An estimation-theoretic framework for image-flow computation

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