Alomari, M, Duckworth, P orcid.org/0000-0001-9052-6919, Gatsoulis, Y et al. (2 more authors) (2017) A qualitative approach for online activity recognition. In: Advances in Cooperative Robotics. CLAWAR 2016: 19th International Conference on Climbing and Walking Robots and the Support Technologies for Mobile Machines, 12-14 Sep 2016, London, UK. World Scientific , pp. 747-754. ISBN 978-981-3149-12-0
Abstract
We present a novel qualitative, dynamic length sliding window method which enables a mobile robot to temporally segment activities taking place in live RGB-D video. We demonstrate how activities can be learned from observations by encoding qualitative spatio-temporal relationships between entities in the scene. We also show how a Nearest Neighbour model can recognise activities taking place even if they temporally co-occur. Our system is validated on a challenging dataset of daily living activities.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | (c) 2016, World Scientific . This is an author produced version of a paper published in Advances in Cooperative Robotics . Uploaded in accordance with the publisher's self-archiving policy. |
Keywords: | Activity Recognition; Temporal Segmentation; HRI; QSR |
Dates: |
|
Institution: | The University of Leeds |
Academic Units: | The University of Leeds > Faculty of Engineering & Physical Sciences (Leeds) > School of Computing (Leeds) |
Funding Information: | Funder Grant number EU - European Union FP7-ICT-600623 |
Depositing User: | Symplectic Publications |
Date Deposited: | 11 Aug 2017 08:46 |
Last Modified: | 15 Sep 2017 01:47 |
Status: | Published |
Publisher: | World Scientific |
Identification Number: | 10.1142/9789813149137_0086 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:120057 |