测绘通报 ›› 2022, Vol. 0 ›› Issue (3): 70-75.doi: 10.13474/j.cnki.11-2246.2022.0080

• 学术研究 • 上一篇    下一篇

基于随机森林特征优选的冬小麦分类方法

冯志立1, 肖锋2, 卢小平1, 郝波3, 王如意3, 朱睿3   

  1. 1. 河南理工大学自然资源部矿山时空信息与生态修复重点实验室, 河南 焦作 454003;
    2. 河南测绘工程院, 河南 郑州 450003;
    3. 郑州智象测绘信息技术有限公司, 河南 郑州 450003
  • 收稿日期:2021-03-29 出版日期:2022-03-25 发布日期:2022-04-01
  • 通讯作者: 卢小平。E-mail:hpuluxp@163.com
  • 作者简介:冯志立(1997-),男,硕士生,研究方向为摄影测量与遥感技术。E-mail:1619448670@qq.com
  • 基金资助:
    国家重点研发计划重点专项(2016YFC0803103)

Winter wheat classification method based on feature optimization of random forest

FENG Zhili1, XIAO Feng2, LU Xiaoping1, HAO Bo3, WANG Ruyi3, ZHU Rui3   

  1. 1. Key Laboratory of Mine Temporal and Spatial Information and Ecological Restoration, Ministry of Natural Resources, Henan University of Technology, Jiaozuo 454003, China;
    2. Henan Institute of Surveying and Mapping Engineering, Zhengzhou 450003, China;
    3. Zhengzhou Zhixiang Surveying and Mapping Information Technology Co., Ltd., Zhengzhou 450003, China
  • Received:2021-03-29 Online:2022-03-25 Published:2022-04-01

摘要: 本文基于多时相Landsat 8 OLI数据,进行综合光谱、植被指数的特征提取与特征选择的方法研究。通过分析光谱与植被指数特征时序变化,提取最佳时相光谱,构建小麦提取特征;采用基于重要性与Pearson相关性的随机森林特征选择算法优选特征。结果表明:利用优选特征分类时,总体精度为89.78%,小麦分类精度为98.33%;与优选前特征的分类结果相比,精度分别提高了2.96%、2.55%;基于重要性与Pearson相关性的随机森林特征选择提高了分类精度和分类器工作效率。

关键词: 特征选择;随机森林;Pearson相关性;冬小麦

Abstract: Based on the multi-temporal Landsat 8 OLI data,this paper conducts research on the feature extraction and feature selection methods of comprehensive spectral features and vegetation index features.By analyzing the temporal changes of the spectral and vegetation index features,the optimal time-phase spectrum is extracted,and the wheat extraction features are constructed.A random forest feature selection algorithm based on importance and Pearson correlation is used to select features and classify them.The results show that:when using the selected features to classify,the overall accuracy of classification is 89.78%,and the classification accuracy of wheat is 98.33%.Compared with the classification results of the features before optimization,the classification accuracy is increased by 2.96% and 2.55%,respectively.Random forest feature selection based on importance and relevance not only improves the classification accuracy,but also improves the efficiency of the classifier.

Key words: feature selection;random forest;Pearson correlation;winter wheat extraction

中图分类号: