Spectral–spatial classification of hyperspectral images using deep convolutional neural networks

By Jun Yue, Wenzhi Zhao, Shanjun Mao, Hui Liu. 2015

465 citations recorded by the source corpus.

Subfields: Atmospheric Science, Biomedical Engineering, Media Technology

How researchers see this paper

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

In Atmospheric Science

In Biomedical Engineering

In Media Technology

Citations in the corpus

A deep learning framework for hyperspectral image classification using spatial pyramid pooling (2016, methodology): “As a result, deep convolutional neural networks (DCNNs) model consisting of the convolution layers and the down-sampling layers has been introduced for hyperspectral image classi ﬁ cation (Yue et al. 2015).”
Convolutional Neural Networks for Large-Scale Remote-Sensing Image Classification (2017, unknown): “Recent works have incorporated convolutions on the spatial domain after extracting the principal components of the hyperspectral image [19]–[21], and the idea of reasoning”
Towards better exploiting convolutional neural networks for remote sensing scene classification (2016, methodology): “[16] used fine-tuning method to classify hyperspectral images.”
Spectral-Spatial Classification of Hyperspectral Imagery with 3D Convolutional Neural Network (2017, methodology): “In order to evaluate the efficacy of the proposed 3D-CNN method, we compared it with three deep learning HSI classification approaches: SAE-LR [29], DBN-LR [31], and 2D-CNN [33].”
Deep Learning for Hyperspectral Image Classification: An Overview (2019, methodology): “In [56], [57], and [65]–[67], PCA was first performed on the whole hyperspectral data to reduce the dimensionality of the original space, and then the spatial information contained in the neighborhood region of the input hyperspectral pixel was exploited by a 2-D CNN.”
Deep Learning for Remote Sensing Data: A Technical Tutorial on the State of the Art (2016, background): “In the architecture of the conventional CNNs, the final layer is followed by some fully connected layers and finally the classification layer.”
Implementation of machine-learning classification in remote sensing: an applied review (2018, methodology): “We do not consider the many new machine-learning algorithms [e.g. extreme learning machines (kernel-based extreme learning machines (KELMs)) (Pal, Maxwell, and Warner 2013) and deep convolution neural networks (Yue et al. 2015)], because such methods have not yet been widely adopted.”
HSI-BERT: Hyperspectral Image Classification Using the Bidirectional Encoder Representation From Transformers (2020, methodology): “[28] employed the principal component analysis (PCA) followed by CNN to learn the spatial–spectral information.”
Deep Learning Based Oil Palm Tree Detection and Counting for High-Resolution Remote Sensing Images (2016, methodology): “In recent years, deep learning based methods have also been applied to hyperspectral image classification [20,21], large-scale land cover classification [22], scene classification [23–25], and object detection [26,27], etc.”
Remote Sensing Image Scene Classification Using Multi-Scale Completed Local Binary Patterns and Fisher Vectors (2016, background): “[14] presented the PatreoNet, which has the capability to learn specific spatial features from remote sensing images without any pre-processing step or descriptor evaluation.”
Deep Learning for Classification of Hyperspectral Data: A Comparative Review (2019, unknown): “Trying to go around this problem, [51] and [52] proposed another approach.”
Spectral–Spatial Feature Tokenization Transformer for Hyperspectral Image Classification (2022, methodology): “In [37] and [38], a 2-D-CNN model was proposed to extract the spatial fea-”
Multiscale Dynamic Graph Convolutional Network for Hyperspectral Image Classification (2019, methodology): “[54] projected hyperspectral data to several principal components before adopting CNN to extract spectral–spatial features.”