Hyperspectral Image Classification Using a Hybrid 3D-2D Convolutional Neural Networks

Due to the unique feature of the three-dimensional convolution neural network, it is used in image classification. There are some problems such as noise, lack of labeled samples, the tendency to overfitting, a lack of extraction of spectral and spatial features, which has challenged the classificati...

Full beskrivning

Bibliografiska uppgifter

Huvudupphov:	Saeed Ghaderizadeh, Dariush Abbasi-Moghadam, Alireza Sharifi, Na Zhao, Aqil Tariq
Materialtyp:	Artigo
Språk:	Inglês
Utgiven:	IEEE 2021-01-01
Serie:	IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Ämnen:	Convolutional neural network (CNN) deep learning hyperspectral image (HSI) classification spectral-spatial features
Länkar:	https://ieeexplore.ieee.org/document/9495233/
Taggar:	Lägg till en tagg Inga taggar, Lägg till första taggen!