Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks

By Yushi Chen, Hanlu Jiang, Chunyang Li, Xiuping Jia, Pedram Ghamisi. IEEE Transactions on Geoscience and Remote Sensing, 2016

2,659 citations recorded by the source corpus.

Subfields: Atmospheric Science, Media Technology

View Paper: https://www.semanticscholar.org/paper/10fb16414324a5db44f5d830adcb4810af59eed0

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 Media Technology

Citations in the corpus

Joint Deep Learning for land cover and land use classification (2019, methodology): “Followed by the suggestions from Chen et al. (2016), the number of layers for CNN network was set as six with three convolutional layers and three pooling layers to balance the complexity and the robustness of the network.”
Spectral–Spatial Residual Network for Hyperspectral Image Classification: A 3-D Deep Learning Framework (2018, methodology): “Therefore, in contrast to the obvious accuracy-decreasing effects reported in [17] and [22], the consistent HSI classification performance of SSRNs with varying layers demonstrated that the residual connections mitigate the decreasing-accuracy effects in other deep learning models.”
Multisource Remote Sensing Data Classification Based on Convolutional Neural Network (2018, methodology): “In [41]–[43], more CNNs were employed for deep feature extraction.”
SpectralFormer: Rethinking Hyperspectral Image Classification With Transformers (2021, methodology): “An overview of currently well-recognized backbone networks for the HS image classification task, such as autoencoders [16], CNNs [17], RNNs [18], GANs [19], CapsNet [20], GCNs [21], and Transformers [22].”
A Fast Dense Spectral-Spatial Convolution Network Framework for Hyperspectral Images Classification (2018, methodology): “(2) It has a deeper structure than the SSFC framework, and the methods in [11,12] which are CNN-based deep learning methods.”
Spatial-Spectral Transformer for Hyperspectral Image Classification (2021, methodology): “After that, several deep learning models such as the deep belief network [20], CNN [21,22], recurrent neural network [23,24], generative adversarial network [25,26], and capsule network [27,28] were investigated for HSI classification and obtained good classification performance.”
Deep Learning for Land Use and Land Cover Classification Based on Hyperspectral and Multispectral Earth Observation Data: A Review (2020, methodology): “In the case of remote sensing, 3D CNNs are used to extract spectral-spatial [114,115] and spatial-temporal [113] features.”
Generative Adversarial Networks for Hyperspectral Image Classification (2018, methodology): “Recently, the deep methods and CNNs have shown their excellent performance in HSI classification and feature extraction [23].”
Learning to Diversify Deep Belief Networks for Hyperspectral Image Classification (2017, background): “[22] proposed a 3-D-CNN to further capture both the spatial and spectral information.”
Advances in Hyperspectral Image and Signal Processing: A Comprehensive Overview of the State of the Art (2017, methodology): “High-level features, such as object-based [83] and so-called deep learning features [84], have been used for CD and classification.”
Deep learning for remote sensing image classification: A survey (2018, methodology): “Most recently, following the success of DL in natural image processing, DL methods have been introduced into HSI classification, achieving impressive results (Chen, Jiang, Li, Jia, & Ghamisi, 2016; Chen, Lin, Zhao, Wang, & Gu, 2017; Chen, Zhao, & Jia, 2015; Li, Zhang, & Shen, 2017).”
Spectral-Spatial Classification of Hyperspectral Imagery with 3D Convolutional Neural Network (2017, positive): “Note that another 3D-CNN-based HSI classification approach has been independently developed in [47], where the convolution formula of Equation (2), larger window size (27 × 27), and more complex net architecture (three 3D convolution layers with many more kernels) were adopted (albeit also with no p”
A new deep convolutional neural network for fast hyperspectral image classification (2017, methodology): “AdagradOptimizer and by the method in Chen et al. (2016).”
Hyperspectral Image Classification With Deep Feature Fusion Network (2018, methodology): “With the strong ability of extracting features, the CNN has been recently introduced to classify HSIs [43], [46], [48].”