摘要
提出一种极限学习机(ELM)和支持向量机(SVM)相融合的遥感图像分类模式.选取ELM为基础分类器,以SVM来修正改善分类效率.仿真实验结果表明,该算法不仅具有较高的分类精度,而且消除一些训练样本标签对分类的负面影响.结合ALOS/PALSAR、PSM图像与SVM、ANN(Artificial Neural Network)方法进行对比分析,发现该方法鲁棒性较好.
Data classification is a key step of the remote sensing data into thematic map information. Find a good classification method and improve the accuracy of data processing are highly challenging problems. In this paper, we propose a fusion classification model based on extreme learning machine （ELM） and support vector machine（SVM） for remote sensing image classification. Choose ELM based classifier and correction to improve the classification efficiency by SVM. Simulation experiment results show that the algorithm not only has higher classification accuracy,and eliminate some of the training sample tag on the negative impact for classification. Combining ALOS/PALSAR, PSM images, comparative analysis with SVM and artificial neural network（ANN）, show the robustness of the method.
作者
古丽娜孜.艾力木江
乎西旦.居马洪
孙铁利
梁义
Gulnaz Alimjan Hurxida Jumahun SUN Tie-li LIANG Yi(School of Electronics and In{ormation Engineering, Yili Normal University, Yining 835000, China School of Geographical Science, Northeast Normal University, Changchun 130024 ,China School of Computer Science and In{ormation Technology, Northeast Normal University, Changchun 130117, China)
出处
《东北师大学报（自然科学版）》
CAS
CSCD
北大核心
2017年第1期53-61,共9页
Journal of Northeast Normal University(Natural Science Edition)
基金
国家自然科学基金资助项目(61663045)
新疆高校科研计划重点研究项目(XJEDU2014I043)
伊犁师范学院重点项目(2016YSZD04)
关键词
支持向量机
遥感数据
极限学习机
分类精度
support vector machines
remote sensing data
extreme learning machine
classification accuracy
