Visual Tracking and Reconstruction of 3D Curves in Medical Image Analysis = Vizualno praćenje i rekonstrukcija 3D krivulja za analizu medicinskih slika : doctoral thesis = doktorska disertacija / Tomislav Petković ml. ; [mentor Sven Lončarić]
By: Petković, Tomislav ml
.
Contributor(s): Lončarić, Sven [ths].
Material type: 
TextPublisher: Zagreb : T. Petković ml. ;Fakultet elektrotehnike i računarstva, 2010Description: vii, 158 str. : graf. prikazi ; 30 cm + CD.Summary: Visual tracking of moving objects is one of important open problems in the eld of computer vision. Due to complexity instead of a general purpose solution usually only solutions for a well-dened application are considered. Furthermore, the visual tracking in the eld of bio-medicine is often based on transmissive and projective acquisition model making the existing procedures not applicable due to acquisition model incompatibility. Better results can be achieved by utilizing methods adapted to the acquisition model. In this dissertation a modular tracking algorithm to visually track moving objects that can be represented by a 3D curve is presented. The described algorithm is adapted to the acquisition model. As the acquisition geometry is projective reconstruction of the curve position and orientation is also discussed and the limitations to reconstruction uniqueness and accuracy are given in regard to the number of available views. Guidewire tracking during minimally invasive endovascular interventions is used as an example. Keywords: 3D curve reconstruction from projections, transmissive imaging, guidewire tracking, guidewire reconstructionSummary: Vizualno pracenje pokretnih objekata predstavlja jedan od vaznih otvorenih problema racunalnog vida. Zbog slozenosti problema se umjesto opceg konstruiraju algoritmi samo za usko denirane primjene. Nadalje, vizualno pracenje u bio-medicini se cesto temelj na transmisijskom projektivnom snimanju pa postoje ci postupci nisu prikladni jer ne odgovaraju takvom modelu snimanja. Bolji rezultati se mogu ocekivati upotrebom metoda prilagodenih takvom snimanju. U okviru disertacije predlozen je modularni postupak za vizualno pracenje pokretnih objekata koji se mogu priblizno opisati 3D krivuljom. Opisani postupak je dodatno prilagoden transmisijskom projektivnom snimanju. Kako se radi o projektivnom snimanju 3D objekta osim pracenja razmatra se i problem rekonstrukcije polozaja i orijentacije te se daju ogranicenja na jedinstvenost i tocnost rekonstrukcije ovisno o broju dostupnih pogleda. Kao primjer primjene daje se pracenje katetera tijekom minimalno invazivnih vaskularnih zahvata. Kljucne rijeci: rekonstrukcija 3D krivulje iz projekcija, transmisijsko snimanje, pracenje katetera, rekonstrukcija katetera
| Item type | Current location | Call number | Vol info | Copy number | Status | Notes | Date due | Barcode | Item holds |
|---|---|---|---|---|---|---|---|---|---|
Doktorska disertacija
|
Središnja knjižnica KF | KF-4379 | 004.92 PETKO vis | 28541 | Available | 0000000798600 | |||
|
Doktorska disertacija
|
Središnja knjižnica | KF-4379 | 004.92 PETKO vis | 28542 | 1 | 0000000798617 | |||
|
Doktorska disertacija
|
Središnja knjižnica | KF-4379 | 004.92 PETKO vis | 28541/cd | 1 | CD | 0000000798624 |
Visual tracking of moving objects is one of important open problems in the eld of computer vision. Due to complexity instead of a general purpose solution usually only solutions for a well-dened application are considered. Furthermore, the visual tracking in the eld of bio-medicine is often based on transmissive and projective acquisition model making the existing procedures not applicable due to acquisition model incompatibility. Better results can be achieved by utilizing methods adapted to the acquisition model. In this dissertation a modular tracking algorithm to visually track moving objects that can be represented by a 3D curve is presented. The described algorithm is adapted to the acquisition model. As the acquisition geometry is projective reconstruction of the curve position and orientation is also discussed and the limitations to reconstruction uniqueness and accuracy are given in regard to the number of available views. Guidewire tracking during minimally invasive endovascular interventions is used as an example. Keywords: 3D curve reconstruction from projections, transmissive imaging, guidewire tracking, guidewire reconstruction
Vizualno pracenje pokretnih objekata predstavlja jedan od vaznih otvorenih problema racunalnog vida. Zbog slozenosti problema se umjesto opceg konstruiraju algoritmi samo za usko denirane primjene. Nadalje, vizualno pracenje u bio-medicini se cesto temelj na transmisijskom projektivnom snimanju pa postoje ci postupci nisu prikladni jer ne odgovaraju takvom modelu snimanja. Bolji rezultati se mogu ocekivati upotrebom metoda prilagodenih takvom snimanju. U okviru disertacije predlozen je modularni postupak za vizualno pracenje pokretnih objekata koji se mogu priblizno opisati 3D krivuljom. Opisani postupak je dodatno prilagoden transmisijskom projektivnom snimanju. Kako se radi o projektivnom snimanju 3D objekta osim pracenja razmatra se i problem rekonstrukcije polozaja i orijentacije te se daju ogranicenja na jedinstvenost i tocnost rekonstrukcije ovisno o broju dostupnih pogleda. Kao primjer primjene daje se pracenje katetera tijekom minimalno invazivnih vaskularnih zahvata. Kljucne rijeci: rekonstrukcija 3D krivulje iz projekcija, transmisijsko snimanje, pracenje katetera, rekonstrukcija katetera
There are no comments for this item.