Search

Widespread use of high-resolution satellite images may be found in many fields and applications. Its ability to record the earth's surface in more detail benefits regional spatial management, natural resources and disaster monitoring, and several other fields. The smaller coverage is unfortunate if areas are not visible due to cloud contamination. The presence of clouds can reduce or even eliminate the information in the image. Cloud detection on high-resolution images is a challenge because this image only has four channels: blue, green, red, and NIR. While the thermal channel, which is often used to detect the presence of clouds, is not owned by this image. This study proposes a method to identify clouds in high-resolution satellite imagery based on this limitation. The cloud detection software in this paper uses U-Net version 1.0. This software can be executed on a server or personal computer (PC). The model applied to the Dice coefficient and IoU to know how the segmentation model performs. The results of this cloud detection process are cloud detection raster data. This software generates the percentage of clouds in an image as a.txt file. The dice model is recommended for the cloud detection method based on the accuracy assessment. Users can utilize these results, especially in overcoming cloud constraints on high-resolution satellite imagery. This software is expected to fulfill the needs of remote-sensing data users. [ABSTRACT FROM AUTHOR]

The mosaic image is an essential process for merging several images, especially for very high-resolution satellite images, as its width swath is small. The main issue of mosaic images is the geometric accuracy between the images. This paper proposed a sub-pixel geometric evaluation to assess the geometric shift between the images. It is an essential step for image registration. Image registration is a process to determine a geometric shift involving two or more images with the same object but different acquisition dates, viewpoints, and sensors. The basic idea of image registration in the frequency domain is estimating the shift between the test image and the reference image. In this study, we used the phase cross-correlation function to determine the geometric shift between two different acquisition Pleiades images from each polygon. Phase correlation is based on the translation property of the Fourier Transform. It transforms the displacement of two correlated images in the spatial domain into a phase difference in the frequency domain. The phase correlation algorithm calculates a phase difference map containing a single peak. The peak location is proportional to the value of the shift between the two images. Several Pleiades images were used in the experiment. The image processing level is an ortho-image, which is already pan-sharped. As a result, the highest geometric shift is on Polygon 2 based on the R-value, and the lowest error value is in polygon 1. The experiments also showed that the most significant error value is in the blue band, and the lowest is in the red band. The average geometric shift between the two Pleiades data is 1.187 pixels, with the most shift located in the blue band with a 1.282 pixels shift, and the Root Mean Square Error (RMSE) is 1.8. [ABSTRACT FROM AUTHOR]