Similarity retrieval of video database based on 3D Z-string

Ping Yu, Chein Shung Hwang, Nai Wen Kuo

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Recently, the video retrieval processing is concerned with retrieving videos that are relevant to the users' requests from a large collection of videos, referred to as a video database. We have proposed 3D Z-string to represent symbolic videos accompanying with the string generation and video reconstruction algorithms. In this paper, we proposed the spatial-temporal similarity retrieval approach of vides in 3D Z-string. Our approach defines a set of user assigned weights, based on the factors of spatial-temporal relations of object pairs in a video, in order to rank the retrieval videos. We use dynamic programming to calculate the similarity measures and propose the similarity retrieval algorithm. By providing various criterion of similarity between videos to match user requirement, our proposed similarity retrieval algorithm has discrimination power about different criteria.

Original languageEnglish
Title of host publication2nd International Symposium on Electronic Commerce and Security, ISECS 2009
Pages56-59
Number of pages4
Volume2
DOIs
Publication statusPublished - Dec 1 2009
Externally publishedYes
Event2nd International Symposium on Electronic Commerce and Security, ISECS 2009 - Nanchang, China
Duration: May 22 2009May 24 2009

Publication series

Name2nd International Symposium on Electronic Commerce and Security, ISECS 2009
Volume2

Conference

Conference2nd International Symposium on Electronic Commerce and Security, ISECS 2009
Country/TerritoryChina
CityNanchang
Period5/22/095/24/09

Keywords

  • 3D Z-string
  • Similarity retrieval
  • Spatial-temporal inference
  • Video database

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Economics and Econometrics
  • Finance

Fingerprint

Dive into the research topics of 'Similarity retrieval of video database based on 3D Z-string'. Together they form a unique fingerprint.

Cite this