Academic Journal
Προβολή σε EDS

Stereo Vision-Based Detection and 3D Localization of Loose Oil Palm Fruits Using YOLOv8 and Hungarian Matching.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Stereo Vision-Based Detection and 3D Localization of Loose Oil Palm Fruits Using YOLOv8 and Hungarian Matching.
Συγγραφείς: Warni, Elly1 (AUTHOR), Indrabayu1 (AUTHOR) indrabayu@unhas.ac.id, Achmad, Andani2 (AUTHOR), Syarif, Syafruddin2 (AUTHOR), Rudi3 (AUTHOR), Sadi, Nadya Petroya1 (AUTHOR)
Πηγή: Ingénierie des Systèmes d'Information. Feb2026, Vol. 31 Issue 2, p579-589. 11p.
Θεματικοί όροι: Object recognition (Computer vision), Assignment problems (Programming), Stereopsis, Harvesting machinery, Precision farming, Depth maps (Digital image processing)
Περίληψη: Accurate detection and localization of loose oil palm fruits are essential for improving harvesting efficiency, reducing post-harvest losses, and supporting automation in oil palm plantations. This study develops and evaluates a stereo vision-based perception system that integrates YOLOv8 object detection with Hungarian matching to detect loose oil palm fruits and establish reliable correspondence between stereo image pairs. Three YOLOv8 variants, namely YOLOv8n, YOLOv8s, and YOLOv8m, were systematically evaluated under different camera heights ranging from 20 to 50 cm and object distances from 20 to 120 cm. The results show that YOLOv8s achieved the best overall detection and matching performance, reaching an accuracy of 94.79% and an F1-score of 0.972, with the most favorable detection performance observed at a camera height of 30 cm. For distance estimation, stereo triangulation combined with ground-plane projection produced the lowest error at a camera height of 50 cm, achieving a Mean Absolute Percentage Error (MAPE) of 0.86% and a Mean Absolute Error (MAE) of 0.62 cm. These findings demonstrate that the proposed stereo vision system can localize loose oil palm fruits with centimeter-level accuracy under varying operational settings. The developed framework provides a practical and reliable perception module for autonomous harvesting robots and offers technical support for precision agriculture applications in oil palm plantations. [ABSTRACT FROM AUTHOR]
Copyright of Ingénierie des Systèmes d'Information is the property of International Information & Engineering Technology Association (IIETA) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Βάση Δεδομένων: Business Source Index
FullText Text:
  Availability: 0
Header DbId: bsx
DbLabel: Business Source Index
An: 193060140
RelevancyScore: 1390
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 1390.35424804688
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Stereo Vision-Based Detection and 3D Localization of Loose Oil Palm Fruits Using YOLOv8 and Hungarian Matching.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Warni%2C+Elly%22">Warni, Elly</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Indrabayu%22">Indrabayu</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> indrabayu@unhas.ac.id</i><br /><searchLink fieldCode="AR" term="%22Achmad%2C+Andani%22">Achmad, Andani</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Syarif%2C+Syafruddin%22">Syarif, Syafruddin</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Rudi%22">Rudi</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Sadi%2C+Nadya+Petroya%22">Sadi, Nadya Petroya</searchLink><relatesTo>1</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Ingénierie+des+Systèmes+d'Information%22">Ingénierie des Systèmes d'Information</searchLink>. Feb2026, Vol. 31 Issue 2, p579-589. 11p.
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Object+recognition+%28Computer+vision%29%22">Object recognition (Computer vision)</searchLink><br /><searchLink fieldCode="DE" term="%22Assignment+problems+%28Programming%29%22">Assignment problems (Programming)</searchLink><br /><searchLink fieldCode="DE" term="%22Stereopsis%22">Stereopsis</searchLink><br /><searchLink fieldCode="DE" term="%22Harvesting+machinery%22">Harvesting machinery</searchLink><br /><searchLink fieldCode="DE" term="%22Precision+farming%22">Precision farming</searchLink><br /><searchLink fieldCode="DE" term="%22Depth+maps+%28Digital+image+processing%29%22">Depth maps (Digital image processing)</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Accurate detection and localization of loose oil palm fruits are essential for improving harvesting efficiency, reducing post-harvest losses, and supporting automation in oil palm plantations. This study develops and evaluates a stereo vision-based perception system that integrates YOLOv8 object detection with Hungarian matching to detect loose oil palm fruits and establish reliable correspondence between stereo image pairs. Three YOLOv8 variants, namely YOLOv8n, YOLOv8s, and YOLOv8m, were systematically evaluated under different camera heights ranging from 20 to 50 cm and object distances from 20 to 120 cm. The results show that YOLOv8s achieved the best overall detection and matching performance, reaching an accuracy of 94.79% and an F1-score of 0.972, with the most favorable detection performance observed at a camera height of 30 cm. For distance estimation, stereo triangulation combined with ground-plane projection produced the lowest error at a camera height of 50 cm, achieving a Mean Absolute Percentage Error (MAPE) of 0.86% and a Mean Absolute Error (MAE) of 0.62 cm. These findings demonstrate that the proposed stereo vision system can localize loose oil palm fruits with centimeter-level accuracy under varying operational settings. The developed framework provides a practical and reliable perception module for autonomous harvesting robots and offers technical support for precision agriculture applications in oil palm plantations. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Ingénierie des Systèmes d'Information is the property of International Information & Engineering Technology Association (IIETA) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=bsx&AN=193060140
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.18280/isi.310225
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 11
        StartPage: 579
    Subjects:
      – SubjectFull: Object recognition (Computer vision)
        Type: general
      – SubjectFull: Assignment problems (Programming)
        Type: general
      – SubjectFull: Stereopsis
        Type: general
      – SubjectFull: Harvesting machinery
        Type: general
      – SubjectFull: Precision farming
        Type: general
      – SubjectFull: Depth maps (Digital image processing)
        Type: general
    Titles:
      – TitleFull: Stereo Vision-Based Detection and 3D Localization of Loose Oil Palm Fruits Using YOLOv8 and Hungarian Matching.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Warni, Elly
      – PersonEntity:
          Name:
            NameFull: Indrabayu
      – PersonEntity:
          Name:
            NameFull: Achmad, Andani
      – PersonEntity:
          Name:
            NameFull: Syarif, Syafruddin
      – PersonEntity:
          Name:
            NameFull: Rudi
      – PersonEntity:
          Name:
            NameFull: Sadi, Nadya Petroya
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 02
              Text: Feb2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 16331311
          Numbering:
            – Type: volume
              Value: 31
            – Type: issue
              Value: 2
          Titles:
            – TitleFull: Ingénierie des Systèmes d'Information
              Type: main
ResultId 1