Analyses of riverbed shape evolution are crucial for environmental protection and local water management. For narrow rivers located in forested, mountain areas, it is difficult to use remote sensing data used for large river regions. We performed a study of the Prądnik River, located in the Ojców National Park (ONP), Poland. A multitemporal analysis of various data sets was performed. Light detection and ranging (LiDAR)-based data and orthophotomaps were compared with classical survey methods, and 78 cross-sectional profiles were done via GNSS and tachymetry. In order to add an extra time step, the old maps of this region were gathered, and their content was compared with contemporary data. The analysis of remote sensing data suggests that they do not provide sufficient information on the state and changes of riverbanks, river course or river depth. LiDAR data sets do not show river bottoms, and, due to plant life, do not document riverbanks. The orthophotomaps, due to tree coverage and shades, cannot be used for tracking the whole river course. The quality of old maps allows only for general shape analysis over time. This paper shows that traditional survey methods provide sufficient accuracy for such analysis, and the resulted cross-sectional profiles can and should be used to validate other, remote sensing, data sets. We diagnosed problems with the inventory and monitoring of such objects and proposed methods to refine the data acquisition.

In the dynamic field of satellite imagery, the significance of super-resolution (SR) techniques, grounded on advanced deep learning methods, is paramount. A thorough understanding and remediation of the distinct challenges posed by various land cover types for image resolution enhancement form the essence of this research. This work diligently employs two unique neural networks, SRCNN and SwinIR Transformer, to scrutinize their varying impacts on a range of land cover types, ensuring a detailed and comprehensive exploration. This study transcends the mere enhancement of the Sentinel-2 dataset's resolution from 20 m/pix to 10 m/pix. It ambitiously seeks to excavate the intricate trends inherent to different land cover types and their corresponding interactions with SR processes. The application of neural networks on 255 × 254 pixel patches, covering six dominant types—forests, large fields, small fields, urban, sub-urban, and mixed—highlights substantial variations in metrics, underlining the individual interactions of each land cover type with SR techniques. A comprehensive accuracy assessment is meticulously conducted, employing an array of metrics and frequency domains to shed light on the nuanced differences and provide vital insights for optimizing each land cover type's SR approaches. Notably, the PSNR metric reveals significant disparities, particularly in the “forest” and “urban” categories for both SRCNN and SwinIR. According to the PSNR metric, the “forest” class yielded the best results with 66.06 for SRCNN and 67.00 for SwinIR, while the “urban” class marked the lowest with 55.09 and 57.02, respectively, reinforcing the critical nature of this study.

Benchmark datasets is an significant aspect in in many areas such as computer vision, deep learning, geospatial data as they serve as standardized test sets for evaluating the performance of models. Among many techniques of image processing, there is super-resolution (SR) which is aimed at reconstructing a low-resolution (LR) image into a high-resolution (HR) image. For training and validation SR models as a dataset the pairs of HR and LR images are needed, which should be the same apart from resolution. There is a lot of benchmark datasets for super-resolution methods, but they usually include conventional photographs of an common objects, while remote sensing data have different characteristic in general. This paper focuses on the process of preparing datasets for super-resolution in satellite images, where high-resolution and low-resolution image data come from different sources. The case of the single-image super-resolution method was considered. The experiment was performed on Sentinel-2 and PlanetScope data, but the assumptions can also be transferred to data obtained from other satellites. The procedure on how to make the pairs of HR and LR images consistent in terms of time, location and spectral values was proposed. The impact of the processes carried out was measured using image similarity measurement methods such as PSNR, SSIM and SCC.

Precise and complete 3D representations of architectural structures or industrial sites are essential for various applications, including structural monitoring or cadastre. However, acquiring these datasets can be time-consuming, particularly for large objects. Mobile scanning systems offer a solution for such cases. In the case of complex scenes, multiple scanning systems are required to obtain point clouds that can be merged into a comprehensive representation of the object. Merging individual point clouds obtained from different sensors or at different times can be difficult due to discrepancies caused by moving objects or changes in the scene over time, such as seasonal variations in vegetation. In this study, we present the integration of point clouds obtained from two mobile scanning platforms within a built-up area. We utilized a combination of a quadruped robot and an unmanned aerial vehicle (UAV). The PointNet++ network was employed to conduct a semantic segmentation task, enabling the detection of non-ground objects. The experimental tests used the Toronto 3D dataset and DALES for network training. Based on the performance, the model trained on DALES was chosen for further research. The proposed integration algorithm involved semantic segmentation of both point clouds, dividing them into square subregions, and performing subregion selection by checking the emptiness or when both subregions contained points. Parameters such as local density, centroids, coverage, and Euclidean distance were evaluated. Point cloud merging and augmentation enhanced with semantic segmentation and clustering resulted in the exclusion of points associated with these movable objects from the point clouds. The comparative analysis of the method and simple merging was performed based on file size, number of points, mean roughness, and noise estimation. The proposed method provided adequate results with the improvement of point cloud quality indicators.

Simultaneous localization and mapping (SLAM) is essential for the robot to operate in an unknown, vast environment. LiDAR-based SLAM can be utilizable in environments where other sensors cannot deliver reliable measurements. Providing accurate map results requires particular attention due to deviations originating from the device. This study is aimed to assess LiDAR-based mapping quality in a vast environment. The measurements are conducted on a mobile platform. Accuracy of the map collected with the LeGO-LOAM method was performed by making a comparison to a map gathered with geodetic scanning using ICP. The results provided 60% of fitted points in a distance lower than 5 cm and 80% in a distance lower than 10 cm. The findings prove the mileage of the map created with this method for other tasks, including autonomous driving and semantic segmentation.