Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

10-2001

Abstract

Clustering of video data is an important issue in video abstraction, browsing and retrieval. In this paper, we propose a two-level hierarchical clustering approach by aggregating shots with similar motion and color features. Motion features are computed directly from 20 tensor histograms, while color features are represented by 30 color histograms. Cluster validity analysis is further applied to automatically determine the number of clusters at each level. Video retrieval can then be done directly based on the result of clustering. The proposed approach is found to be useful particularly for sports games, where motion and color are important visual cues when searching and browsing the desired video shots. Since most games involve two teams, clsssification and retrieval of teams becomes an interesting topic. To achieve these goals, nevertheless, an initial as well as critical step is to isolate team players from background regions. Thus, we also introduce approach to segment foreground objects (players) prior to classification and retrieval.

Keywords

Hierarchical clustering, Motion and color retrieval, Team classification

Discipline

Data Storage Systems | Graphics and Human Computer Interfaces

Research Areas

Intelligent Systems and Optimization

Publication

Proceedings of the 9th ACM International Conference on Multimedia, Ottawa, Canada, 2001 September 30 - October 5

First Page

51

Last Page

60

Identifier

10.1145/500141.500151

Publisher

Association for Computing Machinery (ACM)

City or Country

Ottawa, Canada

Download

Share

COinS