This paper presents a completely automatic processing chain for orthorectification of optical pushbroom sensors. The procedure is robust and works without manual intervention from raw satellite image to orthoimage. It is modularly divided in four main steps: metadata extraction, automatic ground control point (GCP) extraction, geometric modeling, and orthorectification. The GCP extraction step uses georeferenced vector roads as a reference and produces a file with a list of points and their accuracy estimation. The physical geometric model is based on collinearity equations and works with sensor-corrected (level 1) optical satellite images. It models the sensor position and attitude with second-order piecewise polynomials depending on the acquisition time. The exterior orientation parameters are estimated in a least squares adjustment, employing random sample consensus and robust estimation algorithms for the removal of erroneous points and fine-tuning of the results. The images are finally orthorectified using a digital elevation model and positioned in a national coordinate system. The usability of the method is presented by testing three RapidEye images of regions with different terrain configurations. Several tests were carried out to verify the efficiency of the procedure and to make it more robust. Using the geometric model, subpixel accuracy on independent check points was achieved, and positional accuracy of orthoimages was around one pixel. The proposed procedure is general and can be easily adapted to various sensors.

In response to the increasing need for fast satellite image processing SPACE-SI developed STORM—a fully automatic image processing chain that performs all processing steps from the input optical images to web-delivered map-ready products for various sensors. This paper focuses on the automatic geometric corrections module and its adaptation to very high resolution (VHR) multispectral images. In the automatic ground control points (GCPs) extraction sub-module a two-step algorithm that utilizes vector roads as a reference layer and delivers GCPs for high resolution RapidEye images with near pixel accuracy was initially implemented. Super-fine positioning of individual GCPs onto an aerial orthophoto was introduced for VHR images. The enhanced algorithm is capable of achieving accuracy of approximately 1.5 pixels on WorldView-2 data. In the case of RapidEye images the accuracies of the physical sensor model reach sub-pixel values at independent check points. When compared to the reference national aerial orthophoto the accuracies of WorldView-2 orthoimages automatically produced with the rational function model reach near-pixel values. On a heterogeneous set of 41 RapidEye images the rate of automatic processing reached 97.6%. Image processing times remained under one hour for standard-size images of both sensor types.

Accurate vegetation behavior forecasting is essential for understanding the dynamics of plant life in the context of climate change and other natural or human-induced disturbances. RNN deep learning models represent a modern approach to predict vegetation behavior with a high level of precision. In this paper, we explore the potential of different deep learning and more traditional methods to forecast the normalized difference vegetation index (NDVI), which is directly related to the state of vegetation and its dynamics. A time-series dataset consisting of 70 NDVI images calculated from PlanetScope data from April 2017 to January 2023 were used. Initially, all selected methods were evaluated and compared. From the six tested methods, Simple RNN (SRNN) proved to be the most accurate method for predicting vegetation dynamics. The SRNN model results achieved a mean RMSE of 0.051 when compared to the actual 2022 NDVI values. The high accuracy was reflected in all five studied vegetation classes characterizing the selected Mediterranean test area. The SRNN method performs very well in most months, except in autumn where it underestimates NDVI values. To get thorough insight into the results, we also compared them to the Sentinel-2 NDVI data and climate data consisting of temperature and precipitation values. It was found that most of the prediction differences were due to the irregular variations in meteorological conditions during the year analyzed. The predictive capabilities of RNNs are an effective tool for forecasting vegetation dynamics, but can be further improved by incorporating climate data into the prediction process.

This paper presents an automatic procedure for the geometric corrections of very-high resolution (VHR) optical panchromatic satellite images. The procedure is composed of three steps: an automatic ground control point (GCP) extraction algorithm that matches the linear features that were extracted from the satellite image and reference data; a geometric model that applies a rational function model; and, the orthorectification procedure. Accurate geometric corrections can only be achieved if GCPs are employed to precisely correct the geometric biases of images. Due to the high resolution and the varied acquisition geometry of images, we propose a fast, segmentation based method for feature extraction. The research focuses on densely populated urban areas, which are very challenging in terms of feature extraction and matching. The proposed algorithm is capable of achieving results with a root mean square error of approximately one pixel or better, on a test set of 14 panchromatic Pléiades images. The procedure is robust and it performs well in urban areas, even for images with high off-nadir angles.

Orthoimages have proven to provide useful reference data for a variety of geospatial applications. Their improved versions, true orthoimages, are even more valuable as they have been adjusted also for high objects. Even though true orthoimages have been-over the last decades-generated mainly from aerial images, we believe there is a need to produce true orthoimages also from satellite images. The aim of this article is to present the already developed automatic procedure for generating true orthoimages from very high-resolution optical satellite images. The automatic workflow consists of five modules, starting with the extraction of ground control points, through the geometric processing of image blocks, occlusion detection, orthorectification, and finally the generation of true orthoimages. The orthorectification module uses a high-resolution digital surface model derived from laser scanning data. Occlusion detection is performed using a ray-tracing method based on the incidence angle, which is suitable for images acquired by satellites and processed with rational function models. The usability of the workflow was demonstrated with the test of six Pléiades images that were acquired on different dates and with different viewing angles. The research presents the accuracy of the geometric correction and the quality of the true orthoimage generated with different numbers of images. The results show that satellite-based true orthoimages are suitable for the extraction of spatial information that can be used directly by the end-users.