GGCN: GPU-Based Hyperspectral Image Classification Algorithm

Minghua Zhang; Yaqing Zou; Wei Song; Dongmei Huang; Zhixiang Liu

doi:10.3788/LOP57.201101

Journals >Laser & Optoelectronics Progress >Volume 57 >Issue 20 >Page 201101 > Article

Laser & Optoelectronics Progress
Vol. 57, Issue 20, 201101 (2020)

GGCN: GPU-Based Hyperspectral Image Classification Algorithm

Minghua Zhang¹, Yaqing Zou¹, Wei Song¹, Dongmei Huang^1、2、*, and Zhixiang Liu¹

Author Affiliations

¹College of Information Science, Shanghai Ocean University, Shanghai 201306, China

²College of Electronics and Information Engineering, Shanghai University of Electric Power, Shanghai 200090, China

show less

DOI: 10.3788/LOP57.201101 Cite this Article Set citation alerts

Minghua Zhang, Yaqing Zou, Wei Song, Dongmei Huang, Zhixiang Liu. GGCN: GPU-Based Hyperspectral Image Classification Algorithm[J]. Laser & Optoelectronics Progress, 2020, 57(20): 201101 Copy Citation Text

show less

Fig. 1. Cube-CNN-SVM model framework

Download full size

Fig. 2. Definition form of convolution operation

Download full size

Fig. 3. Matrix multiplication form of convolution operation

Download full size

Fig. 4. Image preprocessing and convolution operation

Download full size

Fig. 5. Model training loss and accuracy variation. (a) Loss; (b) accuracy

Download full size

Fig. 6. Changes in the speedup ratio of different numbers of convolution layers

Download full size

Algorithm:GGCN

Input: Hyperspectral image1, Data preprocessing: processing <<>>i-th iteration: Forward propagation2, Convolutional: convol <<< gridsize, blocksize, 0, stream>>>3, Pooling: maxpooling <<< gridsize, blocksize, 0, stream>>>4, Fully connected: fullyconnected <<< gridsize, blocksize, 0, stream>>>5, Output: output <<>>6, Copy classification results to CPU to calculate the loss: 7, Copy data: cudaMemcpy()8, Calculate the loss: lossfunction()Backward propagation9, Output: bp_output <<< gridsize, blocksize, 0, stream>>>10, Fully Connected: bp_fullyconnected<<< gridsize, blocksize,0,stream>>>11, Pooling: bp_maxpooling <<>>12, Convolutional: bp_update_kernel <<< gridsize, blocksize, 0, stream>>>OutputEnd

Table 1. Algorithm pseudocode

Dataset	Sensor	Class number	Dimension	Top 5 classes	Size /MB
KSC	AVIRIS	13	512 × 614×176	Water, scrub, spartna-marsh,mud-flats, salt-marsh	56.8
PU	POSIS	9	610×340×103	Meadows, asphalt, bare-soil,self-blocking bricks, trees	33.2
Indian Pines	AVIRIS	16	145×145×224	Soybean-mintill, corn-notill, woods,soybean-notill, corn-mintill	5.7

Table 2. Information of the remote sensing datasets

Dataset	Neighbor pixel extract strategy	Time /s
Dataset	Neighbor pixel extract strategy	CPU	PNPE	G-PNPE
KSC	1P4N8N	2.654.896.21	0.450.881.12	0.510.921.22
PU	1P4N8N	2.213.303.87	0.310.520.66	0.330.490.71
Indian Pines	1P4N8N	1.05 1.652.17	0.170.210.28	0.180.200.26

Table 3. Comparison of time consumption of different data preprocessing methods

Dataset	Method	Time /s		Speedup ratio
Dataset	Method	MBGD(batchsize is 10)	MBGD(batchsize is 100)	Speedup ratio
KSC	Cube-CNN-SVMGCNGGCN	23123.623487.342834.01	23012.493322.342598.78	1.06.68.2
PU	Cube-CNN-SVMGCNGGCN	2231.23351.46286.22	2187.75338.11230.06	1.06.37.8
Indian Pines	Cube-CNN-SVMGCNGGCN	453.62107.3484.01	422.49102.3480.78	1.04.25.1

Table 4. Comparison of running time and speedup of different classification models

Dataset	Method	Accuracy /%
Dataset	Method	MBGD(batchsize is 10)	MBGD(batchsize is 100)
KSC	Cube-CNN-SVMGCNGGCN	93.7893.3393.67	93.4793.1293.92
PU	Cube-CNN-VMGCNGGCN	96.6796.2396.34	95.2195.6195.69
Indian Pines	Cube-CNN-SVMGCNGGCN	94.7894.7394.87	94.6794.5294.42

Table 5. Accuracy of different classification models

Layer	Percentage /%
Layer	GCN	GGCN
Preprocessing	1.0	2.4
Convolution	38.2	28.0
Pooling	2.4	5.6
Fully connection	27.1	24.0
Output	19.0	22.0
Others	13.3	18.0

Table 6. Ratio of time between the improved model and the original model

Minghua Zhang, Yaqing Zou, Wei Song, Dongmei Huang, Zhixiang Liu. GGCN: GPU-Based Hyperspectral Image Classification Algorithm[J]. Laser & Optoelectronics Progress, 2020, 57(20): 201101

Download Citation

Set citation alerts for the article

Tools

Set citation alerts for the article

Save the article for my favorites

Paper Information