Semester

Summer

Date of Graduation

2004

Document Type

Thesis

Degree Type

MS

College

Statler College of Engineering and Mineral Resources

Department

Lane Department of Computer Science and Electrical Engineering

Committee Chair

Donald A. Adjeroh.

Abstract

The efficiency of a video indexing technique depends on the efficiency of the video segmentation algorithm which is a fundamental step in video indexing. Video segmentation is a process of splitting up a video sequence into its constituent scenes. This work focuses on the problem of video segmentation. A content-based approach has been used which segments a video based on the information extracted from the video itself. The main emphasis is on using structural information in the video such as edges as they are largely invariant to illumination and motion changes. The edge-based features have been used in conjunction with the intensity-based features in a multi-resolution framework to improve the performance of the segmentation algorithm.;To further improve the performance and to reduce the problem of automated choice of parameters, we introduce adaptation in the video segmentation process. (Abstract shortened by UMI.).

Share

COinS