Görüntü Tabanlı Amatör Drone Tespiti: Derin Öğrenmede Yeni Yaklaşımların Performans Analizi

Abstract

İnsansız hava araçlarına (İHA) olan ilgi önemli ölçüde artmıştır. Otonom çalışabilen İHA’lar, çeşitli alanlara kolaylıkla konuşlandırılabilmeleri nedeniyle uygulama alanlarını genişletmiştir. İHA’ların faaliyet alanlarının genişlemesi, aynı zamanda güvenlik sorunlarını da beraberinde getirmektedir. İHA uçuşları için yasaklanmış olan yerler yasal olarak tanımlanmış olsa da ihlallerin tespitine yönelik tedbirlerin alınması gerekmektedir. Bu çalışmada, ultraviyole görüntüler üzerinde nesnelerin tespit edilmesi için kullanılan ve son zamanlarda önerilen yöntemler test edilmiş ve performansları tartışılmıştır. Modelleri, çeşitli drone görüntülerini toplayarak oluşturduğumuz GDrone isimli yeni bir veri seti üzerinde test ettik. Test edilen YOLOv6 ve YOLOv7 modelleri daha önce bir drone veri seti ile test edilmemiştir. Deneysel testlere göre en başarılı model YOLOv7 mimarisi oldu ve GDrone veri kümesindeki mAP (ortalama hassasiyet) değeri %95,8 olarak belirlendi.

Keywords

• İnsansız hava araçları
• amatör drone tespiti
• evrişimli sinir ağları
• İHA veri seti

Supporting Institution

Gaziantep İslam Bilim ve Teknoloji Üniversitesi

Project Number

2021-FM-02

Vision-Based Amateur Drone Detection: Performance Analysis of New Approaches in Deep Learning

Abstract

Interest in unmanned aerial vehicles (UAVs) has increased significantly. UAVs capable of autonomous operations have expanded their application areas as they can be easily deployed in various fields. The expansion of UAVs’ areas of operation also brings safety issues. Although legally prohibited places forUAV flights are defined, measures should be taken to detect violations. This study tested recently proposed methods that are used to detect objects from images on UV images, and their performances were discussed. We tested the models on a new dataset named GDrone that we created by collecting various images of drones. Two tested models, YOLOv6 and YOLOv7, have never been tested with a drone dataset. According to the experimental tests, the most successful model was YOLOv7 architecture, and its mAP (mean Average Precision) was 95.8% on GDrone dataset.

Keywords

• Unmanned aerial vehicles
• amateur drone detection
• convolutional neural networks
• UAW dataset

Project Number

2021-FM-02

References

1. Aktürk, Cemal, Emrah Aydemir, and Yasr Mahdi Hama Rashid. 2023. “Classification of Eye Images by Personal Details with Transfer Learning Algorithms.” Acta Informatica Pragensia 12(1):32-53. google scholar
2. Al-Emadi, Sara, Abdulla Al-Ali, Amr Mohammad, and Abdulaziz Al-Ali. 2019. “Audio Based Drone Detection and Identification Using Deep Learning.” Pp. 459-64 in 2019 15th International Wireless Communications & Mobile Computing Conference (IWCMC). IEEE. google scholar
3. Al-Hourani, Akram, Sithamparanathan Kandeepan, and Abbas Jamalipour. 2015. “Stochastic Geometry Study on Device-to-Device Communi-cation as a Disaster Relief Solution.” IEEE Transactions on Vehicular Technology 65(5):3005-17. google scholar
4. Al-Sa’d, Mohammad F., Abdulla Al-Ali, Amr Mohamed, Tamer Khattab, and Aiman Erbad. 2019. “RF-Based Drone Detection and Identification Using Deep Learning Approaches: An Initiative towards a Large Open Source Drone Database.” Future Generation Computer Systems 100:86-97. google scholar
5. Aydin, Ahmet, Mehmet Umut Salur, and İlhan Aydin. 2021. “Fine-Tuning Convolutional Neural Network Based Railway Damage Detection.” Pp. 216-21 in IEEE EUROCON 2021-19th International Conference on Smart Technologies. IEEE. google scholar
6. Behera, Dinesh Kumar, and Arockia Bazil Raj. 2020. “Drone Detection and Classification Using Deep Learning.” Pp. 1012-16 in 2020 4th International Conference on Intelligent Computing and Control Systems (ICICCS). IEEE. google scholar
7. Carter, Ashton B., and David N. Schwartz. 2010. Ballistic Missile Defense. Brookings Institution Press. google scholar
8. Ding, Xiaohan, Xiangyu Zhang, Ningning Ma, Jungong Han, Guiguang Ding, and Jian Sun. 2021. “Repvgg: Making Vgg-Style Convnets Great Again.” Pp. 13733-42 in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. google scholar

9. Fang, Yuxin, Bencheng Liao, Xinggang Wang, Jiemin Fang, Jiyang Qi, Rui Wu, Jianwei Niu, and Wenyu Liu. 2021. “You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection.” Advances in Neural Information Processing Systems 34:26183-97. google scholar
10. Girshick, Ross. 2015. “Fast R-Cnn.” Pp. 1440-48 in Proceedings of the IEEE international conference on computer vision. google scholar
11. Khan, Gul Zameen, Eun-Chan Park, and Ruben Gonzalez. 2017. “M 3-Cast: A Novel Multicast Scheme in Multi-Channel and Multi-Rate Wifi Direct Networks for Public Safety.” IEEE Access 5:17852-68. google scholar
12. Korkmaz, Adem, Cemal Aktürk, and Tarık Talan. 2023. “Analyzing the User’s Sentiments of ChatGPT Using Twitter Data.” Iraqi Journal For Computer Science and Mathematics 4(2):202-14. google scholar
13. Lee, Dongkyu, Woong Gyu La, and Hwangnam Kim. 2018. “Drone Detection and Identification System Using Artificial Intelligence.” Pp. 1131-33 in 2018 International Conference on Information and Communication Technology Convergence (ICTC). IEEE. google scholar
14. Liu, Hansen, Kuangang Fan, Qinghua Ouyang, and Na Li. 2021. “Real-Time Small Drones Detection Based on Pruned Yolov4.” Sensors 21(10):3374. google scholar
15. Liu, Hao, Zhiqiang Wei, Yitong Chen, Jie Pan, Le Lin, and Yunfang Ren. 2017. “Drone Detection Based on an Audio-Assisted Camera Array.” Pp. 402-6 in 2017 IEEE Third International Conference on Multimedia Big Data (BigMM). IEEE. google scholar
16. Liu, Wei, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, and Alexander C. Berg. 2016. “Ssd: Single Shot Multibox Detector.” Pp. 21-37 in Computer Vision-ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part I 14. Springer. google scholar
17. Müller, Thomas. 2017. “Robust Drone Detection for Day/Night Counter-UAV with Static VIS and SWIR Cameras.” Pp. 302-13 in Ground/Air Multisensor Interoperability, Integration, and Networking for Persistent ISR VIII. Vol. 10190. SPIE. google scholar
18. Nalamati, Mrunalini, Ankit Kapoor, Muhammed Saqib, Nabin Sharma, and Michael Blumenstein. 2019. “Drone Detection in Long-Range Surveillance Videos.” Pp. 1-6 in 2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS). IEEE. google scholar
19. Onishi, Masanori, and Takeshi Ise. 2021. “Explainable Identification and Mapping of Trees Using UAV RGB Image and Deep Learning.” Scientific Reports 11(1):903. google scholar
20. Pham, Giao N., and Phong H. Nguyen. 2020. “Drone Detection Experiment Based on Image Processing and Machine Learning.” google scholar
21. Redmon, Joseph, Santosh Divvala, Ross Girshick, and Ali Farhadi. 2016. “You Only Look Once: Unified, Real-Time Object Detection.” Pp. 779-88 in Proceedings of the IEEE conference on computer vision and pattern recognition. google scholar
22. Sahin, Oyku, and Sedat Ozer. 2021. “Yolodrone: Improved Yolo Architecture for Object Detection in Drone Images.” Pp. 361-65 in 2021 44th International Conference on Telecommunications and Signal Processing (TSP). IEEE. google scholar
23. Talan, Tarik. 2021. “Artificial Intelligence in Education: A Bibliometric Study.” International Journal of Research in Education and Science 7(3):822-37. google scholar
24. Tang, Fengxiao, Zubair Md Fadlullah, Nei Kato, Fumie Ono, and Ryu Miura. 2017. “AC-POCA: Anticoordination Game Based Partially Over-lapping Channels Assignment in Combined UAV and D2D-Based Networks.” IEEE Transactions on Vehicular Technology 67(2):1672-83. google scholar
25. Vattapparamban, Edwin, Ismail Güvenç, Ali I. Yurekli, Kemal Akkaya, and Selçuk Uluağaç. 2016. “Drones for Smart Cities: Issues in Cybersecurity, Privacy, and Public Safety.” Pp. 216-21 in 2016 international wireless communications and mobile computing conference (IWCMC). IEEE. google scholar
26. Wang, Chien-Yao, Alexey Bochkovskiy, and Hong-Yuan Mark Liao. 2023. “YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors.” Pp. 7464-75 in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. google scholar
27. Wang, Chien-Yao, Hong-Yuan Mark Liao, and I. Hau Yeh. 2022. “Designing Network Design Strategies through Gradient Path Analysis.” ArXiv Preprint ArXiv:2211.04800. google scholar
28. Zhao, Jianqing, Xiaohu Zhang, Jiawei Yan, Xiaolei Qiu, Xia Yao, Yongchao Tian, Yan Zhu, and Weixing Cao. 2021. “A Wheat Spike Detection Method in UAV Images Based on Improved YOLOv5.” Remote Sensing 13(16):3095. google scholar
29. Zheng, Ye, Zhang Chen, Dailin Lv, Zhixing Li, Zhenzhong Lan, and Shiyu Zhao. 2021. “Air-to-Air Visual Detection of Micro-UAVs: An Experimental Evaluation of Deep Learning.” IEEE Robotics and Automation Letters 6(2):1020-27. google scholar