Motion segmentation and estimation

Author

Tian, Tina Yu ; Shah, Mubarak

Author_Institution

Dept. of Comput. Sci., Central Florida Univ., Orlando, FL, USA

Volume

2

fYear

1994

fDate

13-16 Nov 1994

Firstpage

785

Abstract

Applies mean field technique and presents a deterministic algorithm to determine the optical flow and motion boundaries. To deal with the problem of large motion, the authors present an adaptive multigrid approach, which also greatly reduces the computation time. This algorithm is fully parallelizable and iterative. The performance of the proposed method is compared against known algorithms using performance measures proposed by Barren et al. [1992]. Experimental results indicate that the present approach provides good estimates of optical flow and motion boundaries

Keywords

adaptive signal processing; edge detection; image segmentation; image sequences; iterative methods; motion estimation; parallel algorithms; adaptive multigrid approach; computation time; deterministic algorithm; estimation; fully parallelizable algorithm; iterative algorithm; large motion; mean field technique; motion boundaries; motion segmentation; optical flow; Computer science; Computer vision; Cost function; Image motion analysis; Iterative algorithms; Motion estimation; Motion segmentation; Optical computing; Simulated annealing; Smoothing methods;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 1994. Proceedings. ICIP-94., IEEE International Conference

Conference_Location

Austin, TX

Print_ISBN

0-8186-6952-7

Type

conf

DOI

10.1109/ICIP.1994.413678

Filename

413678