Video data mining using con .gurations of viewpoint invariant regions

Authors:
  • JSJ. Sivic
    J. Sivic
  • AZA. Zisserman
    A. Zisserman

Abstract
We describe a method for obtaining the principal objects, characters and scenes in a video by measuring the reoccur- rence of spatial configurations of viewpoint invariant fea- tures. We investigate two aspects of the problem: the scale of the configurations, and the similarity requirements for clustering configurations. The problem is challenging firstly because an object can undergo substantial changes in imaged appearance throughout a video (due to viewpoint and illumination change, and partial occlusion), and secondly because con- figurations are detected imperfectly, so that inexact patterns must be matched. The novelty of the method is that viewpoint invariant fea- tures are used to form the configurations, and that efficient methods from the text analysis literature are employed to reduce the matching complexity. Examples of 'mined' objects are shown for a feature length film and a sitcom.

This publication has 17 references indexed in Scilit: