Euclidean Invariant Snake for Joint Stereoscopic Segmentation

Author

Charmiw, M.A. ; Derrode, S. ; Ghorbel, F.

Author_Institution

GRIFT, Ecole Nationale des Sci. de l´´Informatique, Manouba

Volume

1

fYear

0

fDate

0-0 0

Firstpage

1074

Lastpage

1079

Abstract

In this paper, we present the application of a recent method of snakes with geometric shape prior for the segmentation of a pair of calibrated stereo images. Contours in one image of the pair are found using those in the other image as reference. The initialization of the snakes algorithm on the second image is performed automatically by matching only four particular points. The method is then adapted for object motion tracking in mono and stereo video sequences. The outlines of the algorithm are detailed and some experimental results are given and commented

Keywords

geometry; image matching; image motion analysis; image segmentation; image sequences; stereo image processing; Euclidean invariant snake; Fourier descriptors; calibrated stereo images; epilines; geometric shape; image contour; image matching; joint stereoscopic segmentation; object motion tracking; snakes algorithm; stereo video tracking; Active contours; Cameras; GSM; Image converters; Image segmentation; Laboratories; Shape; Stereo vision; Tracking; Video sequences; Fourier descriptors; SSnakes; epilines; invariant; shape prior; stereo video tracking; stereovisioin; video tracking;

fLanguage

English

Publisher

ieee

Conference_Titel

Information and Communication Technologies, 2006. ICTTA '06. 2nd

Conference_Location

Damascus

Print_ISBN

0-7803-9521-2

Type

conf

DOI

10.1109/ICTTA.2006.1684523

Filename

1684523