Deep Learning-Based Semantic Segmentation of Urban Features in Satellite Images: A Review and Meta-Analysis
Reads0
Chats0
TLDR
In this paper, a review and meta-analysis of deep learning-based semantic segmentation in urban remote sensing images is presented. But, the focus of this paper is on urban sensing images.Abstract:
Availability of very high-resolution remote sensing images and advancement of deep learning methods have shifted the paradigm of image classification from pixel-based and object-based methods to deep learning-based semantic segmentation. This shift demands a structured analysis and revision of the current status on the research domain of deep learning-based semantic segmentation. The focus of this paper is on urban remote sensing images. We review and perform a meta-analysis to juxtapose recent papers in terms of research problems, data source, data preparation methods including pre-processing and augmentation techniques, training details on architectures, backbones, frameworks, optimizers, loss functions and other hyper-parameters and performance comparison. Our detailed review and meta-analysis show that deep learning not only outperforms traditional methods in terms of accuracy, but also addresses several challenges previously faced. Further, we provide future directions of research in this domain.read more
Citations
More filters
Journal ArticleDOI
A comprehensive review on deep learning based remote sensing image super-resolution methods
TL;DR: In this paper , a review of the DL-based single image super-resolution (SISR) methods on optical remote sensing images is presented, including DL models, commonly used remote sensing datasets, loss functions, and performance evaluation metrics.
Journal ArticleDOI
Forest Fire Risk Prediction: A Spatial Deep Neural Network-Based Framework
TL;DR: In this article, a spatial framework was proposed to quantify the forest fire risk in the Northern Beaches area of Sydney, Australia by using deep neural networks to assess forest fire susceptibility.
Journal ArticleDOI
A Review of Landcover Classification with Very-High Resolution Remotely Sensed Optical Images-Analysis Unit, Model Scalability and Transferability
Rongjun Qin,Tao Li +1 more
TL;DR: In this article , the authors present a systematic overview of existing methods by starting from learning methods and varying basic analysis units for landcover mapping tasks, to challenges and solutions on three aspects of scalability and transferability with a remote sensing classification focus including (1) sparsity and imbalance of data; (2) domain gaps across different geographical regions; and (3) multi-source and multi-view fusion.
Journal ArticleDOI
Earth Observation for Sustainable Infrastructure: A Review
Yongze Song,Peng Wu +1 more
TL;DR: This study presents a systematical literature review to identify trends of Earth observation for sustainable infrastructure (EOSI), investigate the relationship between EOSI and Sustainable Development Goals (SDGs), and explore challenges and future directions of EOSi.
Journal ArticleDOI
Multi-Object Segmentation in Complex Urban Scenes from High-Resolution Remote Sensing Data
TL;DR: In this article, a multi-level context gating UNet (MCG-UNet) and bi-directional ConvLSTM UNet model (BCL-Unet) were proposed for multi-object segmentation.
References
More filters
Journal ArticleDOI
Semantic segmentation of slums in satellite images using transfer learning on fully convolutional neural networks
Michael Wurm,Thomas Stark,Xiao Xiang Zhu,Xiao Xiang Zhu,Matthias Weigand,Matthias Weigand,Hannes Taubenböck +6 more
TL;DR: Using transfer learning capabilities of FCNs to slum mapping in various satellite images is found to be extremely valuable in retrieving information on small-scaled urban structures such as slum patches even in satellite images of decametric resolution.
Journal ArticleDOI
Semisupervised Hyperspectral Image Classification Based on Generative Adversarial Networks
TL;DR: A semisupervised framework for HSI data based on a 1-D GAN that enables the automatic extraction of spectral features for H SI classification and achieves very promising results with a small number of labeled samples.
Journal ArticleDOI
MARTA GANs: Unsupervised Representation Learning for Remote Sensing Image Classification
TL;DR: An unsupervised model called multiple-layer feature-matching generative adversarial networks (MARTA GANs) to learn a representation using only unlabeled data to improve the classification performance compared with other state-of-the-art methods.
Journal ArticleDOI
DeepUNet: A Deep Fully Convolutional Network for Pixel-Level Sea-Land Segmentation
TL;DR: DeepUNet as discussed by the authors uses DownBlocks instead of convolution layers in the contracting path and uses UpBlock in the expansive path to get more precise segmentation results, and the two novel blocks bring two new connections that are U-connection and Plus connection.