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

被引：10

作者：

Zhang Xiaonan ^{[1
,2
]}

Zhong Xing ^{[1
,3
]}

Zhu Ruifei ^{[1
,3
]}

Gao Fang ^{[3
]}

Zhang Zuoxing ^{[1
,2
]}

Bao Songze ^{[1
,2
]}

Li Zhuqiang ^{[3
]}

机构：

[1] Chinese Acad Sci, Changchun Inst Opt Fine Mech & Phys, Changchun 130033, Jilin, Peoples R China

[2] Univ Chinese Acad Sci, Beijing 100019, Peoples R China

[3] Chang Guang Satellite Technol Co Ltd, Key Lab Satellite Remote Sensing Applicat Technol, Changchun 130102, Jilin, Peoples R China

来源：

ACTA OPTICA SINICA | 2018年 / 38卷 / 11期

关键词：

remote sensing; convolutional neural network; image complexity; scene classification;

D O I：

10.3788/A0S201838.1128001

中图分类号：

O43 [光学];

学科分类号：

070207 ; 0803 ;

摘要：

A scene classification algorithm of remote sensing images based on the integrated convolutional neural network (CNN) is proposed. A back-propagation network is constructed to measure the complexity of scene images. The classification of these images is conducted with the CNN based on the complexity level of each image, thus, the scene classification of remoting sensing images is achieved. With the proposed algorithm, the experimental verification of the open data of NWPU-RES1SC15 is conducted and the classification accuracy of 89.33% for Type I test and that of 92.53% for Type 11 arc obtained, respectively. The average running time is 0.41 s. Compared with the VGG-16 model for fine tuning and training, the classification accuracy by the proposed algorithm is increased by 2.19% and 2.17%, respectively. Simultaneously, the prediction rate is increased by 33%. Thus, the efficiency and practicality of this proposed algorithm arc confirmed.

引用

页数：11

共 25 条

[1] Andrew Zisserman, 2015, Arxiv, DOI arXiv:1409.1556
[2] Cardaci M., 2005, Fuzzy Logic and Applications. 6th International Workshop, WILF 2005. Revised Selected Papers (Lecture Notes in Artificial Intelligence Vol. 3849), P305
[3] Chen YQ, 2015, INT CONF MACH LEARN, P295, DOI 10.1109/ICMLC.2015.7340938
[4] [陈燕芹 Chen Yanqin], 2015, [中国光学, Chinese Optics], V8, P407
[5] Remote Sensing Image Scene Classification: Benchmark and State of the Art
Cheng, Gong
Han, Junwei
Lu, Xiaoqiang
[J]. PROCEEDINGS OF THE IEEE, 2017, 105 (10) : 1865 - 1883
[6] [高程程 Gao Chengcheng], 2010, [计算机系统应用, Computer Systems & Applications], V19, P195
[7] He K., 2016, PROC CVPR IEEE, P770, DOI DOI 10.1109/CVPR.2016.90
[8] Transferring Deep Convolutional Neural Networks for the Scene Classification of High-Resolution Remote Sensing Imagery
Hu, Fan
Xia, Gui-Song
Hu, Jingwen
Zhang, Liangpei
[J]. REMOTE SENSING, 2015, 7 (11) : 14680 - 14707
[9] Densely Connected Convolutional Networks
Huang, Gao
Liu, Zhuang
van der Maaten, Laurens
Weinberger, Kilian Q.
[J]. 30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 2261 - 2269
[10] Kingma D P., 2014, 2015 INT C LEARNING, DOI DOI 10.48550/ARXIV.1412.6980

← 1 2 3 →