SAVASA - Standards-based approach to video archive search and analysis

Authors: Suzanne Little, Kathy Clawson, Cem Direkoglu, Seán Gaines, Francesca Gaudino, Roberto Giménez, Iveel Jargalsaikhan, Emmanouil Kafetzakis, Tasos Kourtis, Jun Liu, Ana Martínez Llorens, Anna Mereu, Giorgio Montefiore, Marcos Nieto, Noel E. OConnor, Karina V

Date: 03.07.2013


PDF

Abstract

This demonstration shows the integration of video analysis and search tools to facilitate the interactive retrieval of video segments depicting specific activities from surveillance footage. The implementation was developed by members of the SAVASA project for participation in the interactive surveillance event detection (SED) task of TRECVid 2012. This year, for the first time, the purpose of the interactive SED task was to evaluate systems’ ability to support users in identifying video segments showing an event in a large collection of surveillance videos. Project partners worked together to analyse video and provide a query interface enabling users to search and identify matching video segments. The collaborative integration of components from multiple partners and the participation of end user partners in evaluating the system are the novel aspects of this work.

BIB_text

@Article {
author = {Suzanne Little, Kathy Clawson, Cem Direkoglu, Seán Gaines, Francesca Gaudino, Roberto Giménez, Iveel Jargalsaikhan, Emmanouil Kafetzakis, Tasos Kourtis, Jun Liu, Ana Martínez Llorens, Anna Mereu, Giorgio Montefiore, Marcos Nieto, Noel E. OConnor, Karina V},
title = {SAVASA - Standards-based approach to video archive search and analysis},
keywds = {

Multimedia retrieval, semantic analysis, multiarchive search, person detection


}
abstract = {

This demonstration shows the integration of video analysis and search tools to facilitate the interactive retrieval of video segments depicting specific activities from surveillance footage. The implementation was developed by members of the SAVASA project for participation in the interactive surveillance event detection (SED) task of TRECVid 2012. This year, for the first time, the purpose of the interactive SED task was to evaluate systems’ ability to support users in identifying video segments showing an event in a large collection of surveillance videos. Project partners worked together to analyse video and provide a query interface enabling users to search and identify matching video segments. The collaborative integration of components from multiple partners and the participation of end user partners in evaluating the system are the novel aspects of this work.


}
date = {2013-07-03},
year = {2013},
}
Vicomtech

Parque Científico y Tecnológico de Gipuzkoa,
Paseo Mikeletegi 57,
20009 Donostia / San Sebastián (Spain)

+(34) 943 309 230

close overlay