Object-based cloud and cloud shadow detection in Landsat imagery

Cloud and cloud shadow screening across Queensland, Australia: An automated method for Landsat TM/ETM + time series

Improving Fmask cloud and cloud shadow detection in mountainous area for Landsats 4–8 images

Prior knowledge of the background land surface reflectance (LSR) constitutes one of the most important factors affecting the precision of cloud shadow detection. To resolve this problem, a surface reflectance-based cloud shadow detection (SRCSD) algorithm is proposed for multitemporal Landsat images. Monthly surface reflectance data sets constructed from MODIS surface reflectance products (MOD09A1) were used to provide the background LSR for cloud shadow detection. Based on the background LSR, the possible variation in the top of atmosphere (TOA) reflectance for each clear pixel can be estimated using the radiative transfer equation under different atmospheric conditions. If a pixel has a smaller TOA reflectance than the minimum value of the possible range under clear conditions, it is identified as being shadow covered. One hundred and twenty-five Landsat 8 Operational Land Imager scenes covered by various surface types were selected to evaluate the feasibility of the algorithm. A validation using manual cloud shadow masks showed that the average producer’s accuracy and user’s accuracy were approximately 0.805 and 0.893, respectively. A comparison of the results of the SRCSD algorithm with those of an object-based cloud shadow detection algorithm (Fmask) recently developed for Landsat images revealed that SRCSD generally detects cloud shadows better than Fmask. The most significant improvement of the SRCSD algorithm is the better detection capability for thin and broken cloud shadows, and this algorithm can be extended to multiple types of satellite data after proper modification.

Cloud cover has become a major problem in the use of optical satellite imageries, particularly in Indonesian region located along equator or tropical region with high cloud cover almost all year round. In this study, a new method for cloud and cloud shadow detection using Landsat imagery for specific Indonesian region was developed to provide a more efficient and effective way to detect clouds and cloud shadows. Landsat Top of Atmosphere (TOA) reflectance and Brightness Temperature (BT) were used as inputs into the model. The first step was to detect cloud based on cloud physical properties using albedo and thermal bands, the second step was to detect cloud shadows using the Near Infrared (NIR), and Short Wave Infrared (SWIR) bands, and finally, the geometric relationships were used to match the cloud and cloud shadow layer, before proceeding to the production of the final cloud and cloud shadow mask. The results were then compared with other method such as tree base cloud separation. It showed that method we proposed could provide better result than tree base method, the accuracy result of this method was 98.75%.

The use of Landsat data to answer ecological questions is greatly increased by the effective removal of cloud and cloud shadow from satellite images. We develop a novel algorithm to identify and classify clouds and cloud shadow, SPARCS: Spatial Procedures for Automated Removal of Cloud and Shadow. The method uses a neural network approach to determine cloud, cloud shadow, water, snow/ice and clear sky classification memberships of each pixel in a Landsat scene. It then applies a series of spatial procedures to resolve pixels with ambiguous membership by using information, such as the membership values of neighboring pixels and an estimate of cloud shadow locations from cloud and solar geometry. In a comparison with FMask, a high-quality cloud and cloud shadow classification algorithm currently available, SPARCS performs favorably, with substantially lower omission errors for cloud shadow (8.0% and 3.2%), only slightly higher omission errors for clouds (0.9% and 1.3%, respectively) and fewer errors of commission (2.6% and 0.3%). Additionally, SPARCS provides a measure of uncertainty in its classification that can be exploited by other algorithms that require clear sky pixels. To illustrate this, we present an application that constructs obstruction-free composites of images acquired on different dates in support of a method for vegetation change detection.

A cloud shadow detection method combined with cloud height iteration and spectral analysis for Landsat 8 OLI data

Cloud and cloud shadow cover on satellite images limit remote sensing and geo-information systems (GIS) applications in all application areas, especially for change detection and time series analyses. A novel method of cloud and cloud shadow removal called Multitemporal Cloud Removal (MCR) is proposed in this paper. The method has main steps: (1) radiometric correction, (2) cloud and cloud shadow detection, and (3) image reconstruction. Top of Atmosphere (TOA) radiometric correction converts digital number values to TOA reflectance for Landsat 8 OLI was first completed. In the second step, Multi-temporal Cloud Masking (MCM) was used to detect cloud and cloud shadow. This method uses a target image which has cloud and cloud shadow contaminated pixels and a reference image which is clear. The aim is to obtain the difference in reflectance values in visible, near-infrared and short wave infrared bands between target and reference images. These values can be used to detect cloud and cloud shadow in Landsat 8 images. The Landsat 8 cirrus band is used to detect thin cirrus cloud in this method. We use target image and reference image from a sequence acquisition dates of Landsat 8 images to avoid the significant land cover change. In the last step, we use multitemporal images to reconstruct pixels which are contaminated by cloud and cloud shadow. Cloud and cloud shadow contaminated pixels on the target image are replaced by pixels from the reference image. Landsat 8 images which have heterogeneous land cover and variety of cloud types are chosen in the experiments to prove that MCR is robust method for removing cloud and cloud shadow and can be used for image that has heterogeneous land cover and variety of cloud types. We use visual and statistical assessments to evaluate the results. As results show, cloud and cloud shadow can be removed by MCR. In visual evaluation, the corrected images are similar to the reference image. In statistical assessments between corrected and references images, the correlation coefficient for each band is quite high (>0.9) for the thick cloud case and equal to 1 for thin cloud case. Within band tandard deviations in the reference image and the corrected image were higher in the corrected image compared to the the reference image and original image. Although not comprehensive, the visual and statistical assessments, provide some indication that th MCR method was robust method for removing cloud and cloud shadow in Landsat 8 images examined in this work. The advantage of this appoach is that original reflectance values can be retained as long as they are not contaminated by cloud and cloud shadow. In addition, as we use a sequence acquisition date of Landsat 8 images, we can produce free cloud and cloud shadow images.

Cloud and cloud shadow detection in Landsat imagery based on deep convolutional neural networks

Optical data plays an important role in various remote sensing applications. However, cloud and cloud shadow contamination reduce the availability of optical data, especially in tropical regions. Accurate identification of cloud and cloud shadow is an essential step in optical image preprocessing. The Function of Mask (FMASK) [1] is one of the most widely used cloud and cloud shadow detection methods. In view of the problems of some thin clouds and cloud shadows omission errors in tropical regions of FMASK, we develop an improved FMASK algorithm in tropical regions from the following two aspects: (1) Cloud detection: Firstly, the parameters and thresholds of FMASK are adjusted to generate the basic cloud layer; Secondly, the cloud index layer is calculated based on the bright features of clouds; Then, combining the temporal randomness and spectral characteristics of cloud, other bright objects are excluded and thin clouds are retained. (2) Cloud shadow detection: Firstly, the dark features of cloud shadows are mainly used to detect the basic cloud shadow layer; Secondly, combining the spectral and randomness characteristics of cloud shadow to avoid the interference of other dark objects. We randomly selected three experimental areas in tropical regions to verify the proposed algorithm developed in this paper. Through comparing and evaluating the accuracy of the clouds and cloud shadows mask generated based on the method in this paper with real samples drawn manually, the experiment results show that the average overall precision of clouds and cloud shadows mask generated based on the algorithm in this paper exceeding 80%. This improved FMASK algorithm improves the accuracy of clouds and cloud shadows detection in several tropical regions for Landsat images.

Cloud and cloud shadow detection is an important preprocess before using satellite images for different applications. It can be considered as a classification process, in which the objective pixels are partitioned into cloud/cloud shadow or non-cloud/non-cloud shadow classes. However, some cloud pixels, especially the thin cloud pixels, can be considered as a mixture of reflectances of clouds and land objects. In fuzzy clustering, the data points can belong to two or more clusters; hence, fuzzy clustering may better characterize the status of one given pixel belonging to clouds or non-clouds. The fuzzy c-means method (FCM), one typical fuzzy clustering method, was utilized in this study for cloud and cloud shadow detection. In addition, the “flood-fill” morphological transformation may misclassify some clear-sky areas surrounded by clouds as cloud shadows as a whole, so a modified cloud shadow index calculation was proposed. Moreover, a cloud and cloud shadow spatial matching strategy based on the projection direction and spatial coexistence was used to exclude some pseudo cloud shadows. Fewer predefined parameters and spectral bands are needed is one characteristic of the proposed method. In this study, 41 scenes including 27 Landsat ETM+ images in eight latitude zones and 14 Landsat OLI images comprising seven land cover types, including barren, forest, grass, shrubland, urban, water, and wetlands areas, with percentages of cloud cover from 4.99% to 97.63%, were utilized to confirm the validity of the FCM. The detected results demonstrate that the thick and thin clouds along with their associated cloud shadows can be precisely extracted by using the FCM. Compared with the function of mask (Fmask) method, the FCM has relatively lower producer agreement rates, but it misclassifies as clouds fewer clear-sky pixels; compared with the support vector machine (SVM) method, the FCM can achieve better cloud detection accuracy. The results demonstrate that the FCM can attain a better balance between cloud pixel detection and non-cloud pixel exclusion.

Automatic cloud and cloud shadow detection in tropical areas for PlanetScope satellite images

Clouds and their shadows significantly affect satellite imagery, resulting in a loss of radiometric information in the shadowed areas. This loss reduces the accuracy of land cover classification and object detection. Among various cloud shadow detection methods, the geometric-based method relies on the geometry of the sun and sensor to provide consistent results across diverse environments, ensuring better interpretability and reliability. It is well known that the direction of shadows in raw satellite images depends on the sun’s illumination and sensor viewing direction. Orthoimages are typically corrected for relief displacements caused by oblique sensor viewing, aligning the shadow direction with the sun. However, previous studies lacked an explicit experimental verification of this alignment, particularly for cloud shadows. We observed that this implication may not be realized for cloud shadows, primarily due to the unknown height of clouds. To verify this, we used Rapideye orthoimages acquired in various viewing azimuth and zenith angles and conducted experiments under two different cases: the first where the cloud shadow direction was estimated based only on the sun’s illumination, and the second where both the sun’s illumination and the sensor’s viewing direction were considered. Building on this, we propose an automated approach for cloud shadow detection. Our experiments demonstrated that the second case, which incorporates the sensor’s geometry, calculates a more accurate cloud shadow direction compared to the true angle. Although the angles in nadir images were similar, the second case in high-oblique images showed a difference of less than 4.0° from the true angle, whereas the first case exhibited a much larger difference, up to 21.3°. The accuracy results revealed that shadow detection using the angle from the second case improved the average F1 score by 0.17 and increased the average detection rate by 7.7% compared to the first case. This result confirms that, even if the relief displacement of clouds is not corrected in the orthoimages, the proposed method allows for more accurate cloud shadow detection. Our main contributions are in providing quantitative evidence through experiments for the application of sensor geometry and establishing a solid foundation for handling complex scenarios. This approach has the potential to extend to the detection of shadows in high-resolution satellite imagery or UAV images, as well as objects like high-rise buildings. Future research will focus on this.

Abstract. Cloud shadows are observed by the TROPOMI satellite instrument as a result of its high spatial resolution compared to its predecessor instruments. These shadows contaminate TROPOMI's air quality measurements, because shadows are generally not taken into account in the models that are used for aerosol and trace gas retrievals. If the shadows are to be removed from the data, or if shadows are to be studied, an automatic detection of the shadow pixels is needed. We present the Detection AlgoRithm for CLOud Shadows (DARCLOS) for TROPOMI, which is the first cloud shadow detection algorithm for a spaceborne spectrometer. DARCLOS raises potential cloud shadow flags (PCSFs), actual cloud shadow flags (ACSFs), and spectral cloud shadow flags (SCSFs). The PCSFs indicate the TROPOMI ground pixels that are potentially affected by cloud shadows based on a geometric consideration with safety margins. The ACSFs are a refinement of the PCSFs using spectral reflectance information of the PCSF pixels and identify the TROPOMI ground pixels that are confidently affected by cloud shadows. Because we find indications of the wavelength dependence of cloud shadow extents in the UV, the SCSF is a wavelength-dependent alternative for the ACSF at the wavelengths of TROPOMI's air quality retrievals. We validate the PCSF and ACSF with true-colour images made by the VIIRS instrument on board Suomi NPP orbiting in close proximity to TROPOMI on board Sentinel-5P. We find that the cloud evolution during the overpass time difference between TROPOMI and VIIRS complicates this validation strategy, implicating that an alternative cloud shadow detection approach using co-located VIIRS observations could be problematic. We conclude that the PCSF can be used to exclude cloud shadow contamination from TROPOMI data, while the ACSF and SCSF can be used to select pixels for the scientific analysis of cloud shadow effects.

Developing clear-sky, cloud and cloud shadow mask for producing clear-sky composites at 250-meter spatial resolution for the seven MODIS land bands over Canada and North America

Analysis of aerial images provided by satellites enables continuous monitoring and is a central component of many applications, including precision farming. Nonetheless, this analysis is often impeded by the presence of clouds and cloud shadows, which obscure the underlying region of interest and introduce incorrect values that bias analysis. In this paper, we outline a method for cloud shadow detection, and demonstrate our method using Canadian farmland data obtained from the Sentinel-2 satellite. Our approach builds on other object-based cloud and cloud shadow detection methods that generate preliminary shadow candidate masks which are refined by matching clouds to their respective shadows. We improve on these components by using ray-casting and inverse texture mapping methods to quickly identify cloud shadows, allowing for the immediate removal of false positives during image processing. Leveraging our ray-casting-based approach, we further improve our results by implementing a probability analysis based on the cloud probability layer provided by the Sentinel-2 satellite to account for missed shadow pixels. An evaluation of our method using the average producer (82.82%) and user accuracy (75.55%) both show a marked improvement over the performance of other object-based methods. Methodologically, our work demonstrates how incorporating probability analysis as a post-processing step can improve the generation of shadow masks.