基于特征筛选和二级分类的极化SAR建筑提取算法

摘要

提出一种基于特征筛选和二级分类的建筑提取算法.该算法首先对极化SAR数据进行精致Lee滤波,获取多维极化特征和纹理特征构成原始特征集;然后将随机森林作为初级分类器评估各特征的重要性,依据重要性排名进行特征筛选;最后通过支持向量机对特征子集进行次级分类,并用邻域投票法将两级分类结果融合.AIRSAR极化数据实验结果表明,本算法可有效提高极化SAR建筑提取准确率.%In this work,a building extraction method,based on feature selection and two-level classification,for polarimetric SAR (POLSAR) image is proposed.Firstly,some polarimetric features and texture features are extracted from POLSAR data via refined Lee filter as the initial feature set.Then,by using the random forest as the primary classifier and evaluating features' importance meanwhile,the feature subset is obtained according to the importance rank.Secondary classification is made for the selected feature subset by the support vector machine,and the final result is achieved by combining the primary results and secondary results together using neighborhood voting.The experimental results on AIRSAR system demonstrate that the proposed method effectively improves the extraction accuracy.