Abstract
Support Vector Machine(SVM) classification method is a great prospective method for land cover remote sensing classification an present. An improved SVM classification method for land cover remote sensing classification was proposed in this paper. Firstly, analyzing existing preprocessing methods for hyperspectral image, and achieving a series of pre-process methods by taking HJ-1 Satellite HSI image of YongDing City in ZhangJiajie Country as study object. Secondly, analyzing the existing band extraction methods, and proposing a new method which to use subspace decomposition, adaptive band selection and spectral distance these three methods to implement band extraction. Thirdly, proposing improved SVM classification which is based on band extraction and making experiment. Finally, a comparison study was proposed to compare improved SVM classification and SVM classification without band extraction. The results indicate that the classification precision is improved from 78.77% to 82.30% and Kappa coefficient is up to 0.7425. The improved SVM method can improve the efficiency and accuracy of land cover remote sensing classification.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
