diplomsko delo
Andrej Zadnikar (Avtor), Tomaž Dobravec (Mentor)

Povzetek

Zaznavanje objektov na topografskih kartah

Ključne besede

zaznavanje objektov;topografska karta;Houghova linearna transformacija;konvolucijska maska;Sobelov operator;odvod;gradient;računalništvo;visokošolski strokovni študij;diplomske naloge;

Podatki

Jezik: Slovenski jezik
Leto izida:
Tipologija: 2.11 - Diplomsko delo
Organizacija: UL FRI - Fakulteta za računalništvo in informatiko
Založnik: [A. Zadnikar]
UDK: 004(043.2)
COBISS: 7189332 Povezava se bo odprla v novem oknu
Št. ogledov: 110
Št. prenosov: 7
Ocena: 0 (0 glasov)
Metapodatki: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Ostali podatki

Sekundarni jezik: Angleški jezik
Sekundarni naslov: [Detection of structures on topographic maps]
Sekundarni povzetek: The purpose of this graduation thesis is to develop an algorithm to automatically acquire positions of buildings or objects on a topographic map and assign found objects their boundary lines. The thesis first presents some established methods for image processing and analysis. The presented methods are: • use of convolution masks for picture filtering • use of the Sobel operator for edge detection • derivation for gradient checking • linear Hough transform This is followed by the description of an algorithm that uses the aforementioned methods to find approximate positions of all objects and assign each object their boundary lines. The output of the algorithm is a set of polygons that represent, with their shape and position, buildings on the topographic map. The results can be represented in a 3D environment with some additional processing. The described and implemented algorithm works well but still has a lot of room for improvement.
Sekundarne ključne besede: object detection;topographic map;linear Hough transform;convolution mask;Sobel operator;derivative;gradient;computer science;diploma;
Vrsta datoteke: application/pdf
Vrsta dela (COBISS): Diplomsko delo
Komentar na gradivo: Univerza v Ljubljani, Fakulteta za računalništvo in informatiko
Strani: 49 str.
ID: 23868185
Priporočena dela:
, diplomsko delo
, diplomsko delo