Title :
Analysis of motion and curvature in image sequences
Author :
Barth, Erhardt ; Stuke, Ingo ; Mota, Cicero
Author_Institution :
Inst. for Neuro- & Bioinformatics, Univ. of Lubeck, Germany
Abstract :
We briefly review a recent development in the area of computer vision and multidimensional signal processing. Image sequences are regarded as hypersurfaces and useful properties are derived from the geometry of that hypersurface. Besides demonstrating the uniqueness of curvature, new methods for the analysis of single and multiple motions are presented including the case of occluded motions
Keywords :
computational geometry; computer vision; image motion analysis; image sequences; multidimensional signal processing; computer vision; curvature; geometry; hypersurfaces; image sequences; motion analysis; multidimensional signal processing; multiple motions; occluded motions; single motions; Computer vision; Filters; Geometry; Image analysis; Image motion analysis; Image sequence analysis; Image sequences; Motion analysis; Motion detection; Tensile stress;
Conference_Titel :
Image Analysis and Interpretation, 2002. Proceedings. Fifth IEEE Southwest Symposium on
Conference_Location :
Sante Fe, NM
Print_ISBN :
0-7695-1537-1
DOI :
10.1109/IAI.2002.999919
