oru.sePublikationer
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Towards continuous activity monitoring with temporal constraints
Örebro University, School of Science and Technology. (AASS)
Örebro University, School of Science and Technology. (AASS)ORCID iD: 0000-0002-3122-693X
Örebro University, School of Science and Technology. (AASS)ORCID iD: 0000-0002-9652-7864
2009 (English)Conference paper, (Refereed)
Abstract [en]

This paper focuses on a temporal reasoning approach for human activity recognition. Specifically, we show how search and temporal propagation are used to enable long term and continuous activity recognition. Two specific issues are addressed, namely maintaining performance over long monitoring horizons and ensuring future temporal consistency of recognized activities. We propose a complete search algorithm for activity recognition which addresses these issues, in which an admissible pruning technique allows improved performance. We show a sufficient condition for guaranteeing future admissibility, and experimental results which test the limits and practical applicability of the system are presented.

Place, publisher, year, edition, pages
2009.
National Category
Computer Science Engineering and Technology
Research subject
Computer Science
Identifiers
URN: urn:nbn:se:oru:diva-8482OAI: oai:DiVA.org:oru-8482DiVA: diva2:275917
Conference
4th Workshop on Planning and Plan Execution for Real-World Systems (at ICAPS-09), Thessaloniki, Greece
Available from: 2009-11-09 Created: 2009-11-09 Last updated: 2015-07-29Bibliographically approved

Open Access in DiVA

No full text

Other links

PDF

Search in DiVA

By author/editor
Ullberg, JonasLoutfi, AmyPecora, Federico
By organisation
School of Science and Technology
Computer ScienceEngineering and Technology

Search outside of DiVA

GoogleGoogle Scholar

Total: 256 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf