Unmanned aerial vehicle (UAV) photogrammetry is one of the most effective methods for capturing a terrain in smaller areas. Capturing a steep terrain is more complex than capturing a flat terrain. To fly a mission in steep rugged terrain, a ground control station with a terrain following mode is required, and a quality digital elevation model (DEM) of the terrain is needed. The methods and results of capturing such terrain were analyzed as part of the Belca rockfall surveys. In addition to the national digital terrain model (NDTM), two customized DEMs were developed to optimize the photogrammetric survey of the steep terrain with oblique images. Flight heights and slant distances between camera projection centers and terrain are analyzed in the article. Some issues were identified and discussed, namely the vertical images in steep slopes and the steady decrease of UAV heights above ground level (AGL) with the increase of height above take-off (ATO) at 6%-8% rate. To compensate for the latter issue, the custom DEMs and NDTM were tilted. Based on our experience, the proposed optimal method for capturing the steep terrain is a combination of vertical and oblique UAV images.

The paper describes two different methods for extraction of two types of urban objects from lidar digital surface model (DSM) and digital aerial images. Within the preprocessing digital terrain model (DTM) and orthoimages for three test areas were generated from aerial images using automatic photogrammetric methods. Automatic building extraction was done using DSM and multispectral orthoimages. First, initial building mask was created from the normalized digital surface model (nDSM), then vegetation was eliminated from the building mask using multispectral orthoimages. The final building mask was produced employing several morphological operations and buildings were vectorised using Hough transform. Automatic extraction of other green urban features (trees and natural ground) started from orthoimages using iterative object-based classification. This method required careful selection of segmentation parameters; in addition to basic spectral bands also information from nDSM was included. After the segmentation of images the segments were classified based on their attributes (spatial, spectral, geometrical, texture) using rule set classificator. First iteration focused on visible (i.e. unshaded) urban features, and second iteration on objects in deep shade. Results from both iterations were merged into appropriate classes. Evaluation of the final results (completeness, correctness and quality) was carried out on a per-area level and on a per-object level by ISPRS Commission III, WG III/4.

One of the main concerns of land administration in developed countries is to keep the cadastral system up to date. The goal of this research was to develop an approach to detect visible land boundaries and revise existing cadastral data using deep learning. The convolutional neural network (CNN), based on a modified architecture, was trained using the Berkeley segmentation data set 500 (BSDS500) available online. This dataset is known for edge and boundary detection. The model was tested in two rural areas in Slovenia. The results were evaluated using recall, precision, and the F1 score—as a more appropriate method for unbalanced classes. In terms of detection quality, balanced recall and precision resulted in F1 scores of 0.60 and 0.54 for Ponova vas and Odranci, respectively. With lower recall (completeness), the model was able to predict the boundaries with a precision (correctness) of 0.71 and 0.61. When the cadastral data were revised, the low values were interpreted to mean that the lower the recall, the greater the need to update the existing cadastral data. In the case of Ponova vas, the recall value was less than 0.1, which means that the boundaries did not overlap. In Odranci, 21% of the predicted and cadastral boundaries overlapped. Since the direction of the lines was not a problem, the low recall value (0.21) was mainly due to overly fragmented plots. Overall, the automatic methods are faster (once the model is trained) but less accurate than the manual methods. For a rapid revision of existing cadastral boundaries, an automatic approach is certainly desirable for many national mapping and cadastral agencies, especially in developed countries.

The main goal of our research was to design and implement an innovative target that would be suitable for accurately registering point clouds produced from unmanned aerial vehicle (UAV) images and terrestrial laser scans. Our new target is composed of three perpendicular planes that combine the properties of plane and volume targets. The new target enables the precise determination of reference target points in aerial and terrestrial point clouds. Different types of commonly used plane and volume targets as well as the new target were placed in an established test area in order to evaluate their performance. The targets were scanned from multiple scanner stations and surveyed with an unmanned aerial vehicle DJI Phantom 4 PRO at three different altitudes (20, 40, and 75 m). The reference data were measured with a Leica Nova MS50 MultiStation. Several registrations were performed, each time with a different target. The quality of these registrations was assessed on the check points. The results showed that the new target yielded the best results in all cases, which confirmed our initial expectations. The proposed new target is innovative and not difficult to create and use.

The article addresses automatic building extraction from IKONOS images in suburban areas. In the proposed approach, we used a stereo pair of IKONOS images. Automatic photogrammetric methods of image matching were used to generate a digital surface model (DSM) and a digital elevation model. In further processing, single-image methods were used. The orthophotos of individual bands were created. The initial building mask was generated from the calculated normalized DSM (nDSM). The calculated normalized difference vegetation index and the road data extracted from the existing topographical database were used to remove vegetation and traffic surfaces. The mask was further improved with our own combination of methods based on non-linear diffusion filtering, unsupervised classification, colour segmentation and region growing. The final mask was vectorized using the Hough transform. Compared with a reference building database, 83.2% of the buildings in the test area were detected using the proposed approach with a quality percentage (how likely a building pixel produced by an automatic approach is correct) of 49.46.