Usporedba metoda procjene dubine pri praćenju lica

master's thesis

• Title (english): Comparison of Depth Estimation Methods in Face Tracking
• Author: Luka Bunić
• Mentor: Igor Sunday Pandžić (mentor)
• Committee member: Igor Sunday Pandžić (predsjednik povjerenstva)
• Committee member: Mirko Sužnjević (član povjerenstva)
• Committee member: Krešimir Pripužić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2022-07-13, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Procjena udaljenosti lica od kamere je problem čija rješenja imaju široku primjenu. Kako bi detektirali lice potrebno je upotrijebiti neki od brojnih algoritama za detekciju, te iskoristiti dobivene pozicije u svrhu procjene dubine. U slučaju jedne kamere rješenje se nalazi u mjerenju poznatih dimenzija lica na slici. Detekcijom više značajki, moguće je i rekonstruirati i cijelu 3D pozu lica, te tako dobiti preciznije vrijednosti dubine. Međutim, uporabom dvije kalibrirane kamere možemo dobiti dubinu bilo koje točke vidljive na obje kamere, te se udaljenost lica svodi na mjerenje otklona iste točke na licu.

Abstract (english)

Face depth estimation in camera scene is an engineering problem whose solutions have widespread use. To measure face depth, we first must detect its presence in camera scene. We accomplish this using one of many facial detection algorithms to determine its position on screen and subsequently calculate its depth. In case of one camera, solution lies in measuring dimensions of one or more facial features on screen. Detecting and measuring multiple features to reconstruct 3D facial pose, yields greater precision in depth estimation. Using two cameras it is possible to estimate depth of any point visible on two screens and face depth estimation can be resolved by measuring disparity of the selected point on face.

• Keywords: procjena dubine; stereo vid; OpenCV; Visage SDK; mjerenje udaljenosti od kamere; detekcija značajki lica; detekcija lica
• Keywords (english): depth estimation; stereo vision; OpenCV; Visage SDK; camera distance measurement; facial feature detection; face detection
• Language: croatian
• URN:NBN: urn:nbn:hr:168:807293
• 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: 2023-01-13 14:39:42