欢迎访问林业科学,今天是

林业科学 ›› 2018, Vol. 54 ›› Issue (8): 88-98.doi: 10.11707/j.1001-7488.20180810

• 论文与研究报告 • 上一篇    下一篇

基于改进转换分离度特征选择规则的土地覆盖分类比较

张莹1,2, 张晓丽1,3,4, 李宏志1,3,4, 黎良财1,3,4   

  1. 1. 北京林业大学 北京 100083;
    2. 中国交通通信信息中心 北京 100011;
    3. 北京林业大学精准林业北京市重点实验室 北京 100083;
    4. 北京林业大学省部共建森林培育与保护重点实验室 北京 100083
  • 收稿日期:2017-06-08 修回日期:2018-05-22 出版日期:2018-08-25 发布日期:2018-08-18
  • 基金资助:
    国家"863"高新技术研究与发展计划项目(2012AA102001-5)。

A Comparison of Landcover Classification Based on the Improved Transformed Divergence Analysis

Zhang Ying1,2, Zhang Xiaoli1,3,4, Li Hongzhi1,3,4, Li Liangcai1,3,4   

  1. 1. Beijing Forestry University Beijing 100083;
    2. China Transport Telecommunications & Information Center Beijing 100011;
    3. Beijing Key Laboratory of Precision Forestry, Beijing Forestry University Beijing 100083;
    4. Key Laboratory for Silviculture and Conservation of Ministry of Education, Beijing Forestry University Beijing 100083
  • Received:2017-06-08 Revised:2018-05-22 Online:2018-08-25 Published:2018-08-18

摘要: [目的]提出一种考虑样本概率的可分离距离与波段相关系数结合的特征选择方法,以提高土地覆盖分类的正确率。[方法]以中亚热带区域的福建省将乐县为研究区,从Landsat-8 OLI影像中获取植被指数和纹理特征,利用改进方法和传统方法选择出最佳特征,通过比较最佳特征参与下植被类别的可分离值,判别2种方法在特征选择时的准确度;采用支持向量机分类方法(SVM)分别对原始光谱和改进方法选择的最佳特征进行分类,探索最佳植被指数和纹理特征在提高地区土地覆盖分类中的作用。[结果]改进可分离性判据在避免选择冗余波段的同时,能准确选择出具有更高区分度的特征;对于植被指数和纹理特征,单一特征均不能使植被类别可分性达到最大,而2个特征组合可明显提高植被类别的可分性;比值植被指数及小窗口的反差、协方差和二阶矩纹理特征比同窗口其他纹理对提高研究区植被分类精度具有更重要的价值;植被指数加入原始光谱并没有明显提高研究区的整体分类精度,而纹理特征与原始光谱结合对提高植被分类精度相当有价值,最佳植被指数、最佳纹理特征和原始光谱结合可取得最佳分类结果,整体分类精度提高7.41%,Kappa系数(OKA)提高8.5%。[结论]基于改进转换分离度特征选择规则的土地覆盖分类方法能平衡所有类别间的可分性,较好避免选择相互冗余的特征,从而保证选择出具有较高的多类别可分性且冗余较小的特征,提高类别分类的正确率。

关键词: OLI影像, 最佳植被指数, 最佳纹理特征, 改进可分离分析, 支持向量机分类

Abstract: [Objective] A feature selection method is proposed for improving the accuracy of land cover classification, which considers the combination of separable distance of sample probability and band correlation coefficient.[Method] The several derived vegetation indices and texture characteristics used were extracted from Landsat-8 OLI data in Jiangle county of Fujian Province. Then the optimal features were identified by traditional feature selection method and improved method, respectively. By comparing the separable values of vegetation types based on the best features, the accuracy of feature selection based on two methods was determined. The different scenarios based on primary spectral data, selected vegetation indices and textural images were classified by support vector machine classification algorithm to explore selected features on improving the land cover classes.[Result] The improved separability method can more accurately select the features with higher discrimination while avoiding the selection of redundant bands. For vegetation index and texture features, a single feature cannot maximize the separability of vegetation classes while two feature combinations can significantly improve vegetation separability. Compared with the other texture features in the same window sizes, the ratio vegetation index and the texture features based on contrast, variance and the second moment with small window sizes had a better performance in improving the vegetation classification accuracy. The combinations of optimal vegetation indices as extra bands into OLI multi-spectral bands did not significantly improve overall classification performance (OCA). The combination of textural images and primary spectral bands improved the OCA, which was especially valuable for improving vegetation classification accuracy. The combination of both vegetation indices and textural images with multi-spectral bands provided the best classification performance. The overall classification accuracy and overall Kappa coefficient (OKA) were increased by 7.41% and 8.5%, respectively.[Conclusion] The feature selection method based on improved transformation divergence can balance the separability among all classes, better to avoid redundant features. So, the selected features by the improved method can increase accuracy of specified classes in the study area.

Key words: OLI remote sensing image, optimal vegetation index, optimal texture feature, improved divergence analysis, support vector machine (SVM) classification

中图分类号: