Hyperspectral Image Classification Based on Hypergraph and Convolutional Neural Network

Yuzhen Liu; Zhengquan Jiang; Fei Ma; Chunhua Zhang

doi:10.3788/LOP56.111007

Laser & Optoelectronics Progress, Volume. 56, Issue 11, 111007(2019)

Hyperspectral Image Classification Based on Hypergraph and Convolutional Neural Network

Yuzhen Liu^1、**, Zhengquan Jiang^2、*, Fei Ma¹, and Chunhua Zhang³

Author Affiliations

¹ School of Electronics and Information Engineering, Liaoning Technical University, Huludao, Liaoning 125105, China

² Graduate School, Liaoning University of Engineering and Technology, Huludao, Liaoning 125105, China

³ Liaoning Unicom Fuxin Branch, Fuxin, Liaoning 123100, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(13)

Fig. 1. Schematic of G-CNN classification model

Download full size

Fig. 2. Relationship between spectral and spatial information of hyperspectral images

Download full size

Fig. 3. Super-edge construction based on spectral features

Download full size

Fig. 4. Hypergraph construction of spatial relationship. (a) 4 neighborhood; (b) 8 neighborhood; (c) 16 neighborhood; (d) 24 neighborhood

Download full size

Fig. 5. Schematic of CNN classification model

Download full size

Fig. 6. Effect of number of training samples on accuracy of algorithm

Download full size

Fig. 7. Influence of experimental parameter change on experimental precision. (a) P; (b) U; (c) δ

Download full size

Fig. 8. Classification results by different algorithms on Indian Pines dataset. (a) Ground-truth; (b) SVM; (c) G-SVM; (d) Shallower CNN; (e) Contextual Deep CNN; (f) SPPF CNN; (g) G-CNN; (h) label

Download full size

Table 1. Number of training samples and test samples in Indian Pines dataset

View table

Table 1. Number of training samples and test samples in Indian Pines dataset

No.	Class	Number oftraining samples	Number ofteat samples
1	Corn-notill	200	1228
2	Corn-mintill	200	630
3	Grass-pasture	200	283
4	Hay-windrowed	200	278
5	Soybean-notill	200	772
6	Soybean-mintill	200	2255
7	Soybean-clean	200	393
8	Woods	200	1065
Total		1600	6904

Table 2. Parameter setting of convolutional neural network
View table
Table 2. Parameter setting of convolutional neural network
Dataset t₁ s₁ t₂ s₂ t₃ s₃ t₄ s₄ N₆ N₇
Indian Pines 21 1 2 2 21 1 2 2 100 8
University of Pavia 10 1 2 2 10 1 2 2 100 9
Salinas 21 1 2 2 21 1 2 2 100 16

Table 3. Training time and test time for each algorithm on Indian Pines datasets
View table
Table 3. Training time and test time for each algorithm on Indian Pines datasets
Item SVM G-SVM Shallower CNN Contextual Deep CNN SPPF CNN G-CNN
Training time 0.21 4.74 287.16 431.71 2704.34 337.08
Testing time 1.12 0.92 0.23 3.35 19.57 0.29

Table 4. Overall classification accuracy of each model on three datasets%
View table
Table 4. Overall classification accuracy of each model on three datasets%
Algorithm IndianPines Universityof Pavia Salinas
SVM 85.86 86.83 87.12
G-SVM 89.40 90.91 90.97
Shallower CNN^[12] 90.12 92.34 92.18
Contextual Deep CNN^[13] 93.30 95.01 95.47
SPPF CNN^[14] 94.87 91.74 94.21
G-CNN 96.63 97.42 97.27

Table 5. G-CNN classification results%
View table
Table 5. G-CNN classification results%
Parameter IndianPines Universityof Pavia Salinas
OA 96.63 97.42 97.27
AA 96.87 97.83 97.44
Kappa 96.54 97.18 97.12

Tools

Get Citation

Copy Citation Text

Yuzhen Liu, Zhengquan Jiang, Fei Ma, Chunhua Zhang. Hyperspectral Image Classification Based on Hypergraph and Convolutional Neural Network[J]. Laser & Optoelectronics Progress, 2019, 56(11): 111007

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites