Classification of Remote Sensing Images Based on Band Selection and Multi-mode Feature Fusion

As feature data in multimodal remote sensing images belong to multiple modes and are complementary to each other, the traditional method of single-mode data analysis and processing cannot effectively fuse the data of different modes and express the correlation between different modes. In order to solve this problem, make better fusion of different modal data and the relationship between the said features, this paper proposes a fusion method of multiple modal spectral characteristics and radar remote sensing imageaccording to the spatial dimension in the form of a vector or matrix for effective integration, by training the SVM model. Experimental results show that the method based on band selection and multi-mode feature fusion can effectively improve the robustness of remote sensing image features. Compared with other methods, the fusion method can achieve higher classification accuracy and better classification effect.

[1]  Huan Liu,et al.  Feature Selection for High-Dimensional Data: A Fast Correlation-Based Filter Solution , 2003, ICML.

[2]  Hassan Ghassemian,et al.  Fusion of MS and PAN Images Preserving Spectral Quality , 2015, IEEE Geoscience and Remote Sensing Letters.

[3]  Philomina Simon,et al.  A Bi-level IHS Transform for Fusing Panchromatic and Multispectral Images , 2013, PReMI.

[4]  T. J. Majumdar,et al.  ERS-2 SAR and IRS-1C LISS III data fusion: A PCA approach to improve remote sensing based geological interpretation , 2007 .

[5]  Xi Chen,et al.  An optimized K-means clustering algorithm based on BC-QPSO for remote sensing image , 2017, 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[6]  Yi Ma,et al.  Coastal wetland classification based on high resolution SAR and optical image fusion , 2016, IGARSS.

[7]  Khairul Munadi,et al.  Study on the spectral quality preservation derived from multisensor image fusion techniques between JERS-1 SAR and Landsat TM data , 2003, IGARSS 2003. 2003 IEEE International Geoscience and Remote Sensing Symposium. Proceedings (IEEE Cat. No.03CH37477).

[8]  C. Dupas,et al.  SAR AND LANDSAT TM IMAGE FUSION FOR LAND COVER CLASSIFICATION IN THE BRAZILIAN ATLANTIC FOREST DOMAIN , 2000 .

[9]  R. Chandrakanth,et al.  Fusion of High Resolution Satellite SAR and Optical Images , 2011, 2011 International Workshop on Multi-Platform/Multi-Sensor Remote Sensing and Mapping.

[10]  Ming Zhao,et al.  A Robust Delaunay Triangulation Matching for Multispectral/Multidate Remote Sensing Image Registration , 2015, IEEE Geoscience and Remote Sensing Letters.

[11]  Richard R. Forster,et al.  Fusion of hyperspectral and radar data using the IHS transformation to enhance urban surface features , 2003 .

[12]  Xiaodong Yu,et al.  Remote sensing image classification based on dynamic Co-evolutionary parameter optimization of SVM , 2018, J. Intell. Fuzzy Syst..

[13]  Xiaodong Yu,et al.  PTL-CFS based deep convolutional neural network model for remote sensing classification , 2018, Computing.

[14]  Liu Bin,et al.  Multispectral Image Fusion Based on HSV and Red-black Wavelet Transform , 2012 .

[15]  Parvaneh Saeedi,et al.  Robust Weighted Graph Transformation Matching for Rigid and Nonrigid Image Registration , 2012, IEEE Transactions on Image Processing.

[16]  Chengming Zhang,et al.  The Classification Method of Multi-spectral Remote Sensing Images Based on Self-adaptive Minimum Distance Adjustment , 2012, CCTA.

[17]  D. Amarsaikhan,et al.  Advanced Classification of Lands at TM and Envisat Images of Mongolia , 2013 .

[18]  Javier Marcello,et al.  Evaluation of Spatial and Spectral Effectiveness of Pixel-Level Fusion Techniques , 2013, IEEE Geoscience and Remote Sensing Letters.