An Image Analysis of Coastal Debris Detection -Detection of microplastics using deep learning-

DOI

説明

To address the issue of litter drifting ashore, this study developed a deep learning-based microplastic detection system. The system employed yolov7 [1] as its deep learning network, complemented by SAHI (Slicing Aided Hyper Inference) [2] as an additional vision library. yolov7 is renowned for its efficacy in real-time object detection. Our experimental framework involved four tests, utilizing two variations of yolov7 - the standard model and yolov7-e6e - in conjunction with SAHI. The effectiveness of each test was quantified using metrics such as Intersection over Union (IoU), Precision, Recall, F-measure, and Detection Time in seconds. For our dataset, we gathered images from actual cleanup locations, such as Hokuto Mizukumi Park. The model's discriminator underwent 700 training iterations, with a learning rate set at 0.001. Experimental results showed that it detects fairly small microplastics.

収録刊行物

キーワード

詳細情報 詳細情報について

  • CRID
    1390862931515304320
  • DOI
    10.5954/icarob.2024.os16-4
  • ISSN
    21887829
  • 本文言語コード
    en
  • データソース種別
    • JaLC
    • Crossref
    • OpenAIRE
  • 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