MEKANSAL PİRAMİT HAVUZLAMA TABANLI EVRİŞİMLİ SİNİR AĞI İLE OTOMATİK DRONE SINIFLANDIRMA

Hava sahalarının önemli olduğu bölgelerde dronları tespit etmek zorlu bir konu haline gelmiştir. Bu araçların kontrolsüz uçuşları ve konuşlanmaları da istenmeyen bölgelerde çeşitli güvenlik sorunlarına sebep olur. Bu çalışmada, dronları kuşlardan ayırarak etkili bir şekilde sınıflandırabilmek için bir evrişimli sinir ağı (ESA) modeli önerilmiştir. Önerilen model, ön eğitimli AlexNet ile mekansal piramit havuzlama (MPH) yapısı kullanılarak tasarlanmıştır. Böylece, ağın evrişimsel katmanlarından gelen yerel öznitelikler birleştirerek ağın nesne özelliklerini daha kapsamlı bir şekilde öğrenmesi sağlanmış ve önerilen modelin sınıflandırma performansı artırılmıştır. Ayrıca, eğitim görüntülerinde çevrimdışı veri artırma tekniği uygulanarak örnek sayısı artırılmıştır. Önerilen yöntemin performansı AlexNet, ShuffleNet, GoogLeNet ve DarkNet gibi sıklıkla kullanılan ön eğitimli ESA mimarileri ile karşılaştırılmıştır. Gerçekleştirilen deneysel çalışmalarda önerilen yöntemin doğruluk, kesinlik, duyarlılık, özgüllük ve F1-skor değerleri sırasıyla %98.89, %97.83, %100, %97.78 ve %98.90 olarak elde edilmiştir. Çalışmada elde edilen tüm sonuçlar incelendiğinde, önerilen yöntemin farklı ortamlara ait drone görüntülerini kuşlardan ayırarak başarımı yüksek bir şekilde sınıflayabildiğini ortaya koymaktadır.

Anahtar Kelimeler:

Drone sınıflandırma, evrişimli sinir ağları, mekansal piramit hazulama, derin öğrenme

AUTOMATED DRONE CLASSIFICATION WITH A SPATIAL PYRAMID POOLING-BASED CONVENTIONAL NEURAL NETWORK

Keywords:

Drone classification, convolutional neural networks, spatial pyramid pooling, deep learning,

PDF

___

Anwar, M.Z., Kaleem, Z., Jamalipour, A., 2019. Machine Learning Inspired Sound-Based Amateur Drone Detection for Public Safety Applications. IEEE Trans. Veh. Technol. 68, 2526–2534. https://doi.org/10.1109/TVT.2019.2893615
Basak, S., Rajendran, S., Pollin, S., Scheers, B., 2022. Combined RF-Based Drone Detection and Classification. IEEE Trans. Cogn. Commun. Netw. 8, 111–120. https://doi.org/10.1109/TCCN.2021.3099114
Basbug, A.M., Sert, M., 2019. Acoustic Scene Classification Using Spatial Pyramid Pooling with Convolutional Neural Networks. 13th IEEE Int. Conf. Semant. Comput. ICSC 2019 128–131. https://doi.org/10.1109/ICSC.2019.00029
Coluccia, A., Fascista, A., Schumann, A., Sommer, L., Dimou, A., Zarpalas, D., Méndez, M., de la Iglesia, D., González, I., Mercier, J.-P., Gagné, G., Mitra, A., Rajashekar, S., 2021. Drone vs. Bird Detection: Deep Learning Algorithms and Results from a Grand Challenge. Sensors 21, 2824. https://doi.org/10.3390/s21082824
Coluccia, A., Parisi, G., Fascista, A., 2020. Detection and Classification of Multirotor Drones in Radar Sensor Networks: A Review. Sensors 20, 4172. https://doi.org/10.3390/s20154172
Dale, H., Baker, C., Antoniou, M., Jahangir, M., Atkinson, G., Harman, S., 2022. SNR‐dependent drone classification using convolutional neural networks. IET Radar, Sonar Navig. 16, 22–33. https://doi.org/10.1049/rsn2.12161
Grác, Š., Beňo, P., Duchoň, F., Dekan, M., Tölgyessy, M., 2020. Automated detection of multi-rotor UAVs using a machine-learning approach. Appl. Syst. Innov. 3, 1–23. https://doi.org/10.3390/asi3030029
Han, X., Zhong, Y., Cao, L., Zhang, L., 2017. Pre-trained alexnet architecture with pyramid pooling and supervision for high spatial resolution remote sensing image scene classification. Remote Sens. 9. https://doi.org/10.3390/rs9080848
Hassanalian, M., Abdelkefi, A., 2017. Classifications, applications, and design challenges of drones: A review. Prog. Aerosp. Sci. 91, 99–131. https://doi.org/10.1016/j.paerosci.2017.04.003
Huang, Z., Wang, J., Fu, X., Yu, T., Guo, Y., Wang, R., 2020. DC-SPP-YOLO: Dense connection and spatial pyramid pooling based YOLO for object detection. Inf. Sci. (Ny). 522, 241–258. https://doi.org/10.1016/j.ins.2020.02.067
Jamil, S., n.d. Malicious Drones Dataset [WWW Document]. URL https://www.kaggle.com/datasets/sonainjamil/malicious-drones
Kim, B.K., Kang, H.S., Lee, S., Park, S.O., 2021. Improved Drone Classification Using Polarimetric Merged-Doppler Images. IEEE Geosci. Remote Sens. Lett. 18, 1946–1950. https://doi.org/10.1109/LGRS.2020.3011114
Kılıç, R., Kumbasar, N., Oral, E.A., Ozbek, I.Y., 2022. Drone classification using RF signal based spectral features. Eng. Sci. Technol. an Int. J. 28, 101028. https://doi.org/10.1016/j.jestch.2021.06.008
Lashgari, E., Liang, D., Maoz, U., 2020. Data augmentation for deep-learning-based electroencephalography. J. Neurosci. Methods 346, 108885. https://doi.org/10.1016/j.jneumeth.2020.108885
Li, Z., Liu, F., Yang, W., Peng, S., Zhou, J., 2021. A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects. IEEE Trans. Neural Networks Learn. Syst. 1–21. https://doi.org/10.1109/tnnls.2021.3084827
Liu, J., Xu, Q.Y., Chen, W.S., 2021. Classification of Bird and Drone Targets Based on Motion Characteristics and Random Forest Model Using Surveillance Radar Data. IEEE Access 9, 160135–160144. https://doi.org/10.1109/ACCESS.2021.3130231
Lykou, G., Moustakas, D., Gritzalis, D., 2020. Defending Airports from UAS: A Survey on Cyber-Attacks and Counter-Drone Sensing Technologies. Sensors 20, 3537. https://doi.org/10.3390/s20123537
Oh, H.M., Lee, H., Kim, M.Y., 2019. Comparing Convolutional Neural Network(CNN) models for machine learning-based drone and bird classification of anti-drone system. Int. Conf. Control. Autom. Syst. 2019-Octob, 87–90. https://doi.org/10.23919/ICCAS47443.2019.8971699
Ouyang, X., Gu, K., Zhou, P., 2018. Spatial Pyramid Pooling Mechanism in 3D Convolutional Network for Sentence-Level Classification. IEEE/ACM Trans. Audio Speech Lang. Process. 26, 2167–2179. https://doi.org/10.1109/TASLP.2018.2852502
Seidaliyeva, U., Akhmetov, D., Ilipbayeva, L., Matson, E.T., 2020. Real-Time and Accurate Drone Detection in a Video with a Static Background. Sensors 20, 3856. https://doi.org/10.3390/s20143856
Singha, S., Aydin, B., 2021. Automated drone detection using YOLOv4. Drones 5. https://doi.org/10.3390/drones5030095
Taha, B., Shoufan, A., 2019. Machine Learning-Based Drone Detection and Classification: State-of-the-Art in Research. IEEE Access 7, 138669–138682. https://doi.org/10.1109/ACCESS.2019.2942944
Takahashi, R., Matsubara, T., Uehara, K., 2020. Data Augmentation Using Random Image Cropping and Patching for Deep CNNs. IEEE Trans. Circuits Syst. Video Technol. 30, 2917–2931. https://doi.org/10.1109/TCSVT.2019.2935128
Tan, Y.S., Lim, K.M., Tee, C., Lee, C.P., Low, C.Y., 2021. Convolutional neural network with spatial pyramid pooling for hand gesture recognition. Neural Comput. Appl. 33, 5339–5351. https://doi.org/10.1007/s00521-020-05337-0
Uddin, Z., Altaf, M., Bilal, M., Nkenyereye, L., Bashir, A.K., 2020. Amateur Drones Detection: A machine learning approach utilizing the acoustic signals in the presence of strong interference. Comput. Commun. 154, 236–245. https://doi.org/10.1016/j.comcom.2020.02.065
Walia, H., n.d. Bird vs Drone New Dataset [WWW Document]. URL https://www.kaggle.com/datasets/harshwalia/bird-vs-drone-new
Wojtanowski, J., Zygmunt, M., Drozd, T., Jakubaszek, M., Życzkowski, M., Muzal, M., 2021. Distinguishing Drones from Birds in a UAV Searching Laser Scanner Based on Echo Depolarization Measurement. Sensors 21, 5597. https://doi.org/10.3390/s21165597
Yee, P.S., Lim, K.M., Lee, C.P., 2022. DeepScene: Scene classification via convolutional neural network with spatial pyramid pooling. Expert Syst. Appl. 193, 116382. https://doi.org/10.1016/j.eswa.2021.116382
YEŞİLAY, R.B., MACİT, A., 2020. DÜNYADA VE TÜRKİYE’DE DRONE EKONOMİSİ: GELECEĞE YÖNELİK BEKLENTİLER. Beykoz Akad. Derg. 8, 239–251. https://doi.org/10.14514/BYK.m.26515393.2020.8/1.239-251
Yue, J., Mao, S., Li, M., 2016. A deep learning framework for hyperspectral image classification using spatial pyramid pooling. Remote Sens. Lett. 7, 875–884. https://doi.org/10.1080/2150704X.2016.1193793
Zhang, X., Mehta, V., Bolic, M., Mantegh, I., 2020. Hybrid AI-enabled Method for UAS and Bird Detection and Classification. IEEE Int. Conf. Syst. Man Cybern. 2020-Octob, 2803–2807. https://doi.org/10.1109/SMC42975.2020.9282965