Deep Learning Methods for Remote Sensing

doi:10.3390/books978-3-0365-4630-8

Reprint

Download Flyer

Deep Learning Methods for Remote Sensing

Edited by

October 2022

344 pages

ISBN978-3-0365-4629-2 (Hardback)
ISBN978-3-0365-4630-8 (PDF)

https://doi.org/10.3390/books978-3-0365-4630-8

Free download (PDF)

This book is a reprint of the Special Issue Deep Learning Methods for Remote Sensing that was published in

Chemistry & Materials Science

Engineering

Environmental & Earth Sciences

Summary

Remote sensing is a field where important physical characteristics of an area are exacted using emitted radiation generally captured by satellite cameras, sensors onboard aerial vehicles, etc. Captured data help researchers develop solutions to sense and detect various characteristics such as forest fires, flooding, changes in urban areas, crop diseases, soil moisture, etc. The recent impressive progress in artificial intelligence (AI) and deep learning has sparked innovations in technologies, algorithms, and approaches and led to results that were unachievable until recently in multiple areas, among them remote sensing. This book consists of sixteen peer-reviewed papers covering new advances in the use of AI for remote sensing.

Format

Hardback

License

Keywords

full convolutional network; U-Net; cultivated land extraction; deep learning; remote sensing; target detection; high resolution remote sensing image; chimney; faster R-CNN; spatial analysis; super-resolution; Generative Adversarial Networks; Convolutional Neural Networks; disease classification; changes detection; fully convolutional feature maps; outdated building map; VHR images; gully erosion susceptibility; deep learning neural network; DLNN; particle swarm optimization; PSO; geohazard; geoinformatics; ensemble model; erosion; hazard map; spatial model; deep learning; natural hazard; extreme events; rural settlements; fully convolutional network; multi-scale context; high spatial resolution images; flash-flood potential index; remote sensing sensors; bivariate statistics; deep learning neural network; alternating decision trees; ensemble models; deep-learning; fusion; mask R-CNN; object-based; optical sensors; scattered vegetation; very high-resolution; off-grid; DOA estimation; circularly fully convolutional networks; space-frequency pseudo-spectrum; high resolution; typhoon; rainfall; convolutional networks; image segmentation; prediction; ensemble learning; machine learning; feature extraction; AGB; NSFs; radar modulation signal; time–frequency analysis; complex Morlet wavelet; image enhancement; channel-separable ResNet; remote sensing images; change detection; attention mechanism; cross-layer feature fusion; power transmission lines; vibration dampers detection; unmanned aerial vehicle (UAV); deep neural networks; attention mechanism; wildfire detection; fire classification; fire segmentation; vision transformers; UAV; aerial images; three-dimensional scene; temperature field; intelligent prediction; network; geometry structure; meteorological parameters; thermophysical parameters