Performance of U-Net with ResNet-101 backbone using different combinations of input datasets.

<p>Note that multispectral, multispectral with NDVI, and multispectral with NDRE, models referred to as M1, M2, M3, respectively.</p>

Saved in:

Bibliographic Details
Main Author:	Guntaga Logavitool (20577175) (author)
Other Authors:	Teerayut Horanont (499185) (author), Aakash Thapa (20577178) (author), Kritchayan Intarat (20577181) (author), Kanok-on Wuttiwong (20577184) (author)
Published:	2025
Subjects:	Genetics Biotechnology Ecology Plant Biology Environmental Sciences not elsewhere classified Biological Sciences not elsewhere classified Information Systems not elsewhere classified severely infected fields patch extraction methods ndre &# 8212 improve training robustness experimental paddy fields cause yield losses bacterial panicle blight bacterial leaf blight including mean intersection disease inoculation techniques usually attacks rice accurate damage mapping 101 backbone trained uav multispectral imaging accurate mapping 101 backbone sheath blight rice disease mean recall disease extent rice diseases rice based suitable uav study introduces severity level scale detection regulatory authorities net architecture minimizing misclassification flowering stage findings demonstrate experiment concludes developed methodology broader application based datasets band combinations accurately allocating 16 %.
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items