Analiza dinamičnosti videa pomoću vektora pomaka

undergraduate thesis

• Title (english): Analysis of Video Dynamics Using Motion Vectors
• Author: Dino Tognon
• Mentor: Daniel Hofman (mentor)
• Committee member: Daniel Hofman (član povjerenstva)
• Committee member: Leon Dragić (član povjerenstva)
• Committee member: Alen Duspara (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-07-01, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Kao glavni cilj ovog rada osmišljeni su algoritmi za ocjenu dinamičnosti i kategorizaciju video zapisa na temelju vektora pomaka. Vektori pomaka su sastavni dio H.264 standarda. Koriste se u koraku izbacivanja vremenske redundancije. Algoritmi su vrednovani nad skupom od trideset primjera, izdvojene su glavne karakteristike svakog algoritma te je navedeno kada je koji ispravno koristiti. Osmišljeno je pet kategorija video zapisa po dinamičnosti, te su na temelju vrednovanja određene granične... More vrijednosti kategorija za svaki algoritam. Algoritmi su uspoređeni i po svojstvu kategorizacije na skupu od dvadeset i četiri testna primjera. Razvijen je alat koja implementira razvijene algoritme te omogućava njihovo izvođenje nad odabranim video zapisima. Razvijeni alat za ekstrakciju vektora pomaka iz video zapisa koristi alat mpegflow. Less

Abstract (english)

The main goal of this paper was to develop algorithms for estimating the dynamism and categorization of videos based on motion vectors. Motion vectors are an integral part of the H.264 standard, where they are used for removal of time redundancy. The algorithms were evaluated over a set of thirty examples, the main characteristics of each algorithm were singled out and clear guidelines were given when to use which algorithm. Five categories of videos were designed according to dynamism, and... More based on the previously done evaluation, category limit values for each algorithm were determined. Categorization properties of algorithms was compared on a set of twenty-four test examples. A software tool has been developed that implements the developed algorithms and enables their use on selected videos. The developed tool uses the mpegflow tool to extract motion vectors from videos. Less

• Keywords: vektor pomaka; H.264; dinamičnost; dinamičnost video zapisa; VDTA; ASSV; PNNV; TS; UVL; algoritmi dinamičnosti; kategorizacija dinamičnosti; analiza dinamičnosti
• Keywords (english): motion vector; H.264; dynamism; video dynamism; VDTA; ASSV; PNNV; TS; UVL; dynamism algorithm; dynamism categorization; dynamism analyzation
• Language: croatian
• URN:NBN: urn:nbn:hr:168:361395
• 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: 2023-01-15 11:23:03