A novel framework combining band selection algorithm and improved 3D prototypical network for tree species classification using airborne hyperspectral images

•A novel framework for obtaining optimal classification results using airborne HSI.•The FAST 3D-CNN P-Net method can improve the feature extraction process.•The CNN-based band selection algorithm performs better in dimensionality reduction.•The proposed framework exhibits optimal performance on seve...

Full description

Saved in:

Bibliographic Details
Published in:	Computers and electronics in agriculture Vol. 219; p. 108813
Main Authors:	Wu, Jing, Chen, Long, Wang, Jiaqi, Li, Yunfan, Chen, Erxue, Zhang, Xiaoli
Format:	Journal Article
Language:	English
Published:	Elsevier B.V 01.04.2024
Subjects:	agriculture Airborne hyperspectral images algorithms Band selection Convolutional neural network data collection electronics forest trees forests inventories Multiple tree species classification Prototypical network Prototypical network Band selection Multiple tree species classification Convolutional neural network Airborne hyperspectral images
ISSN:	0168-1699, 1872-7107
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Be the first to leave a comment!