Model comparison of object detection algorism YOLO based on the cone detection from the imagery of tree crowns of <i>Abies sachalinensis </i>

DOI
  • HANAOKA So
    Hokkaido Regional Breeding Office, Forest Tree Breeding Center, Forestry and Forest Products Research Institute
  • FUKATSU Eitaro
    Genetic Resources Department, Forest Tree Breeding Center, Forestry and Forest Products Research Institute

Bibliographic Information

Other Title
  • トドマツの樹冠画像からの球果検出に基づく物体検出アルゴリズムYOLO のモデル比較

Abstract

<p>Differences in the accuracy of cone detection on the tree crown of Abies sachalinensis were compared using multiple models of the object detection algorithm “You Only Look Once” (YOLO). Training and validation were conducted using YOLOv4 and YOLOv5m, which both showed an average precision (AP) of around 0.9. Five models of YOLOv5 (YOLOv5n, YOLOv5s, YOLOv5m, YOLOv5l, and YOLOv5x) with different neural network layer sizes were also compared. AP was 0.9 in all models except for YOLOv5n, and the accuracy was similar regardless of the neural network layer size.</p>

Journal

Keywords

Details 詳細情報について

  • CRID
    1390294807617690496
  • DOI
    10.20756/ffpri.21.4_267
  • ISSN
    21899363
    09164405
  • Text Lang
    ja
  • Data Source
    • JaLC
  • Abstract License Flag
    Disallowed

Report a problem

Back to top