones, 3(3), 58. https://doi.org/10.3390/drones3030058
13. Hu, J., Wang, L., Hu, T., Guo, C., & Wang, Y. (2022). Autonomous maneuver decision making of dual-uav cooperative air combat based on deep reinforcement learning. Electronics, 11(3), 467. https://doi.org/10.3390/electronics11030467
14. Hu, Y., Liu, Y., Kaushik, A., Masouros, C., & Thompson, J. (2023). Timely data collection for uav-based iot networks: a deep reinforcement learning approach. IEEE Sensors Journal, 23(11), 12295-12308. https://doi.org/10.1109/jsen.2023.3265935
15. Bălaşa, R., Bîlu, M. C., & Iordache, C. (2022). A proximal policy optimization reinforcement learning approach to unmanned aerial vehicles attitude control. Land Forces Academy Review, 27(4), 400-410. https://doi.org/10.2478/raft-2022-0049
16. Madridano, Á., Al-Kaff, A., Flores, P., Martín, D., & Escalera, A. d. l. (2021). Software architecture for autonomous and coordinated navigation of uav swarms in forest and urban firefighting. Applied Sciences, 11(3), 1258. https://doi.org/10.3390/app11031258
17. Fei, S., Hassan, M. A., Xiao, Y., Su, X., Chen, Z., Cheng, Q., … & Ma, Y. (2022). Uav-based multi-sensor data fusion and machine learning algorithm for yield prediction in wheat. Precision Agriculture, 24(1), 187-212. https://doi.org/10.1007/s11119-022-09938-8
18. Eskandari, R., Mahdianpari, M., Mohammadimanesh, F., Salehi, B., Brisco, B., & Homayouni, S. (2020). Meta-analysis of unmanned aerial vehicle (uav) imagery for agro-environmental monitoring using machine learning and statistical models. Remote Sensing, 12(21), 3511. https://doi.org/10.3390/rs12213511
19. Yin, Y., Wang, Z., Zheng, L., Su, Q., & Guo, Y. (2024). Autonomous uav navigation with adaptive control based on deep reinforcement learning. Electronics, 13(13), 2432. https://doi.org/10.3390/electronics13132432
20. Loquercio, A., Maqueda, A. I., del‐Blanco, C. R., & Scaramuzza, D. (2018). Dronet: learning to fly by driving. IEEE Robotics and Automation Letters, 3(2), 1088-1095. https://doi.org/10.1109/lra.2018.2795643
21. Huang, H., Yang, Y., Wang, H., Ding, Z., Sari, H., & Adachi, F. (2020). Deep reinforcement learning for uav navigation through massive mimo technique. IEEE Transactions on Vehicular Technology, 69(1), 1117-1121. https://doi.org/10.1109/tvt.2019.2952549
22. Huang, H., Yang, Y., Wang, H., Ding, Z., Sari, H., & Adachi, F. (2020). Deep reinforcement learning for uav navigation through massive mimo technique. IEEE Transactions on Vehicular Technology, 69(1), 1117-1121. https://doi.org/10.1109/tvt.2019.2952549
23. Sieberth, T., Wackrow, R., & Chandler, J. H. (2014). Motion blur disturbs – the influence of motion‐blurred images in photogrammetry. The Photogrammetric Record, 29(148), 434-453. https://doi.org/10.1111/phor.12082
24. Sieberth, T., Wackrow, R., & Chandler, J. H. (2015). Uav image blur – its influence and ways to correct it. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XL-1/W4, 33-39. https://doi.org/10.5194/isprsarchives-xl-1-w4-33-2015
25. Єремеєв, О., Lukin, V., Okarma, K., & Egiazarian, K. (2023). Efficiency increasing of no-reference image quality assessment in uav applications. Computer Modeling and Intelligent Systems, 3392, 246-260. https://doi.org/10.32782/cmis/3392-21
26. Мударисов, С. and Miftakhov, I. (2024). Deep learning methods and uav technologies for crop disease detection. Agricultural Machinery and Technologies, 18(4), 24-33. https://doi.org/10.22314/2073-7599-2024-18-4-24-33
27. Rui-hua, W., Xiao, X., Guo, B., Qin, Q., & Chen, R. (2018). An effective image denoising method for uav images via improved generative adversarial networks. Sensors, 18(7), 1985. https://doi.org/10.3390/s18071985
28. Sarıbaş, H., Kahvecıoğlu, S., & Çevıkalp, H. (2018). Car localization in aerial images taken from quadcopter. RTET-2018, AAEBM-18, BEHSS-18, BLEIS-18, CEECE-2018 April 24-26, 2018 Pattaya (Thailand). https://doi.org/10.17758/dirpub2.dir0418111
29. KATAR, O. and Duman, E. (2022). U-net based car detection method for unmanned aerial vehicles. Mühendislik Bilimleri Ve Tasarım Dergisi, 10(4), 1141-1154. https://doi.org/10.21923/jesd.1087477
30. Scaramuzza, D. (2017). Application challenges from a bird's‐eye view. Computer Vision in Vehicle Technology, 122-132. https://doi.org/10.1002/9781118868065.ch6
31. Yoon, S. and Kim, T. (2024). Seamline optimization based on triangulated irregular network of tiepoints for fast uav image mosaicking. Remote Sensing, 16(10), 1738. https://doi.org/10.3390/rs16101738
32. El Naser, Y. H., Karayel, D., Demirsoy, M. S., Sarıkaya, M. S., & Peker, N. Y. (2024). Robotic arm trajectory tracking using image processing and kinematic equations. Black Sea Journal of Engineering and Science, 7(3), 436-444.
33. El Naser, Y. H., Demirsoy, B., Erin, K., & Demirsoy, M. S. Chaotic Speed Control of a DC Motor Using the Sprott-A System for Robotic End-Effector Applications. Black Sea Journal of Engineering and Science, 8(5), 1406-1414.
34. Sarıkaya, M. S., Demirsoy, M. S., & Kutlu, M. Ç. Design of a Chaotic Speed-Controlled Mixing Device and Efficiency Analysis in Biogas. Black Sea Journal of Engineering and Science, 8(3), 672-679.