Fast Geodesic Active Contours

Active contours for video object tracking using region, boundary and shape information

“…Further, using fast numerical schemes for resolving the level set in Eq. (11) (see [7,33] and the references given there) can significantly enhance the speed of the algorithm. Finally, multiple-object tracking can be implemented in parallel programming with a special processing step to handle object occlusions.…”

“…Among the model-based tracking methods, active contours have gained popularity in the last few years [5][6][7]14,15,17]. With active contours, non-rigid bodies can be tracked thanks to the deformation capacity of the contours.…”

“…For example, in [15,16], the authors propose partitioning the difference image between two successive frames of the sequence in order to separate the moving objects from the background. In [7], a fast boundary-based method is proposed for object contour tracking. However, only the edge information is used as a cue for tracking, which makes the method sensitive to noise.…”

Automatic 4D endocardium segmentation using hierarchical registration and model guided level set segmentation

“…[14], geometric deformable models are defined as the zero level set of an implicit function /, defined on the entire image. The evolution of the surface is defined via partial differential equation on the implicit function /.…”

Adaptive active contours based on local and global intensity information for image segmentation

“…Existing implicit active contour models can be roughly categorized, based on the image features used for segmentation, into two basic classes: edge-based models [3][4][5][6][7][8] and region-based models [9][10][11][12][13][14][15]. Edge-based models utilize typically image gradient as an image-based force to attract the contour toward the boundaries of the desired objects.…”