This thesis is devoted to analyzing and processing hyperspectral images mainly with deep learning methods. To fully exploit the spectral-spatial information of hyperspectral data, convolutional neural network with parameter tuning is proposed for hyperspectral classification. Besides, to solve the problem of limited labeled samples in hyperspectral images, unsupervised feature extraction methods based on improved generative adversarial network and convolutional autoencoder are investigated. In addition, a multi-scale denoising autoencoder framework is designed for denoising and improvements of target detection. The results on simulated and real-world data demonstrate that the effectiveness of the proposed methods and their promising prospec...
One of the most important tasks in hyperspectral imaging is the classification of the pixels in the ...
In this paper, we propose a spectral-spatial feature extraction framework based on deep learning (DL...
Les images hyperspectrales (HSI) fournissent des informations spectrales détaillées sur les objets a...
This thesis is devoted to analyzing and processing hyperspectral images mainly with deep learning me...
Hyperspectral Image Classification is an important research problem in remote sensing.Classification...
Deep learning based methods have recently been successfully explored in hyperspectral image classifi...
International audienceIn recent years, deep learning techniques revolutionized the way remote sensin...
Deep learning methods have been successfully applied to learn feature representations for high-dimen...
Convolutional neural networks (CNNs) have exhibited excellent performance in hyperspectral image cla...
A generative adversarial network (GAN) usually contains a generative network and a discriminative n...
In recent years, hyperspectral imaging has been a popular subject in the remote sensing community by...
In this letter, a new deep learning framework for spectral-spatial classification of hyperspectral i...
Hyperspectral imaging is a technique which uses hyperspectral sensors to collect spectral informatio...
The spectral signatures of the materials contained in hyperspectral images, also called endmembers (...
Spatial and spectral information are obtained simultaneously by hyperspectral remote sensing. Joint ...
One of the most important tasks in hyperspectral imaging is the classification of the pixels in the ...
In this paper, we propose a spectral-spatial feature extraction framework based on deep learning (DL...
Les images hyperspectrales (HSI) fournissent des informations spectrales détaillées sur les objets a...
This thesis is devoted to analyzing and processing hyperspectral images mainly with deep learning me...
Hyperspectral Image Classification is an important research problem in remote sensing.Classification...
Deep learning based methods have recently been successfully explored in hyperspectral image classifi...
International audienceIn recent years, deep learning techniques revolutionized the way remote sensin...
Deep learning methods have been successfully applied to learn feature representations for high-dimen...
Convolutional neural networks (CNNs) have exhibited excellent performance in hyperspectral image cla...
A generative adversarial network (GAN) usually contains a generative network and a discriminative n...
In recent years, hyperspectral imaging has been a popular subject in the remote sensing community by...
In this letter, a new deep learning framework for spectral-spatial classification of hyperspectral i...
Hyperspectral imaging is a technique which uses hyperspectral sensors to collect spectral informatio...
The spectral signatures of the materials contained in hyperspectral images, also called endmembers (...
Spatial and spectral information are obtained simultaneously by hyperspectral remote sensing. Joint ...
One of the most important tasks in hyperspectral imaging is the classification of the pixels in the ...
In this paper, we propose a spectral-spatial feature extraction framework based on deep learning (DL...
Les images hyperspectrales (HSI) fournissent des informations spectrales détaillées sur les objets a...