Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{179693,
        author = {Tanuj Yadav and Bhavya Saini and Dr.Pintu Kumar Ram and Dr.Manish Kumar Ojha},
        title = {Intelligent Object Detection Using SAR Imaging for Surveillance In Defence : A MobileViT Approach},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {9207-9210},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=179693},
        abstract = {Synthetic Aperture Radar (SAR) imaging plays a crucial role in defence surveillance due to its all-weather, day-night imaging capabilities. Traditional Convolutional Neural Networks (CNNs) like ResNet-18 and VGG16 have been widely used for SAR target detection, but they struggle with long-range dependencies and computational efficiency. This paper proposes a pure MobileViT-based approach for SAR object detection using the MSTAR dataset, leveraging the strengths of Vision Transformers (ViTs) while maintaining computational efficiency. We compare MobileViT with CNN-based models (ResNet-18 and VGG16) in terms of accuracy, model size, and inference speed. Experimental results demonstrate that MobileViT achieves superior performance with fewer parameters, making it suitable for real-time defence applications.},
        keywords = {SAR Imaging, MobileViT, Object Detection, MSTAR Dataset, Defence Surveillance, CNN, ResNet-18, VGG16},
        month = {June},
        }