Hyperspectral Image Classification with Convolutional Neural Networks

Slavkovikj, Viktor; Verstockt, Steven; Neve, Wesley De; Hoecke, Sofie Van; Walle, Rik Van de

doi:10.1145/2733373.2806306

Cited by 93 publications

(65 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The architecture alternates convolutions and dimension reduction (either by PCA or by sampling) followed by a multi-layer perceptron for the final classification step, as shown in Figure 5, with 2D convolutions in red and 1D fully connected layers in blue. As an alternative, [50] flattens the spatial dimensions to produce a 2D image with a different shape, instead of an hypercube, and then applies a traditional 2D CNN on the resulting image. One drawback of these methods is that they try to make hyperspectral images similar to RGB ones, i.e.…”

Section: B Spectral Classificationmentioning

confidence: 99%

Deep Learning for Classification of Hyperspectral Data: A Comparative Review

Audebert

Saux

Lefèvre

2019

IEEE Geosci. Remote Sens. Mag.

461

194

View full text Add to dashboard Cite

In recent years, deep learning techniques revolutionized the way remote sensing data are processed. Classification of hyperspectral data is no exception to the rule, but has intrinsic specificities which make application of deep learning less straightforward than with other optical data. This article presents a state of the art of previous machine learning approaches, reviews the various deep learning approaches currently proposed for hyperspectral classification, and identifies the problems and difficulties which arise to implement deep neural networks for this task. In particular, the issues of spatial and spectral resolution, data volume, and transfer of models from multimedia images to hyperspectral data are addressed. Additionally, a comparative study of various families of network architectures is provided and a software toolbox is publicly released to allow experimenting with these methods. 1 This article is intended for both data scientists with interest in hyperspectral data and remote sensing experts eager to apply deep learning techniques to their own dataset.

show abstract

Section: B Spectral Classificationmentioning

confidence: 99%

Deep Learning for Classification of Hyperspectral Data: A Comparative Review

Audebert

Saux

Lefèvre

2019

IEEE Geosci. Remote Sens. Mag.

461

194

View full text Add to dashboard Cite

show abstract

“…However, with this approach, each retrained spectral dimension is processed independently with standard 2D convolutional filters. Another approach is developed in [41], where a 3D convolution is literally deployed by the first layer followed by two 1D Convs and ending with two Fully Connected Layers (FC). This approach is close to the one presented in [42] but adds spatial information.…”

Section: State Of the Art DL For Rsmentioning

confidence: 99%

3-D Deep Learning Approach for Remote Sensing Image Classification

Hamida

Benoît

Lambert

et al. 2018

IEEE Trans. Geosci. Remote Sensing

569

240

View full text Add to dashboard Cite

Recently, a variety of approaches has been enriching the field of Remote Sensing (RS) image processing and analysis. Unfortunately, existing methods remain limited faced to the rich spatio-spectral content of today's large datasets. It would seem intriguing to resort to Deep Learning (DL) based approaches at this stage with regards to their ability to offer accurate semantic interpretation of the data. However, the specificity introduced by the coexistence of spectral and spatial content in the RS datasets widens the scope of the challenges presented to adapt DL methods to these contexts. Therefore, the aim of this paper is firstly to explore the performance of DL architectures for the RS hyperspectral dataset classification and secondly to introduce a new three-dimensional DL approach that enables a joint spectral and spatial information process. A set of three-dimensional schemes is proposed and evaluated. Experimental results based on well known hyperspectral datasets demonstrate that the proposed method is able to achieve a better classification rate than state of the art methods with lower computational costs.

show abstract

“…This becomes a major obstacle to exploiting deep learning in hyperspectral imagery, where the number of labeled samples are quite limited due to high expense of manually labeling and even the available labels are not always reliable [17]. To extract deep spectral-spatial representation, a conventional strategy is to train a network or a classifier based on patch-based samples, as did in [16][17][18][19][20]. However, this will further aggregate the sample shortage problem, if the overlap of training and testing samples is not allowed.…”

Section: Introductionmentioning

confidence: 99%

Spectral-Spatial Feature Extraction and Classification by ANN Supervised With Center Loss in Hyperspectral Imagery

Guo

Zhu

2019

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

In this paper, we propose a spectral-spatial feature extraction and classification framework based on artificial neuron network (ANN) in the context of hyperspectral imagery. With limited labeled samples, only spectral information is exploited for training and spatial context is integrated posteriorly at the testing stage. Taking advantage of recent advances in face recognition, a joint supervision symbol that combines softmax loss and center loss is adopted to train the proposed network, by which intra-class features are gathered while inter-class variations are enlarged. Based on the learned architecture, the extracted spectrum-based features are classified by a center classifier. Moreover, to fuse the spectral and spatial information, an adaptive spectral-spatial center classifier is developed, where multiscale neighborhoods are considered simultaneously, and the final label is determined using an adaptive voting strategy. Finally, experimental results on three well-known datasets validate the effectiveness of the proposed methods compared with the state-of-the-art approaches.

show abstract

Hyperspectral Image Classification with Convolutional Neural Networks

Cited by 93 publications

References 21 publications

Deep Learning for Classification of Hyperspectral Data: A Comparative Review

Deep Learning for Classification of Hyperspectral Data: A Comparative Review

3-D Deep Learning Approach for Remote Sensing Image Classification

Spectral-Spatial Feature Extraction and Classification by ANN Supervised With Center Loss in Hyperspectral Imagery

Contact Info

Product

Resources

About