<?xml version="1.0"?><rdf:RDF xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:edm="http://www.europeana.eu/schemas/edm/" xmlns:wgs84_pos="http://www.w3.org/2003/01/geo/wgs84_pos" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:rdaGr2="http://rdvocab.info/ElementsGr2" xmlns:oai="http://www.openarchives.org/OAI/2.0/" xmlns:owl="http://www.w3.org/2002/07/owl#" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:ore="http://www.openarchives.org/ore/terms/" xmlns:skos="http://www.w3.org/2004/02/skos/core#" xmlns:dcterms="http://purl.org/dc/terms/"><edm:WebResource rdf:about="http://www.dlib.si/stream/URN:NBN:SI:DOC-4IJSZJJY/6-c4fba2c5de4532-2-17da95a85-eae6fa2/PDF"><dcterms:extent>12839 KB</dcterms:extent></edm:WebResource><edm:WebResource rdf:about="http://www.dlib.si/stream/URN:NBN:SI:DOC-4IJSZJJY/7a7c2a71-6d8e-4267-a3f1-e2f35a62d027/TEXT"><dcterms:extent>144 KB</dcterms:extent></edm:WebResource><edm:WebResource rdf:about="http://www.dlib.si/stream/URN:NBN:SI:DOC-4IJSZJJY/863819b8-fca1-4bca-8886-b3721b84f6d4/WEB"><dcterms:extent>0 KB</dcterms:extent></edm:WebResource><edm:ProvidedCHO rdf:about="URN:NBN:SI:DOC-4IJSZJJY"><dcterms:issued>2012</dcterms:issued><dc:creator>Mongus, Domen</dc:creator><dc:contributor>Žalik, Borut</dc:contributor><dc:format xml:lang="sl">X, 90 str., 30 cm</dc:format><dc:identifier>COBISSID:16270870</dc:identifier><dc:identifier>URN:URN:NBN:SI:doc-4IJSZJJY</dc:identifier><dc:language>sl</dc:language><dc:publisher xml:lang="sl">D. Mongus</dc:publisher><dc:source xml:lang="sl">visokošolska dela</dc:source><dc:subject xml:lang="en">algorithms</dc:subject><dc:subject xml:lang="sl">algoritmi</dc:subject><dc:subject xml:lang="en">automatic data filtering</dc:subject><dc:subject xml:lang="en">computational geometry</dc:subject><dc:subject xml:lang="sl">daljinsko zaznavanje</dc:subject><dc:subject xml:lang="en">digital terrain model</dc:subject><dc:subject xml:lang="sl">digitalni model reliefa</dc:subject><dc:subject xml:lang="sl">Disertacije</dc:subject><dc:subject xml:lang="sl">LiDAR</dc:subject><dc:subject xml:lang="sl">matematična morfologija</dc:subject><dc:subject xml:lang="en">mathematical morphology</dc:subject><dc:subject xml:lang="en">pattern recognition</dc:subject><dc:subject xml:lang="sl">Podatki</dc:subject><dc:subject xml:lang="sl">računalniška geometrija</dc:subject><dc:subject xml:lang="sl">razpoznavanje vzorcev</dc:subject><dc:subject xml:lang="en">remote sensing</dc:subject><dc:subject xml:lang="sl">samodejno foltriranje podatkov</dc:subject><dc:subject xml:lang="en">thin plate spline</dc:subject><dc:subject xml:lang="sl">zlepki tankih plošč</dc:subject><dc:title xml:lang="sl">Brezparametrični algoritem gradnje digitalnega modela reliefa iz podatkov LiDAR| doktorska disertacija|</dc:title><dc:description xml:lang="sl">This dissertation considers two new methods for automatic generation of digital terrain models from LiDAR data. The first method iterates a thin platespline interpolated surface towards the ground, while pointsć residuals from the surface are inspected at each iteration, with a gradually decreasing structural element. Top-hat transformation is used to enhance discontinuities caused by surface objects. Finally, parameter-free ground point filtering is achieved by automatic thresholding, based on a standard deviation. The experiments show that this method correctly determines DTM even in those casesof difficult terrain features. The expected accuracy of ground point determination on those datasets commonly used in practice today is over 96%, while the average total error produced on the ISPRS benchmark dataset is under6%. The second method uses an adaptive morphological filter, where the size of the structural element is defined by the distance of a point from itćsnearest edge. The input data is arranged into a grid and compass edge detection based on the Sobel operator is applied for edge extraction. Morphological region-filling is used in order to segment grid-cells into foreground and background regions, while the distance transformation of the foreground regions defines the size of the structural element for each foreground grid-cell. Finally, LiDAR point-filtering is achieved using adaptive top-hat transformation, followed by a constant thresholding. As confirmed by experiments, the average CPU execution time decreases by more than 94% compared to the first method, while the accuracy improves by nearly 20% on low-density datasets, and by nearly 30% on high-density datasets</dc:description><dc:description xml:lang="sl">V doktorski disertaciji opišemo dva postopka gradnje digitalnega modela reliefa iz podatkov LiDAR. Prva metoda iterativno približuje zlepke tankih plošč proti terenu, pri čemer s postopnim zmanjševanjem strukturnega elementa opravlja filtriranje točk glede na njihove viške razlike z interpolacijsko ploskvijo. S cilindrično transformacijo okrepimo nezveznosti v porazdelitvi točk, ki so posledica prisotnosti objektov. Brezparametrično pragovno filtriranje dosežemo samodejno s pragovno vrednostjo, definirano s standardno deviacijo. Rezultati pokažejo, da metoda pravilno določi teren tudi v najzahtevnejših primerih. Pričakovana natančnost metode nad podatki, danes uporabljenimi v vsakodnevni praksi, je več kot 96 %, medtem ko povprečna skupna napaka nad naborom testnih podatkov združenja ISPRS ne preraste 6 %. Druga metoda uporablja prilagodljiv morfološki filter, kjer je velikost strukturnega elementa v vsaki točki določena glede na njeno razdaljo do najbližjega roba. Vhodni nabor podatkov v ta namen najprej razporedimo v mrežo, nad katero izvedemo zaznavo robov z metodo kompas in Sobelovim operatorjem. Z morfološkim polnjenjem regij razdelimo mrežo v regije ospredja in ozadja. Definicijo strukturnega elementa izpeljemo iz transformacije razdalj regij ospredja. Končno filtriranje podatkov opravimo s cilindrično transformacijo in pragovnim filtriranjem. Z rezultati pokažemo, da na ta način v primerjavi s prvo metodo dosežemo 94 % višjo računsko učinkovitost, medtem ko je natančnost metode višja za 20 % nad podatki z nižjo ločljivostjo ter 30 % nad podatki z višjo ločljivostjo</dc:description><edm:type>TEXT</edm:type><dc:type xml:lang="sl">visokošolska dela</dc:type><dc:type xml:lang="en">theses and dissertations</dc:type><dc:type rdf:resource="http://www.wikidata.org/entity/Q1266946" /></edm:ProvidedCHO><ore:Aggregation rdf:about="http://www.dlib.si/?URN=URN:NBN:SI:DOC-4IJSZJJY"><edm:aggregatedCHO rdf:resource="URN:NBN:SI:DOC-4IJSZJJY" /><edm:isShownBy rdf:resource="http://www.dlib.si/stream/URN:NBN:SI:DOC-4IJSZJJY/6-c4fba2c5de4532-2-17da95a85-eae6fa2/PDF" /><edm:rights rdf:resource="http://rightsstatements.org/vocab/InC/1.0/" /><edm:provider>Slovenian National E-content Aggregator</edm:provider><edm:intermediateProvider xml:lang="en">National and University Library of Slovenia</edm:intermediateProvider><edm:dataProvider xml:lang="sl">Univerza v Mariboru, Fakulteta za elektrotehniko računalništvo in informatiko</edm:dataProvider><edm:object rdf:resource="http://www.dlib.si/streamdb/URN:NBN:SI:DOC-4IJSZJJY/maxi/edm" /><edm:isShownAt rdf:resource="http://www.dlib.si/details/URN:NBN:SI:DOC-4IJSZJJY" /></ore:Aggregation></rdf:RDF>