Sciweavers

30 search results - page 4 / 6
» Multi-feature vector flow for active contour tracking
Sort
View
ICIP
2006
IEEE
14 years 9 months ago
Vector Field Convolution for Image Segmentation using Snakes
Snakes, or active contours, have been widely used in image processing applications. Typical roadblocks to consistent performance include limited capture range, noise sensitivity, ...
Bing Li, Scott T. Acton
ICPR
2008
IEEE
14 years 9 months ago
Accelerating active contour algorithms with the Gradient Diffusion Field
Active contours were proposed by Kass et al. as a way to represent the contours of an image. Although the method is simple, one of its shortcomings is its inability to converge in...
Willie Kiser, Pradeep Sen, Chris Musial
EMMCVPR
2003
Springer
14 years 1 months ago
Curvature Vector Flow to Assure Convergent Deformable Models for Shape Modelling
Poor convergence to concave shapes is a main limitation of snakes as a standard segmentation and shape modelling technique. The gradient of the external energy of the snake represe...
Debora Gil, Petia Radeva
ICPR
2008
IEEE
14 years 9 months ago
Learning motion patterns in crowded scenes using motion flow field
Learning typical motion patterns or activities from videos of crowded scenes is an important visual surveillance problem. To detect typical motion patterns in crowded scenarios, w...
Min Hu, Mubarak Shah, Saad Ali
ICCV
2001
IEEE
14 years 9 months ago
Flux Maximizing Geometric Flows
Several geometric active contour models have been proposed for segmentation in computer vision. The essential idea is to evolve a curve (in 2D) or a surface (in 3D) under constrai...
Alexander Vasilevskiy, Kaleem Siddiqi