International Journal of Soft Computing
ISSN: OnlineISSN: Print 1816-9503
Abstract
Open access in space remote sensing has allowed easy access to satellite imagery, however, access to high resolution imagery is not given to everyone but only to those who master space technology. Thus, this paper presents a new approach for improving the quality of Sentinel‐2 satellite images by super‐resolution by exploiting deep learning techniques. In this context, the work carried out proposes a generic solution that improves the spatial resolution from 10‐2.5 m (scaling factor 4) to take into account the constraints of volumetry and dependence between spectral bands imposed by the specificities of satellite images. We propose the FSRSI model which exploits the potential of deep convolutional networks (CNN) and integrates new state‐of‐theart concepts including Network In Network, end‐to‐end learning, multiscale fusion, neural network optimization and acceleration and filter transfer. Our model has also been improved by an efficient mosaicking technique for Super‐Resolution of satellite images in addition to the consideration of inter‐spectral dependence combined with the efficient choice of training data. Our approach shows better performance than has been proven in the field of spatial imagery. Our experimental results show that our algorithm restores the details of satellite images quickly and efficiently outperforming several state‐of‐the‐art methods. These performances were observed following a benchmark with several neural networks and an experimentation with applications to a carefully constructed dataset. The proposed solution showed promising results in terms of visual and perceptual quality with a better inference speed.
How to cite this article:
omar soufi and fatima-zahra belouadha. FSRSI: New Deep Learning‐Based Approach for Super‐Resolution of Multispectral Satellite Images.
DOI: https://doi.org/10.36478/10.59218/makijcs.2022.27.57
URL: https://www.makhillpublications.co/view-article/1816-9503/10.59218/makijcs.2022.27.57