Dejan Grigillo

Automated building extraction from IKONOS images in suburban areas

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.

Classification based building detection from GeoEye-1 images

High-resolution satellite imagery is being increasingly employed for large-scale topographic mapping, and especially for updating spatial databases. GeoEye-1 is one of the latest in a series of commercial high-resolution earth observation satellites. The paper presents a method for building detection from GeoEye-1 imagery. The initial building mask was created with supervised classification based on the object approach. In the next steps the building mask was enhanced employing, unsupervised classification and region growing. The final results of the building detection are evaluated.

Determination of Large Wood Accumulation in a Steep Forested Torrent Using Laser Scanning

In order to estimate large wood (LW) recruitment potential in torrential watersheds, and to describe the interactions of wood and torrential sediments in a cascading forested torrential channel, we performed a field survey of the lower reach of the Kuzlovec Torrent in the Gradascica watershed, using a terrestrial laser scanner (TLS). The point cloud consisted of several million points. The points were coloured with images made with digital camera to support visual interpretation of the captured objects. Data were used to create digital terrain model (DTM) (0.05 m grid cell) of the torrential channel area to be used for modelling of torrential flows. Furthermore, the point cloud was used for recognition of fallen trees and dead wood (574 LW pieces were recognised), and the results were compared with manual dead wood survey. Approximately 20 % of the LW was not recognised using TLS if compared to the manual survey. The amount of LW was estimated to be ~0.1 m3 per running meter of the torrential channel, and dead tree volume (~30 m3/ha) was compared to the average forest stand for the area (346 m3/ha)–LW found close to the torrential channel represents ~8 % of the wooden biomass. The time consumed for the LW volume calculation stressed the need for the further automation of the procedures.

What about topography? Status and quality of topographic data in Slovenia

Topographic data, an important part of the National Spatial Data Infrastructure, have been given serious attention since Slovenias independence. It has become publicly available, updated and harmonised. Financing of topographic data in Slovenia has significantly decreased over the previous decade. As a result, the present status is far from acceptable or expected. The current status of the topographic data, as well as its quality and usability for potential users is discussed in this article. The overview starts with basic source data, aerial surveys, photographs and orthophotos. The quality of orthophotos largely depends on the DTM quality. Topographic data is nowadays organised in thematic datasets (geographical names, building cadastre, etc.) or joined in datasets of different levels of accuracy and details. The status in Slovenia is compared to those in some neighbouring and other comparable countries.