Advanced Deep Learning Strategies for the Analysis of Remote Sensing Images
Bazi, Yakoub
Advanced Deep Learning Strategies for the Analysis of Remote Sensing Images - Basel, Switzerland MDPI - Multidisciplinary Digital Publishing Institute 2021 - 1 electronic resource (438 p.)
Open Access
The rapid growth of the world population has resulted in an exponential expansion of both urban and agricultural areas. Identifying and managing such earthly changes in an automatic way poses a worth-addressing challenge, in which remote sensing technology can have a fundamental role to answer-at least partially-such demands. The recent advent of cutting-edge processing facilities has fostered the adoption of deep learning architectures owing to their generalization capabilities. In this respect, it seems evident that the pace of deep learning in the remote sensing domain remains somewhat lagging behind that of its computer vision counterpart. This is due to the scarce availability of ground truth information in comparison with other computer vision domains. In this book, we aim at advancing the state of the art in linking deep learning methodologies with remote sensing image processing by collecting 20 contributions from different worldwide scientists and laboratories. The book presents a wide range of methodological advancements in the deep learning field that come with different applications in the remote sensing landscape such as wildfire and postdisaster damage detection, urban forest mapping, vine disease and pavement marking detection, desert road mapping, road and building outline extraction, vehicle and vessel detection, water identification, and text-to-image matching.
Creative Commons
English
books978-3-0365-0987-7 9783036509860 9783036509877
10.3390/books978-3-0365-0987-7 doi
Research & information: general
synthetic aperture radar despeckling multi-scale LSTM sub-pixel high-resolution remote sensing imagery road extraction machine learning DenseUNet scene classification lifting scheme convolution CNN image classification deep features hand-crafted features Sinkhorn loss remote sensing text image matching triplet networks EfficientNets LSTM network convolutional neural network water identification water index semantic segmentation high-resolution remote sensing image pixel-wise classification result correction conditional random field (CRF) satellite object detection neural networks single-shot deep learning global convolution network feature fusion depthwise atrous convolution high-resolution representations ISPRS vaihingen Landsat-8 faster region-based convolutional neural network (FRCNN) single-shot multibox detector (SSD) super-resolution remote sensing imagery edge enhancement satellites open-set domain adaptation adversarial learning min-max entropy pareto ranking SAR Sentinel-1 Open Street Map U-Net desert road infrastructure mapping monitoring deep convolutional networks outline extraction misalignments nearest feature selector hyperspectral image classification two stream residual network Batch Normalization plant disease detection precision agriculture UAV multispectral images orthophotos registration 3D information orthophotos segmentation wildfire detection convolutional neural networks densenet generative adversarial networks CycleGAN data augmentation pavement markings visibility framework urban forests OUDN algorithm object-based high spatial resolution remote sensing Generative Adversarial Networks post-disaster building damage assessment anomaly detection Unmanned Aerial Vehicles (UAV) xBD feature engineering orthophoto unsupervised segmentation
Advanced Deep Learning Strategies for the Analysis of Remote Sensing Images - Basel, Switzerland MDPI - Multidisciplinary Digital Publishing Institute 2021 - 1 electronic resource (438 p.)
Open Access
The rapid growth of the world population has resulted in an exponential expansion of both urban and agricultural areas. Identifying and managing such earthly changes in an automatic way poses a worth-addressing challenge, in which remote sensing technology can have a fundamental role to answer-at least partially-such demands. The recent advent of cutting-edge processing facilities has fostered the adoption of deep learning architectures owing to their generalization capabilities. In this respect, it seems evident that the pace of deep learning in the remote sensing domain remains somewhat lagging behind that of its computer vision counterpart. This is due to the scarce availability of ground truth information in comparison with other computer vision domains. In this book, we aim at advancing the state of the art in linking deep learning methodologies with remote sensing image processing by collecting 20 contributions from different worldwide scientists and laboratories. The book presents a wide range of methodological advancements in the deep learning field that come with different applications in the remote sensing landscape such as wildfire and postdisaster damage detection, urban forest mapping, vine disease and pavement marking detection, desert road mapping, road and building outline extraction, vehicle and vessel detection, water identification, and text-to-image matching.
Creative Commons
English
books978-3-0365-0987-7 9783036509860 9783036509877
10.3390/books978-3-0365-0987-7 doi
Research & information: general
synthetic aperture radar despeckling multi-scale LSTM sub-pixel high-resolution remote sensing imagery road extraction machine learning DenseUNet scene classification lifting scheme convolution CNN image classification deep features hand-crafted features Sinkhorn loss remote sensing text image matching triplet networks EfficientNets LSTM network convolutional neural network water identification water index semantic segmentation high-resolution remote sensing image pixel-wise classification result correction conditional random field (CRF) satellite object detection neural networks single-shot deep learning global convolution network feature fusion depthwise atrous convolution high-resolution representations ISPRS vaihingen Landsat-8 faster region-based convolutional neural network (FRCNN) single-shot multibox detector (SSD) super-resolution remote sensing imagery edge enhancement satellites open-set domain adaptation adversarial learning min-max entropy pareto ranking SAR Sentinel-1 Open Street Map U-Net desert road infrastructure mapping monitoring deep convolutional networks outline extraction misalignments nearest feature selector hyperspectral image classification two stream residual network Batch Normalization plant disease detection precision agriculture UAV multispectral images orthophotos registration 3D information orthophotos segmentation wildfire detection convolutional neural networks densenet generative adversarial networks CycleGAN data augmentation pavement markings visibility framework urban forests OUDN algorithm object-based high spatial resolution remote sensing Generative Adversarial Networks post-disaster building damage assessment anomaly detection Unmanned Aerial Vehicles (UAV) xBD feature engineering orthophoto unsupervised segmentation