1. CSN
  2. All Volumes and Issues
  3. Volume 7, Number 1, 2025
  4. Recognizing Military Equipment From Satellite Images Using AI

Recognizing Military Equipment From Satellite Images Using AI

CSN.
2025;
Volume 7, Number 1
: pp. 47 - 59
https://doi.org/10.23939/csn2025.01.047
Authors:
  1. V. O. Vytrykush
  2. N. V. Huzynets
1
Lviv Polytechnic National University, Department of Electronic Computing Machines
2
Lviv Polytechnic National University

Neural networks training systems used for military equipment recognition on the images are considered in the article. The implementation, considered in the article, uses pretrained part of the model with freezing most of the trained parameters and fined tuning of some part of the model with using extra data set including artificially obtained images. Two widely used recognition networks was considered: ResNet50 and Xception. After these two networks analysis, we can say that the best approach for training the network is using data expansion strategy. This means that during training we can expand the image base by providing different representations of these images.

ResNet50
Xceprion
data augmentation
image recognition
  1. Keras API reference. URL: https://keras.io/api/.
  2. Redmon           J.,          Farhadi           A.          YOLOv3:An          incremental             improvement.URL:http://arxiv.org/abs/1804.02767.
  3. MathType. URL: http://www.mathtype.com.
  4. Hiippala T. Recognizing military vehicles in social media images using deep learning. In: IEEE International     Conference     on     Intelligence     and      Security      Informatics.      2017.      Doi: https/doi.org/ 10.1109/ISI.2017.8004875.
  5. Digital Geography Lab. (n.d). URL: https://github.com/DigitalGeographyLab/MilVehicles/.
  6. Pedregosa F., Varoquaux G., Gramfort A., Michel V., Thirion B., Grisel O., Blondel M., Prettenhofer P., Weiss R., Dubourg V., Vanderplas J., Passos A., Cournapeau D., Brucher M., Perrot M., Duchesnay E. Scikit-learn: Machine learning in Python. Journal of Machine Learning. 2019. Doi: https://doi.org/10.48550/arXiv.1201.0490.
  7. He K., Zhang X., Ren S., J. Sun. Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021. Doi: https://doi.org/10.48550/arXiv.1201.0490.
  8. Chollet F. Xception: deep learning with depth-wise separable convolutions. In: Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, 2020. Doi: https://doi.org/10.1109/CVPR.2017.195.
  9. Deng J., Dong W., Socher R., Li L.-J., Li K., Fei-Fei L. ImageNet: A large-scale hierarchical image database. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR’09). 2019. Doi: https/doi.org/    10.1109/CVPR.2009.5206848.
  10. Create           production-grade             machine           learning           models           with          TensorFlow.            URL:https://www.tensorflow.org/.
  11. Algorythm for hyper-parameter optimization. URL: https://papers.nips.cc/paper_files/paper/2011/ hash/86e8f7ab32cfd12577bc 2619bc635690-Abstract.html.
  12. Krizhevsky, A., Sutskever, I., Hinton, G. E. ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems. 2012.Pp. 1097–110. Doi: https://doi.org/ 10.48550/arXiv.1201.0490.