Scholarlink

Abstract <p>A method for processing a set of hyperspectral data in order to form a representative system of characteristics is proposed, and objects are classified using seven different systems of characteristics in narrow spectral intervals (30 nm) of the visible and near infrared spectral ranges based on measured spectral radiance coefficients (SRCs). It is shown that it is advisable to use systems of three characteristics for classifying 12 types of plants and camouflage coatings. At the same time, traditional vegetation indices often used to study plants do not provide sufficiently high accuracy of classifying objects of the selected types. Simultaneous use of two difference indices is more effective in comparison with them. However, the best classification accuracy is provided by systems of three characteristics, which are integrated SRC values in specially selected spectral ranges. It should be noted that when classifying objects into two classes, the classification accuracy is or close to 100<InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\%\)</EquationSource> <!--OptelIns2570046Borzov-m1--> </InlineEquation> in almost all cases.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Study of Hyperspectral Characteristic Systems for Classification of Natural and Anthropogenic Objects

  • 期刊论文

  • 发表日期：

    2025年8月1日

查看全文
  • S. M. Borzov,
  • E. S. Nezhevenko,
  • S. I. Orlov,
  • O. I. Potaturkin,
  • S. B. Uzilov

摘要

Abstract

A method for processing a set of hyperspectral data in order to form a representative system of characteristics is proposed, and objects are classified using seven different systems of characteristics in narrow spectral intervals (30 nm) of the visible and near infrared spectral ranges based on measured spectral radiance coefficients (SRCs). It is shown that it is advisable to use systems of three characteristics for classifying 12 types of plants and camouflage coatings. At the same time, traditional vegetation indices often used to study plants do not provide sufficiently high accuracy of classifying objects of the selected types. Simultaneous use of two difference indices is more effective in comparison with them. However, the best classification accuracy is provided by systems of three characteristics, which are integrated SRC values in specially selected spectral ranges. It should be noted that when classifying objects into two classes, the classification accuracy is or close to 100 \(\%\) in almost all cases.