Robust computation of image-motion and scene-depth

Author

Singh, Ajit

Author_Institution

Siemens Corp. Res., Princeton, NJ, USA

fYear

1991

fDate

9-11 Apr 1991

Firstpage

2730

Abstract

A new framework is described for computing image flow from time-varying imagery and recovering scene-depth from image flow. In this framework, image flow information available in the time-varying imagery is classified into two categories-conservation information and neighborhood information. Each type of information is recovered in the form of an estimate accompanied by a covariance matrix. Image flow is then computed, along with confidence measures, by fusing the two estimates on the basis of their covariance matrices. Dense depth-maps are computed from image flow using Kalman filtering

Keywords

Kalman filters; filtering and prediction theory; matrix algebra; pattern recognition; picture processing; Kalman filtering; confidence measures; conservation information; covariance matrix; dense depth maps; image flow; image-motion; neighborhood information; pattern recognition; picture processing; scene-depth; time-varying imagery; Covariance matrix; Data mining; Distributed computing; Estimation theory; Information filtering; Information filters; Motion estimation; Pixel; Rendering (computer graphics); Robustness;

fLanguage

English

Publisher

ieee

Conference_Titel

Robotics and Automation, 1991. Proceedings., 1991 IEEE International Conference on

Conference_Location

Sacramento, CA

Print_ISBN

0-8186-2163-X

Type

conf

DOI

10.1109/ROBOT.1991.132044

Filename

132044