Knowing what you don’t know: Novelty detection for action recognition in personal robots

Thomas Moerland, Aswin Chandarr, Maja Rudinac, P.P. Jonker

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

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 novelty 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.
Original languageEnglish
Title of host publicationProceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
Subtitle of host publicationVISIGRAPP 2016
EditorsNadia Magnenat-Thalmann, Paul Richard, Lars Linsen, Alexandru Telea, Sebastiano Battiato, Francisco Imai , José Braz
PublisherSciTePress
Pages317-327
Volume4
ISBN (Print)978-989-758-175-5
DOIs
Publication statusPublished - 2016
Event11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Rome, Italy
Duration: 27 Feb 201629 Feb 2016
http://www.visapp.visigrapp.org/

Conference

Conference11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
Abbreviated titleVISIGRAPP 2016
CountryItaly
CityRome
Period27/02/1629/02/16
Internet address

Keywords

  • Action Recognition
  • Novelty Detection
  • Anomaly Detection
  • Computer Vision
  • Personal Robots

Fingerprint

Dive into the research topics of 'Knowing what you don’t know: Novelty detection for action recognition in personal robots'. Together they form a unique fingerprint.

Cite this