Object Detection and Instance Segmentation with YOLOV8: Progress and Limitations

説明

This research employs object detection and instance segmentation algorithms to distinguish between objects and backgrounds and to interpret the detected objects. The YOLOV8 (You Only Look Once) framework and COCO dataset are utilized for detecting and interpreting the objects. Additionally, the accuracy of detection, segmentation, and interpretation is tested by placing objects at various distances from the camera. The algorithm's performance was evaluated, and the results were documented. In the experiments, a sample of 11 objects was tested, and 8 of them were successfully detected at distances of 45cm, 75cm, 105cm, and 135cm. For instance, segmentation, segmentation maps appeared clean when detecting a single object but faced challenges when multiple objects overlapped.

収録刊行物

詳細情報 詳細情報について

  • CRID
    1390018506585195392
  • DOI
    10.5954/icarob.2024.os23-5
  • ISSN
    21887829
  • 本文言語コード
    en
  • データソース種別
    • JaLC
    • Crossref
  • 抄録ライセンスフラグ
    使用不可

問題の指摘

ページトップへ