Hyperspectral Image Classification With Deep Learning Models

Yang, Xiaofei; Ye, Yunming; Li, Xutao; Lau, Raymond Y. K.; Zhang, Xiaofeng; Huang, Xiaohui

doi:10.1109/tgrs.2018.2815613

Cited by 389 publications

(198 citation statements)

References 33 publications

Supporting

Mentioning

158

Contrasting

Unclassified

Order By: Relevance

“…At the same time, Zhong et al [54] developed an improved DBN model, named diversified DBN, to regularize the pretraining and fine-tuning procedures of DBN, which significantly improved the performance of DBN in terms of classification accuracies. In addition, 1-D CNN [55]- [58], 1-D GAN [46], [59], and RNN [44], [58], [60] were also used to extract spectral features for HSI classification. In [61], Li et al used pixel-pair features extracted by CNN to explore correlation between hyperpsectral pixels, where the convolution operation was mainly executed in the spectral domain.…”

Section: A Spectral-feature Networkmentioning

confidence: 99%

Deep Learning for Hyperspectral Image Classification: An Overview

Li¹,

Song²,

Fang³

et al. 2019

IEEE Trans. Geosci. Remote Sensing

1,220

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: A Spectral-feature Networkmentioning

confidence: 99%

Deep Learning for Hyperspectral Image Classification: An Overview

Li¹,

Song²,

Fang³

et al. 2019

IEEE Trans. Geosci. Remote Sensing

1,220

452

View full text Add to dashboard Cite

show abstract

“…To address this defect, deep learning [15], [16], [17], [18] has been extensively employed for hyperspectral image classification and has attracted increasing attention for its strong representation ability. The main reason is that deep learning methods can automatically obtain abstract high-level representations by gradually aggregating the low-level features, by which the complicated feature engineering can be avoided [19]. The first attempt to use deep learning methods for hyperspectral image classification was made by Chen et al [20], where the stacked autoencoder was built for highlevel feature extraction.…”

mentioning

confidence: 99%

Multiscale Dynamic Graph Convolutional Network for Hyperspectral Image Classification

Wan

Gong

Zhong

et al. 2020

IEEE Trans. Geosci. Remote Sensing

346

141

View full text Add to dashboard Cite

Convolutional Neural Network (CNN) has demonstrated impressive ability to represent hyperspectral images and to achieve promising results in hyperspectral image classification. However, traditional CNN models can only operate convolution on regular square image regions with fixed size and weights, so they cannot universally adapt to the distinct local regions with various object distributions and geometric appearances. Therefore, their classification performances are still to be improved, especially in class boundaries. To alleviate this shortcoming, we consider employing the recently proposed Graph Convolutional Network (GCN) for hyperspectral image classification, as it can conduct the convolution on arbitrarily structured non-Euclidean data and is applicable to the irregular image regions represented by graph topological information. Different from the commonly used GCN models which work on a fixed graph, we enable the graph to be dynamically updated along with the graph convolution process, so that these two steps can be benefited from each other to gradually produce the discriminative embedded features as well as a refined graph. Moreover, to comprehensively deploy the multi-scale information inherited by hyperspectral images, we establish multiple input graphs with different neighborhood scales to extensively exploit the diversified spectral-spatial correlations at multiple scales. Therefore, our method is termed 'Multi-scale Dynamic Graph Convolutional Network' (MDGCN). The experimental results on three typical benchmark datasets firmly demonstrate the superiority of the proposed MDGCN to other state-of-the-art methods in both qualitative and quantitative aspects.

show abstract

“…This improves the training of the network efficiency with fewer samples. (2) The method can also detect multi-class changes in an end-to-end manner. Most CD methods focus on binary CD to identify specific changes, but the proposed method can discriminate the nature changes in the sample-generation step.…”

Section: Background Of Hyperspectral Change Detectionmentioning

confidence: 99%

“…from various platforms, such as aircraft, satellites, and unmanned aerial vehicles [1]. The spectral profiles obtained from HSIs help to achieve target detection, classification, as well as change detection (CD) because of the profiles ability to distinguish the spectrally similar materials and describe the finer spectral changes [2,3].CD is the process of identifying changes in land cover or land use that have occurred over time in the same geographical area [4]. Applications of CD techniques include assessing natural disasters, monitoring crops, and managing water resources [5][6][7].…”

mentioning

confidence: 99%

See 1 more Smart Citation

Change Detection in Hyperspectral Images Using Recurrent 3D Fully Convolutional Networks

et al. 2018

View full text Add to dashboard Cite

Hyperspectral change detection (CD) can be effectively performed using deep-learning networks. Although these approaches require qualified training samples, it is difficult to obtain ground-truth data in the real world. Preserving spatial information during training is difficult due to structural limitations. To solve such problems, our study proposed a novel CD method for hyperspectral images (HSIs), including sample generation and a deep-learning network, called the recurrent three-dimensional (3D) fully convolutional network (Re3FCN), which merged the advantages of a 3D fully convolutional network (FCN) and a convolutional long short-term memory (ConvLSTM). Principal component analysis (PCA) and the spectral correlation angle (SCA) were used to generate training samples with high probabilities of being changed or unchanged. The strategy assisted in training fewer samples of representative feature expression. The Re3FCN was mainly comprised of spectral-spatial and temporal modules. Particularly, a spectral-spatial module with a 3D convolutional layer extracts the spectral-spatial features from the HSIs simultaneously, whilst a temporal module with ConvLSTM records and analyzes the multi-temporal HSI change information. The study first proposed a simple and effective method to generate samples for network training. This method can be applied effectively to cases with no training samples. Re3FCN can perform end-to-end detection for binary and multiple changes. Moreover, Re3FCN can receive multi-temporal HSIs directly as input without learning the characteristics of multiple changes. Finally, the network could extract joint spectral-spatial-temporal features and it preserved the spatial structure during the learning process through the fully convolutional structure. This study was the first to use a 3D FCN and a ConvLSTM for the remote-sensing CD. To demonstrate the effectiveness of the proposed CD method, we performed binary and multi-class CD experiments. Results revealed that the Re3FCN outperformed the other conventional methods, such as change vector analysis, iteratively reweighted multivariate alteration detection, PCA-SCA, FCN, and the combination of 2D convolutional layers-fully connected LSTM. from various platforms, such as aircraft, satellites, and unmanned aerial vehicles [1]. The spectral profiles obtained from HSIs help to achieve target detection, classification, as well as change detection (CD) because of the profiles ability to distinguish the spectrally similar materials and describe the finer spectral changes [2,3].CD is the process of identifying changes in land cover or land use that have occurred over time in the same geographical area [4]. Applications of CD techniques include assessing natural disasters, monitoring crops, and managing water resources [5][6][7]. Moreover, CD has offered the benefit of hyperspectral remote sensing over the past two decades. As HSIs offer more-detailed information about spectral changes than multispectral images, HSIs can improve the performance of CD [8]. Ho...

show abstract

Hyperspectral Image Classification With Deep Learning Models

Cited by 389 publications

References 33 publications

Deep Learning for Hyperspectral Image Classification: An Overview

Deep Learning for Hyperspectral Image Classification: An Overview

Multiscale Dynamic Graph Convolutional Network for Hyperspectral Image Classification

Change Detection in Hyperspectral Images Using Recurrent 3D Fully Convolutional Networks

Contact Info

Product

Resources

About