Authors:
Jocsan Ferreira
1
;
Leandro Silva
1
;
Mauricio Escarpinati
2
;
André Backes
3
and
João Mari
1
Affiliations:
1
Institute of Exacts and Technological Sciences, Federal University of Viçosa, Brazil
;
2
School of Computer Science, Federal University of Uberlandia, Brazil
;
3
Department of Computing, Federal University of São Carlos, Brazil
Keyword(s):
Cloud Segmentation, Satellite Images, Deep Learning.
Abstract:
This work evaluates methods based on deep learning to perform cloud segmentation in satellite images. Wwe compared several semantic segmentation architectures using different encoder structures. In this sense, we fine-tuned three architectures (U-Net, LinkNet, and PSPNet) with four pre-trained encoders (ResNet-50, VGG-16, MobileNet V2, and EfficientNet B2). The performance of the models was evaluated using the Cloud-38 dataset. The training process was carried out until the validation loss stabilized, according to the early stopping criterion, which provides a comparative analysis of the best models and training strategies to perform cloud segmentation in satellite images. We evaluated the performance using classic evaluation metrics, i.e., pixel accuracy, mean pixel accuracy, mean IoU, and frequency-based IoU. Results demonstrated that the tested models are capable of segmenting clouds with considerable performance, with emphasis on the following values: (i) 96.19% pixel accuracy fo
r LinkNet with VGG-16 encoder, (ii) 92.58% mean pixel accuracy for U-Net with MobileNet V2 encoder, (iii) 87.21% mean IoU for U-Net with VGG-16 encoder, and (iv) 92.89% frequency-based IoU for LinkNet with VGG-16 encoder. In short, the results of this study provide valuable information for developing satellite image analysis solutions in the context of precision agriculture.
(More)