loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Thomas Moerland ; Aswin Chandarr ; Maja Rudinac and Pieter Jonker

Affiliation: Technical University Delft, Netherlands

Keyword(s): Action Recognition, Novelty Detection, Anomaly Detection, Computer Vision, Personal Robots.

Related Ontology Subjects/Areas/Topics: Applications ; Pattern Recognition ; Robotics ; Software Engineering

Abstract: Novelty detection is essential for personal robots to continuously learn and adapt in open environments. This paper specifically studies novelty detection in the context of action recognition. To detect unknown (novel) human action sequences we propose a new method called background models, which is applicable to any generative classifier. Our closed-set action recognition system consists of a new skeleton-based feature combined with a Hidden Markov Model (HMM)-based generative classifier, which has shown good earlier results in action recognition. Subsequently, novelty detection is approached from both a posterior likelihood and hypothesis testing view, which is unified as background models. We investigate a diverse set of background models: sum over competing models, filler models, flat models, anti-models, and some reweighted combinations. Our standard recognition system has an inter-subject recognition accuracy of 96% on the Microsoft Research Action 3D dataset. Moreover, the nov elty detection module combining anti-models with flat models has 78% accuracy in novelty detection, while maintaining 78% standard recognition accuracy as well. Our methodology can increase robustness of any current HMM-based action recognition system against open environments, and is a first step towards an incrementally learning system. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 44.200.196.114

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Moerland, T.; Chandarr, A.; Rudinac, M. and Jonker, P. (2016). Knowing What You Don’t Know - Novelty Detection for Action Recognition in Personal Robots. In Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2016) - Volume 4: VISAPP; ISBN 978-989-758-175-5; ISSN 2184-4321, SciTePress, pages 317-327. DOI: 10.5220/0005677903170327

@conference{visapp16,
author={Thomas Moerland. and Aswin Chandarr. and Maja Rudinac. and Pieter Jonker.},
title={Knowing What You Don’t Know - Novelty Detection for Action Recognition in Personal Robots},
booktitle={Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2016) - Volume 4: VISAPP},
year={2016},
pages={317-327},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005677903170327},
isbn={978-989-758-175-5},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2016) - Volume 4: VISAPP
TI - Knowing What You Don’t Know - Novelty Detection for Action Recognition in Personal Robots
SN - 978-989-758-175-5
IS - 2184-4321
AU - Moerland, T.
AU - Chandarr, A.
AU - Rudinac, M.
AU - Jonker, P.
PY - 2016
SP - 317
EP - 327
DO - 10.5220/0005677903170327
PB - SciTePress