Multitemporal Relearning With Convolutional LSTM Models for Land Use Classification

Multitemporal Relearning With Convolutional LSTM Models for Land Use Classification

In this article, we present a novel hybrid framework, which integrates spatial–temporal semantic segmentation with postclassification relearning, for multitemporal land use and land cover (LULC) classification based on very high resolution (VHR) satellite imagery. To efficiently obtain op...

Full description

Bibliographic Details
Main Authors: Yue Zhu, Christian Geis, Emily So, Ying Jin
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Classification postprocessing (CPP)
con- volutional neural networks (CNNs)
deep learning (DL)
multi- temporal land use classification
relearning
Online Access:https://ieeexplore.ieee.org/document/9343734/

Internet

https://ieeexplore.ieee.org/document/9343734/

Similar Items