Motion and segmentation prediction in image sequences based on moving object tracking

Author

Bors, Adrian G. ; Pitas, Ioannis

Author_Institution

Dept. of Inf., Thessaloniki Univ., Greece

fYear

1998

fDate

4-7 Oct 1998

Firstpage

663

Abstract

The image sequence is represented as a set of moving regions which make up moving objects. Motion, position and gray level (or color) information is used for segmenting the moving objects. A criterion is proposed for modeling the 3-D motion and segmentation. After identifying the occluding regions, the moving objects are tracked over the next frames. Prediction is employed for estimating the future moving object position and its optical flow

Keywords

image colour analysis; image representation; image sequences; motion estimation; prediction theory; radial basis function networks; tracking; 3D motion; 3D segmentation; color information; gray level information; image representation; image sequences; median radial basis function algorithm; motion prediction; moving object tracking; moving objects segmentation; moving regions; occluding regions; optical flow; position estimation; segmentation prediction; Computer vision; Image motion analysis; Image segmentation; Image sequences; Informatics; Motion estimation; Motion segmentation; Predictive models; Probability; Tracking;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 1998. ICIP 98. Proceedings. 1998 International Conference on

Conference_Location

Chicago, IL

Print_ISBN

0-8186-8821-1

Type

conf

DOI

10.1109/ICIP.1998.999052

Filename

999052