期刊
REMOTE SENSING
卷 13, 期 3, 页码 -出版社
MDPI
DOI: 10.3390/rs13030331
关键词
imaging; machine learning; crop phenotyping; plant phenotyping; imaging sensors; imagery algorithms; climate change; remote sensing
类别
资金
- Biotechnology and Biological Sciences Research Council [BB/P026834/1]
- BBSRC [BB/P026834/1] Funding Source: UKRI
Phenotyping involves quantitative assessment of plant traits, but natural growth cycles can be slow. Deep learning and machine learning-based high-throughput phenotyping offer solutions to automate and accelerate experimental processes. The study demonstrates predicting plant growth using segmentation masks and shows strong performance on public datasets.
Phenotyping involves the quantitative assessment of the anatomical, biochemical, and physiological plant traits. Natural plant growth cycles can be extremely slow, hindering the experimental processes of phenotyping. Deep learning offers a great deal of support for automating and addressing key plant phenotyping research issues. Machine learning-based high-throughput phenotyping is a potential solution to the phenotyping bottleneck, promising to accelerate the experimental cycles within phenomic research. This research presents a study of deep networks' potential to predict plants' expected growth, by generating segmentation masks of root and shoot systems into the future. We adapt an existing generative adversarial predictive network into this new domain. The results show an efficient plant leaf and root segmentation network that provides predictive segmentation of what a leaf and root system will look like at a future time, based on time-series data of plant growth. We present benchmark results on two public datasets of Arabidopsis (A. thaliana) and Brassica rapa (Komatsuna) plants. The experimental results show strong performance, and the capability of proposed methods to match expert annotation. The proposed method is highly adaptable, trainable (transfer learning/domain adaptation) on different plant species and mutations.
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