Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

Automatically segmenting lifelog data into events

Doherty, Aiden R. orcid logoORCID: 0000-0003-4395-7702 and Smeaton, Alan F. orcid logoORCID: 0000-0003-1028-8389 (2008) Automatically segmenting lifelog data into events. In: WIAMIS 2008 - 9th International Workshop on Image Analysis for Multimedia Interactive Services, 7-9 May 2008, Klagenfurt, Austria. ISBN 978-0-7695-3130-4

A personal lifelog of visual information can be very helpful as a human memory aid. The SenseCam, a passively capturing wearable camera, captures an average of 1,785 images per day, which equates to over 600,000 images per year. So as not to overwhelm users it is necessary to deconstruct this substantial collection of images into digestable chunks of information, i.e. into distinct events or activities. This paper improves on previous work on automatic segmentation of SenseCam images into events by up to 29.2\%, primarily through the introduction of intelligent threshold selection techniques, but also through improvements in the selection of normalisation, fusion, and vector distance techniques. Here we use the most extensive dataset ever used in this domain, 271,163 images collected by 5 users over a time period of one month with manually groundtruthed events.
Item Type:Conference or Workshop Item (Invited Talk)
Event Type:Workshop
Additional Information:http://wiamis2008.itec.uni-klu.ac.at/
Subjects:Computer Science > Lifelog
Computer Science > Information storage and retrieval systems
Computer Science > Multimedia systems
DCU Faculties and Centres:Research Institutes and Centres > Centre for Digital Video Processing (CDVP)
Research Institutes and Centres > CLARITY: The Centre for Sensor Web Technologies
DCU Faculties and Schools > Faculty of Engineering and Computing > School of Computing
Published in: WIAMIS 2008 - 9th International Workshop on Image Analysis for Multimedia Interactive Services. International Workshop on Image Analysis for Multimedia Interactive Services 9. IEEE Computer Science Digital Library. ISBN 978-0-7695-3130-4
Publisher:IEEE Computer Science Digital Library
Official URL:http://dx.doi.org/10.1109/WIAMIS.2008.32
Copyright Information:© 2008 IEEE.
Funders:Science Foundation Ireland, Irish Research Council for Science Engineering and Technology
ID Code:4651
Deposited On:30 Jun 2009 09:45 by Dr Aiden Doherty . Last Modified 24 Jul 2023 14:48

Full text available as:

[thumbnail of Aiden_Doherty_WIAMIS_08.pdf]
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Creative Commons: Attribution-Noncommercial-No Derivative Works 4.0


Downloads per month over past year

Archive Staff Only: edit this record