Generation of semantic regions from image sequences

Abstract

The simultaneous interpretation of object behaviour from real world image sequences is a highly desirable goal in machine vision. Although this is rather a sophisticated task, one method for reducing the complexity in stylized domains is to provide a context specific spatial model of that domain. Such a model of space is particularly useful when considering spatial event detection where the location of an object could indicate the behaviour of that object within the domain. To date, this approach has suffered the drawback of having to generate the spatial representation by hand for each new domain. A method is described, complete with experimental results, for automatically generating a region based context specific model of space for strongly stylized domains from the movement of objects within that domain.