This research aimed at automizing the procedure of visible boundary delineation from Unmanned Aerial Vehicle (UAV) imagery through deep learning. U-Net architecture was selected to train the model and predict visible boundaries. The model was trained on an available edge detection dataset, which was the closest to our domain problem. The model was tested on a tiled UAV images. The U-Net architecture was implemented in Keras and written in Python, running on top of the TensorFlow library. The training was done through Google Colaboratory. The average percentage of correctly detected visible boundaries was almost 80% for the tiled UAV images. This percentage is very satisfying since the model was trained on everyday imagery which is very different from UAV ones. The automatic boundary detection by using U-Net is applicable mostly for rural areas where the visibility of the boundaries is continuous.
B.03 Paper at an international scientific conference
COBISS.SI-ID: 43718659For an accurate building outline extraction from a point cloud, various factors affecting the quality should be considered. In this research, we analysed the influence of point cloud density on the quality of the extracted building outlines. The input data was a classified photogrammetric point cloud, obtained from the dense image matching of images acquired by an optical sensor mounted on the unmanned aerial vehicle (UAV). For outline extraction, we selected two procedures, namely the direct approach and the raster approach. In the direct approach, building outlines are extracted directly from the points that have been classified as buildings where we used the Douglas-Peucker algorithm. This is followed by the shape regularisation to ensure perpendicular angles of the outline. In the raster approach, we first rasterised the building points and then extracted the building outlines using the Hough transform. In both approaches, the result is a roof outline in a 2D plane representing the maximum extent of the building above the surface. The building outlines were extracted from point clouds with five different densities. For both approaches, the quality assessment has shown that point cloud density has an impact on the building outline extraction, especially on the completeness of the outlines.
B.03 Paper at an international scientific conference
COBISS.SI-ID: 33093379Members of the project group are actively involved as members of editorial board and as reviewers of the journal Geodetski vestnik, the main journal in the field of geodesy and geoinformatics in Slovenia. Anka Lisec has been editor-in-chief since 2014. Geodetski vestnik has been publishing continuously since 1956 and bringing together a wide range of papers on research, theory and professional practice in geodesy, surveying, geoinformatics, remote sensing and land management. It is an interdisciplinary journal concerned with technical, social, economic, political, legal, physical and planning aspects of geodesy, surveying, real estate management and spatial planning. By publishing the content of various, but always high-quality contributions, the journal has exceeded its professional impact in the field of geodesy and is becoming more and more interesting for reading and publishing for other scientific and professional fields. From 2007 is Geodetski vestnik included in WoS.
C.04 Editorial board of an international magazine
COBISS.SI-ID: 5091842