The Open UniversitySkip to content
 

Towards Effective Indexing for Large Video Sequence Data

Shen, Heng Tao; Ooi, Beng Chin; Zhou, Xiaofang and Huang, Zhou (2005). Towards Effective Indexing for Large Video Sequence Data. In: Proceedings of ACM SIGMOD 2005 Conference (SIGMOD 2005), 13-16 Jun 2005, Baltimore, Maryland.

DOI (Digital Object Identifier) Link: http://dx.doi.org/10.1145/1066157.1066240
Google Scholar: Look up in Google Scholar

Abstract

With rapid advances in video processing technologies and ever fast increments in network bandwidth, the popularity of video content publishing and sharing has made similarity search an indispensable operation to retrieve videos of user interests. The video similarity is usually measured by the percentage of similar frames shared by two video sequences, and each frame is typically represented as a high-dimensional feature vector. Unfortunately, high complexity of video content has posed the following major challenges for fast retrieval: (a) effective and compact video representations, (b) efficient similarity measurements, and (c) efficient indexing on the compact representations. In this paper, we propose a number of methods to achieve fast similarity search for very large video database. First, each video sequence is summarized into a small number of clusters, each of which contains similar frames and is represented by a novel compact model called Video Triplet (ViTri). ViTri models a cluster as a tightly bounded hypersphere described by its position, radius, and density. The ViTri similarity is measured by the volume of intersection between two hyperspheres multiplying the minimal density, i.e., the estimated number of similar frames shared by two clusters. The total number of similar frames is then estimated to derive the overall similarity between two video sequences. Hence the time complexity of video similarity measure can be reduced greatly. To further reduce the number of similarity computations on ViTris, we introduce a new one dimensional transformation technique which rotates and shifts the original axis system using PCA in such a way that the original inter-distance between two high-dimensional vectors can be maximally retained after mapping. An efficient B+-tree is then built on the transformed one dimensional values of ViTris' positions. Such a transformation enables B+-tree to achieve its optimal performance by quickly filtering a large portion of non-similar ViTris. Our extensive experiments on real large video datasets prove the effectiveness of our proposals that outperform existing methods significantly.

Item Type: Conference Item
Extra Information: ISBN: 1-59593-060-4
Academic Unit/Department: Knowledge Media Institute
Item ID: 9182
Depositing User: Users 6898 not found.
Date Deposited: 01 Oct 2007
Last Modified: 02 Dec 2010 20:04
URI: http://oro.open.ac.uk/id/eprint/9182
Share this page:

Altmetrics

Scopus Citations

Actions (login may be required)

View Item
Report issue / request change

Policies | Disclaimer

© The Open University   + 44 (0)870 333 4340   general-enquiries@open.ac.uk