Selection of spectral features for land cover type classification

作者：

Highlights：

• A selection scheme for spectral features has been proposed.

• Classification performance has been evaluated using four types of classifiers.

• True Skill Statistics, a unified performance metric, has been employed.

• Features have been ranked using Condorcet ranking.

• Even with only three features, a classification score of 81.84% has been obtained.

摘要

•A selection scheme for spectral features has been proposed.•Classification performance has been evaluated using four types of classifiers.•True Skill Statistics, a unified performance metric, has been employed.•Features have been ranked using Condorcet ranking.•Even with only three features, a classification score of 81.84% has been obtained.

论文关键词：Satellite imagery,Spectral features,Feature selection,Condorcet ranking,Land cover classification

论文评审过程：Received 28 June 2017, Revised 14 February 2018, Accepted 17 February 2018, Available online 19 February 2018, Version of Record 19 March 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.02.028