Abstract. The recently increasing development of whole sky imagers enables temporal and spatial high-resolution sky observations. One application already performed in most cases is the estimation of fractional sky cover. A distinction between different cloud types, however, is still in progress. Here, an automatic cloud classification algorithm is presented, based on a set of mainly statistical features describing the color as well as the texture of an image. The k-nearest-neighbour classifier is used due to its high performance in solving complex issues, simplicity of implementation and low computational complexity. Seven different sky conditions are distinguished: high thin clouds (cirrus and cirrostratus), high patched cumuliform clouds (cirrocumulus and altocumulus), stratocumulus clouds, low cumuliform clouds, thick clouds (cumulonimbus and nimbostratus), stratiform clouds and clear sky. Based on the Leave-One-Out Cross-Validation the algorithm achieves an accuracy of about 97%. In addition, a test run of random images is presented, still outperforming previous algorithms by yielding a success rate of about 75%, or up to 88% if only "serious" errors with respect to radiation impact are considered. Reasons for the decrement in accuracy are discussed, and ideas to further improve the classification results, especially in problematic cases, are investigated.

Automatic cloud classification of whole sky images

The automatic ship detection method for thermal infrared remote sensing images (TIRSIs) is of great significance due to its broad applicability in maritime security, port management, and target searching, especially at night. Most ship detection algorithms utilize manual features to detect visible image blocks which are accurately cut, and they are limited by illumination, clouds, and atmospheric strong waves in practical applications. In this paper, a complete YOLO-based ship detection method (CYSDM) for TIRSIs under complex backgrounds is proposed. In addition, thermal infrared ship datasets were made using the SDGSAT-1 thermal imaging system. First, in order to avoid the loss of texture characteristics during large-scale deep convolution, the TIRSIs with the resolution of 30 m were up-sampled to 10 m via bicubic interpolation method. Then, complete ships with similar characteristics were selected and marked in the middle of the river, the bay, and the sea. To enrich the datasets, the gray value stretching module was also added. Finally, the improved YOLOv5 s model was used to detect the ship candidate area quickly. To reduce intra-class variation, the 4.23–7.53 aspect ratios of ships were manually selected during labeling, and 8–10.5 μm ship datasets were constructed. Test results show that the precision of the CYSDM is 98.68%, which is 9.07% higher than that of the YOLOv5s algorithm. CYSDM provides an effective reference for large-scale, all-day ship detection.

/pdf/a-complete-yolo-based-ship-detection-method-for-thermal-26ha9byr.pdf

A Complete YOLO-Based Ship Detection Method for Thermal Infrared Remote Sensing Images under Complex Backgrounds

The multiple Exp-function method is employed for searching the multiple soliton solutions for the new extended ( )- dimensional Jimbo-Miwa-like (JM) equation, the extended ( )- dimensional Calogero-Bogoyavlenskii-Schiff (eCBS) equation, the generalization of the ( )- dimensional Bogoyavlensky-Konopelchenko (BK) equation, and a variable-coefficient extension of the DJKM (vDJKM) equation, which contain one-soliton-, two-soliton-, and triple-soliton-kind solutions. The physical phenomena of these gained multiple soliton solutions are analyzed and indicated in figures by selecting suitable values.

/pdf/investigating-one-two-and-triple-wave-solutions-via-multiple-3po2djhmbw.pdf

Investigating One-, Two-, and Triple-Wave Solutions via Multiple Exp-Function Method Arising in Engineering Sciences

The systematic monitoring of the Earth using optical satellites is limited by the presence of clouds. Accurately detecting these clouds is necessary to exploit satellite image archives in remote sensing applications. Despite many developments, cloud detection remains an unsolved problem with room for improvement, especially over bright surfaces and thin clouds. Recently, advances in cloud masking using deep learning have shown significant boosts in cloud detection accuracy. However, these works are validated in heterogeneous manners, and the comparison with operational threshold-based schemes is not consistent among many of them. In this work, we systematically compare deep learning models trained on Landsat-8 images on different Landsat-8 and Sentinel-2 publicly available datasets. Overall, we show that deep learning models exhibit a high detection accuracy when trained and tested on independent images from the same Landsat-8 dataset (intra-dataset validation), outperforming operational algorithms. However, the performance of deep learning models is similar to operational threshold-based ones when they are tested on different datasets of Landsat-8 images (inter-dataset validation) or datasets from a different sensor with similar radiometric characteristics such as Sentinel-2 (cross-sensor validation). The results suggest that (i) the development of cloud detection methods for new satellites can be based on deep learning models trained on data from similar sensors and (ii) there is a strong dependence of deep learning models on the dataset used for training and testing, which highlights the necessity of standardized datasets and procedures for benchmarking cloud detection models in the future.

Benchmarking Deep Learning Models for Cloud Detection in Landsat-8 and Sentinel-2 Images

Accurate and rapid cloud detection is exceedingly significant for improving the downlink efficiency of on-orbit data, especially for the microsatellites with limited power and computational ability. However, the inference speed and large model limit the potential of on-orbit implementation of deep-learning-based cloud detection method. In view of the above problems, this paper proposes a lightweight network based on depthwise separable convolutions to reduce the size of model and computational cost of pixel-wise cloud detection methods. The network achieves lightweight end-to-end cloud detection through extracting feature maps from the images to generate the mask with the obtained maps. For the visible and thermal infrared bands of the Landsat 8 cloud cover assessment validation dataset, the experimental results show that the pixel accuracy of the proposed method for cloud detection is higher than 90%, the inference speed is about 5 times faster than that of U-Net, and the model parameters and floating-point operations are reduced to 12.4% and 12.8% of U-Net, respectively.

/pdf/lightweight-u-net-for-cloud-detection-of-visible-and-thermal-2ew4lg94yx.pdf

Lightweight U-Net for cloud detection of visible and thermal infrared remote sensing images

Cloud detection (CD) with deep learning (DL) algorithms has been greatly developed in the applications involving the predictions of extreme weather and climate. In this review, the different conventional CD methods based on threshold, time differentiation, machine learning, and the intelligent algorithms including convolution neural networks (CNN), simple linear iterative clustering (SLIC), and semantic segmentation algorithms (SSAs) are introduced in detail, and, especially, the majority of CD publications employing the advanced and prevalent DL algorithms during the last decade are summarized and analyzed. First, in terms of the detection for different types of clouds, we meticulously compare the labels, scenarios and volumes of three popular CD datasets and put forward further the constructive recommendations about the cloud images selection, multi-bands images preprocessing, and truth labels combination for creating similar datasets. Subsequently, the structures, detection accuracies, and operating speeds of several different CD network models comprising the fully convolutional neural networks (FCNs), U-Net, SegNet, pyramid scene parsing network (PSPNet), as well as the associated derivatives are conducted elaborately to explore the comprehensively optimal performance for CD. In addition, aiming at expanding the applications in the resource-limited space-borne environment, we conclude the mainstream compression strategies of a number of different lightweight networks. Finally, the various limitations constraining the performance of the existing state-of-the-art DL CD methods and the corresponding development tendency are presented, which, expectantly, could be referential for the following researches.

A review on deep learning techniques for cloud detection methodologies and challenges

Geometric positioning of a remote sensing image is one of the core technologies for the quantitative application of the geostationary satellite data. Affected by the change of the incident angle of the sunlight, the spatial thermal environment surrounding the remote sensing cameras (RSCs), especially the geostationary RSCs, fluctuates greatly and has a noticeable impact on the installation matrix based on the reference to the satellite body. Therefore, the spatial thermal environment will ultimately influence the camera’s geometric positioning model and the final positioning accuracy. This paper proposes a novel correction method based on stellar observations for correcting geometric positioning error caused by spatial thermal deformation (STD) of geostationary optical payloads. The proposed method overcomes the drawbacks associated with current stabilization methods that involve shutting down the camera to reduce STD effects. Experimental results show that the positioning error corrected by the proposed method can be within ±1.9 pixels ( $2{\sigma }$ ) at a 95% confidence level and better than the ±18 pixels before correction.

/pdf/a-correction-method-for-thermal-deformation-positioning-14ftr0eirb.pdf

A Correction Method for Thermal Deformation Positioning Error of Geostationary Optical Payloads

Improved distortion correction method and applications for large aperture infrared tracking cameras

Due to the response variations within a pixel, response of sensor varies with the positions of the point target. The accurate measurement of intra-pixel response of the sensor is the key to high-precision centroid estimation and radiometric calibration. In this paper, we establish an intra-pixel response model based on the pixel structure and use Gauss function to describe the beam spot profile. We further calculate the full width at half maximum (FWHM) of the Gauss function and the fill factor of the infrared sensor using the grid search algorithm. Experimental results show that the Gauss function FWHM differences among different pixels using the same radius could be less than 6%. The fill factors are not constant in different pixels because of errors in the process of manufacture and assembly, and the error between model and measured values is less than 3.6%. This work could be useful for stellar calibration and centroid estimation.

Xiaoyan Li

Papers

Lightweight U-Net for cloud detection of visible and thermal infrared remote sensing images

A review on deep learning techniques for cloud detection methodologies and challenges

A Correction Method for Thermal Deformation Positioning Error of Geostationary Optical Payloads

Improved distortion correction method and applications for large aperture infrared tracking cameras

A method for the characterization of intra-pixel response of infrared sensor