Deep Learning Model for Water/Ice/Land Classification Using Large-Scale Medium Resolution Satellite Images

Water/Ice/Land region classification is an important remote sensing tasks, which analyze the occurrence of water, ice on the earth surface. Common remote sensing practices such as thresholding, spectral analysis, and statistical approaches generally do not produce globally reliable classification re...

Full description

Saved in:
Bibliographic Details
Published inIGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium pp. 3884 - 3887
Main Authors Poliyapram, Vinayaraj, Imamoglu, Nevrez, Nakamura, Ryousuke
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.07.2019
Subjects
Artificial satellites
classification
CNN
Convolution
Deep learning
Earth
Ice
Image resolution
Landsat-8
Remote sensing
UNet
Online AccessGet full text

Cover

More Information
Summary:Water/Ice/Land region classification is an important remote sensing tasks, which analyze the occurrence of water, ice on the earth surface. Common remote sensing practices such as thresholding, spectral analysis, and statistical approaches generally do not produce globally reliable classification results. Even the robust deep learning models do not perform enough due to the limitation of ground truth available for training and the medium resolution of the Open satellite images. Therefore, in this research, we used a relatively easy method to generate ground truth for randomly selected locations around the globe. Then, we utilized a simplified variant of well-known UNet deep convolutional neural network (CNN) structure with a dilated CNN layers, skip connections and without any max-pooling layers. The proposed model shows better performance in medium resolution satellite images (Landsat-8) compared to state-of-the-art models such as UNet and DeepWaterMap applied on the same task.
ISSN:2153-7003
DOI:10.1109/IGARSS.2019.8900323