International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Target Recognition in SAR Images for Military Applications |
|---|---|
| ABSTRACT | Modern military operations require timely intelligence, secure asset management, and automated target recognition for effective decision-making. This project presents a web- based Defence Intelligence & Asset Management System integrated with a Target Recognition pipeline for Synthetic Aperture Radar (SAR) imagery. The system provides defence-related news accessible to all users, while a secured two- step authenticated admin module allows authorized personnel to register and manage military vehicle data with full CRUD capabilities and view-only access to sensitive details. The core research component focuses on automatic detection and classification of military targets such as tanks, trucks, and ships in SAR images. A deep learning pipeline is built using YOLO-based object detection for real-time inference, enhanced with Generative Adversarial Networks (GANs) such as DH-GAN or PeaceGAN to augment limited SAR datasets. Detected targets are logged for mission tracking, and the system additionally suggests the tactical role and potential impact of each identified target. This integrated approach combines secure web technologies with advanced computer vision techniques to support situational awareness in defence applications. |
| AUTHOR | CHETHAN G M, GANESH VINAYAK HEGDE, G R GIREESH, PROF. SUPRIYA SUDHIR Dept. of CSE, BNM Institute of Technology, Bengaluru, India Assistant Professor, Dept. of CSE, BNM Institute of Technology, Bengaluru, India |
| VOLUME | 180 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1401058 |
| pdf/58_Target Recognition in SAR Images for Military Applications.pdf | |
| KEYWORDS | |
| References | [1] J. Smith, A. Kumar, and L. Zhang, "Deep learning for SAR target classification: A review," IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1234- 1248, 2024. [2] M. Chen, P. Li, and S. Wang, "Real-time SAR vehicle detection using YOLO-based networks," in Proc. International Conference on Radar Systems, 2023, pp. 112-119. [3] R. Patel and J. Lee, "Generative adversarial networks for SAR image augmentation," IEEE Access, vol. 9, pp. 56789-56799, 2021. [4] Y. Zhao, H. Liu, and F. Sun, "Multi-feature fusion for robust target recognition in SAR imagery," Remote Sensing Letters, vol. 14, no. 2, pp. 198-205, 2023 [5] G. Kumar and T. Das, "Noise suppression and feature extraction in SAR images using deep CNNs," Journal of Applied Remote Sensing, vol. 15, no. 1, p. 016502, 2024. [6] S. Nguyen and K. Tran, "Multi-canonical correlation analysis for feature fusion in SAR target classification," IEEE Signal Processing Letters, vol. 28, pp. 276-280, 2021. [7] D. Kim, J. Park, and S. Choi, "Hybrid SAR target recognition with CNN and SVM," in Proc. International Conference on Image Processing, 2022, pp. 549-553. [8] L. Wang and M. Zhao, "Enhancing SAR target classification with synthetic data and multi-modal learning," IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 16, pp. 2234-2243, 2023. [9] A. Gupta and N. Singh, "Comprehensive deep learning framework for SAR military target recognition," Defense Technology, vol. 19, no. 7, pp. 2045-2054, 2024. [10] J. Park and H. Kim, "Real-time object detection in SAR images using YOLOv5," Journal of Defense Modeling and Simulation, vol. 21, no. 3, pp. 189-200, 2023. [11] S. Lee, Y. Cho, and K. Han, "Speckle noise reduction in SAR imagery with deep residual networks," Remote Sensing, vol. 15, no. 5, p. 1203, 2023. [12] V. Murphy and D. Patel, "Support vector machine based taxonomy for SAR target recognition," in Proc. IEEE International Geoscience and Remote Sensing Symposium, 2022, pp. 794-798. |
