diplomsko delo
Nikola Sekulovski (Author), Marko Meža (Mentor)

Abstract

Diplomsko delo obravnava implementacijo algoritma SIFT na platformi Android za zaznavanje predmetov v videoposnetku v živo na podlagi referenčnih slik, shranjenih v pomnilniku. Implementacija je bila izvedena v več fazah testiranja, da bi zmanjšali število napak ter olajšali in pospešili odpravljanje težav. V prvem koraku je bilo treba zagotoviti, da bo program deloval samo na slikah na namizni napravi. Isti program je bil nato preizkušen na napravi z operacijskim sistemom Android, nato pa je bil nadgrajen za delovanje na videu. Končni program deluje, kot je bilo predvideno, vendar je zaznavanje predmetov vsekakor pomanjkljivo. Vsi predmeti niso prepoznavni; zmogljivost algoritma je omejena neodvisno od njegovih parametrov. Boljše rezultate bi dosegli z uporabo boljše strojne opreme (boljši telefon), vendar je koncept že dokazan.

Keywords

algoritem SIFT;Android;univerzitetni študij;Elektrotehnika;diplomske naloge;

Data

Language: Slovenian
Year of publishing:
Typology: 2.11 - Undergraduate Thesis
Organization: UL FE - Faculty of Electrical Engineering
Publisher: [N. Sekulovski]
UDC: 004.932.72'1:004.451.9Android(043.2)
COBISS: 121173251 Link will open in a new window
Views: 25
Downloads: 11
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Computer vision on the Android platform
Secondary abstract: The thesis addresses implementing the SIFT algorithm on an Android platform to detect objects in live video based on reference images stored in memory. The implementation was done in several stages of testing to minimize the number of errors and to make troubleshooting easier and faster. The first step was to assure that the program will work on images alone on a desktop device. The same program was then tested on an Android device and afterwards was upgraded to work on video. The final program works as intended. However, the object detection is certainly flawed. Not all objects are recognizable and the performance of the algorithm is limited independent of its parameters. Better results would be observed by using better hardware (a better phone). However, the proof of concept is there.
Secondary keywords: SIFT;Android;
Type (COBISS): Bachelor thesis/paper
Study programme: 1000313
Embargo end date (OpenAIRE): 1970-01-01
Thesis comment: Univ. v Ljubljani, Fak. za elektrotehniko
Pages: XVI, 25 str.
ID: 16439165