| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:OVREDNOTENJE POSNETKOV LiDAR ZA ZAZNAVO OBJEKTOV
Authors:ID Rupnik, Bojan (Author)
ID Žalik, Borut (Mentor) More about this mentor... New window
Files:.pdf EDOK_Rupnik_Bojan_2016.pdf (16,31 MB)
MD5: 38AAB68378DCD4B8D9D39AB3B3F73BD9
 
Language:Slovenian
Work type:Dissertation
Typology:2.08 - Doctoral Dissertation
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:Doktorska disertacija obravnava vrednotenje posnetkov LiDAR za zmožnost zaznave objektov. V njej opišemo osnove zajemanja zemeljskega površja s tehnologijo LiDAR ter predstavimo najpomembnejše karakteristike za oceno kakovosti pridobljenih posnetkov. Pri pregledu sorodnih del na področju analize kakovosti se osredotočimo na lokalno gostoto točk in razmik med njimi ter na njun vpliv na najpogostejše procese pri obdelavi podatkov LiDAR. Za natančno oceno gostote in razmika med točkami v posnetkih LiDAR razvijemo lastno metodo, ki temelji na prostorski delitvi z Voronoijevim diagramom. Metoda z analizo časovnih zapisov identificira območja šibkih odbojev, ki jih lahko pripišemo vodnim površinam in jih snemalnik ni zmožen kakovostno posneti. Ta območja izločimo iz posnetka in analizo osredotočimo na tista, ki omogočajo snemanje. Izkaže se, da sta gostota točk, potrebna za razpoznavo objekta, in velikost objekta v nelinearni funkcijski odvisnosti. Na osnovi te funkcijske odvisnosti in lokalnih gostot točk, pridobljenih iz Voronoijevega diagrama, lahko določimo področja, ki zagotovo omogočajo klasifikacijo objekta.
Keywords:LiDAR, gostota točk, lokalni razmik med točkami, Voronoijev diagram, zaznavanje objektov
Place of publishing:Maribor
Publisher:[B. Rupnik]
Year of publishing:2016
PID:20.500.12556/DKUM-61892 New window
UDC:528.873:621.396.969.969.3(043.3)
COBISS.SI-ID:19819798 New window
NUK URN:URN:SI:UM:DK:0BB02C29
Publication date in DKUM:16.09.2016
Views:2211
Downloads:221
Metadata:XML DC-XML DC-RDF
Categories:KTFMB - FERI
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share



Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Secondary language

Language:English
Title:LiDAR scan evaluation for object detection
Abstract:The presented thesis examines the evaluation of LiDAR scans regarding their capacity for object detection. It covers the basics of topographic scanning using LiDAR technology and introduces most essential characteristics for evaluating the acquired scans. Studying related work on quality analysis the focus is set on local point density and point spacing, as well as their impact on the most common procedures of LiDAR processing. A new method for precise estimation of the actual point density and spacing is presented that is based on spatial division using the Voronoi diagram. Based on the analysis of scan times, the method identifies areas of weak returns that can be attributed to water surfaces, which are not fully detectable by the scanner. Those areas are omitted from the scan, thus, the analysis is focused on those that allow quality scanning only. By omitting those areas and by locally measuring the point density and spacing per each individual point, the method evaluates the LiDAR scan’s capacity for detecting objects. A nonlinear functional dependency between the required point density for object detection and the size of the object is revealed. Based on this function and local point densities acquired by the Voronoi diagram we can determine in which areas object classification is definitely possible.
Keywords:LiDAR, local point density, local point spacing, Voronoi diagram, object detecion


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica