An Information Retrieval Approach to Identifying Infrequent Events in Surveillance Video
Authors: Suzanne Litlle, Iveel Jargalsaikhan, Cem Direkoglu, Noel E. OConnor, Alan F. Smeaton, Kathy Clawson, Hao Li, Jun Liu, Bryan Scotney, Hui Wang, Marcos Nieto
Date: 16.04.2013
Abstract
This paper presents work on integrating multiple computer visionbased approaches to surveillance video analysis to support user retrieval of video segments showing human activities. Applied computer vision using real-world surveillance video data is an extremely challenging research problem, independently of any information retrieval (IR) issues. Here we describe the issues faced in developing both generic and specific analysis tools and how they were integrated for use in the new TRECVid interactive surveillance event detection task. We present an interaction paradigm and discuss the outcomes from face-to-face end user trials and the resulting feedback on the system from both professionals, who manage surveillance video, and computer vision or machine learning experts. We propose an information retrieval approach to finding events in surveillance video rather than solely relying on traditional annotation using specifically trained classifiers.
BIB_text
author = {Suzanne Litlle, Iveel Jargalsaikhan, Cem Direkoglu, Noel E. OConnor, Alan F. Smeaton, Kathy Clawson, Hao Li, Jun Liu, Bryan Scotney, Hui Wang, Marcos Nieto},
title = {An Information Retrieval Approach to Identifying Infrequent Events in Surveillance Video},
keywds = {
Surveillance event detection, video analysis
}
abstract = {
This paper presents work on integrating multiple computer visionbased approaches to surveillance video analysis to support user retrieval of video segments showing human activities. Applied computer vision using real-world surveillance video data is an extremely challenging research problem, independently of any information retrieval (IR) issues. Here we describe the issues faced in developing both generic and specific analysis tools and how they were integrated for use in the new TRECVid interactive surveillance event detection task. We present an interaction paradigm and discuss the outcomes from face-to-face end user trials and the resulting feedback on the system from both professionals, who manage surveillance video, and computer vision or machine learning experts. We propose an information retrieval approach to finding events in surveillance video rather than solely relying on traditional annotation using specifically trained classifiers.
}
isi = {1},
date = {2013-04-16},
year = {2013},
}
