full
search.png

Search

close.png

Cancel

arrow
Volume 19, Issue 1
Remote Sensing Image Scene Classification Based on Deep Learning Feature Fusion

Liqi Wang, Cheng Zhang, Yuchao Hou, Xiuhui Tan, Rong Cheng, Xiang Gao & Yanping Bai

DOI: 10.4208/JICS-2024-005

J. Info. Comput. Sci. , 19 (2024), pp. 65-80.

[An open-access article; the PDF is free to any online user.]

Preview Full PDF 86 1082

Cited by

google scholar semantic scholar
Export citation
  • Abstract

In view that traditional manual feature extraction method cannot effectively extract the overall deep image information, a new method of scene classification based on deep learning feature fusion is proposed for remote sensing images. First, the Grey Level Co-occurrence Matrix (GLCM) and Local Binary Patterns (LBP) are used to extract the shallow information of texture features with relevant spatial characteristics and local texture features as well; second, the deep information of images is extracted by the AlexNet migration learning network, and a 256-dimensional fully connected layer is added as feature output while the last fully connected layer is removed; and the two features are adaptively integrated, then the remote sensing images are classified and identified by the Grid Search optimized Support Vector Machine (GS-SVM). The experimental results on 21 types of target data of the public dataset UC Merced and 7 types of target data of RSSCN7 produced average accuracy rates of 94.77% and 93.79%, respectively, showing that the proposed method can effectively improve the classification accuracy of remote sensing image scenes.

  • Keywords

Image classification, Convolutional Neural Network (CNN), Grey Level Co-occurrence Matrix (GLCM), Local Binary Patterns (LBP), migration learning, Support Vector Machine (SVM).

  • AMS Subject Headings

68U10, 68T05

  • Copyright

COPYRIGHT: © Global Science Press

  • Email address
  • BibTex
  • RIS
  • TXT
@Article{JICS-19-65, author = {Wang , LiqiZhang , ChengHou , YuchaoTan , XiuhuiCheng , RongGao , Xiang and Bai , Yanping}, title = {Remote Sensing Image Scene Classification Based on Deep Learning Feature Fusion}, journal = {Journal of Information and Computing Science}, year = {2024}, volume = {19}, number = {1}, pages = {65--80}, abstract = {

In view that traditional manual feature extraction method cannot effectively extract the overall deep image information, a new method of scene classification based on deep learning feature fusion is proposed for remote sensing images. First, the Grey Level Co-occurrence Matrix (GLCM) and Local Binary Patterns (LBP) are used to extract the shallow information of texture features with relevant spatial characteristics and local texture features as well; second, the deep information of images is extracted by the AlexNet migration learning network, and a 256-dimensional fully connected layer is added as feature output while the last fully connected layer is removed; and the two features are adaptively integrated, then the remote sensing images are classified and identified by the Grid Search optimized Support Vector Machine (GS-SVM). The experimental results on 21 types of target data of the public dataset UC Merced and 7 types of target data of RSSCN7 produced average accuracy rates of 94.77% and 93.79%, respectively, showing that the proposed method can effectively improve the classification accuracy of remote sensing image scenes.

}, issn = {3080-180X}, doi = {https://doi.org/10.4208/JICS-2024-005}, url = {http://global-sci.org/intro/article_detail/jics/23880.html} }
TY - JOUR T1 - Remote Sensing Image Scene Classification Based on Deep Learning Feature Fusion AU - Wang , Liqi AU - Zhang , Cheng AU - Hou , Yuchao AU - Tan , Xiuhui AU - Cheng , Rong AU - Gao , Xiang AU - Bai , Yanping JO - Journal of Information and Computing Science VL - 1 SP - 65 EP - 80 PY - 2024 DA - 2024/03 SN - 19 DO - http://doi.org/10.4208/JICS-2024-005 UR - https://global-sci.org/intro/article_detail/jics/23880.html KW - Image classification, Convolutional Neural Network (CNN), Grey Level Co-occurrence Matrix (GLCM), Local Binary Patterns (LBP), migration learning, Support Vector Machine (SVM). AB -

In view that traditional manual feature extraction method cannot effectively extract the overall deep image information, a new method of scene classification based on deep learning feature fusion is proposed for remote sensing images. First, the Grey Level Co-occurrence Matrix (GLCM) and Local Binary Patterns (LBP) are used to extract the shallow information of texture features with relevant spatial characteristics and local texture features as well; second, the deep information of images is extracted by the AlexNet migration learning network, and a 256-dimensional fully connected layer is added as feature output while the last fully connected layer is removed; and the two features are adaptively integrated, then the remote sensing images are classified and identified by the Grid Search optimized Support Vector Machine (GS-SVM). The experimental results on 21 types of target data of the public dataset UC Merced and 7 types of target data of RSSCN7 produced average accuracy rates of 94.77% and 93.79%, respectively, showing that the proposed method can effectively improve the classification accuracy of remote sensing image scenes.

Wang , LiqiZhang , ChengHou , YuchaoTan , XiuhuiCheng , RongGao , Xiang and Bai , Yanping. (2024). Remote Sensing Image Scene Classification Based on Deep Learning Feature Fusion. Journal of Information and Computing Science. 19 (1). 65-80. doi:10.4208/JICS-2024-005
Copy to clipboard
BibteX RIS TXT
The citation has been copied to your clipboard