Entity

Time filter

Source Type

Novo Mesto, Slovenia

Zaletelj J.,University of Ljubljana | Cotar K.,Center odlicnosti Vesolje
Elektrotehniski Vestnik/Electrotechnical Review | Year: 2015

The paper proposes a procedure of automatic evaluation of results of road detection from satellite imagery. Four different road-detection algorithms are used to generate binary masks of the road network from the medium-resolution RapidEye satellite images. The empirical measures of correctness, completeness and overall quality of the extracted roads are defined based on the detected and reference road masks. Hand-drawn road masks of a smaller portion of the satellite images are used as a standard reference. In its second part, the paper proposes on automatic generation of the reference road masks from the vector road data available from GIS. It compares the results of four road-detection methods by using two different reference masks, one generated automatically from GIS data and the other generated by hand. The GIS-based automatic evaluation is found acceptable for a relative evaluation of different road detection algorithms though not yet sufficiently accurate for an absolute evaluation of the road-detection correctness and completeness. Source


Lenarcic A.S.,Center odlicnosti Vesolje | Mesner N.,Geodetski Institute Slovenije | Ostir K.,Institute za antropoloske in prostorske studije
Geodetski Vestnik | Year: 2015

Sentinel satellites and the European Copernicus programme have begun to provide huge amounts of high spatial and temporal resolution images, which need to be processed quickly and preferably automatically. Object based classification is the most commonly used method for the interpretation of high spatial resolution optical images. It is a challenging process of object borders recognition (segmentation) and classification of segments in the user-defined classes (classification). The quality of the segmentation is crucial because it has a direct impact on the quality of final classification results. Several algorithms have been developed for optical remote sensing imagery segmentation with varying (depending on the purpose of the analysis) accuracy. Knowledge of algorithms and adequacy of application are crucial for high quality segmentation results. In this paper, we give an overview of optical remote sensing imagery segmentation algorithms and the possibility of their application. Besides, an overview of object based classification software, with a focus on segmentation process, is given. The intent of this paper is not to provide a recipe for the best algorithm and software selection, but to support users with knowledge they might need to be able to obtain the best possible segmentation results of an analysis in given circumstances. © 2015 Zvava Geodetov Slovenije. All rights reserved. Source


Veljanovski T.,Institute za antropoloske in prostorske studije | Veljanovski T.,Center odlicnosti Vesolje | Pehani P.,Institute za antropoloske in prostorske studije | Pehani P.,Center odlicnosti Vesolje | And 3 more authors.
Geodetski Vestnik | Year: 2012

This article presents a review and comparison of the detection capability of water facilities or water surfaces with different systems of remote sensing: optical and radar satellite sensors, as well as optical sensors on aircraft. The capabilities of water detection are estimated from several aspects: differences in the spatial and spectral resolution of imagery, the complexity of imagery pre-processing requirements, and the method of analysis and interpretation feasibilities for the type and purpose of mapping. Particular attention is paid to evaluating the applicability of remote sensing data in light of the detection efficiency of water areas in heterogeneously structured environments. Source


Spatially and temporally differentiated (dynamic) road pricing considers several parameters of internal and external costs when calculating the height of the road toll. Finding the link between the impact of a certain parameter on the environment and individual road sections presents a challenge for calculation of the dynamic road toll for individual road sections. The article presents methodology to transform ascertained spatial distribution of noise impacts on the environment to road segments, based on the study of noise impacts on humans. The method also permits classification of road segments into impact classes according to time, and thus enables spatially and temporally differentiated toll. Source

Discover hidden collaborations