Sparse Pixel Training of Convolutional Neural Networks for Land Cover Classification

Sparse Pixel Training of Convolutional Neural Networks for Land Cover Classification

Convolutional Neural Networks (CNN) have become the core of modern machine learning approaches. In addition to its inspiring interior design idea, the success of CNN depends mainly on two factors, the first is the availability of training data and the second is the computing power of the used device...

Full description

Bibliographic Details
Main Authors: Noureldin Laban, Bassam Abdellatif, Hala M. Ebeid, Howida A. Shedeed, Mohamed F. Tolba
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Satellite image
land cover classification
U-Net convolutional neural network
sparse training
pixel-based classification
Online Access:https://ieeexplore.ieee.org/document/9389718/

Internet

https://ieeexplore.ieee.org/document/9389718/

Similar Items