Visual Abstraction of Wildlife Footage Using Gaussian Mixture Models and the Minimum Description Length Criterion

bstraction of Wildlife Footage using Gaussian Mixture Models and the Minimum Description Length Criterion David Gibson Neill Campbell Barry Thomas Department of Computer Science University of Bristol Bristol BS8 1UB, United Kingdom E-mail: fgibson,campbell,[e-mail] In this paper, we present a novel approach for clipbased key frame extraction. Our framework allows both clips with subtle changes as well as clips containing rapid shot changes, fades and dissolves to be well approximated. that creating key frame video abstractions can be achieved by transforming each frame of a video sequence into an eigenspace and then clustering this space using Gaussian Mixture Models (GMMs). A Minimum Description Length (MDL) criterion is then used to determine the optimal number of GMM components to use in the clustering. The image nearest to the centres of each of the GMM components are selected as key frames. Unlike previous work this technique relies on global video clip properties and...

• Type: Conference
• Year: 2002
• Where: ICPR
• Authors: David P. Gibson, Neill W. Campbell, Barry T. Thomas
• Keywords: Computer Vision, Footage Containing Dissolves, Gaussian Mixture Models, ICPR 2002, Key Frame Video