Logo: to the web site of Uppsala University

uu.sePublications from Uppsala University
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association
  • 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
A fast instance selection method for support vector machines in building extraction
Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Computerized Image Analysis and Human-Computer Interaction. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Automatic control. Uppsala University, Disciplinary Domain of Science and Technology, Mathematics and Computer Science, Department of Information Technology, Division of Visual Information and Interaction. University of Gävle.ORCID iD: 0000-0003-0085-5829
2020 (English)In: Applied Soft Computing, ISSN 1568-4946, E-ISSN 1872-9681, Vol. 97, article id 106716Article in journal (Refereed) Published
Abstract [en]

Training support vector machines (SVMs) for pixel-based feature extraction purposes from aerial images requires selecting representative pixels (instances) as a training dataset. In this research, locality-sensitive hashing (LSH) is adopted for developing a new instance selection method which is referred to as DR.LSH. The intuition of DR.LSH rests on rapidly finding similar and redundant training samples and excluding them from the original dataset. The simple idea of this method alongside its linear computational complexity make it expeditious in coping with massive training data (millions of pixels). DR.LSH is benchmarked against two recently proposed methods on a dataset for building extraction with 23,750,000 samples obtained from the fusion of aerial images and point clouds. The results reveal that DR.LSH outperforms them in terms of both preservation rate and maintaining the generalization ability (classification loss). The source code of DR.LSH can be found in https://github.com/mohaslani/DR.LSH.

Place, publisher, year, edition, pages
2020. Vol. 97, article id 106716
Keywords [en]
Support vector machines, Data reduction, Instance selection, Big data, Building extraction
National Category
Computer Sciences Other Earth and Related Environmental Sciences
Research subject
Computerized Image Processing
Identifiers
URN: urn:nbn:se:uu:diva-425980DOI: 10.1016/j.asoc.2020.106716ISI: 000603366700004OAI: oai:DiVA.org:uu-425980DiVA, id: diva2:1502940
Funder
European Regional Development Fund (ERDF), 20201871Available from: 2020-11-23 Created: 2020-11-23 Last updated: 2021-02-23Bibliographically approved

Open Access in DiVA

fulltext(2836 kB)262 downloads
File information
File name FULLTEXT01.pdfFile size 2836 kBChecksum SHA-512
eeeed8d281ee4d461c4abda9426f2207d7938d69c98613afd536442bef57fbe014f9ffefd2e6e04ddc702ad49c12c49b34799d9025a980a099d56b8e731d3595
Type fulltextMimetype application/pdf

Other links

Publisher's full text

Authority records

Seipel, Stefan

Search in DiVA

By author/editor
Seipel, Stefan
By organisation
Computerized Image Analysis and Human-Computer InteractionAutomatic controlDivision of Visual Information and Interaction
In the same journal
Applied Soft Computing
Computer SciencesOther Earth and Related Environmental Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 262 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 134 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association
  • 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