期刊
ICES JOURNAL OF MARINE SCIENCE
卷 77, 期 4, 页码 1440-1455出版社
OXFORD UNIV PRESS
DOI: 10.1093/icesjms/fsaa029
关键词
convolutional neural network; machine vision; Prince William Sound; zooplankton
资金
- North Pacific Research Board [1502]
- Exxon Valdez Oil Spill Trustee Council [19120114-G]
A novel plankton imager was developed and deployed aboard a profiling mooring in Prince William Sound in 2016-2018. The imager consisted of a 12-MP camera and a 0.137x telecentric lens, along with darkfield illumination produced by an in-line ring/condenser lens system. Just under 2.5 x 10(6) images were collected during 3 years of deployments. A subset of almost 2 x 10(4) images was manually identified into 43 unique classes, and a hybrid convolutional neural network classifier was developed and trained to identify the images. Classification accuracy varied among the different classes, and applying thresholds to the output of the neural network (interpretable as probabilities or classifier confidence), improved classification accuracy in non-ambiguous groups to between 80% and 100%.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据