Praćenje višestrukog broja objekata jedne klase uz tehniku re-identifikacije

master's thesis

• Title (english): Tracking multiple objects of one class with re-identification technique
• Author: Dominik Vrbanić
• Mentor: Stjepan Bogdan (mentor)
• Committee member: Stjepan Bogdan (član povjerenstva)
• Committee member: Zdenko Kovačić (član povjerenstva)
• Committee member: Goran Vasiljević (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2022-09-12, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovome diplomskom radu nabrojane su i ukratko objašnjene najsuvremenije tehnologije
za prac´enje više pokretnih objekata u slici. Takod¯er su predstavljeni neki od izazova u tom
podruˇcju. Odabran je jedan od algoritama, Deep SORT, koji koristi neuronske mreže kako
bi pratio objekte u stvarnom vremenu. Algoritam je implementiran i testiran na problemu
pra´cenja bespilotnih letjelica.

Abstract (english)

In this diploma thesis, the most modern technologies for tracking several moving objects
in the image are listed and briefly explained. Some of the challenges in this area are also
presented. One of the algorithms, Deep SORT, was chosen, which uses neural networks to
track objects in real time. The algorithm was implemented and tested on the problem of
unmanned aerial vehicles tracking.

• Keywords: praćenje objekata; neuronske mreže; sijamske neuronske mreže; stvarno vrijeme; bespilotna letjelica; Deep SORT
• Keywords (english): object tracking; neural networks; siamese neural networks; real time; unmanned aerial vehicle; Deep SORT
• Language: croatian
• URN:NBN: urn:nbn:hr:168:917652
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-14 10:14:35