Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Micro-doppler classification with boosting in perimeter protection
Blekinge Tekniska Högskola, Fakulteten för teknikvetenskaper, Institutionen för matematik och naturvetenskap.ORCID-id: 0000-0003-0701-706x
Totalforsvarets forskningsinstitut, SWE.
2017 (Engelska)Ingår i: IET Conference Publications, Institution of Engineering and Technology , 2017, nr CP728Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

In security surveillance at the perimeter of critical infrastructure, such as airports and power plants, approaching objects have to be detected and classified. Especially important is to distinguish between humans, animals and vehicles. In this paper, micro-Doppler data (from movement of internal parts of the target) have been collected with a small radar. From time-velocity diagrams of the data, physical features have been extracted and used in a Boosting classifier to distinguish between the classes "human", "animal" and "man-made object". This type of classifier has received much attention lately, but not in radar micro-Doppler classification. The classification result on the current data reaches 90% correct classification with this classifier. The ability to distinguish between humans and animals is good on this data. This classifier type gives insight into the classifier and the utilized features, and is easy to use. A comparison with a SVM (Support Vector Machine) classifier, which is common for micro-Doppler, has also been performed. © 2017 Institution of Engineering and Technology. All rights reserved.

Ort, förlag, år, upplaga, sidor
Institution of Engineering and Technology , 2017. nr CP728
Nyckelord [en]
Boosting, Classification, Micro-doppler, Radar, Airport security, Animals, Object detection, Radar systems, Support vector machines, Boosting classifiers, Classification results, Perimeter protection, Physical features, Security surveillance, SVM(support vector machine), Classification (of information)
Nationell ämneskategori
Signalbehandling Annan elektroteknik och elektronik
Identifikatorer
URN: urn:nbn:se:bth-16646Scopus ID: 2-s2.0-85048690177OAI: oai:DiVA.org:bth-16646DiVA, id: diva2:1228518
Konferens
2017 International Conference on Radar Systems, Radar 2017, Belfast
Tillgänglig från: 2018-06-28 Skapad: 2018-06-28 Senast uppdaterad: 2018-06-29Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Scopus

Personposter BETA

Björklund, Svante

Sök vidare i DiVA

Av författaren/redaktören
Björklund, Svante
Av organisationen
Institutionen för matematik och naturvetenskap
SignalbehandlingAnnan elektroteknik och elektronik

Sök vidare utanför DiVA

GoogleGoogle Scholar

urn-nbn

Altmetricpoäng

urn-nbn
Totalt: 83 träffar
RefereraExporteraLänk till posten
Permanent länk

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