Authors: Peter Whaite and Frank P. Ferrie
Download (970 KB)
Abstract: Many strategies in computer vision assume the existence of general purpose models that can be used to characterize a scene or environment at various levels of abstraction. The usual assumptions are that a selected model is competent to describe a particular attribute, and that the parameters of this model can be estimated by interpreting the input data in an appropriate manner (e.g. location of lines and edges, segmentation into parts or regions, etc.). This paper considers the problem of determining when these assumptions break down so that an alternate model may be considered or further interpretation of data performed. Specifically, we consider how this can be accomplished with a minimum of a-priori knowledge using an approach that actively builds a description of the environment (i.e. structure and noise) over several different viewpoints. We show that a gaze planning strategy used to minimize model parameter variance can also be used to decide whether the model itself provides an adequate description of the environment.