UPM Institutional Repository

Estimating body related soft biometric traits in video frames


Citation

Arigbabu, Olasimbo Ayodeji and Syed Ahmad Abdul Rahman, Sharifah Mumtazah and Wan Adnan, Wan Azizun and Yussof, Salman and Iranmanesh, Vahab and Malallah, Fahad Layth (2014) Estimating body related soft biometric traits in video frames. The Scientific World Journal, 2014. art. no. 460973. pp. 1-12. ISSN 2356-6140; ESSN: 1537-744X

Abstract

Soft biometrics can be used as a prescreening filter, either by using single trait or by combining several traits to aid the performance of recognition systems in an unobtrusive way. In many practical visual surveillance scenarios, facial information becomes difficult to be effectively constructed due to several varying challenges. However, from distance the visual appearance of an object can be efficiently inferred, thereby providing the possibility of estimating body related information. This paper presents an approach for estimating body related soft biometrics; specifically we propose a new approach based on body measurement and artificial neural network for predicting body weight of subjects and incorporate the existing technique on single view metrology for height estimation in videos with low frame rate. Our evaluation on 1120 frame sets of 80 subjects from a newly compiled dataset shows that the mentioned soft biometric information of human subjects can be adequately predicted from set of frames.


Download File

[img] PDF
37493.pdf
Restricted to Repository staff only

Download (3MB)

Additional Metadata

Item Type: Article
Divisions: Faculty of Engineering
DOI Number: https://doi.org/10.1155/2014/460973
Publisher: Hindawi Publishing Corporation
Keywords: Soft biometrics; Body weights and measures
Depositing User: Nabilah Mustapa
Date Deposited: 16 Dec 2015 08:36
Last Modified: 16 Dec 2015 08:36
Altmetrics: http://www.altmetric.com/details.php?domain=psasir.upm.edu.my&doi=10.1155/2014/460973
URI: http://psasir.upm.edu.my/id/eprint/37493
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item