In the goal of the CRP is foreseen use of remote sensing data and automatic building extraction. The update of topographic databases is an important task for organizations that maintain them. The article describes a method for automatic building extraction from digital surface model and multispectral orthophoto and the use of extraction results for the building change detection in the topographic database. The results of the automatic building extraction were compared to the building cadastre and the actual situation on the ground. The automatic method detected 94% of all buildings in the area. We concluded that the described method is appropriate for capturing of the building data for the topographic database in scales 1 : 10.000 and smaller. Automatic change detection results (completeness 94% and correctness 78%) indicate that the described method is appropriate for building change detection.
COBISS.SI-ID: 5364577
Automated building extraction from satellite imagery and other remote sensing data is one of goals of CRP. The article addresses automatic building extraction from stereo IKONOS images in suburban areas. Automatic methods of image matching were used to generate a digital surface model (DSM) and a digital elevation model. 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. Compared with a reference building database, 83% of the buildings in the test area were detected using the proposed approach with a quality of 49%.
COBISS.SI-ID: 5728097
Slovenia has a crucial problem of regular updating of topographic data at different levels. The largest scale map which is regularly updated is Nationaltopographic map at the scale 1: 50,000, but without any detailed data capture in wooden areas. Larger scale topographic maps and basic topographic database were captured only partly and they have no strict updating program. On the other hand the airborne laser scanning data became one of the most promising source data for deriving different spatial data. Some methods and procedures are already efficiently used in urban environment and forestry, while use for deriving topographic features is still rare. Therefore some tests about possible use of ASL data for updating topographic data were made. As a study area part of Sava valley near the Jesenice with neighboring slopes was used. According to analyses and tests some rules which can be followed in attempt to partly automate the procedure of recognising specific features for updating topographic maps were extracted.
COBISS.SI-ID: 5488481