Scene Classification of Remote Sensing Images Based on Integrated Convolutional Neural Networks

Xiaonan Zhang; Xing Zhong; Ruifei Zhu; Fang Gao; Zuoxing Zhang; Songze Bao; Zhuqiang Li

doi:10.3788/AOS201838.1128001

Acta Optica Sinica, Volume. 38, Issue 11, 1128001(2018)

Scene Classification of Remote Sensing Images Based on Integrated Convolutional Neural Networks

Xiaonan Zhang^1,2、*, Xing Zhong^1,3、*, Ruifei Zhu^1,3, Fang Gao³, Zuoxing Zhang^1,2, Songze Bao^1,2, and Zhuqiang Li³

¹ Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, Changchun, Jilin 130033, China

² University of Chinese Academy of Sciences, Beijing 100049, China

³ Key Laboratory of Satellite Remote Sensing Application Technology of Jilin Province, Chang Guang Satellite Technology Co., Ltd, Changchun, Jilin 130102, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(13)

Fig. 1. Architecture of integrated neural network

Download full size

Fig. 2. Flow chart of integrated network construction

Download full size

Fig. 3. Scene images of NWPU-RESISC45 dataset

Download full size

Fig. 4. Accuracy, loss value and learning rate versus number of cycles in training process of ResNet-50.(a) Accuracy; (b) loss value; (c) learning rate

Download full size

Fig. 5. Classification results based on CNN

Download full size

Fig. 6. Accuracy and loss value versus number of cycles in training process of BP network. (a) Accuracy; (b) loss value

Download full size

Fig. 7. Confusion matrix obtained after classification prediction of dataset by integrated model

Download full size

Fig. 8. Single accuracy comparison with those of other algorithms

Download full size

Fig. 9. Classification accuracies and prediction time of various models

Download full size

Fig. 10. Impact of number of scene categories classified by AlexNet on performance of integrated model

Download full size

Table 1. Training parameters and results of each network

View table

Table 1. Training parameters and results of each network

Model	Input size /(pixel×pixel)	Batch size /frame	Number of cycles	Training accuracy /%
Model	Input size /(pixel×pixel)	Batch size /frame	Number of cycles	Experiment I	Experiment II
AlexNet	224×224	256	300	81.22	85.46
ResNet-50	224×224	256	300	86.52	90.52
ResNet-152	224×224	128	600	85.11	90.11
DenseNet-169	224×224	128	600	82.44	87.44
VGG-16^[2]	-	-	-	87.15	90.36
Proposed model	-	-	-	88.47	92.53

Table 2. Performance comparison among several algorithms
View table
Table 2. Performance comparison among several algorithms
Method Color-histogram BoVW VGG-16 ResNet-50 Proposed Competition
Accuracy /% 27.52 44.97 90.36 90.59 92.53 93.41
Standard deviation 0.2184 0.2051 0.0673 0.0657 0.0593 0.0451
Prediction time /s - - 0.62 0.47 0.41 2.26

Table 3. Average accuracy comparison with those of other algorithms

View table

Table 3. Average accuracy comparison with those of other algorithms

Method	Accuracy /%(experiment I)	Accuracy /%(experiment II)
GIST^[2]	15.90	17.88
LBP^[2]	19.20	21.74
Color histograms^[2]	24.84	27.52
BoVW+SPM^[2]	27.83	32.96
LLC^[2]	38.81	40.03
BoVW^[2]	41.72	44.97
GoogLeNet^[2]	82.57	86.02
VGG-16^[2]	87.15	90.36
AlexNet^[2]	81.22	85.16
Two-streamDFF^[13]	80.22	83.16
ResNet-50	87.69	90.59
Proposed model	89.34	92.53

Tools

Get Citation

Copy Citation Text

Xiaonan Zhang, Xing Zhong, Ruifei Zhu, Fang Gao, Zuoxing Zhang, Songze Bao, Zhuqiang Li. Scene Classification of Remote Sensing Images Based on Integrated Convolutional Neural Networks[J]. Acta Optica Sinica, 2018, 38(11): 1128001

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites