2017 IEEE International Conference on Image Processing (ICIP) 2017
DOI: 10.1109/icip.2017.8297014
|View full text |Cite
|
Sign up to set email alerts
|

Multi-scale 3D deep convolutional neural network for hyperspectral image classification

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

1
159
0
4

Year Published

2019
2019
2022
2022

Publication Types

Select...
4
4
1

Relationship

0
9

Authors

Journals

citations
Cited by 322 publications
(164 citation statements)
references
References 13 publications
1
159
0
4
Order By: Relevance
“…The goal of this algorithm is to obtain the material properties of a single-pixel for the identification of different kinds of ground objects in hyperspectral images. In the three public available hyperspectral datasets [26][27][28][29][30][31], the Indian Pines datasets and Salinas datasets target the farmland of different crops and the natural topography. They are continuous large areas of the same category, and the classification effect will be better by using the method of spatial spectrum combination.…”
Section: Resultsmentioning
confidence: 99%
See 1 more Smart Citation
“…The goal of this algorithm is to obtain the material properties of a single-pixel for the identification of different kinds of ground objects in hyperspectral images. In the three public available hyperspectral datasets [26][27][28][29][30][31], the Indian Pines datasets and Salinas datasets target the farmland of different crops and the natural topography. They are continuous large areas of the same category, and the classification effect will be better by using the method of spatial spectrum combination.…”
Section: Resultsmentioning
confidence: 99%
“…In this paper, we compare NG-APC model with the classical SVM, the new 1D-CNN [28,29] 2D-CNN [30], 3D-CNN algorithms [31][32][33][34], and RNN [35]. We refer some of these algorithms by nshaud/DeepHyperX on GitHub.…”
Section: Resultsmentioning
confidence: 99%
“…Zhu et al [12] presented a generative adversarial network comprised of two parts 1D and 2D convolutions. He et al [13] used five layered multi-scale 3D CNN and Chen et al [14] used logistic regression as final classifier for combined data of LIDAR and HS image. Lee et al [18] proposed a contextual deep CNN by concurrently extracting multiple 3-dimensional local convolutional features with different sizes jointly exploiting spatial and spectral features of HS image.…”
Section: Related Workmentioning
confidence: 99%
“…72.76%(8) 80.95% (11) 86.62% (12) LFDA 71.09% (24) 76.43% (28) 82.50% (8 Finally, we compared the proposed method with the other state-of-the-art deep learning methods of 1D-CNN, the CNN classifier proposed by Hu et al [7], the five-layer CNN classifier proposed by Mei et al [49], and the M3D-DCNN classifier proposed by He et al [50]. All the methods, were compared under the same experimental settings (number of training samples, patch size, etc.)…”
Section: Rldementioning
confidence: 99%