Detection of hidden camouflaged tanks based on deep learning: comparative analysis of state-of-the-art YOLO networks

Year 2023, Volume: 13 Issue: 4, 1082 - 1093, 15.10.2023

Ahmet Furkan Bayram , Vasif Nabiyev

https://doi.org/10.17714/gumusfenbil.1271208

Cited By: 4

Abstract

Detection and tracking of enemy targets is vital to military operations. In this study, the use of deep learning techniques to detect camouflaged tanks is examined. The main purpose of this study is to detect camouflaged tanks hidden in forest areas. In this way, the detection and tracking of enemy targets can be done more effectively and the security of the soldiers can be ensured. The YOLO architecture combines object detection and classification into a single network, resulting in faster and more accurate results. YOLOv5, YOLOv6, YOLOv7 and YOLOv8 architectural designs are compared. The YOLOv6 architectural design outperforms other designs. This design obtained 0,983 mAP50 value, 0,966 precision, 0,935 recall and 0,950 F1 score as a result of performance analysis using 2.234 tank images and 774 car images. The results of this study show that YOLO architectural designs show high performance in object detection and classification.

Keywords

Deep learning, Camouflage tank detection, YOLOv6, Armored vehicles

Derin öğrenme tabanlı saklanan kamufle tankların tespiti: son teknoloji YOLO ağlarının karşılaştırmalı analizi

Abstract

Düşman hedeflerinin tespiti ve takibi, askeri operasyonlar için hayati öneme sahiptir. Bu çalışmada, kamufle tankların tespiti için derin öğrenme tekniklerinin kullanılması incelenmektedir. Bu çalışmanın temel amacı, ormanlık alanlarda gizlenmiş kamufle tankların tespit edilmesini sağlamaktır. Bu sayede, düşman hedeflerinin tespiti ve takibi daha etkili bir şekilde yapılabilmekte ve askerlerin güvenliği sağlanabilmektedir. YOLO mimarisi, nesne tespiti ve sınıflandırma işlemlerini tek bir ağda birleştirerek daha hızlı ve doğru sonuçlar elde etmeyi sağlamaktadır. YOLOv5, YOLOv6, YOLOv7 ve YOLOv8 mimari tasarımları karşılaştırılmıştır. YOLOv6 mimari tasarımı, diğer tasarımlardan daha iyi performans göstermiştir. Bu tasarım, 2.234 adet tank görüntüsü ve 774 adet otomobil görüntüsü kullanılarak yapılan performans analizi sonucunda 0,983 mAP50 değerini, 0,966 kesinliği, 0,935 anma ve 0,950 F1 skorunu elde etmiştir. Bu çalışmanın sonuçları, farklı YOLO mimari tasarımlarının nesne tespiti ve sınıflandırma işlemlerinde yüksek performans elde ettiğini göstermektedir.

Keywords

Derin öğrenme, Kamuflajlı tank tespiti, YOLOv6, Zırhlı araçlar

Thanks

Yazarlar, makalenin inceleme ve değerlendirme aşamasında yapmış oldukları katkılardan dolayı editör ve hakemlere teşekkür etmektedir.

References

• Boyuk, M., Duvar, R., & Urhan, O. (2020). Deep learning based vehicle detection with images taken from unmanned air vehicle. Proceedings - 2020 Innovations in Intelligent Systems and Applications Conference, ASYU 2020. https://doi.org/10.1109/ASYU50717.2020.9259868
• Gupta, P., Pareek, B., Singal, G., & Rao, D. V. (2022). Edge device based military vehicle detection and classification from UAV. Multimedia Tools and Applications, 81(14), 19813–19834. https://doi.org/10.1007/S11042-021-11242-Y/FIGURES/12
• Haque, E., Rahman, A., Junaeid, I., Hoque, S. U., & Paul, M. (2022). Rice Leaf Disease Classification And Detection Using YOLOv5.
• Kaggle (t.y.). Military Tanks Dataset (Images). https://www.kaggle.com/datasets/antoreepjana/military-tanks-dataset-images
• Kaggle (t.y.). War Tank Images Dataset. https://www.kaggle.com/datasets/icanerdogan/war-tank-images-dataset
• Kamran, F., Shahzad, M., & Shafait, F. (2019). Automated military vehicle detection from low-altitude aerial images. 2018 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2018. https://doi.org/10.1109/DICTA.2018.8615865
• Kyrkou, C., Plastiras, G., Theocharides, T., Venieris, S. I., & Bouganis, C. S. (2018). DroNet: Efficient convolutional neural network detector for real-time UAV applications. Proceedings of the 2018 Design, Automation and Test in Europe Conference and Exhibition, 967–972. https://doi.org/10.23919/DATE.2018.8342149
• Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., Nie, W., Li, Y., Zhang, B., Liang, Y., Zhou, L., Xu, X., Chu, X., Wei, X., & Wei, X. (2022). YOLOv6: A single-stage object detection framework for industrial applications. Arxiv.Org. https://doi.org/10.48550/arxiv.2209.02976
• Liu, K., Tang, H., He, S., Yu, Q., Xiong, Y., & Wang, N. (2021). Performance validation of YOLO variants for object detection. Proceedings of the 2021 International Conference on Bioinformatics and Intelligent Computing, BIC 2021, 239–243. https://doi.org/10.1145/3448748.3448786
• Mansour, A., Hassan, A., Hussein, W. M., & Said, E. (2019). Automated vehicle detection in satellite images using deep learning. IOP Conference Series: Materials Science and Engineering, 610(1). https://doi.org/10.1088/1757-899X/610/1/012027
• Reis, D., Kupec, J., Hong, J., & Daoudi, A. (n.d.). Real-Time Flying Object Detection with YOLOv8.
• Sun, Y., Wang, W., Zhang, Q., Ni, H., & Zhang, X. (2022). Improved YOLOv5 with transformer for large scene military vehicle detection on SAR image. 2022 7th International Conference on Image, Vision and Computing, ICIVC 2022, 87–93. https://doi.org/10.1109/ICIVC55077.2022.9887095
• Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y. M. (2022). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. Arxiv.Org. https://doi.org/10.48550/arxiv.2207.02696
• Xie, X., & He, C. (2017). Object detection of armored vehicles based on deep learning in battlefield environment. Proceedings - 2017 4th International Conference on Information Science and Control Engineering, ICISCE 2017, 1568–1570. https://doi.org/10.1109/ICISCE.2017.327
• Yong, S. P., & Yeong, Y. C. (2018). Human object detection in forest with deep learning based on drone’s vision. 2018 4th International Conference on Computer and Information Sciences: Revolutionising Digital Landscape for Sustainable Smart Society, ICCOINS 2018 - Proceedings. https://doi.org/10.1109/ICCOINS.2018.8510564