This paper proposes a framework to train an artifact-free thin cloud removal model using Generative Adversarial Nets (GANs) with thick cloud masks. Satellite images are useful in various applications, however their exploitation is often limited by a presence of clouds. The proposed model can safely remove thin clouds for cloudy images while preserving thick clouds areas without creating undesired artifacts. In order to train the model, we propose a following framework divided in three blocks: generation of thick cloud masks for training images based on texture and spectrum analysis, selection of input-target couples of training images and training of the model using the GAN framework. The use of cloud masks for the training images allows the training of a model for clouds removal, robust to artifact generation in areas with thick clouds. Experimental results show that our model can actually avoid the generation of artifacts, and outperforms the conventional method in terms of SSIM index in testing.

Toizumi, T., Zini, S., Sagi, K., Kaneko, E., Tsukada, M., Schettini, R. (2019). Artifact-Free Thin Cloud Removal Using Gans. In Proceedings - International Conference on Image Processing, ICIP (pp.3596-3600). IEEE Computer Society [10.1109/ICIP.2019.8803652].

Artifact-Free Thin Cloud Removal Using Gans

Zini, Simone;Schettini, Raimondo
2019

Abstract

This paper proposes a framework to train an artifact-free thin cloud removal model using Generative Adversarial Nets (GANs) with thick cloud masks. Satellite images are useful in various applications, however their exploitation is often limited by a presence of clouds. The proposed model can safely remove thin clouds for cloudy images while preserving thick clouds areas without creating undesired artifacts. In order to train the model, we propose a following framework divided in three blocks: generation of thick cloud masks for training images based on texture and spectrum analysis, selection of input-target couples of training images and training of the model using the GAN framework. The use of cloud masks for the training images allows the training of a model for clouds removal, robust to artifact generation in areas with thick clouds. Experimental results show that our model can actually avoid the generation of artifacts, and outperforms the conventional method in terms of SSIM index in testing.
poster + paper
Cloud removal.; Generative adversarial nets; Multi-spectral image; Remote sensing;
Remote sensing, Generative adversarial nets, Multi-spectral image, Cloud removal.
English
26th IEEE International Conference on Image Processing, ICIP 2019
2019
Proceedings - International Conference on Image Processing, ICIP
9781538662496
2019
2019-
3596
3600
8803652
none
Toizumi, T., Zini, S., Sagi, K., Kaneko, E., Tsukada, M., Schettini, R. (2019). Artifact-Free Thin Cloud Removal Using Gans. In Proceedings - International Conference on Image Processing, ICIP (pp.3596-3600). IEEE Computer Society [10.1109/ICIP.2019.8803652].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/254408
Citazioni
  • Scopus 8
  • ???jsp.display-item.citation.isi??? 7
Social impact