liu.seSearch for publications in DiVA
Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • 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
Semantic Segmentation of Oblique Views in a 3D-Environment
Linköpings universitet, Institutionen för systemteknik, Datorseende.
2019 (engelsk)Independent thesis Advanced level (degree of Master (Two Years)), 20 poäng / 30 hpOppgave
Abstract [en]

This thesis presents and evaluates different methods to semantically segment 3D-models by rendered 2D-views. The 2D-views are segmented separately and then merged together. The thesis evaluates three different merge strategies, two different classification architectures, how many views should be rendered and how these rendered views should be arranged. The results are evaluated both quantitatively and qualitatively and then compared with the current classifier at Vricon presented in [30].

The conclusion of this thesis is that there is a performance gain to be had using this method. The best model was using two views and attains an accuracy of 90.89% which can be compared with 84.52% achieved by the single view network from [30]. The best nine view system achieved a 87.72%. The difference in accuracy between the two and the nine view system is attributed to the higher quality mesh on the sunny side of objects, which typically is the south side.

The thesis provides a proof of concept and there are still many areas where the system can be improved. One of them being the extraction of training data which seemingly would have a huge impact on the performance.

sted, utgiver, år, opplag, sider
2019. , s. 81
Emneord [en]
Semantic segmentation, 3D segmentation, oblique views, multiview segmentation, satellite imagery, convolutional neural networks
HSV kategori
Identifikatorer
URN: urn:nbn:se:liu:diva-153866ISRN: LiTH-ISY-EX--18/5185--SEOAI: oai:DiVA.org:liu-153866DiVA, id: diva2:1278684
Eksternt samarbeid
Vricon Systems AB
Fag / kurs
Computer Vision Laboratory
Presentation
2019-01-08, Systemet, Linköping, 10:00 (engelsk)
Veileder
Examiner
Tilgjengelig fra: 2019-01-15 Laget: 2019-01-14 Sist oppdatert: 2019-01-15bibliografisk kontrollert

Open Access i DiVA

fulltext(104651 kB)123 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 104651 kBChecksum SHA-512
96607061351e6b0a2cff02bbec681970525de232f2356eb6693b5aafb872386818a2006326d59d085e8793fe81ea6439a44c6538c41768bec43327d2aef06089
Type fulltextMimetype application/pdf

Søk i DiVA

Av forfatter/redaktør
Tranell, Victor
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 123 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: 671 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • 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