Deidentifikacija osoba u video zapisima uporabom virtualnih ljudskih likova

undergraduate thesis

• Title (english): Person de-identification in video sequences by using virtual human characters
• Author: Josip Mandić
• Mentor: Tomislav Hrkać (mentor)
• Committee member: Tomislav Hrkać (predsjednik povjerenstva)
• Committee member: Danko Ivošević (član povjerenstva)
• Committee member: Darijan Marčetić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2015-07-13, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Ovaj rad opisuje postupak deidentifikacije snimljene osobe pomoću virtualnog lika. U tekstu su objašnjene metode i korištene tehnologije za izradu programa koji bi na učitanu video snimku ubacio izrađeni 3D model te učinio da se taj model ponaša kao snimljena osoba u videu. Za snimanje je korišten Microsoft Kinect uređaj zbog svojih senzora dubine i RGB senzora slike. Izrada modela je napravljena u besplatnom alatu MakeHuman, dok je čitavo rješenje napisano u Microsoft Visual Studiu korištenjem OpenGl kao glavnog alata za manipulaciju prikaza podataka videa, Kinect podataka i podataka 3D modela.

Abstract (english)

This work describes the procedure of deidentificating the recorded person through visual characters. In this text are explained the methods and used technologies for program production. Those programs would inject the manufactured 3-D model into the loaded video recording and make them work out as a recorded person. Microsoft Kinect is used for the shooting beacuse of his depth sensors and RGB picture sensor. Model craftmanship was made in the freeware tool Make Human, while the whole solution is realised in Microsoft Visual Studio, using the OpenGL as the main tool for manipulating video data, Kinect data and the 3D model data.

• Keywords: kinect; opengl; skeletonizacija; prikaz kostura uporabom kinect uređaja; makehuman modeliranje; računalni vid; collada format; assimp
• Keywords (english): kinect; opengl; skeletal tracking; Kinect skeleton data; makehuman modeling; computer vision; collada format; assimp
• Language: croatian
• URN:NBN: urn:nbn:hr:168:616501
• 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 10:22:42