Cloud Detection Method Research Articles

CURRENT TECHNOLOGIES OF AUTOMATIC CLOUD MAPPING

The article discusses the experience of using machine learning methods (gradient boosting, deep neural networks) for cloud detection and mapping on the example of the Perm Region using high spatial resolution images in visible range (Sentinel-2). With existing cloud detection algorithms (Fmask, Sen2Cor) Comparisons are made, as well as with the basic cloud mask provided with Sentinel-2 images. For automatic production of cartographic data Python script in the ArcGIS environment was cones fad.

An Effective Cloud Detection Method for Gaofen-5 Images via Deep Learning

Recent developments in hyperspectral satellites have dramatically promoted the wide application of large-scale quantitative remote sensing. As an essential part of preprocessing, cloud detection is of great significance for subsequent quantitative analysis. For Gaofen-5 (GF-5) data producers, the daily cloud detection of hundreds of scenes is a challenging task. Traditional cloud detection methods cannot meet the strict demands of large-scale data production, especially for GF-5 satellites, which have massive data volumes. Deep learning technology, however, is able to perform cloud detection efficiently for massive repositories of satellite data and can even dramatically speed up processing by utilizing thumbnails. Inspired by the outstanding learning capability of convolutional neural networks (CNNs) for feature extraction, we propose a new dual-branch CNN architecture for cloud segmentation for GF-5 preview RGB images, termed a multiscale fusion gated network (MFGNet), which introduces pyramid pooling attention and spatial attention to extract both shallow and deep information. In addition, a new gated multilevel feature fusion module is also employed to fuse features at different depths and scales to generate pixelwise cloud segmentation results. The proposed model is extensively trained on hundreds of globally distributed GF-5 satellite images and compared with current mainstream CNN-based detection networks. The experimental results indicate that our proposed method has a higher F1 score (0.94) and fewer parameters (7.83 M) than the compared methods.

Cloud Detection for Satellite Imagery Using Attention-Based U-Net Convolutional Neural Network

Cloud detection is an important and difficult task in the pre-processing of satellite remote sensing data. The results of traditional cloud detection methods are often unsatisfactory in complex environments or the presence of various noise disturbances. With the rapid development of artificial intelligence technology, deep learning methods have achieved great success in many fields such as image processing, speech recognition, autonomous driving, etc. This study proposes a deep learning model suitable for cloud detection, Cloud-AttU, which is based on a U-Net network and incorporates an attention mechanism. The Cloud-AttU model adopts the symmetric Encoder-Decoder structure, which achieves the fusion of high-level features and low-level features through the skip-connection operation, making the output results contain richer multi-scale information. This symmetrical network structure is concise and stable, significantly enhancing the effect of image segmentation. Based on the characteristics of cloud detection, the model is improved by introducing an attention mechanism that allows model to learn more effective features and distinguish between cloud and non-cloud pixels more accurately. The experimental results show that the method proposed in this paper has a significant accuracy advantage over the traditional cloud detection method. The proposed method is also able to achieve great results in the presence of snow/ice disturbance and other bright non-cloud objects, with strong resistance to disturbance. The Cloud-AttU model proposed in this study has achieved excellent results in the cloud detection tasks, indicating that this symmetric network architecture has great potential for application in satellite image processing and deserves further research.

Simultaneous Cloud Detection and Removal From Bitemporal Remote Sensing Images Using Cascade Convolutional Neural Networks

Clouds and cloud shadows heavily affect the quality of the remote sensing images and their application potential. Algorithms have been developed for detecting, removing, and reconstructing the shaded regions with the information from the neighboring pixels or multisource data. In this article, we propose an integrated cloud detection and removal framework using cascade convolutional neural networks, which provides accurate cloud and shadow masks and repaired images. First, a novel fully convolutional network (FCN), embedded with multiscale aggregation and the channel-attention mechanism, is developed for detecting clouds and shadows from a cloudy image. Second, another FCN, with the masks of the detected cloud and shadow, the cloudy image, and a temporal image as the input, is used for the cloud removal and missing-information reconstruction. The reconstruction is realized through a self-training strategy that is designed to learn the mapping between the clean-pixel pairs of the bitemporal images, which bypasses the high demand of manual labels. Experiments showed that our proposed framework can simultaneously detect and remove the clouds and shadows from the images and the detection accuracy surpassed several recent cloud-detection methods; the effects of image restoring outperform the mainstream methods in every indicator by a large margin. The data set used for cloud detection and removal is made open.

An Improved Cloud Detection Method for GF-4 Imagery

Clouds are significant barriers to the application of optical remote sensing images. Accurate cloud detection can help to remove contaminated pixels and improve image quality. Many cloud detection methods have been developed. However, traditional methods either rely heavily on thermal infrared bands or clear-sky images. When traditional cloud detection methods are used with Gaofen 4 (GF-4) imagery, it is very difficult to separate objects with similar spectra, such as ice, snow, and bright sand, from clouds. In this paper, we propose a new method, named Real-Time-Difference (RTD), to detect clouds using a pair of images obtained by the GF-4 satellite. The RTD method has four main steps: (1) data preprocessing, including transforming digital value (DN) to Top of Atmosphere (TOA) reflectance, and orthographic and geometric correction; (2) the computation of a series of cloud indexes for a single image to highlight clouds; (3) the calculation of the difference between a pair of real-time images in order to obtain moved clouds; and (4) confirming the clouds and background by analyzing their physical and dynamic features. The RTD method was validated in three sites located in the Hainan, Liaoning, and Xinjiang areas of China. The results were compared with those of a popular classifier, Support Vector Machine (SVM). The results showed that RTD outperformed SVM; for the Hainan, Liaoning, and Xinjiang areas, respectively, the overall accuracy of RTD reached 95.9%, 94.1%, and 93.9%, and its Kappa coefficient reached 0.92, 0.88, and 0.88. In the future, we expect RTD to be developed into an important means for the rapid detection of clouds that can be used on images from geostationary orbit satellites.

Deep Matting for Cloud Detection in Remote Sensing Images

Cloud detection, as an important preprocessing operation for remote sensing (RS) image analysis, has received increasing attention in recent years. Most of the previous cloud detection methods consider the detection as a pixel-wise image classification problem (cloud versus background), which inevitably leads to a category-ambiguity when dealing with the detection of thin clouds. In this article, starting from the RS imaging mechanism on cloud images, we re-examine the cloud detection under a totally different point of view, i.e., to formulate cloud detection as a mixed energy separation between foreground and background images. This process can be further equivalently implemented under a deep learning-based image matting framework with a clear physical significance. More importantly, the proposed method is capable to deal with three different but related tasks, i.e., “cloud detection,” “cloud removal,” and “cloud cover assessment,” under a unified framework. The experimental results on the three satellite image data sets demonstrate the effectiveness of our method, especially for those hard but common examples in RS images, such as the thin and wispy cloud.

Comparison of Cloud Cover Detection Algorithms on Sentinel–2 Images of the Amazon Tropical Forest

Tropical forests regulate the global water and carbon cycles and also host most of the world’s biodiversity. Despite their importance, they are hard to survey due to their location, extent, and particularly, their cloud coverage. Clouds hinder the spatial and radiometric correction of satellite imagery and also diminishing the useful area on each image, making it difficult to monitor land change. For this reason, our purpose is to identify the cloud detection algorithm best suited for the Amazon rainforest on Sentinel–2 images. To achieve this, we tested four cloud detection algorithms on Sentinel–2 images spread in five areas of the Amazonia. Using more than eight thousand validation points, we compared four cloud detection methods: Fmask 4, MAJA, Sen2Cor, and s2cloudless. Our results point out that FMask 4 has the best overall accuracy on images of the Amazon region (90%), followed by Sen2Cor’s (79%), MAJA (69%), and S2cloudless (52%). We note the choice of method depends on the intended use. Since MAJA reduces the number of false positives by design, users that aim to improve the producer’s accuracy should consider its use.

Cloud Detection Based on Convolutional Neural Network using Different Bands Information for Landsat 8 OLI

The existence of clouds has seriously affected the application of remote sensing data. Therefore, accurate cloud detection is of great significance in remote sensing image processing and application. Traditional cloud detection methods are complex to operate and often require the additional ancillary information. An automatic cloud detection method based on convolutional neural network (CNN) is proposed in this study. The method utilizes a convolutional network structure to classify training samples for cloud and non-cloud. In order to make full use of image information, images of different band numbers are applied to evaluate the influence of the spectrum on cloud detection. Experiments and verification on Landsat 8 images show that the proposed method based on CNN can comprehensively and automatically detect different types of clouds on different surface types, and the cloud detection result using 7 bands is the optimal. The algorithm takes full advantage of image information and does not rely on thermal infrared information, which has practical application value for improving image utilization and subsequent retrieval of remote sensing parameters.

Improved cloud detection for Landsat 8 images using a combined neural network model

ABSTRACTHigh-precision cloud detection is a key step in the processing of remote sensing imagery. However, the existing cloud detection methods struggle to extract high-accuracy cloud pixels, especially for images of thin and fragmented clouds or those over high-brightness surfaces. In this study, we developed a new model by combining the existing models of Fully Convolutional Network-8 sample (FCN-8s) and U-network (U-net) (based on the three visible bands) to take full advantage of spectral and spatial information. In the proposed Fully Convolutional Network Ensembling Learning (FCNEL) model, U-net and FCN-8s initially conduct separate classifications based on their relative strengths, and their outputs are fused by the voting strategy to integrate multi-scale features from both the models. Different surface and cloud types in Landsat 8 Operational Land Imager (OLI) data were used to test the model, which showed an average overall accuracy of 91.68% and an average producer accuracy of 98.52%. Thus, the proposed FCNEL model was superior to FCN-8s or U-net as well as the widely used function of mask algorithm. The proposed method has good adaptability to various cloud types and diverse underlying surface environments.

Cloud Detection from FY-4A’s Geostationary Interferometric Infrared Sounder Using Machine Learning Approaches

FengYun-4A (FY-4A)’s Geostationary Interferometric Infrared Sounder (GIIRS) is the first hyperspectral infrared sounder on board a geostationary satellite, enabling the collection of infrared detection data with high temporal and spectral resolution. As clouds have complex spectral characteristics, and the retrieval of atmospheric profiles incorporating clouds is a significant problem, it is often necessary to undertake cloud detection before further processing procedures for cloud pixels when infrared hyperspectral data is entered into assimilation system. In this study, we proposed machine-learning-based cloud detection models using two kinds of GIIRS channel observation sets (689 channels and 38 channels) as features. Due to differences in surface cover and meteorological elements between land and sea, we chose logistic regression (lr) model for the land and extremely randomized tree (et) model for the sea respectively. Six hundred and eighty-nine channels models produced slightly higher performance (Heidke skill score (HSS) of 0.780 and false alarm rate (FAR) of 16.6% on land, HSS of 0.945 and FAR of 4.7% at sea) than 38 channels models (HSSof 0.741 and FAR of 17.7% on land, HSS of 0.912 and FAR of 7.1% at sea). By comparing visualized cloud detection results with the Himawari-8 Advanced Himawari Imager (AHI) cloud images, the proposed method has a good ability to identify clouds under circumstances such as typhoons, snow covered land, and bright broken clouds. In addition, compared with the collocated Advanced Geosynchronous Radiation Imager (AGRI)-GIIRS cloud detection method, the machine learning cloud detection method has a significant advantage in time cost. This method is not effective for the detection of partially cloudy GIIRS’s field of views, and there are limitations in the scope of spatial application.

Cloud detection methodologies: variants and development\u2014a review

Cloud detection is an essential and important process in satellite remote sensing. Researchers proposed various methods for cloud detection. This paper reviews recent literature (2004–2018) on cloud detection. Literature reported various techniques to detect the cloud using remote-sensing satellite imagery. Researchers explored various forms of Cloud detection like Cloud/No cloud, Snow/Cloud, and Thin Cloud/Thick Cloud using various approaches of machine learning and classical algorithms. Machine learning methods learn from training data and classical algorithm approaches are implemented using a threshold of different image parameters. Threshold-based methods have poor universality as the values change as per the location. Validation on ground-based estimates is not included in many models. The hybrid approach using machine learning, physical parameter retrieval, and ground-based validation is recommended for model improvement.

A robust ragged cloud detection algorithm for remote sensing image

Cloud detection plays a significant role in remote sensing (RS) image processing. Numbers of cloud detection algorithms have been developed in the literature. However, they suffer the weakness of omitting thin and small cloud, and poor ability of differentiating the cloud from confusing ground region (e.g. artificial building). In this study, a robust ragged cloud detection algorithm for RS image is proposed. First, the simple linear iterative clustering method is applied to segment ragged cloud. Then, the improved Qtsu's method is introduced to remove the redundant superpixel. Finally, the Natural Scene Statistic is designed to classify the cloud region. Finally, original image will be classified into thick cloud, thin cloud and non-cloud. Experimental results indicate that the proposed model outperforms the state-of-the-art methods for cloud detection.

Cloud Detection in High-Resolution Remote Sensing Images Using Multi-features of Ground Objects

The existence of clouds in high-resolution remote sensing images influences target recognition and feature classification. Therefore, finding areas covered with clouds is an important preprocessing step in remote sensing image applications. This paper proposes a cloud detection method for satellite images with high resolution using ground objects’ multi-features, such as color, texture, and shape. First, the highly reflective areas are extracted from the image using the minimum cross entropy threshold method. Second, the multi-scale image decomposition based on domain transform filter extracts the texture features of ground objects. Finally, based on the shape features, regular-shaped artificial ground objects are removed to further improve cloud detection accuracy. The experimental results show that the proposed method not only improves the overall accuracy rate but also reduces the false positive rate compared to the classical traditional cloud detection methods. The method is suitable for cloud detection in high-resolution remote sensing images with complex ground objects.

Using Convolutional Neural Networks for Cloud Detection from Meteor-M No. 2 MSU-MR Data

A method for cloud detection using the machine-learning algorithm based on a convolutional neural network is presented. Input data are satellite images received from the MSU-MR multispectral low-resolution scanning unit onboard the Meteor-M No. 2 satellite. The developed method can be an alternative to the traditional algorithms of cloud detection based on the calculation of differential indices and thresholds. The algorithm is verified using the machine-learning metrics, comparing the resulting cloud mask with the reference one obtained by interpreting the satellite image by an experienced meteorologist. It was also compared (for verification) with a similar product based on VIIRS spectroradiometer data. The cloud mask computed using the algorithm allows the automatic thematic processing of satellite images.

Cloud Detection in Remote Sensing Images Based on Multiscale Features-Convolutional Neural Network

Cloud detection in remote sensing images is a challenging but significant task. Due to the variety and complexity of underlying surfaces, most of the current cloud detection methods have difficulty in detecting thin cloud regions. In fact, it is quite meaningful to distinguish thin clouds from thick clouds, especially in cloud removal and target detection tasks. Therefore, we propose a method based on multiscale features-convolutional neural network (MF-CNN) to detect thin cloud, thick cloud, and noncloud pixels of remote sensing images simultaneously. Landsat 8 satellite imagery with various levels of cloud coverage is used to demonstrate the effectiveness of our proposed MF-CNN model. We first stack visible, near-infrared, short-wave, cirrus, and thermal infrared bands of Landsat 8 imagery to obtain the combined spectral information. The MF-CNN model is then used to learn the multiscale global features of input images. The high-level semantic information obtained in the process of feature learning is integrated with low-level spatial information to classify the imagery into thick, thin and noncloud regions. The performance of our proposed model is compared to that of various commonly used cloud detection methods in both qualitative and quantitative aspects. Compared to other cloud detection methods, the experimental results show that our proposed method has a better performance not only in thick and thin clouds but also in the entire cloud regions.

Cloud Detection Using Super Pixel Classification and Semantic Segmentation

Cloud detection plays a very significant role in remote sensing image processing. This paper introduces a cloud detection method based on super pixel level classification and semantic segmentation. Firstly, remote sensing images are segmented into super pixels. Segmented super pixels compose a super pixel level remote sensing image database. Though cloud detection is essentially a binary classification task, our database is labeled into four categories to improve the generalization ability: thick cloud, cirrus cloud, building, and other culture. Secondly, the super pixel level database is used to train our cloud detection models based on convolution neural network (CNN) and deep forest. Hierarchical fusion CNN is proposed considering super pixel level images contain less semantic information than normal images. Taking full advantage of low-level features like color and texture information, it is more applicable for super pixel level classification. Besides, a distance metric is proposed to refine ambiguous super pixels. Thirdly, an end-to-end cloud detection model based on semantic segmentation is introduced. This model has no restrictions on the input size, and takes less time. Experimental results show that compared with other cloud detection methods, our proposed method achieves better performance.

Cloud detection on small satellites based on lightweight U-net and image compression

An effective onboard cloud detection method in small satellites will greatly improve the downlink data transmission efficiency and reduce the platform memory cost. A methodology combining a convolutional neural network and wavelet image compression is proposed to explore the possibility of onboard cloud detection. A lightweight neural network based on U-net architecture is established and evaluated. The red, green, blue, and infrared waveband images from the Landsat-8 dataset are trained and tested to estimate the performance of the mythology. Then a LeGall-5/3 wavelet transform is applied on the dataset to accelerate the neural network and improve the feasibility of the onboard implementation. The experiment results on advanced RISC machines-based embedded platform illustrate that by taking advantage of a mature image compression system in small satellites; the time cost and peak memory cost required by the neural network will be reduced significantly while the segment accuracy is only slightly decreased. The proposed method provides a good possibility of onboard cloud detection for small satellites.

Cloud Detection in Satellite Images Based on Natural Scene Statistics and Gabor Features

Cloud detection is an important task in remote sensing (RS) image processing. Numerous cloud detection algorithms have been developed. However, most existing methods suffer from the weakness of omitting small and thin clouds, and from an inability to discriminate clouds from photometrically similar regions, such as buildings and snow. Here, we derive a novel cloud detection algorithm for optical RS images, whereby test images are separated into three classes: thick clouds, thin clouds, and noncloudy. First, a simple linear iterative clustering algorithm is adopted that is able to segment potential clouds, including small clouds. Then, a natural scene statistics model is applied to the superpixels to distinguish between clouds and surface buildings. Finally, Gabor features are computed within each superpixel and a support vector machine is used to distinguish clouds from snow regions. The experimental results indicate that the proposed model outperforms state-of-the-art methods for cloud detection.

Cloud Detection Method for High Resolution Remote Sensing Imagery Based on the Spectrum and Texture of Superpixels

Cloud Detection Method for High Resolution Remote Sensing Imagery Based on the Spectrum and Texture of Superpixels

Cloud detection using infrared atmospheric sounding interferometer observations by logistic regression

ABSTRACT Hyper-spectral infrared radiance data play an important role in cloud detection. To improve the cloud detection accuracy, this study proposes a novel cloud detection method based on the logistic regression model that uses the Infrared Atmospheric Sounding Interferometer (IASI) radiance data of four characteristic channels as the training features. Due to significant differences in the terrain between the land and the sea, the data from the oceans and continents are trained separately. Thereafter, the proposed scheme is verified and compared with existing methods. The results show that the accuracy of the proposed method (97% at sea and 88% on land) outperforms that of the existing Advanced Very High Resolution Radiometer (AVHRR)/IASI scheme (75% at sea and 55% on land). In addition, the proposed method uses only IASI observations as input and thus does not require the use of other auxiliary data.