DeepShoot

Introduction

The DeepShoot tool was developed to enable fully automated analysis of plant shoot visible light (RGB) images. Deep learning segmentation models incorporated in DeepShot were separately trained on three different plant types (Arabidopsis, Maize, Barley) grown in greenhouse facilities and imaged from side and top views.

Key Features

The main two tasks automatically performed by DeepShoot include (i) binary segmentation of plant shoots followed by (ii) calculation of of a number of phenotypic traits of segmented plant structures. For the segmentation task, users should select an appropriate segmentation model (e.g., Arabidopsis/top view or Maize/side view). Despite the fact that DeepShoot segmentation models were trained on particular types of plants, they can also be applied to segmentation and phenotyping of other optically similar plants.

Downloads

Download the DeepShoot tool for Windows x64 (300MB)
Download the DeepShoot tool for Linux (500MB)

By downloading, installing and/or using this software the user agrees with the following license conditions.

This software requires MATLAB R2021a run-time libraries to be installed:

Download MATLAB R2021a run-time for Windows x64 (~2GB).
Download MATLAB R2021a run-time for Linux (~2GB).

Windows users should also install the run-time components from the following link: https://www.microsoft.com/en-us/download/details.aspx?id=48145.

References

[1] Narisetti N, Henke M, Neumann K, Stolzenburg F, Altmann T and Gladilin E (2022) Deep Learning Based Greenhouse Image Segmentation and Shoot Phenotyping (DeepShoot). Front. Plant Sci. 13:906410. https://doi.org/10.3389/fpls.2022.906410

Leibniz Institute of Plant Genetics and Crop Plant Research (IPK)
OT Gatersleben
Corrensstrasse 3
06466 Stadt Seeland,
Telefon: +49 (0)39482 50
Telefax: +49 (0)39482 5139
E-Mail: info@ipk-gatersleben.de
Internet: www.ipk-gatersleben.de