DocumentCode :
2584340
Title :
An estimation-theoretic framework for image-flow computation
Author :
Singh, Ajit
fYear :
1990
fDate :
4-7 Dec 1990
Firstpage :
168
Lastpage :
177
Abstract :
A novel framework for computing image flow from time-varying imagery is described. This framework offers the following principal advantages. First, it allows estimation of certain types of discontinuous flow fields without any prior knowledge about the location of discontinuities. The flow fields thus recovered are not blurred at motion boundaries. Second, covariance matrices (or alternatively, confidence measures) are associated with the estimate of image flow at each stage of computation. The estimation-theoretic nature of the framework and its ability to provide covariance matrices make it very useful in the context of applications such as incremental estimation of scene-depth using techniques based on Kalman filtering. The framework is used to recover image flow from two image sequences. To illustrate an application, the image-flow estimates and their covariance matrices thus obtained are also used to recover scene depth
Keywords :
Kalman filters; computer vision; computerised picture processing; estimation theory; matrix algebra; Kalman filtering; confidence measures; covariance matrices; discontinuous flow fields; image sequences; image-flow computation; incremental estimation; motion boundaries; scene-depth; time-varying imagery; Apertures; Computer science; Covariance matrix; Data mining; Filtering; Image sequences; Kalman filters; Motion estimation; Spatiotemporal phenomena; Velocity measurement;
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.1990.139516
Filename :
139516
Link To Document :
بازگشت