Human Systems Integration Division @ NASA Ames

In some computer vision applications, we may need to analyze large numbers of similar frames depicting various aspects of an event. In this situation, the appearance may change signicantle within the sequence, hampering eorts to track particular features. Active shape models [1] oer one approach to this problem, by "learning" the relationship between appearance and world-state from a small set of hand-labeled training examples. In this paper we propose a method for partitioning the input image set which addresses two problems: rst, it provides an automatic method for selecting a set of training images for hand-labeling; second, it results in a partitioning of the image space into regions suitable for local model adaptation. Repeated application of the partitioning procedure results in a tree-structured representation of the image space. The resulting structure can be used to dene corresponding neighborhoods in the shape model parameter space; a new image may be processed efficiently by rst inserting it into the tree, and then solving for model parameters within the corresponding restricted domain. The ideas are illustrated with examples from an outdoor gaze tracking application.