吉林大学学报(信息科学版) ›› 2020, Vol. 38 ›› Issue (2): 185-191.

• • 上一篇    下一篇

基于 CatBoost 算法的面向对象土地利用分类

姜琦刚1 ,杨秀艳 1 ,杨长保 1 ,赵振贺 2
  

  1. 1. 吉林大学 地球探测科学与技术学院,长春 130026; 2. 北方自动控制技术研究所,太原 030006
  • 收稿日期:2019-05-05 出版日期:2020-03-24 发布日期:2020-05-20
  • 作者简介:姜琦刚(1964— ),男,江苏江阴人,吉林大学教授,博士生导师,主要从事 GIS 与遥感地学环境研究,(Tel)86-17696103986(E-mail)jiangqigang@ jlu. edu. cn。
  • 基金资助:
    辽吉黑区自然资源更新调查基金资助项目(3S2170124423)

Object-Oriented Land Use Classification Based on CatBoost Algorithm

JIANG Qigang 1 ,YANG Xiuyan 1 ,YANG Changbao 1 ,ZHAO Zhenhe 2   

  1. 1. College of Geo-Exploration Science and Technology,Jilin University,Changchun 130026,China;
    2. North Automatic Control Technology Institute,Taiyuan 030006,China
  • Received:2019-05-05 Online:2020-03-24 Published:2020-05-20

摘要: 为实现较高层次的遥感影像分类及有效去除高维特征的信息冗余,以 Sentinel-2 遥感影像为数据源,应
用 CatBoost 算法对龙江县进行了面向对象的土地利用分类。利用 CatBoost 算法对全部特征集进行降维,分别使
用 CatBoost、RF(Random Forest)和 AdaBoost 算法进行土地利用分类并对分类结果进行对比。研究结果表明,
CatBoost、RF 和 AdaBoost 算法的 Kappa 系数均在 0. 77 以上,且 CatBoost 算法的 Kappa 系数高达 0. 911 4。因此
CatBoost分类法是土地利用分类的有效方法,为土地类型的划分提供了快捷可行的方法。

关键词:  , Sentinel-2 影像, CatBoost 算法, 土地利用分类, 面向对象

Abstract:  Recently,land use classification based on machine learning algorithm and remote sensing data has
been a hot topic for scholars at home and abroad. In this study,Sentinel-2 remote sensing image is used as the
data source to classify land use of Longjiang County. In order to achieve high level remote sensing image
classification and effectively remove the information redundancy of high dimensional features,the CatBoost
algorithm is used to reduce the dimension of all feature sets. The feature set is used to train RF algorithm and
AdaBoost algorithm. The results show that the Kappa coefficient of CatBoost,RF and AdaBoost algorithm are all
above 0. 77,and the Kappa coefficient of CatBoost algorithm is up to 0. 911 4; CatBoost classification is an
effective method of land use classification,which provides a fast and feasible method for the classification of land
types.

Key words: Sentinel-2 image, CatBoost algorithm, land use classification, object-oriented

中图分类号: 

  •