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 | EarthVision: A Smart Deep Learning Approach for Satellite Image Classification |
|---|---|
| ABSTRACT | Satellite imagery analysis plays an important role in various applications of earth observation, such as land use monitoring, urban planning, and agriculture as well as disaster management. The conventional image classification techniques generally have limited accuracy due to the presence of complex spatial patterns, along with numerous variations within each class. This paper brings forth one of the most effective satellite image classification systems that utilize pretrained deep learning models in combination with the attention mechanism to enhance feature representation and thus improve classification performance. Such systems employ transfer learning so that they avoid the complexity of training, while the attention module enhances the discriminative focus of the satellite images. Thus, the experimental results demonstrate significantly improved accuracy, robustness, and generalization over the traditional convolutional neural network methods, making it more pragmatic for real-world remote sensing applications. |
| AUTHOR | YASHAS T G S, RUTHU M S, SINDHU J M, VARSHA K P, DR. NIRANJAN MURTHY C UG Students, Dept. of CSE, Jain Institute of Technology, Davangere, Karnataka, India Associate Professor, Dept. of CSE, Jain Institute of Technology, Davangere, Karnataka, India |
| VOLUME | 177 |
| DOI | DOI: 10.15680/IJIRCCE.2025.1312128 |
| pdf/128_EarthVision A Smart Deep Learning Approach for Satellite Image Classification.pdf | |
| KEYWORDS | |
| References | [1] K. He, X. Zhang, S. Ren, and J. Sun, "Deep Residual Learning for Image Recognition," Proceedings of the IEEE Computer Vision and Pattern Recognition Conference (CVPR), 2016, pp. 770-778. [2] M. Tan, Q. Le, "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks," in Proceedings of International Conference on Machine Learning, 2019. [3] A. Vaswani et al., "Attention Is All You Need," Advances in Neural Information Processing Systems (NeurIPS), 2017. [4] G. Cheng, C. Yang, X. Yao, L. Guo, and J. Han, "When Deep Learning Meets Metric Learning: Remote Sensing Image Classification via Learning Discriminative CNNs," IEEE Transactions on Geoscience and Remote Sensing, vol. 56, no. 5, pp. 2811-2821, 2018. [5] Y. Bengio, A. Courville, and P. Vincent, "Representation Learning: A Review and New Perspectives," IEEE Transactions on Pattern Analysis and Machine Intelligence 35, no. 8 (2013): 1798–1828. |
