Name
Abstract | ||
|---|---|---|
Using variational calculus we develop an active contour model to segment an object across a number of image frames in the presence of an optical flow field. We define an energy functional that is locally minimized when the object is tracked across the entire image stack. Unlike classical snakes, image forces and regularization terms are integrated over the full set of images in the proposed model. This results in a new formulation of active contours. The method is demonstrated by segmenting the ascending aorta in a phase-contrast cine MRI dataset. Techniques to compute the required optical flow field and a "one-click" contour initialization step are suggested for this particular modality. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1109/ISBI.2010.5490136 | ISBI |
Keywords | Field | DocType |
optical flow field,entire image,contour initialization step,active contour model,image sequence segmentation,required optical flow field,mri dataset,active contour,image frame,image force,optical imaging,phase contrast,mri,computer science,magnetic resonance imaging,image segmentation,optical computing,variational calculus,biomedical imaging,optical flow,segmentation,regularization,computer vision,calculus | Active contour model,Computer vision,Pattern recognition,Segmentation,Computer science,Calculus of variations,Image segmentation,Regularization (mathematics),Artificial intelligence,Initialization,Energy functional,Optical flow | Conference |
ISSN | Citations | PageRank |
1945-7928 | 1 | 0.39 |
References | Authors | |
2 | 7 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Thomas Sangild Sørensen | 1 | 42 | 5.73 |
| Karsten Østergaard Noe | 2 | 16 | 2.09 |
| Christian P. V. Christoffersen | 3 | 1 | 0.39 |
| Martin Kristiansen | 4 | 10 | 0.83 |
| Kim Mouridsen | 5 | 12 | 2.70 |
| Ole Østerby | 6 | 27 | 6.91 |
| Lau Brix | 7 | 1 | 0.39 |