Publication Details

Clustering for Video Retrieval

CHMELAŘ Petr, RUDOLFOVÁ Ivana and ZENDULKA Jaroslav. Clustering for Video Retrieval. In: Data Warehousing and Knowledge Discovery. Lecture Notes in Computer Science, vol. 5691. Heidelberg: Springer Verlag, 2009, pp. 390-401. ISBN 978-3-642-03729-0.
Czech title
Clustering for Video Retrieval
Type
conference paper
Language
english
Authors
Keywords

Incremental clustering, MLD, Leader, ART, video retrieval, feature extraction, SURF, MSER, SIFT, cosine distance.

Abstract

The paper deals with an application of clustering we used as one of data reduction methods included in processing huge amount of video data provided for TRECVid evaluations. The problem we solved by means of clustering was to partition the local feature descriptors space so that thousands of partitions represent visual words, which may be effectively employed in video retrieval using classical information retrieval techniques. It has proved that well-known algorithms as K-means do not work well in this task or their computational complexity is too high. Therefore we developed a simple clustering method (referred to as MLD) that partitions the high-dimensional feature space incrementally in one to two database scans. The paper describes the problem of video retrieval and the role of clustering in the process, the MLD method and experiments focused on comparison with other clustering methods in the video retrieval application context.

Published
2009
Pages
390-401
Proceedings
Data Warehousing and Knowledge Discovery
Series
Lecture Notes in Computer Science
Volume
5691
Conference
20th International Conference on Database and Expert Systems Applications, Linz, AT
ISBN
978-3-642-03729-0
Publisher
Springer Verlag
Place
Heidelberg, DE
BibTeX
@INPROCEEDINGS{FITPUB8965,
   author = "Petr Chmela\v{r} and Ivana Rudolfov\'{a} and Jaroslav Zendulka",
   title = "Clustering for Video Retrieval",
   pages = "390--401",
   booktitle = "Data Warehousing and Knowledge Discovery",
   series = "Lecture Notes in Computer Science",
   volume = 5691,
   year = 2009,
   location = "Heidelberg, DE",
   publisher = "Springer Verlag",
   ISBN = "978-3-642-03729-0",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/8965"
}
Back to top