Institutions | About Us | Help | Gaeilge
rian logo


Mark
Go Back
Exploiting contextual data for event retrieval in surveillance video
Kelly, Philip; Ó Conaire, Ciarán; O'Connor, Noel E.
Contextual information is vital for the robust extraction of semantic information in automated surveillance systems. We have developed a scene independent framework for the detection of events in which we provide 2D and 3D contextual data for the scene under surveillance via a novel fast and convenient interface tool. In addition, the proposed framework illustrates the use of integral images, not only for detection, as with the classic Viola-Jones object detector, but also for efficient tracking. Finally, we provide a quantitative assessment of the performance of the proposed system in a number of physical locations via groundtruthed datasets.
Keyword(s): Image processing; Information retrieval; surveillance; retrieval; event detection
Publication Date:
2009
Type: Other
Peer-Reviewed: Unknown
Language(s): English
Institution: Dublin City University
Citation(s): Kelly, Philip, Ó Conaire, Ciarán and O'Connor, Noel E. ORCID: 0000-0002-4033-9135 <https://orcid.org/0000-0002-4033-9135> (2009) Exploiting contextual data for event retrieval in surveillance video. In: CIVR 2009 - ACM International Conference on Image and Video Retrieval, 8-10 July, 2009, Santorini, Greece. ISBN 978-1-60558-480-5
Publisher(s): Association for Computing Machinery
File Format(s): application/pdf
Related Link(s): http://doras.dcu.ie/4713/1/dcu_CIVR_2009.pdf,
http://dx.doi.org/10.1145/1646396.1646437
First Indexed: 2009-11-05 02:01:32 Last Updated: 2019-02-09 06:58:27