oru.sePublications
34567896 of 226
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • 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
PointNet and geometric reasoning for detection of grape vines from single frame RGB-D data in outdoor conditions
Örebro University, School of Science and Technology. (Centre for Applied Autonomous Sensor Systems)ORCID iD: 0000-0003-4685-379x
Department of Computing science, Umeå University, Umeå, Sweden.ORCID iD: 0000-0002-4600-8652
Department of Industrial Engineering and Management, Ben-Gurion University of the Negev, Beer Sheva, Israel.ORCID iD: 0000-0001-6265-4497
Örebro University, School of Science and Technology. Centre for Applied Autonomous Sensor Systems.ORCID iD: 0000-0002-2953-1564
2020 (English)In: Proceedings of the Northern Lights Deep Learning Workshop, NLDL , 2020, Vol. 1, p. 1-6Conference paper, Published paper (Refereed)
Abstract [en]

In this paper we present the usage of PointNet, a deep neural network that consumes raw un-ordered point clouds, for detection of grape vine clusters in outdoor conditions. We investigate the added value of feeding the detection network with both RGB and depth, contradictory to common practice in agricultural robotics of relying on RGB only. A total of 5057 pointclouds (1033 manually annotated and 4024 annotated using geometric reasoning) were collected in a field experiment conducted in outdoor conditions on 9 grape vines and 5 plants. The detection results show overall accuracy of 91% (average class accuracy of 74%, precision 53% recall 48%) for RGBXYZ data and a significant drop in recall for RGB or XYZ data only. These results suggest the usage of depth cameras for vision in agricultural robotics is crucial for crops where the color contrast between the crop and the background is complex. The results also suggest geometric reasoning can be used for increased training set size, a major bottleneck in the development of agricultural vision systems.

Place, publisher, year, edition, pages
NLDL , 2020. Vol. 1, p. 1-6
Keywords [en]
RGBD, Deep-learning, Agricultural robotics, outdoor vision, grape
National Category
Computer Vision and Robotics (Autonomous Systems) Other Agricultural Sciences
Research subject
Computer Science; Computer Science
Identifiers
URN: urn:nbn:se:oru:diva-80646DOI: 10.7557/18.5155OAI: oai:DiVA.org:oru-80646DiVA, id: diva2:1414586
Conference
3rd Northern Lights Deep Learning Workshop, Tromsö, Norway 20-21 January, 2019
Available from: 2020-03-13 Created: 2020-03-13 Last updated: 2020-03-16Bibliographically approved

Open Access in DiVA

PointNet and geometric reasoning for detection of grape vines from single frame RGB-D data in outdoor conditions(8510 kB)12 downloads
File information
File name FULLTEXT01.pdfFile size 8510 kBChecksum SHA-512
d710dca214ebf95525ad661cc852e31948c9c93a72bb63839cb932b6c3f3c0ecafe0da544707e1696aff20dff4406d6b2dc37846c84ebc3786d742e7ed4f588d
Type fulltextMimetype application/pdf

Other links

Publisher's full text

Authority records BETA

Kurtser, PolinaAndreasson, Henrik

Search in DiVA

By author/editor
Kurtser, PolinaRingdahl, OlaRotstein, NatiAndreasson, Henrik
By organisation
School of Science and Technology
Computer Vision and Robotics (Autonomous Systems)Other Agricultural Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 12 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: 25 hits
34567896 of 226
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • 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