Share Email Print
cover

Proceedings Paper

Variational motion segmentation based on discontinuity-preserving optical flow estimation
Author(s): Bin Dai; Yuqiang Fang; Jinze Song
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In this paper, a variational method for motion segmentation has been proposed, which is realized by first estimate discontinuity-preserving optical flow field and then segmenting. Specifically, the complementarity between estimation and segmentation was emphasized, so two main improvements were presented: firstly, a segmentation-oriented diffusion tensor has been suggested in the optical flow model, which combines the image and flow information and determine the boundaries more effectively; Secondly, according to the characteristic of vector field, a motion segmentation model with considerations of both motion boundaries and region information were established. The results were illustrated with examples of sequence images which show the usefulness of the proposed approach for various problems.

Paper Details

Date Published: 13 January 2012
PDF: 9 pages
Proc. SPIE 8349, Fourth International Conference on Machine Vision (ICMV 2011): Machine Vision, Image Processing, and Pattern Analysis, 83490Q (13 January 2012); doi: 10.1117/12.920952
Show Author Affiliations
Bin Dai, National Univ. of Defense Technology (China)
Yuqiang Fang, National Univ. of Defense Technology (China)
Jinze Song, National Univ. of Defense Technology (China)


Published in SPIE Proceedings Vol. 8349:
Fourth International Conference on Machine Vision (ICMV 2011): Machine Vision, Image Processing, and Pattern Analysis

© SPIE. Terms of Use
Back to Top