izpis_h1_title_alt

Metoda za dolgoročno vizualno sledenje z značilnimi točkami
STRGAR, TINA (Author), Kristan, Matej (Mentor) More about this mentor... This link opens in a new window

.pdfPDF - Presentation file, Download (6,62 MB)

Abstract
V nalogi naslovimo problem dolgoročnega vizualnega sledenja. Izziv predstavljajo dinamično učenje videza tarče, zaznavanje odsotnosti tarče in njeno ponovno detektiranje. Predlagamo sledilnik, ki vizualni model sledene tarče gradi na podlagi lokalnih značilnic in afine preslikave. Dolgoročno sledenje je izvedeno z detekcijo, kratkoročno pa tudi s pomočjo optičnega toka. Pri prileganju preslikave sledilnik uporablja gnezdenje metod: najprej oceni gručo točk, ki verjetno pripadajo tarči, nato pa robustno oceni afino deformacijo. Značilnice za dodajanje modelu so izbrane na podlagi globalne predloge oblike, hkrati pa le-te prispevajo k njenemu posodabljanju, kar tvori povratno zanko. Sledilnik smo testirali na dveh skupinah sekvenc. Prva je namenjena primerjavi dolgoročnih, druga pa kratkoročnih sledilnikov. Rezultate primerjamo s trenutno najnaprednejšimi metodami na področju. Sledilnik se jim v uspešnosti približa, večjo pozornost pa bi bilo potrebno nameniti problemu ponovne detekcije.

Language:Slovenian
Keywords:računalniški vid, dolgoročno vizualno sledenje, dinamično učenje, posplošena Houghova transformacija, afina preslikava
Work type:Bachelor thesis/paper (mb11)
Organization:FRI - Faculty of computer and information science
Year:2014
Views:907
Downloads:343
Metadata:XML RDF-CHPDL DC-XML DC-RDF
 
Average score:(0 votes)
Your score:Voting is allowed only to logged in users.
:
Share:AddThis
AddThis uses cookies that require your consent. Edit consent...

Secondary language

Language:English
Title:A key-point based approach for long-term visual tracking
Abstract:
In the thesis the problem of long-term visual tracking is addressed. The main challenges of the problem are on-line learning of the target's visual appearance, recognition of target's absence and it's redetection. A part-based tracker is proposed using local features and affine transformation. Long-term tracking is performed with tracking-by-detection, supported by optical flow in the short term. Two nested methods are used when fitting the transformation: firstly, a cluster of potential target points is defined, then the affine deformation is robustly estimated. New model features are added based on the global shape template, that is updated by the features themselves, forming a feedback-loop. The tracker is tested on two groups of sequences, the first targeting long-term and the second short-term trackers. The results are compared with the state-of-the-art methods. The performance of the tracker is comparable, though the problem of redetection should be more carefully addressed.

Keywords:computer vision, long-term visual tracking, online learning, general Hough transform, affine transformation

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Comments

Leave comment

You have to log in to leave a comment.

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

Back