Praćenje više lica

undergraduate thesis

• Title (english): Multiple face tracking
• Author: Vilim Šoštarić
• Mentor: Igor Sunday Pandžić (mentor)
• Committee member: Igor Sunday Pandžić (predsjednik povjerenstva)
• Committee member: Nenad Markuš (član povjerenstva)
• Committee member: Martina Manhart (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2016-07-11, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Praćenje lica iz kamere, videa ili drugog medija podrazumijeva analizu i obradu dobivene slike te određivanje karakterističnih točaka na pronađenome licu. Algoritam za praćenje više lica temeljen je na alatu koji prati jedno lice uz paralelizaciju glavnih funkcija te dodavanjem mehanizama sinkronizacije i dodatnih obrada ulaznih i izlaznih podataka. U svrhu paralelizacije programa koristi se višedretvenost algoritma gdje svaki pojedini tracker se odvija u zasebnoj dretvi. Kako bi se algoritam pravilno izvodio, svaka dretva mora zacrniti sva druga lica prije praćenja svoga lica. Algoritam ima vrlo dobru brzinu izvođenja te je adekvatan da primjenu u komercijalne svrhe.

Abstract (english)

Face tracking from camera, video file or an other source consists of analysing and processing the given image, then estimating the feature points of the detected face. The algorithm for multiple face tracking is based on a tool for singe face tracking with added parallel processing of critical functions and synchronisation and input-output processing mechanisms. To achieve parallel processing the algorithm uses multi-threading where every tracker is running in his own thread. To ensure that the algorithm is executing correctly, every thread must darken every other face except it's own in the given image before tracking it's face. The algorithm has a farley good execution speed and is adequate for commercial purposes.

• Keywords: praćenje lica; računalni vid; karakteristične točke; višedretvenost; dretva; obrada slike; OpenCV; FDP
• Keywords (english): face tracking; computer vision; feature points; multithreading; thread; image processing; OpenCV; FDP
• Language: croatian
• URN:NBN: urn:nbn:hr:168:891674
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2018-02-06 12:22:06