Evaluating Geometric Measurement Accuracy Based on 3D Reconstruction of Automated Imagery in a Greenhouse

Abstract

Geometric dimensions of plants are significant parameters for showing plant dynamic responses to environmental variations. An image-based high-throughput phenotyping platform was developed to automatically measure geometric dimensions of plants in a greenhouse. The goal of this paper was to evaluate the accuracy in geometric measurement using the Structure from Motion (SfM) method from images acquired using the automated image-based platform. Images of nine artificial objects of different shapes were taken under 17 combinations of three different overlaps in x and y directions, respectively, and two different spatial resolutions (SRs) with three replicates. Dimensions in x, y and z of these objects were measured from 3D models reconstructed using the SfM method to evaluate the geometric accuracy. A metric power of unit (POU) was proposed to combine the effects of image overlap and SR. Results showed that measurement error of dimension in z is the least affected by overlap and SR among the three dimensions and measurement error of dimensions in x and y increased following a power function with the decrease of POU (R2 = 0.78 and 0.88 for x and y respectively). POUs from 150 to 300 are a preferred range to obtain reasonable accuracy and efficiency for the developed image-based high-throughput phenotyping system. As a study case, the developed system was used to measure the height of 44 plants using an optimal POU in greenhouse environment. The results showed a good agreement (R2 = 92% and Root Mean Square Error = 9.4 mm) between the manual and automated method.

Plant phenotyping relevance

温室画像型ハイスループット表現型解析プラットフォームの3D幾何計測精度をSfMで評価し、植物体高への適用も検証しており、表現型取得手法が研究の中心である。

Code and data availability

The paper's image-derived measurement dataset (images of nine objects under 17 POUs in three replicates) is explicitly deposited as online Supplementary Materials at the MDPI URL, which is an allowed URL. No author analysis code or trained models are stated as publicly available.