Deep Learning for Remote Sensing Data: A Technical Tutorial on the State of the Art

By Liangpei Zhang, Lefei Zhang, Bo Du. 2016

2,002 citations recorded by the source corpus.

Subfields: Media Technology, Ocean Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Media Technology

In Ocean Engineering

Citations in the corpus

Survey of computational intelligence as basis to big flood management: challenges, research directions and future work (2018, positive): “State-of-the-art deep learning methodologies have been successfully applied on target recognition for remote sensing (RS) applications (Zhang, Zhang, & Du, 2016).”
Implementation of machine-learning classification in remote sensing: an applied review (2018, methodology): “Zhang, Zhang, and Du (2016) noted that deep learning has many applications in remote sensing, including image preprocessing, classi ﬁ cation, and target recognition.”
Deep learning classifiers for hyperspectral imaging: A review (2019, methodology): “Following traditional pixel-wise methods, the CNN1D can be employed to perform spectral-spatial classification, rearranging the the spatial information and concatenating it to the spectral features (Zhang et al., 2016).”
A Fast Dense Spectral-Spatial Convolution Network Framework for Hyperspectral Images Classification (2018, methodology): “Since these traditional methods are based on hand-crafted features, hyperspectral data need an algorithm that can learn the representative and discriminative features [7].”
Deep Learning for Land Use and Land Cover Classification Based on Hyperspectral and Multispectral Earth Observation Data: A Review (2020, methodology): “In remote sensing, 2D-CNN is typically adopted to extract the spatial features of the HSI and MSI, considering the continuity of land covers in the spatial domain [105].”
Agricultural remote sensing big data: Management and applications (2018, methodology): “It was strongly believed that deep learning techniques are crucial and important in remote sensing data analysis, particularly for the age of remote sensing big data (Zhang et al. 2016).”
Hyperspectral Image Classification Using Deep Pixel-Pair Features (2017, background): “[19] systematically survey the general way to construct deep networks for remote sensing images and is the first attempt to evaluate the performance of all the state-of-the-art deep learning methods on remote sensing images.”
A review of deep learning methods for semantic segmentation of remote sensing imagery (2021, background): “Zhang, Zhang, and Du (2016) reviewed the fundamental deep learning techniques including convolutional neural networks (CNNs), autoencoders, and restricted Boltz-mann machines, and gave a technical tutorial on the design of deep neural network-based methods for target recognition and scene…”
Very Deep Convolutional Neural Networks for Complex Land Cover Mapping Using Multispectral Remote Sensing Imagery (2018, background): “In such a network, the deconstruction error between the input data at the encoding layer and its reconstruction at the decoding layer is minimized [34].”
A Review of Deep Learning Models for Time Series Prediction (2019, methodology): “Regarding the above superiorities, deep learning-based models have been successfully applied in many ﬁelds pertinent to time series prediction, including remote sensing [11], multi-sensor fusion [12], [13], etc.”
Spectral-Spatial Classification of Hyperspectral Imagery with 3D Convolutional Neural Network (2017, neutral): “applied unsupervised deep feature learning—including stacked autoencoder (SAE) [28] and deep brief network (DBN) [31]—for spectral–spatial feature extraction and classification.”
Deep Learning for LiDAR Point Clouds in Autonomous Driving: A Review (2020, neutral): “etail in [17, 18]. These surveys normally arXiv:2005.09830v1 [cs.CV] 20 May 2020 JOURNAL OF LATEX CLASS FILES 2 focused on reviewing DL applications in visual data [19, 20] and remote sensing imagery [21, 22]. Some are targeted at more speciﬁc tasks such as object detection [23, 24], semantic segmen”
Hyperspectral Image Classification With Deep Feature Fusion Network (2018, methodology): “based on the DL have been applied to analyze remote sensing images [31]–[48].”