Authors:
Laura Arakaki
1
;
Leandro Silva
1
;
2
;
Matheus Silva
1
;
Bruno Melo
2
;
André Backes
3
;
Mauricio Escarpinati
2
and
João Mari
1
Affiliations:
1
Instituto de Ciências Exatas e Tecnológicas, Universidade Federal de Viçosa, Rio Paranaíba, Brazil
;
2
School of Computer Science, Federal University of Uberlândia, Uberlândia, Brazil
;
3
Department of Computing, Federal University of São Carlos, São Carlos-SP, Brazil
Keyword(s):
Cloud Segmentation, U-Net, Cloud-38, Convolutional Neural Networks, Remote Sensing.
Abstract:
Remote sensing images are an important resource for obtaining information for different types of applications. The occlusion of regions of interest by clouds is a common problem in this type of image. Thus, the objective of this work is to evaluate methods based on convolutional neural networks (CNNs) for cloud segmentation in satellite images. We compared three segmentation models, all of them based on the U-Net architecture with different backbones. The first considered backbone is simpler and consists of three contraction blocks followed by three expansion blocks. The second model has a backbone based on the VGG-16 CNN and the third one on the ResNet-18. The methods were tested using the Cloud-38 dataset, composed of 8400 satellite images in the training set and 9201 in the test set. The model considering the simplest backbone was trained from scratch, while the models with backbones based on VGG-16 and ResNet-18 were trained using fine-tuning on pre-trained models with ImageNet.
The results demonstrate that the tested models can segment the clouds in the images satisfactorily, reaching up to 97% accuracy on the validation set and 95% on the test set.
(More)