Fast and accurate circle tracking using active contour models

In this paper, we deal with the problem of circle tracking across an image sequence. We propose an active contour model based on a new energy. The center and radius of the circle is optimized in each frame by looking for local minima of such energy. The energy estimation does not require edge extrac...

Full description

Saved in:
Bibliographic Details
Published in:Journal of real-time image processing 2018-04, Vol.14 (4), p.793-802
Main Authors: Cuenca, Carmelo, González, Esther, Trujillo, Agustín, Esclarín, Julio, Mazorra, Luis, Alvarez, Luis, Martínez-Mera, Juan Antonio, Tahoces, Pablo G., Carreira, José M.
Format: Article
Language:English
Subjects:
Algorithms
Aorta
Computed tomography
Computer Graphics
Computer Science
Contours
Edge detection
Energy
Image Processing and Computer Vision
Image segmentation
Integrals
Medical imaging
Multimedia Information Systems
Original Research Paper
Pattern Recognition
Signal,Image and Speech Processing
Synthetic data
Tracking
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we deal with the problem of circle tracking across an image sequence. We propose an active contour model based on a new energy. The center and radius of the circle is optimized in each frame by looking for local minima of such energy. The energy estimation does not require edge extraction, it uses the image convolution with a Gaussian kernel and its gradient which is computed using a GPU–CUDA implementation. We propose a Newton–Raphson type algorithm to estimate a local minimum of the energy. The combination of an active contour model which does not require edge detection and a GPU–CUDA implementation provides a fast and accurate method for circle tracking. We present some experimental results on synthetic data, on real images, and on medical images in the context of aorta vessel segmentation in computed tomography (CT) images.
ISSN:1861-8200
1861-8219
DOI:10.1007/s11554-015-0531-5