Institutions | About Us | Help | Gaeilge
rian logo


Mark
Go Back
Application of statistical physics for the identification of important events in visual lifelogs
Gurrin, Cathal; Ruskin, Heather J.; Crane, Martin; Li, Na
Visual lifelogging is the process of automatically recording images and other sensor data. Microsoft’s SenseCam is lifelogging camera have mostly been used in medical applications. Experience shows that the SenseCam can be an effective memory aid device, as it helps users to improve recollecting an experience. Given the vast amount of images that are maintained in a visual lifelog, it is a significant challenge to deconstruct a sizeable collection of images into meaningful events for users. In this paper random matrix theory (RMT) is applied to a cross-correlation matrix C, constructed using SenseCam lifelog data streams to identify such events. The analysis reveals a number of eigenvalues that deviate from the spectrum suggested by RMT. The components of the deviating eigenvectors are found to correspond to “distinct significant events” in the visual lifelogs. Finally, the cross-correlation matrix is cleaned by separating the noisy part from non-noisy part of cross-correlation matrix C. Overall, the RMT technique is shown useful to detect major events in SenseCam images.
Keyword(s): Lifelog; Mathematical models; Statistical physics; Eigenvalues and eigenfunctions; Correlation; Visualization; Dementia; Camera
Publication Date:
2013
Type: Other
Peer-Reviewed: Unknown
Language(s): English
Institution: Dublin City University
Citation(s): Gurrin, Cathal ORCID: 0000-0003-2903-3968 <https://orcid.org/0000-0003-2903-3968>, Ruskin, Heather J. ORCID: 0000-0001-7101-2242 <https://orcid.org/0000-0001-7101-2242>, Crane, Martin ORCID: 0000-0001-7598-3126 <https://orcid.org/0000-0001-7598-3126> and Li, Na (2013) Application of statistical physics for the identification of important events in visual lifelogs. In: 2013 IEEE International Conference on Bioinformatics and Biomedicine (IEEE BIBM 2013), 18-21 Dec 2013, Shanghai, China.
Publisher(s): IEEE Computer Society
File Format(s): application/pdf
Related Link(s): http://doras.dcu.ie/19944/1/BIBM.pdf,
http://www.computer.org/csdl/proceedings/bibm/2013/9999/00/06732563.pdf
First Indexed: 2014-05-16 05:52:03 Last Updated: 2020-02-05 06:16:42