Deep Learning for Synthetic Aperture Radar Remote Sensing delves into the transformative synergy between synthetic aperture radar (SAR) and cutting-edge machine learning techniques. Traditionally rooted in signal processing, SAR's active imaging capabilities rise above optical limitations, offering resilience to environmental factors like cloud cover. This book showcases how machine learning augments every stage of SAR image processing, from raw data refinement to advanced information extraction. Through comprehensive coverage of acquisition modes and processing methodologies, including polarimetry and interferometry, this book equips readers with the tools to harness SAR's full potential. Aiming to further enhance remote sensing imaging, it serves as a vital resource for those seeking to integrate SAR data seamlessly into the modern machine learning landscape. Deep Learning for Synthetic Aperture Radar Remote Sensing addresses a critical gap in the intersection of SAR technology and machine learning, offering a pioneering roadmap for researchers and practitioners alike. With its emphasis on modern techniques, it serves as a catalyst for unlocking SAR's untapped potential and shaping the future of Earth observation.
1. 2: A brief introduction to deep learning - p. 25 2. 3: Deep learning for SAR focusing - p. 53 3. 4: Deep learning for artificial SAR image generation - p. 75 4. 5: Deep learning for compression and quantization of SAR data - p. 99 5. 6: Deep learning for SAR amplitude despeckling - p. 127 6. 7: Deep learning for InSAR processing - p. 147 7. 8: Deep learning in SAR tomography - p. 175 8. 9: Deep learning for SAR object detection - p. 201 9. 10: Deep learning based semantic analysis of SAR imagery - p. 227 10. 11: SAR change detection using deep learning - p. 251 11. 12: Deep learning for SAR-based single-image height reconstruction - p. 271 12. 13: Deep learning for estimation of bio- & geophysical parameters from SAR data - p. 287 13. Index - p. 325
Deep Learning for Synthetic Aperture Radar Remote Sensing delves into the transformative synergy between synthetic aperture radar (SAR) and cutting-edge machine learning techniques. Traditionally rooted in signal processing, SAR's active imaging capabilities rise above optical limitations, offering resilience to environmental factors like cloud cover. This book showcases how machine learning augments every stage of SAR image processing, from raw data refinement to advanced information extraction. Through comprehensive coverage of acquisition modes and processing methodologies, including polarimetry and interferometry, this book equips readers with the tools to harness SAR's full potential. Aiming to further enhance remote sensing imaging, it serves as a vital resource for those seeking to integrate SAR data seamlessly into the modern machine learning landscape. Deep Learning for Synthetic Aperture Radar Remote Sensing addresses a critical gap in the intersection of SAR technology and machine learning, offering a pioneering roadmap for researchers and practitioners alike. With its emphasis on modern techniques, it serves as a catalyst for unlocking SAR's untapped potential and shaping the future of Earth observation.
1. 2: A brief introduction to deep learning - p. 25 2. 3: Deep learning for SAR focusing - p. 53 3. 4: Deep learning for artificial SAR image generation - p. 75 4. 5: Deep learning for compression and quantization of SAR data - p. 99 5. 6: Deep learning for SAR amplitude despeckling - p. 127 6. 7: Deep learning for InSAR processing - p. 147 7. 8: Deep learning in SAR tomography - p. 175 8. 9: Deep learning for SAR object detection - p. 201 9. 10: Deep learning based semantic analysis of SAR imagery - p. 227 10. 11: SAR change detection using deep learning - p. 251 11. 12: Deep learning for SAR-based single-image height reconstruction - p. 271 12. 13: Deep learning for estimation of bio- & geophysical parameters from SAR data - p. 287 13. Index - p. 325
