| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font
First page > Show document

Show document Help

Title:SLEDENJE OBRAZOM NA VIDEO POSNETKIH
Authors:ID Bobek, Tilen (Author)
ID Zazula, Damjan (Mentor) More about this mentor... New window
ID Divjak, Matjaž (Comentor)
Files:.pdf UNI_Bobek_Tilen_2012.pdf (10,39 MB)
MD5: 0204AA1C8AC49AEB435F73AF56DAA2A1
PID: 20.500.12556/dkum/e997ed93-6dd4-4f3b-831c-da4cfc26def9
 
Language:Slovenian
Work type:Undergraduate thesis
Typology:2.11 - Undergraduate Thesis
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:V diplomskem delu preučujemo algoritme na področju sledenja obrazom na video posnetkih. Sprva razčlenimo področje raziskovanja in predstavimo teoretično osnovo priljubljenih sledilnih algoritmov. Večji poudarek namenjamo zasnovi lastne sledilne metode, ki za predstavitev obraza uporablja značilnice za opis barv in tekstur. Izhodišče za razvoj predstavlja obstoječi algoritem Camshift, ki temelji na metodi za iskanje lokalnega ekstrema funkcije in opisuje gostoto porazdelitve podatkovnih vrednosti. Razvili smo orodje za analizo učinkovitosti delovanja sledilnih algoritmov, s pomočjo katerega smo preizkusili sledilne metode na izbranih video posnetkih, ki prikazujejo obraze. Dobljene rezultate smo analizirali in jih med seboj primerjali. Ugotovili smo, da sledilna metoda, ki smo jo razvili sami, dosega boljše rezultate od algoritmov, s katerima smo jo primerjali.
Keywords:Računalniški vid, sledenje gibanju, algoritem povprečnega premika, algoritem Camshift, algoritem Lucas-Kanade, optični tok, histogrami, OpenCV, Emgu CV
Place of publishing:Maribor
Publisher:[T. Bobek]
Year of publishing:2012
PID:20.500.12556/DKUM-23081 New window
UDC:004.92(043.2)
COBISS.SI-ID:16209942 New window
NUK URN:URN:SI:UM:DK:OY1A6J1P
Publication date in DKUM:31.05.2012
Views:3641
Downloads:224
Metadata:XML DC-XML DC-RDF
Categories:KTFMB - FERI
:
BOBEK, Tilen, 2012, SLEDENJE OBRAZOM NA VIDEO POSNETKIH [online]. Bachelor’s thesis. Maribor : T. Bobek. [Accessed 13 April 2025]. Retrieved from: https://dk.um.si/IzpisGradiva.php?lang=eng&id=23081
Copy citation
  
Average score:
0.5
1
1.5
2
2.5
3
3.5
4
4.5
5
(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share


Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Secondary language

Language:English
Title:VIDEO TRACKING OF HUMAN FACES
Abstract:In this diploma thesis we are dealing with the video face tracking algorithms. State of the art is revealed first and the theoretical grounds of the most popular tracking algorithms presented. We put more emphasis on deriving our own tracking method which represents faces by color and texture features. Our development began by the existing Camshift algorithm which is based on finding the local extremes of a function and describes the data density distribution. We developed an auxiliary tool for benchmark testing of the tracking algorithms and used it to assess our tracking methods when applied to video clips showing faces. Results were afterwards analysed and compared. We concluded that our tracking method outperformed two comparable algorithms under consideration.
Keywords:Computer vision, motion tracking, Mean-shift algorithm, Camshift algorithm, Lucas-Kanade approach, optical flow, histograms, OpenCV, Emgu CV


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica