Classification of Hyperspectral Images with Different Methods of Training Set Formation

S. M. Borzov, O. I. Potaturkin

Результат исследования: Научные публикации в периодических изданияхстатья

2 Цитирования (Scopus)

Аннотация

The efficiency of the methods of controlled spectral and spectral-spatial classification of vegetation types on the basis of hyperspectral pictures with different methods of training set formation is evaluated. The dependence of the classification accuracy on the number of spectral features is considered. It is shown that simultaneous allowance for spatial and spectral features ensures highquality classification of similarly looking types of vegetation by merely using training sets with the maximum degree of the pixel distribution over the image.

Язык оригиналаанглийский
Страницы (с-по)76-82
Число страниц7
ЖурналOptoelectronics, Instrumentation and Data Processing
Том54
Номер выпуска1
DOI
СостояниеОпубликовано - 1 янв 2018

Fingerprint Подробные сведения о темах исследования «Classification of Hyperspectral Images with Different Methods of Training Set Formation». Вместе они формируют уникальный семантический отпечаток (fingerprint).

  • Цитировать