Remote Sensing Image Classification and Semantic Segmentation

doi:10.3390/books978-3-7258-1366-7

Reprint

Download Flyer

Remote Sensing Image Classification and Semantic Segmentation

Edited by

July 2024

540 pages

ISBN978-3-7258-1365-0 (Hardback)
ISBN978-3-7258-1366-7 (PDF)

https://doi.org/10.3390/books978-3-7258-1366-7 (registering)

Print copies available soon

Free download (PDF)

This book is a reprint of the Special Issue Remote Sensing Image Classification and Semantic Segmentation that was published in

Engineering

Environmental & Earth Sciences

Summary

With the rapid growth in remote sensing imaging technology, vast amounts of remote sensing data are generated, which is significant for land-monitoring systems, and agriculture, etc., for Earth, Mars, etc. In recent decades, deep learning techniques have had a significant effect on remote sensing data processing, especially in image classification and semantic segmentation. However, several challenges still exist due to the limited annotations, the complexity of large-scale areas, and other specific problems, which make it more difficult in real-world applications. Therefore, novel deep neural networks combined with meta-learning, attention mechanisms, or other new transformer technologies need to be given more attention in remote sensing. It is also necessary to develop lightweight, explainable, and robust networks. Moreover, this Special Issue aims to develop state-of-the-art deep networks for more accurate remote sensing image classification and semantic segmentation, which also aims to achieve an efficient cross-domain performance through a lightweight network design.

Format

Hardback

License and Copyright

Keywords

Mars terrain segmentation; semantic segmentation; planetary exploration; semantic segmentation; transformer; channel attention module; hybrid structure; semantic segmentation; 3D convolutional neural network; noisy hyperspectral image; Tucker tensor decomposition; spectral–spatial feature extraction; semantic segmentation; high-resolution remote sensing; self-attention; context modeling; feature alignment; remote sensing; semantic segmentation; transformer; adapter; active–passive remote sensing; canopy height model (CHM); classification; random forest (RF); spectral reconstruction; convolutional transformer; hyperspectral unmixing; multi-head self-attention; hyperspectral image; semantic segmentation; context information; convolutional neural network; attention module; model compression; neural network pruning; frequency domain; lightweight deep neural networks; remote sensing image classification; deep space exploration; planetary rover; rock segmentation; semantic segmentation; double-branch; sea–land segmentation; GF-6; CNN; transformer; remote sensing; high-resolution remote sensing; semantic segmentation; global context information; fine-grained feature; feature fusion; polarimetric synthetic aperture radar (PolSAR) image classification; complex-valued convolutional neural network; complex-valued max pooling; complex-valued nonlinear activation; complex-valued cross-entropy; meta-learning; cross-domain segmentation; few-shot semantic segmentation; transformer; satellite imagery; scene segmentation; deep generative models; mine waste rock; leaching waste dumps; physical stability; closure planning; semantic segmentation in foggy scenes; unsupervised domain adaptation; UDA; self-training; label correction; self-distillation contrastive learning; sample rebalancing; polarimetric synthetic aperture radar (PolSAR) image classification; hyperspectral; LiDAR; fusion classification; transformer; feature fusion; remote sensing scene classification; few-shot learning; data augmentation; feature distortion; segment anything model (SAM); unsupervised domain adaptation; semantic road scene segmentation; image semantic segmentation; instruction set architecture (ISA); field programmable gate array (FPGA); spacecraft component images; land cover classification; SAR and optical images; attention mechanism; multi-scale feature fusion; semantic segmentation; high-resolution remote sensing images; semantic segmentation; ASPP module; local attention network model; activation function; point cloud semantic segmentation; CNN; multi-spatial feature encoding; multi-head attention pooling; cloud shadow segmentation; convolution neural network; attention mechanism; feature fusion; deep learning; polarimetric synthetic aperture radar (PolSAR); reflection symmetric decomposition (RSD); data input scheme; land classification; polarimetric scattering characteristics