A model for the detection of motion over time

Author

Black, Michael J. ; Anandan, P.

Author_Institution

Dept. of Comput. Sci., Yale Univ., New Haven, CT, USA

fYear

1990

fDate

4-7 Dec 1990

Firstpage

33

Lastpage

37

Abstract

A model is proposed for the incremental estimation of visual motion fields from image sequences. The authors´ model exploits three standard constraints on image motion within an optimization framework: (1) data conservation-the intensity structure of a surface patch changes gradually over time; (2) spatial coherence-neighboring points have similar motions; and (3) temporal coherence-the image velocity of a surface patch changes gradually. The authors´ formulation takes into account the possibility of multiple motions at a particular location. They present an incremental scheme for the minimization of the objective function, based on simulated annealing. All computations are parallel, local, and incremental, and occlusion and disocclusion boundaries are estimated

Keywords

computer vision; computerised picture processing; simulated annealing; data conservation; disocclusion boundaries; image sequences; incremental estimation; minimization; model; motion detection; occlusion boundaries; optimization framework; simulated annealing; spatial coherence; temporal coherence; visual motion fields; Computed tomography; Computer science; Concurrent computing; Constraint optimization; Image sequences; Motion detection; Motion measurement; Simulated annealing; Spatial coherence; Stochastic processes;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Vision, 1990. Proceedings, Third International Conference on

Conference_Location

Osaka

Print_ISBN

0-8186-2057-9

Type

conf

DOI

10.1109/ICCV.1990.139487

Filename

139487