Supervised Deep Feature Extraction for Hyperspectral Image Classification

Liu, Bing; Yu, Xi; Zhang, Pengqiang; Yu, Anzhu; Fu, Qiongying; Wei, Xiangpo

doi:10.1109/tgrs.2017.2769673

Cited by 236 publications

(124 citation statements)

References 38 publications

Supporting

Mentioning

115

Contrasting

Order By: Relevance

“…As can be seen, except for 3D-GAN, the deep learning-based methods obtain satisfactory classification [8], EMP [19], EPF [24], JSR [25], 3D-CNN [56], GABOR-CNN [79], CNN-PPF [61], S-CNN [89], 3D-GAN [46], AND [19], (c) JSR [25], (d) EPF [24], (e) 3D-CNN [56], (f) CNN-PPF [61], (g) Gabor-CNN [79], (h) S-CNN [89], (i) 3D-GAN [46], and (j) DFFN [87]. [19], (c) JSR [25], (d) EPF [24], (e) 3D-CNN [56], (f) CNN-PPF [61], (g) Gabor-CNN [79], (h) S-CNN [89], (i) 3D-GAN [46], and (j) DFFN [87]. From the above experimental results, the deep learningbased methods show great advantages over other traditional methods in terms of visual classification maps and quantitative results.…”

Section: Classification Resultsmentioning

confidence: 90%

“…In [75], the label consistency constraint was enforced into the training procedure of SAE. Moreover, the correlation between samples was considered in networks investigated in [61], [89]. In general, network optimization is still a challenging problem.…”

Section: Network Optimizationmentioning

confidence: 99%

“…CLASSIFICATION ACCURACIES (IN PERCENTAGES) OBTAINED BY SVM[8], EMP[19], EPF[24], JSR[25], 3D-CNN[56], GABOR-CNN[79], CNN-PPF[61], S-CNN[89], 3D-GAN[46], AND DFFN [87] ON THE SALINAS IMAGE. THE BEST ACCURACIES ARE MARKED IN BOLD.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Deep Learning for Hyperspectral Image Classification: An Overview

Li¹,

Song²,

Fang³

et al. 2019

IEEE Trans. Geosci. Remote Sensing

1,340

452

View full text Add to dashboard Cite

Hyperspectral image (HSI) classification has become a hot topic in the field of remote sensing. In general, the complex characteristics of hyperspectral data make the accurate classification of such data challenging for traditional machine learning methods. In addition, hyperspectral imaging often deals with an inherently nonlinear relation between the captured spectral information and the corresponding materials. In recent years, deep learning has been recognized as a powerful feature-extraction tool to effectively address nonlinear problems and widely used in a number of image processing tasks. Motivated by those successful applications, deep learning has also been introduced to classify HSIs and demonstrated good performance. This survey paper presents a systematic review of deep learning-based HSI classification literatures and compares several strategies for this topic. Specifically, we first summarize the main challenges of HSI classification which cannot be effectively overcome by traditional machine learning methods, and also introduce the advantages of deep learning to handle these problems. Then, we build a framework which divides the corresponding works into spectralfeature networks, spatial-feature networks, and spectral-spatialfeature networks to systematically review the recent achievements in deep learning-based HSI classification. In addition, considering the fact that available training samples in the remote sensing field are usually very limited and training deep networks require a large number of samples, we include some strategies to improve classification performance, which can provide some guidelines for future studies on this topic. Finally, several representative deep learning-based classification methods are conducted on real HSIs in our experiments.

show abstract

Section: Classification Resultsmentioning

confidence: 90%

Section: Network Optimizationmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning for Hyperspectral Image Classification: An Overview

Li¹,

Song²,

Fang³

et al. 2019

IEEE Trans. Geosci. Remote Sensing

1,340

452

View full text Add to dashboard Cite

show abstract

“…Generally, HSI reduction can be achieved by feature extraction or feature selection (also known as band selection) techniques. For feature extraction [4][5][6][7][8], the original HSI is projected into a lower dimensional space and a reduced data set is generated. While for band selection, some discriminative bands are chosen to represent the original data set without modification.…”

Section: Introductionmentioning

confidence: 99%

Optimal Clustering Framework for Hyperspectral Band Selection

Wang

Zhang

2018

IEEE Trans. Geosci. Remote Sensing

236

132

View full text Add to dashboard Cite

Band selection, by choosing a set of representative bands in hyperspectral image (HSI), is an effective method to reduce the redundant information without compromising the original contents. Recently, various unsupervised band selection methods have been proposed, but most of them are based on approximation algorithms which can only obtain suboptimal solutions toward a specific objective function. This paper focuses on clustering-based band selection, and proposes a new framework to solve the above dilemma, claiming the following contributions: 1) An optimal clustering framework (OCF), which can obtain the optimal clustering result for a particular form of objective function under a reasonable constraint. 2) A rank on clusters strategy (RCS), which provides an effective criterion to select bands on existing clustering structure. 3) An automatic method to determine the number of the required bands, which can better evaluate the distinctive information produced by certain number of bands. In experiments, the proposed algorithm is compared to some state-of-the-art competitors. According to the experimental results, the proposed algorithm is robust and significantly outperform the other methods on various data sets.

show abstract

“…Comparing to classic statistical methods that explicitly designate fully specified modeling procedures, deep learning tries to fit an implicit yet potentially powerful function that can both im-itate bionic mechanism and extract sophisticated features by a data-driven learning process. A number of state-of-art deep learning methods have been applied to HSI processing, for example, unmixing [33], target detection [34], HSI visualization [8], HSI denoising [49], HSI super-resolution [26] and HSI classification [10,48,18,29,31,37,51,40,27,9,25,28].…”

Section: Introductionmentioning

confidence: 99%

Deep Neural Network Based Hyperspectral Pixel Classification With Factorized Spectral-Spatial Feature Representation

Chen

Zhou

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Deep learning has been widely used for hyperspectral pixel classification due to its ability of generating deep feature representation. However, how to construct an efficient and powerful network suitable for hyperspectral data is still under exploration. In this paper, a novel neural network model is designed for taking full advantage of the spectralspatial structure of hyperspectral data. Firstly, we extract pixel-based intrinsic features from rich yet redundant spectral bands by a subnetwork with supervised pre-training scheme. Secondly, in order to utilize the local spatial correlation among pixels, we share the previous subnetwork as a spectral feature extractor for each pixel in a patch of image, after which the spectral features of all pixels in a patch are combined and feeded into the subsequent classification subnetwork. Finally, the whole network is further fine-tuned to improve its classification performance. Specially, the spectral-spatial factorization scheme is applied in our model architecture, making the network size and the number of parameters great less than the existing spectralspatial deep networks for hyperspectral image classification. Experiments on the hyperspectral data sets show that, compared with some state-of-art deep learning methods, our method achieves better classification results while having smaller network size and less parameters.

show abstract

Supervised Deep Feature Extraction for Hyperspectral Image Classification

Cited by 236 publications

References 38 publications

Deep Learning for Hyperspectral Image Classification: An Overview

Deep Learning for Hyperspectral Image Classification: An Overview

Optimal Clustering Framework for Hyperspectral Band Selection

Deep Neural Network Based Hyperspectral Pixel Classification With Factorized Spectral-Spatial Feature Representation

Contact Info

Product

Resources

About