Comparative Performance of U-Net CNN in Multi-Class Aircraft Segmentation and Classification Using Polygon and Bounding Box Annotations
DOI:
https://doi.org/10.55981/ijoa.2025.8155Keywords:
U-Net CNN, Multi-Class Classification, Polygon Annotations, Bounding Box Annotations, Image SegmentationAbstract
Recent advancements in deep learning have revolutionized image processing
tasks such as segmentation and classification. This study investigates the
performance of U- Net-CNN models in multi-class aircraft segmentation and
classification using polygon and bounding box annotations. Military aircraft
classification is crucial for defense applications, as it aids in rapid and accurate
decision-making during critical missions. This study investigates how
these annotation methods affect training time, segmentation accuracy, and
classification performance in multi-class segmentation and classification tasks
involving military aircraft. The research compares polygon and bounding box
methods to evaluate their effectiveness in capturing object details and computational
efficiency. While polygon annotations achieved superior precision with
a mean test accuracy of 0.987 and lower loss of 0.041, bounding boxes excelled
in computational efficiency. Future research should expand datasets and explore
additional annotation techniques to further generalize these findings.
References
Maria, N., Sadia, S., & Khurram, K. (2021). Role of deep learning in brain tumor detection and
classification (2015 to 2020). Comput Med Imaging Graph.
Salakhutdinov, R. (2015). Learning deep generative models. Annual Review of Statistics and
Its Application, 2(1), 361-385.
Sternberg, S. R. (1983). Biomedical image processing. Computer, 16(01), 22-34.
Morgan, F. E., Boudreaux, B., Lohn, A. J., Ashby, M., Curriden, C., Klima, K., & Grossman, D.
(2020). Military applications of artificial intelligence. Santa Monica: RAND Corporation.
Sun, Y., Wang, H., Xue, B., Jin, Y., Yen, G. G., & Zhang, M. (2019). Surrogate-assisted evolutionary
deep learning using an end-to-end random forest-based performance predictor.
IEEE Transactions on Evolutionary Computation, 24(2), 350-364
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate
object detection and semantic segmentation. In Proceedings of the IEEE conference on
computer vision and pattern recognition (pp. 580-587).
Ling, H., Gao, J., Kar, A., Chen, W., & Fidler, S. (2019). Fast interactive object annotation with
curve-gcn. In Proceedings of the IEEE/CVF conference on computer vision and pattern
recognition (pp. 5257-5266).
Yang, F., Hu, L., Liu, X., Huang, S., & Gu, Z. (2023). A large-scale dataset for end-to-end table
recognition in the wild. Scientific Data, 10(1), 110.
Zheng, D., Li, S., Fang, F., Zhang, J., Feng, Y., Wan, B., & Liu, Y. (2023). Utilizing bounding
box annotations for weakly supervised building extraction from remote- sensing images.
IEEE Transactions on Geoscience and Remote Sensing, 61, 1-17.
Marrable, D., Barker, K., Tippaya, S., Wyatt, M., Bainbridge, S., Stowar, M., & Larke, J.
(2022). Accelerating species recognition and labelling of fish from underwater video with
machine-assisted deep learning. Frontiers in Marine Science, 9, 944582.
Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional networks for biomedical
image segmentation. In Medical image computing and computer-assisted intervention–
MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015,
proceedings, part III 18 (pp. 234-241). Springer International Publishing.
Francis, A., Sidiropoulos, P., & Muller, J. P. (2019). CloudFCN: Accurate and robust cloud
detection for satellite imagery with deep learning. Remote Sensing, 11(19), 2312.
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional
neural networks. In: NIPS. pp. 1106–1114 (2012).
Wu, Z. (2019). Muti-type Aircraft of Remote Sensing Images: MTARSI [Data set]. Zenodo.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Rivilyo Mangolat Rizky Sitanggang, Dianita, Bambang Setiadi, Yanif Dwi Kuntjoro
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
