oru.sePublications
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
Mobile Robot Reflectance Acquisition to Detect Plastic Wrapping on Pallets
Örebro University, School of Science and Technology.
2018 (English)Independent thesis Basic level (degree of Bachelor of Fine Arts), 10 credits / 15 HE creditsStudent thesis
Abstract [sv]

Detekteringen av plast som är lindad runt en pall är gjordes med hjälp av en SVM. Vägen till klassifikationen var lång men började med att studera punktmoln för plastad pall och icke plastad pall. Efter att ha studerat punktmolnen så kunde en graf ritas med hjälp av vinkeln och intensiteten för varje punkt det för att se om en skillnad fanns mellan plastad pall och icke plastad pall. Experimenten som var kärnan i mitt projekt var att studera hur pass bra featuren

28x28 som är dimensionerna för histogrammet som byggdes upp med hjälp av intensiteten och vinkeln för varje punkt och featuren 14x14x14 som är dimensionerna för histogrammet som byggdes upp med hjälp av intensiteten, vinkeln och distansen för varje punk presterar noggrannhetmässigt. Det visade sig att 14x14x14 histogrammet generaliserade andra pallar som inte fanns med i träningsdatat bättre än 28x28 histogrammet.

Abstract [en]

The classification of the plastic wrapped pallet was done by using a SVM. The road for the classification was long, but began by studying the point clouds for plastic pallets and non-plastic pallets. After studying the point cloud a graph could be drawn using the angle and intensity for each point to see if there was a difference between plastic pallet and non-plastic pallet. The experiments that were the heart of my project were to study how good the 28x28 feature which the 28x28 is the dimensions of the histogram that were built using the intensity and angle of each point and the 14x14x14 feature,14x14x14 which are the dimensions of the histogram that were built using the intensity, angle and the distance for each point performs classifications wise on new pallets that the SVM was not trained on. The result was that the

14x14x14 histogram generalized other pallets that were not included in the training data performed better than the 28x28 histogram.

 

Place, publisher, year, edition, pages
2018. , p. 42
Keywords [en]
Mobile robots, perception, reflectance estimation, remote sensing
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:oru:diva-68346OAI: oai:DiVA.org:oru-68346DiVA, id: diva2:1236892
Subject / course
Computer Engineering
Supervisors
Examiners
Available from: 2018-08-06 Created: 2018-08-06 Last updated: 2018-08-06Bibliographically approved

Open Access in DiVA

No full text in DiVA

By organisation
School of Science and Technology
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 28 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