A cloud detection algorithm for satellite imagery based on deep learning

Jeppesen, Jesper; Jacobsen, Rune Hylsberg; Inceoglu, Fadil; Toftegaard, Thomas Skjødeberg

doi:10.1016/j.rse.2019.03.039

Cited by 309 publications

(197 citation statements)

References 32 publications

Supporting

Mentioning

195

Contrasting

Unclassified

Order By: Relevance

“…Among the classification methods that use spatial features of images we mention [30] (Markov chains), [31] (Discriminant Analysis), [32] (relying on PCANet and SVM). We also mention the special case of Artificial Intelligence Deep Learning algorithms (e.g., [6,23]).…”

Section: Linear Discriminant Analysis (Lda) It Applies the Bayes Rulmentioning

confidence: 99%

See 1 more Smart Citation

Cloud Detection: An Assessment Study from the ESA Round Robin Exercise for PROBA-V

Amato

Antoniadis

Carfora

2020

Sensors

View full text Add to dashboard Cite

A Round Robin exercise was implemented by ESA to compare different classification methods in detecting clouds from images taken by the PROBA-V sensor. A high-quality dataset of 1350 reflectances and Clear/Cloudy corresponding labels had been prepared by ESA in the framework of the exercise. Motivated by both the experience acquired by one of the authors in this exercise and the availability of such a reliable annotated dataset, we present a full assessment of the methodology proposed therein. Our objective is also to investigate specific issues related to cloud detection when remotely sensed images comprise only a few spectral bands in the visible and near-infrared. For this purpose, we consider a bunch of well-known classification methods. First, we demonstrate the feasibility of using a training dataset semi-automatically obtained from other accurate algorithms. In addition, we investigate the effect of ancillary information, e.g., surface type or climate, on accuracy. Then we compare the different classification methods using the same training dataset under different configurations. We also perform a consensus analysis aimed at estimating the degree of mutual agreement among classification methods in detecting Clear or Cloudy sky conditions.

show abstract

Section: Linear Discriminant Analysis (Lda) It Applies the Bayes Rulmentioning

confidence: 99%

“…It is mainly the case of deep learning algorithms. In this respect we mention [6] who use the results of an algorithm (CFMask [3]) to train their deep RS-Net model for Landsat 8 images, and [7] based on AVIRIS cloud mask. Massive use of such a silver standard dataset for cloud detection was pioneered in [8] in our knowledge.…”

Section: Introductionmentioning

confidence: 99%

Cloud Detection: An Assessment Study from the ESA Round Robin Exercise for PROBA-V

Amato

Antoniadis

Carfora

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…The dataset developed for this study has been available from the USGS since 2017. Another study [28] that trained a classifier using the SPARCS data and evaluated it using the Biome dataset provides a better comparison, although again not using the water and snow/ice classes. That classifier performed at 91% accuracy, which is quite similar to the results reported here.…”

Section: Appendix A2 Comparison With Biome Datasetmentioning

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

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

“…Sun et al [ 20 ] designed a U-Net-based network architecture DRRNet, replacing simple skip connections with encoder adaptive blocks, and using densely connected fusion blocks in the decoder. Jeppesen et al [ 21 ] proposed a U-net-based remote sensing network (RS-Net) for detecting clouds in optical satellite images. Liu et al [ 22 ] proposed a liver CT sequence image segmentation algorithm GIU-Net, which combines an improved U-Net neural network model with graph cutting.…”

Section: Introductionmentioning

confidence: 99%

An Ore Image Segmentation Method Based on RDU-Net Model

Xiao

Liu

et al. 2020

Sensors

View full text Add to dashboard Cite

The ore fragment size on the conveyor belt of concentrators is not only the main index to verify the crushing process, but also affects the production efficiency, operation cost and even production safety of the mine. In order to get the size of ore fragments on the conveyor belt, the image segmentation method is a convenient and fast choice. However, due to the influence of dust, light and uneven color and texture, the traditional ore image segmentation methods are prone to oversegmentation and undersegmentation. In order to solve these problems, this paper proposes an ore image segmentation model called RDU-Net (R: residual connection; DU: DUNet), which combines the residual structure of convolutional neural network with DUNet model, greatly improving the accuracy of image segmentation. RDU-Net can adaptively adjust the receptive field according to the size and shape of different ore fragments, capture the ore edge of different shape and size, and realize the accurate segmentation of ore image. The experimental results show that compared with other U-Net and DUNet, the RDU-Net has significantly improved segmentation accuracy, and has better generalization ability, which can fully meet the requirements of ore fragment size detection in the concentrator.

show abstract

A cloud detection algorithm for satellite imagery based on deep learning

Cited by 309 publications

References 32 publications

Cloud Detection: An Assessment Study from the ESA Round Robin Exercise for PROBA-V

Cloud Detection: An Assessment Study from the ESA Round Robin Exercise for PROBA-V

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

An Ore Image Segmentation Method Based on RDU-Net Model

Contact Info

Product

Resources

About