Institutions | About Us | Help | Gaeilge
rian logo


Mark
Top 100
Go Back
Automated management of more than one million lifelog images
Doherty, Aiden R.; Smeaton, Alan F.
The SenseCam is a passively capturing wearable camera that captures approximately 2,500 images on average per day. This provides a user with an extensive visual diary. Possible applications making use of this device include helping dementia sufferers recall events from short-term memory, and also this device can be used by tourists to maintain an extensive image collection of particular trips. However a large image collection will quickly build up, with an average of 1 million images captured each year. This presents a considerable challenge in terms of managing such a large collection and to make it accessible for users. My research proposes to address this problem in 4 steps: 1) Identifying distinct events within the 2,500 images that are captured daily 2) Highlighting the most unique of those events 3) Finding similar events to a given event 4) Augmenting the low-quality images from the wearable camera with higher quality images from external sources.
Keyword(s): Lifelog; Information storage and retrieval systems; Multimedia systems; Information retrieval; Image processing
Publication Date:
2007
Type: Other
Peer-Reviewed: Unknown
Language(s): English
Institution: Dublin City University
Citation(s): Doherty, Aiden R. ORCID: 0000-0003-4395-7702 <https://orcid.org/0000-0003-4395-7702> and Smeaton, Alan F. ORCID: 0000-0003-1028-8389 <https://orcid.org/0000-0003-1028-8389> (2007) Automated management of more than one million lifelog images. In: Seminar at the School of Computing and Intelligent Systems (SCIS) and Computer Science Research Institute (CSRI), University of Ulster, 21 December 2007, Derry, Northern Ireland.
File Format(s): application/pdf
Related Link(s): http://doras.dcu.ie/4653/1/2007_Aiden_Seminar_Magee.pdf
First Indexed: 2009-11-05 02:01:34 Last Updated: 2019-02-09 06:58:45