Automatic Traits Extraction and Fitting for Field High-throughput Phenotyping Systems

Abstract

ABSTRACT High-throughput phenotyping is a modern technology to measure plant traits efficiently and in large scale by imaging systems over the whole growth season. Those images provide rich data for statistical analysis of plant phenotypes. We propose a pipeline to extract and analyze the plant traits for field phenotyping systems. The proposed pipeline include the following main steps: plant segmentation from field images, automatic calculation of plant traits from the segmented images, and functional curve fitting for the extracted traits. To deal with the challenging problem of plant segmentation for field images, we propose a novel approach on image pixel classification by transform domain neural network models, which utilizes plant pixels from greenhouse images to train a segmentation model for field images. Our results show the proposed procedure is able to accurately extract plant heights and is more stable than results from Amazon Turks, who manually measure plant heights from original images.

Plant phenotyping relevance

圃場画像から植物を分割し、草丈などの形質を自動抽出・曲線近似する高スループット表現型解析パイプラインの開発が主題であり、方法的貢献が明確です。

Code and data availability

The paper explicitly states that the authors' R pipeline code and sample image data are publicly available on GitHub, directly supporting this paper's plant segmentation, trait extraction, and growth-curve fitting analysis.