Title :
Coupled parametric active contours
Author :
Zimmer, Christophe ; Olivo-Marin, J.-C.
Author_Institution :
Quantitative Image Anal. Group, Institut Pasteur, Paris, France
Abstract :
We propose an extension of parametric active contours designed to track nonoccluding objects transiently touching each other, a task where both parametric and single level set-based methods usually fail. Our technique minimizes a cost functional that depends on all contours simultaneously and includes a penalty for contour overlaps. This scheme allows us to take advantage of known constraints on object topology, namely, that objects cannot merge. The coupled contours preserve the identity of previously isolated objects during and after a contact event, thus allowing segmentation and tracking to proceed as desired.
Keywords :
edge detection; image segmentation; object detection; topology; coupled parametric active contours; image segmentation; nonoccluding objects; object topology; object tracking; Active contours; Computational efficiency; Cost function; Equations; Evolution (biology); Image segmentation; Image sequences; Level set; Minimization methods; Topology; 2D video.; Index Terms- Segmentation; active contours; topology; tracking; Algorithms; Animals; Artificial Intelligence; Cell Movement; Humans; Image Enhancement; Image Interpretation, Computer-Assisted; Information Storage and Retrieval; Microscopy, Video; Pattern Recognition, Automated; Subtraction Technique;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.2005.214