TY  - BOOK
AU  - Kawulok,Michal
AU  - Kawulok,Jolanta
AU  - Smolka,Bogdan
AU  - Celebi,M.Emre
ED  - SpringerLink (Online service)
TI  - Super-Resolution for Remote Sensing
T2  - Unsupervised and Semi-Supervised Learning,
SN  - 9783031681066
AV  - Q342 
PY  - 2024///
CY  - Cham
PB  - Springer Nature Switzerland, Imprint: Springer
KW  - Computational intelligence
KW  - Telecommunication
KW  - Computer vision
KW  - Computational Intelligence
KW  - Communications Engineering, Networks
KW  - Computer Vision
N1  - Chapter 1 Introduction to Super-Resolution for Remotely Sensed Hyperspectral Images -- Chapter 2 Real-World Unsupervised Remote Sensing Image Super-Resolution: Addressing Challenges, Solution and Future Prospects -- Chapter 3 Advancements in Deep Learning-Based Super-Resolution for Remote Sensing: A Comprehensive Review and Future Directions -- Chapter 4 Multi-Image Super-Resolution Using Graph Neural Networks -- Chapter 5 Effectiveness Analysis of Example-Based Machine Learning and Deep Learning Methods for Super-Resolution Hyperspectral Images -- Chapter 6 Synergy of Images: Multi-Image Fusion Empowering Super-Resolution in Remote Sensing -- Chapter 7 Unsupervised Pansharpening using ConvNets -- Chapter 8 A comprehensive overview of satellite image fusion: From classical model-based to cutting-edge deep learning approaches -- Chapter 9 Super-Resolution for Spectral Image
N2  - This book provides a comprehensive perspective over the landscape of super-resolution techniques developed for and applied to remotely-sensed images. The chapters tackle the most important problems that professionals face when dealing with super-resolution in the context of remote sensing. These are: evaluation procedures to assess the super-resolution quality; benchmark datasets (simulated and real-life); super-resolution for specific data modalities (e.g., panchromatic, multispectral, and hyperspectral images); single-image super-resolution, including generative adversarial networks; multi-image fusion (temporal and/or spectral); real-world super-resolution; and task-driven super-resolution. The book presents the results of several recent surveys on super-resolution specifically for the remote sensing community. Focuses on reconstruction accuracy compared with ground truth rather than on generating a visually-attractive outcome; Explains how to apply super-resolution to a variety of image modalities inherent to remote sensing; Gathers the description of training datasets and benchmarks that are based on remotely-sensed images
UR  - https://doi.org/10.1007/978-3-031-68106-6
ER  -