CDnet: CNN-Based Cloud Detection for Remote Sensing Imagery

Yang, Jingyu; Guo, Jianhua; Yue, Huanjing; Liu, Zhiheng; Hu, Haofeng; Li, Kun

doi:10.1109/tgrs.2019.2904868

Cited by 141 publications

(77 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Dilated convolutions [39] can enlarge the receptive field using fewer layers while retaining feature density. This is a strategy used successfully on similar classification problems discriminating only clouds and cloud-shadows from clear-sky pixels [24,26]. However, early trials in this study with dilated convolutions produced unacceptable outputs with a structured speckle pattern when discriminating between water and shadows from both terrain and clouds; future work may be able to overcome this issue.…”

Section: Discussionmentioning

confidence: 92%

See 1 more Smart Citation

High-Quality Cloud Masking of Landsat 8 Imagery Using Convolutional Neural Networks

Hughes

Kennedy

2019

Remote Sensing

View full text Add to dashboard Cite

The Landsat record represents an amazing resource for discovering land-cover changes and monitoring the Earth’s surface. However, making the most use of the available data, especially for automated applications ingesting thousands of images without human intervention, requires a robust screening of cloud and cloud-shadow, which contaminate clear views of the land surface. We constructed a deep convolutional neural network (CNN) model to semantically segment Landsat 8 images into regions labeled clear-sky, clouds, cloud-shadow, water, and snow/ice. For training, we constructed a global, hand-labeled dataset of Landsat 8 imagery; this labor-intensive process resulted in the uniquely high-quality dataset needed for the creation of a high-quality model. The CNN model achieves results on par with the ability of human interpreters, with a total accuracy of 97.1%, omitting only 3.5% of cloud pixels and 4.8% of cloud shadow pixels, which is seven to eight times fewer missed pixels than the masks distributed with the imagery. By harnessing the power of advanced tensor processing units, the classification of full images is I/O bound, making this approach a feasible method to generate masks for the entire Landsat 8 archive.

show abstract

Section: Discussionmentioning

confidence: 92%

“…Other deep learning networks have been tested against the Biome dataset and achieve overall accuracies of 94% [27], 95% (Li) [24], and 96.5% [26]. Each of these algorithms is focused on the clouds and cloud-shadow identification problem and do not produce classifications for water or snow/ice.…”

Section: Appendix Amentioning

confidence: 99%

High-Quality Cloud Masking of Landsat 8 Imagery Using Convolutional Neural Networks

Hughes

Kennedy

2019

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Fully convolutional neural networks (FCNN) [15], most of them based on the U-Net architecture [16], produce very accurate results and have the advantage that they can be applied to images of arbitrary size with a fast inference time. Works such as Jeppesen et al [17], Mohajerani and Sahedi [18], [19], Li et al [20], or Yang et al [21] tackle cloud detection in Landsat-8 using Fully Convolutional Neural Networks trained in publicly available manually annotated datasets. They all show very high cloud detection accuracy outperforming the operational Landsat-8 cloud detection algorithm, FMask [22].…”

Section: A Transfer Learning For Cloud Detectionmentioning

confidence: 99%

Cross-Sensor Adversarial Domain Adaptation of Landsat-8 and Proba-V Images for Cloud Detection

Mateo-García

Laparra

López-Puigdollers

et al. 2021

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

The number of Earth observation satellites carrying optical sensors with similar characteristics is constantly growing. Despite their similarities and the potential synergies among them, derived satellite products are often developed for each sensor independently. Differences in retrieved radiances lead to significant drops in accuracy, which hampers knowledge and information sharing across sensors. This is particularly harmful for machine learning algorithms, since gathering new ground truth data to train models for each sensor is costly and requires experienced manpower. In this work, we propose a domain adaptation transformation to reduce the statistical differences between images of two satellite sensors in order to boost the performance of transfer learning models. The proposed methodology is based on the Cycle Consistent Generative Adversarial Domain Adaptation (CyCADA) framework that trains the transformation model in an unpaired manner. In particular, Landsat-8 and Proba-V satellites, which present different but compatible spatio-spectral characteristics, are used to illustrate the method. The obtained transformation significantly reduces differences between the image datasets while preserving the spatial and spectral information of adapted images, which is hence useful for any general purpose cross-sensor application. In addition, the training of the proposed adversarial domain adaptation model can be modified to improve the performance in a specific remote sensing application, such as cloud detection, by including a dedicated term in the cost function. Results show that, when the proposed transformation is applied, cloud detection models trained in Landsat-8 data increase cloud detection accuracy in Proba-V.

show abstract

“…The current cloudy image, a mask map of clouds and cloud shadows, and a cloudless recent image of the same area were prepared in advance as the input. The mask map, which was a binary map where 1 represented the clean pixels (black), and 0 represents the clouds and cloud shadows (white), can be generated from recent CNN-based detection methods [43][44][45] or manual work. When an automatic algorithm was applied, the recall rate should be set high to detect most of the clouds; however, a relatively lower precision score will not affect the performance of the cloud removal task as a large number of clean pixels remain to train the cloud removal network.…”

Section: The Overall Frameworkmentioning

confidence: 99%

Gated Convolutional Networks for Cloud Removal From Bi-Temporal Remote Sensing Images

Dai

Zhang

2020

Remote Sensing

View full text Add to dashboard Cite

Pixels of clouds and cloud shadows in a remote sensing image impact image quality, image interpretation, and subsequent applications. In this paper, we propose a novel cloud removal method based on deep learning that automatically reconstructs the invalid pixels with the auxiliary information from multi-temporal images. Our method’s innovation lies in its feature extraction and loss functions, which reside in a novel gated convolutional network (GCN) instead of a series of common convolutions. It takes the current cloudy image, a recent cloudless image, and the mask of clouds as input, without any requirements of external training samples, to realize a self-training process with clean pixels in the bi-temporal images as natural training samples. In our feature extraction, gated convolutional layers, for the first time, are introduced to discriminate cloudy pixels from clean pixels, which make up for a common convolution layer’s lack of the ability to discriminate. Our multi-level constrained joint loss function, which consists of an image-level loss, a feature-level loss, and a total variation loss, can achieve local and global consistency both in shallow and deep levels of features. The total variation loss is introduced into the deep-learning-based cloud removal task for the first time to eliminate the color and texture discontinuity around cloud outlines needing repair. On the WHU cloud dataset with diverse land cover scenes and different imaging conditions, our experimental results demonstrated that our method consistently reconstructed the cloud and cloud shadow pixels in various remote sensing images and outperformed several mainstream deep-learning-based methods and a conventional method for every indicator by a large margin.

show abstract

CDnet: CNN-Based Cloud Detection for Remote Sensing Imagery

Cited by 141 publications

References 50 publications

High-Quality Cloud Masking of Landsat 8 Imagery Using Convolutional Neural Networks

High-Quality Cloud Masking of Landsat 8 Imagery Using Convolutional Neural Networks

Cross-Sensor Adversarial Domain Adaptation of Landsat-8 and Proba-V Images for Cloud Detection

Gated Convolutional Networks for Cloud Removal From Bi-Temporal Remote Sensing Images

Contact Info

Product

Resources

About