一种改进的全极化雷达影像分类  

An improved full polarization radar image classification method

作　　者：张继超[1] 邹勇 张永红[2] 崔东东 周沛希 李建飞 ZHANG Jichao;ZOU Yong;ZHANG Yonghong;CUI Dongdong;ZHOU Peixi;LI Jianfei(School of Geomatics,Liaoning Technical University,Fuxin,Liaoning 123000,China;Chinese Academy of Surveying and Mapping,Beijing 100036,China;China Energy Construction Group Liaoning Electric Power Survey and Design Institute Co.,Ltd.,Shenyang 110000,China;Liaoning Natural Resources Affairs Service Center,Liaoning Basic Institute of Surveying and Mapping,Jinzhou,Liaoning 121000,China)

机构地区：[1]辽宁工程技术大学测绘与地理科学学院,辽宁阜新123000 [2]中国测绘科学研究院,北京100036 [3]中国能源建设集团辽宁电力勘测设计院有限公司,沈阳110000 [4]辽宁省自然资源事务服务中心辽宁省基础测绘院,辽宁锦州121000

出　　处：《测绘科学》2021年第11期39-46,共8页Science of Surveying and Mapping

基　　金：国家863计划资助项目(2011AA120404);国家自然科学基金项目(41271430,40971225)。

摘　　要：针对面向对象的PolSAR影像分类中"维数灾难"的问题,该文提出过滤式与封装式联合的特征选择方法。该方法利用ReliefF算法和增益率评估模型作为特征过滤器剔除与分类相关性小的特征,采用CART算法进一步对剩余特征进行筛选,获得最优特征子集进行分类,并和Wishart监督分类、不进行ReliefF算法与增益率评估模型特征提取的分类方法进行比较。以GF-3影像数据为例进行实验,结果表明,本方法在时间成本和分类精度上较其他两种方法都有显著提高,验证了该算法在面向对象土地利用分类中的可行性。In order to solve the problem of"disaster of dimensionality"in object-oriented PolSAR image classification,a filtering and encapsulated feature selection method is proposed in this paper.In this method,ReliefF algorithm and gain rate evaluation model are used as feature filters to remove features with little correlation to classification,and then CART algorithm is used to further screen the remaining features to obtain the optimal feature subset for classification.finally,it is compared with the classification methods of Wishart supervised classification,no ReliefF algorithm and gain evaluation model feature extraction.Taking GF-3 image data as an example,the results show that the time cost and classification accuracy of this method are significantly higher than those of the other two methods,which verifies the feasibility of the algorithm in object-oriented land use classification.

关 键 词：极化分解 RELIEFF算法 增益率评估模型 特征选择 CART决策树分类 

分 类 号：P237[天文地球—摄影测量与遥感]