Citation :

Battireddy Surendara, S Abirami, Gurram Sunitha, "Spatial Attention Mechanism for Improved Multi-Focus Satellite Image Fusion: SARA-Net Model," International Journal of Engineering Trends and Technology (IJETT), vol. 74, no. 10, pp. 15-29, 2026. Crossref, https://doi.org/10.14445/22315381/IJETT-V74I10P102

Abstract

Multi-focus image fusion is crucial in various fields, particularly in satellite images, because it creates intricate images with augmented clarity. However, maintaining the original structure is challenging, leading to a reduction in performance. Therefore, this research proposes a Spatial Attention ResNet-50 Network (SARA-Net) model for fusing multiple satellite images. The proposed model utilizes an integration of ResNet-50 and Spatial Attention to effectively extract spatially significant features from actual images. Initially, satellite images from the publicly available SpaceNet datasets are preprocessed by normalization and grayscale conversion to provide consistency. ResNet-50 handles multi-scale feature extraction by residual learning, which addresses vanishing gradient issues, whereas spatial attention assigns adaptive weights to improve relevant spatial information within the feature map. The fusion layer combines these attention features to generate high-resolution and detail-preserving images. On the ten held-out test images, the proposed SARA-Net achieves a PSNR of 48.972 dB, an SSIM of 0.9953, and an entropy value of 8.4319, which is better than the existing methods.

Keywords

Higher entropy values, Multi-focus image fusion, Satellite image, Spatial Attention ResNet-50 Network, Structural similarity index.

References

1. Yu Sun et al., “Image Fusion for the Novelty Rotating Synthetic Aperture System based on Vision Transformer,” Information Fusion, vol. 104, pp. 1-14, 2024.
   [CrossRef] [Google Scholar] [Publisher Link] 
2. Aisha Javed et al., “Deep Learning-based Detection of Urban Forest Cover Change along with Overall Urban Changes using Very-High-Resolution Satellite Images,” Remote Sensing, vol. 15, no. 17, pp. 1-18, 2023.
   [CrossRef] [Google Scholar] [Publisher Link] 
3. Yuanxin Ye et al., “An Adaptive Attention Fusion Mechanism Convolutional Network for Object Detection in Remote Sensing Images,” Remote Sensing, vol. 14, no. 3, pp. 1-18, 2022.
   [CrossRef] [Google Scholar] [Publisher Link]
4. S. Nagarathinam, A. Vasuki, and K. Paramasivam, “PAN and MS Satellite Image Fusion using Fast Guided Filter and PSO Segmentation,” Sādhanā, vol. 48, no. 4, pp. 1-16, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
5. Yuanxin Ye et al., “A Robust Multimodal Remote Sensing Image Registration Method and System using Steerable Filters with First-and Second-Order Gradients,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 188, pp. 331-350, 2022.
   [CrossRef] [Google Scholar] [Publisher Link]
6. Yizhong Pan et al., “Real Image Denoising Via Guided Residual Estimation and Noise Correction,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 33, no. 4, pp. 1994-2000, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
7. Ming Liu et al., “SIFNet: A Self-Attention Interaction Fusion Network for Multisource Satellite Imagery Template Matching,” International Journal of Applied Earth Observation and Geoinformation, vol. 118, pp. 1-11, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
8. DaiXun Li et al., “FedFusion: Manifold-Driven Federated Learning for Multi-Satellite and Multi-Modality Fusion,” IEEE Transactions on Geoscience and Remote Sensing, vol. 62, pp. 1-13, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
9. Mahmoud M. Hammad et al., “Satellite Image Fusion using a Hybrid Traditional and Deep Learning Method,” Geomatics and Environmental Engineering, vol. 17, no. 5, pp. 145-162, 2023.
   [CrossRef] [Google Scholar] [Publisher Link]
10. Hayder Dibs et al., “Fusion Landsat-8 Thermal TIRS and OLI Datasets for Superior Monitoring and Change Detection using Remote Sensing,” Emerging Science Journal, vol. 7, no. 2, pp. 428-444, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
11. Mojtaba Safari, Ali Fatemi, and Louis Archambault, “MedFusionGAN: Multimodal Medical Image Fusion using an Unsupervised Deep Generative Adversarial Network,” BMC Medical Imaging, vol. 23, no. 1, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
12. Simon Anger et al., “High‐Resolution Inverse Synthetic Aperture Radar Imaging of Satellites in Space,” IET Radar, Sonar and Navigation, vol. 18, no. 4, pp. 544-563, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
13. Shuangliang Li, Siwei Li, and Lihao Zhang, “Hyperspectral and Panchromatic Images Fusion based on the Dual Conditional Diffusion Models,” IEEE Transactions on Geoscience and Remote Sensing, vol. 61, pp. 1-15, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
14. Fahime Arabi Aliabad et al., “Identifying and Monitoring Gardens in Urban Areas using Aerial and Satellite Imagery,” Remote Sensing, vol. 15, no. 16, pp. 1-25, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
15. Penglei Li et al., “MFFSP: Multi-Scale Feature Fusion Scene Parsing Network for Landslides Detection based on High-Resolution Satellite Images,” Engineering Applications of Artificial Intelligence, vol. 127, pp. 1-12, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
16. Dana Moukheiber et al., “A Multimodal Framework for Extraction and Fusion of Satellite Images and Public Health Data,” Scientific Data, vol. 11, no. 1, pp. 1-20, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
17. Yukun Zhang et al., “Cross-Task and Cross-Domain SAR Target Recognition: A Meta-Transfer Learning Approach,” Pattern Recognition, vol. 138, pp. 1-11, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
18. Juan Xiao et al., “Deep Learning-based Spatiotemporal Fusion of Unmanned Aerial Vehicle and Satellite Reflectance Images for Crop Monitoring,” IEEE Access, vol. 11, pp. 85600-85614, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]  
19. Chunfeng Yang et al., “Multi-Scale Visual Attention Cascaded Network for Multi-Focus Image Fusion,” 2023 4^th International Conference on Information Science and Education (ICISE-IE), pp. 89-92, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]  
20. Xinzhe Xie et al., “SwinMFF: Toward High-Fidelity End-to-End Multi-Focus Image Fusion via Swin Transformer-based Network,” The Visual Computer, vol. 41, no. 6, pp. 3883-3906, 2025.
    [CrossRef] [Google Scholar] [Publisher Link]  
21. Xingyu Hu et al., “Incrementally Adapting Pretrained Model using Network Prior for Multi-Focus Image Fusion,” IEEE Transactions on Image Processing, vol. 33, pp. 3950-3963, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
22. SpaceNet AOI 11 - Rotterdam, SpaceNet, 2020. [Online]. Available: https://spacenet.ai/rotterdam/
23. Samreen Fiza, and S. Safinaz, “Multi-Focus Image Fusion using Edge Discriminative Diffusion Filter for Satellite Images,” Multimedia Tools and Applications, vol. 83, no. 25, pp. 66087-66106, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
24. Lijing Bu et al., “Enhancing RABASAR for Multi-Temporal SAR Image Despeckling through Directional Filtering and Wavelet Transform,” Sensors, vol. 23, no. 21, pp. 1-17, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
25. Wenzhong Shi, Dizhou Guo, and Hua Zhang, “A Reliable and Adaptive Spatiotemporal Data Fusion method for Blending Multi-Spatiotemporal-Resolution Satellite Images,” Remote Sensing of Environment, vol. 268, pp. 1-24, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
26. Achala Shakya, Mantosh Biswas, and Mahesh Pal, “Fusion and Classification of SAR and Optical Data using Multi-Image Color Components with Differential Gradients,” Remote Sensing, vol. 15, no. 1, pp. 1-15, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
27. Chenxi Duan, Mariana Belgiu, and Alfred Stein, “Feature Enhancement Network for Cloud Removal in Optical Images by Fusing with SAR Images,” International Journal of Remote Sensing, vol. 45, no. 1, pp. 51-67, 2024.
    [CrossRef] [Google Scholar] [Publisher Link]
28. Jiajun Cai, Bo Huang, and Tung Fung, “Progressive Spatiotemporal Image Fusion with Deep Neural networks,” International Journal of Applied Earth Observation and Geoinformation, vol. 108, pp. 1-11, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
29. Jinjin Li et al., “Comparative Analysis of Pixel-Level Fusion Algorithms and a New High-Resolution Dataset for SAR and Optical Image Fusion,” Remote Sensing, vol. 15, no. 23, pp. 1-30, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
30. Pengcheng Hu et al., “Remote Sensing Image Reconstruction Method based on Parameter Adaptive Dual-Channel Pulse-Coupled Neural Network to Optimize Multiscale Decomposition,” IEEE Access, vol. 11, pp. 78084-78103, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
31. S.R. Bandi, M. Anbarasan, and D. Sheela, “Fusion of SAR and Optical Images using Pixel-based CNN,” Neural Network World, vol. 4, pp. 197-213, 2022.
    [CrossRef] [Google Scholar] [Publisher Link]
32. Yingying Kong et al., “A Fusion Method of Optical Image and SAR Image based on Dense-UGAN and Gram–Schmidt Transformation,” Remote Sensing, vol. 13, no. 21, pp. 1-17, 2021.
    [CrossRef] [Google Scholar] [Publisher Link]
33. Jing Fang et al., “A Noisy SAR Image Fusion Method based on NLM and GAN,” Entropy, vol. 23, no. 4, pp. 1-17, 2021.
    [CrossRef] [Google Scholar] [Publisher Link]
34. Runmin Dong et al., “An Adaptive Image Fusion method for Sentinel-2 Images and High-Resolution Images with Long-time Intervals,” International Journal of Applied Earth Observation and Geoinformation, vol. 121, pp. 1-13, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
35. Abhilash Singh, and Kumar Gaurav, “Deep Learning and Data Fusion to Estimate Surface Soil Moisture from Multi-Sensor Satellite Images,” Scientific Reports, vol. 13, no. 1, pp. 1-20, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]
36. Tayeb Benzenati, Yousri Kessentini, and Abdelaziz Kallel, “Spectral–Temporal Fusion of Satellite Images via an End-to-End Two-Stream Attention with an Effective Reconstruction Network,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 16, pp. 1308-1320, 2023.
    [CrossRef] [Google Scholar] [Publisher Link]