Novel Low Cost 3D Surface Model Reconstruction System for Plant Phenotyping

Suxing Liu,Argelia Lorence,Xiuzhen Huang,Lucia Acosta-Gamboa

doi:10.3390/jimaging3030039

Suxing Liu, Argelia Lorence + Show 2 more

Open Access

https://doi.org/10.3390/jimaging3030039

Copy DOI

Abstract

Accurate high-resolution three-dimensional (3D) models are essential for a non-invasive analysis of phenotypic characteristics of plants. Previous limitations in 3D computer vision algorithms have led to a reliance on volumetric methods or expensive hardware to record plant structure. We present an image-based 3D plant reconstruction system that can be achieved by using a single camera and a rotation stand. Our method is based on the structure from motion method, with a SIFT image feature descriptor. In order to improve the quality of the 3D models, we segmented the plant objects based on the PlantCV platform. We also deducted the optimal number of images needed for reconstructing a high-quality model. Experiments showed that an accurate 3D model of the plant was successfully could be reconstructed by our approach. This 3D surface model reconstruction system provides a simple and accurate computational platform for non-destructive, plant phenotyping.

Highlights

One important question for plant phenotyping is how to measure the plants in three dimensions.Measurements such as leaf surface area, fruit volume, and leaf inclination angle are all vital to a non-destructive measurement of plant growth and stress tolerance
Our capturing system consisted of a camera, a rotation stand and a background plate
Arabidopsis thaliana was chosen as our experiment plant since the characteristic overlapping leaves and flat architecture of the rosette present a challenge in reconstructing 3D models

Summary

Introduction

One important question for plant phenotyping is how to measure the plants in three dimensions. Measurements such as leaf surface area, fruit volume, and leaf inclination angle are all vital to a non-destructive measurement of plant growth and stress tolerance. 3D plant phenotyping allows for researchers to gain a deeper understanding of plant architecture that can be used to improve traits such as light interception. Current state of the art 3D reconstruction systems include hardware following the needs and the budget. The hardware includes sensors and computation units. The sensors, which are the vital part of the system, are composed by various kinds of cameras and scanners, such as, LIDAR (Light Detection and Ranging), lasers, Time-of-Flight (ToF) cameras, and Microsoft RGB-D cameras

Objectives

Methods

Results

Conclusion