hh.sePublikasjoner
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
PastVision: Exploring “Seeing” into the Near Past with Thermal Touch Sensing and Object Detection – For Robot Monitoring of Medicine Intake by Dementia Patients
Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).ORCID-id: 0000-0002-4998-1685
Högskolan i Halmstad, Akademin för informationsteknologi, Halmstad Embedded and Intelligent Systems Research (EIS), CAISR Centrum för tillämpade intelligenta system (IS-lab).ORCID-id: 0000-0002-4929-1262
2017 (engelsk)Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

We present PastVision, a proof-of-concept approach that explores combining thermal touch sensing and object detection to infer recent actions by a person which have not been directly observed by a system. Inferring such past actions has received little attention yet in the literature, but would be highly useful in scenarios in which sensing can fail (e.g., due to occlusions) and the cost of not recognizing an action is high. In particular, we focus on one such application, involving a robot which should monitor if an elderly person with dementia has taken medicine. For this application, we explore how to combine detection of touches and objects, as well as how heat traces vary based on materials and a person’s grip, and how robot motions and activity models can be leveraged. The observed results indicate promise for the proposed approach.

sted, utgiver, år, opplag, sider
Linköping: Linköping University Electronic Press, 2017. s. 30-38, artikkel-id 003
Serie
Linköping Electronic Conference Proceedings, ISSN 1650-3686, E-ISSN 1650-3740 ; 137
Emneord [en]
Thermal Sensing, Home Robots, Action Recognition, Monitoring
HSV kategori
Identifikatorer
URN: urn:nbn:se:hh:diva-35045OAI: oai:DiVA.org:hh-35045DiVA, id: diva2:1143200
Konferanse
30th Annual Workshop of the Swedish Artificial Intelligence Society SAIS 2017, May 15–16, 2017, Karlskrona, Sweden
Tilgjengelig fra: 2017-09-20 Laget: 2017-09-20 Sist oppdatert: 2018-02-05bibliografisk kontrollert

Open Access i DiVA

fulltext(442 kB)88 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 442 kBChecksum SHA-512
20700c214a9e30f90c969dbbe94f4cd46307a7873aa8ca95db1c8ec14697f10239f62740456c19406334b22be3793b96adbece8727da844a171f4e71a58bf931
Type fulltextMimetype application/pdf

Personposter BETA

Cooney, MartinBigun, Josef

Søk i DiVA

Av forfatter/redaktør
Cooney, MartinBigun, Josef
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 88 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

urn-nbn

Altmetric

urn-nbn
Totalt: 334 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf