Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Xiangpo Wei"'
Publikováno v:
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 14, Pp 3566-3580 (2021)
This article proposes a novel hierarchical residual network with attention mechanism (HResNetAM) for hyperspectral image (HSI) spectral-spatial classification to improve the performance of conventional deep learning networks. The straightforward conv
Externí odkaz:
https://doaj.org/article/b7bf41704a3f40ecae1cdd9053f68451
Publikováno v:
European Journal of Remote Sensing, Vol 53, Iss 1, Pp 349-357 (2020)
In recent years, deep learning has drawn increasing attention in the field of hyperspectral remote sensing image classification and has achieved great success. However, the traditional convolutional neural network model has a huge parameter space, in
Externí odkaz:
https://doaj.org/article/4bc11f48bcef41ccb21dc791ff722823
Publikováno v:
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 13, Pp 3462-3477 (2020)
Recently, the deep learning models have achieved great success in hyperspectral images (HSI) classification. However, most of the deep learning models fail to obtain satisfactory results under the condition of small samples due to the contradiction b
Externí odkaz:
https://doaj.org/article/4219e648d3dc44219e580b28eba5ff5b
Publikováno v:
European Journal of Remote Sensing, Vol 52, Iss 1, Pp 448-462 (2019)
Convolutional neural networks (CNNs) have strong feature extraction capability, which have been used to extract features from the hyperspectral image. Local binary pattern (LBP) is a simple but powerful descriptor for spatial features, which can less
Externí odkaz:
https://doaj.org/article/c4e0992184564ae39665995fb5353617
Publikováno v:
IEEE Transactions on Geoscience and Remote Sensing. 60:1-16
In this article, we propose a novel multiscale deep learning network with self-calibrated convolution (MSNetSC) for hyperspectral and light detection and ranging (LiDAR) data collaborative classification. Conventional deep learning methods have limit
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4ce17495a3d886d02a6d855c9cf4a71d
https://doi.org/10.1109/tgrs.2021.3106025
https://doi.org/10.1109/tgrs.2021.3106025
Publikováno v:
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 13, Pp 3462-3477 (2020)
Recently, the deep learning models have achieved great success in hyperspectral images (HSI) classification. However, most of the deep learning models fail to obtain satisfactory results under the condition of small samples due to the contradiction b
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cb00d3f590c903272eff6e90066cf136
https://doi.org/10.1109/jstars.2020.3002787
https://doi.org/10.1109/jstars.2020.3002787
Publikováno v:
European Journal of Remote Sensing, Vol 52, Iss 1, Pp 448-462 (2019)
Convolutional neural networks (CNNs) have strong feature extraction capability, which have been used to extract features from the hyperspectral image. Local binary pattern (LBP) is a simple but powerful descriptor for spatial features, which can less
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3dbc8496159022659d334c779bbbddab
https://doi.org/10.1080/22797254.2019.1634980
https://doi.org/10.1080/22797254.2019.1634980
Publikováno v:
Remote Sensing Letters. 10:59-66
In this letter, a dense convolutional neural network (DCNN) is proposed for hyperspectral image classification, aiming to improve classification performance by promoting feature reuse and strengthening the flow of features and gradients. In the netwo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5f97207e56143c727c0b8aca3ef38b16
https://doi.org/10.1080/2150704x.2018.1526424
https://doi.org/10.1080/2150704x.2018.1526424
Publikováno v:
IEEE Transactions on Geoscience and Remote Sensing. 56:1909-1921
Hyperspectral image classification has become a research focus in recent literature. However, well-designed features are still open issues that impact on the performance of classifiers. In this paper, a novel supervised deep feature extraction method
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::74f1f79d133d07bcadf316cc0ec11aef
https://doi.org/10.1109/tgrs.2017.2769673
https://doi.org/10.1109/tgrs.2017.2769673
Publikováno v:
The Photogrammetric Record. 32:48-60
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a406f6cda1b4792e1b1e3c0b7d21c399
https://doi.org/10.1111/phor.12183
https://doi.org/10.1111/phor.12183