Simulation of Automatically Annotated Visible and Multi-/Hyperspectral Images Using the Helios 3D Plant and Radiative Transfer Modeling Framework

Author:

Lei Tong1ORCID,Graefe Jan2,Mayanja Ismael K.3,Earles Mason34,Bailey Brian N.1ORCID

Affiliation:

1. Department of Plant Sciences, University of California, Davis, CA, USA.

2. Leibniz Institute of Vegetable and Ornamental Crops e.V. (IGZ), Großbeeren, Germany.

3. Department of Biological and Agricultural Engineering, University of California, Davis, CA, USA.

4. Department of Viticulture and Enology, University of California, Davis, CA, USA.

Abstract

Deep learning and multimodal remote and proximal sensing are widely used for analyzing plant and crop traits, but many of these deep learning models are supervised and necessitate reference datasets with image annotations. Acquiring these datasets often demands experiments that are both labor-intensive and time-consuming. Furthermore, extracting traits from remote sensing data beyond simple geometric features remains a challenge. To address these challenges, we proposed a radiative transfer modeling framework based on the Helios 3-dimensional (3D) plant modeling software designed for plant remote and proximal sensing image simulation. The framework has the capability to simulate RGB, multi-/hyperspectral, thermal, and depth cameras, and produce associated plant images with fully resolved reference labels such as plant physical traits, leaf chemical concentrations, and leaf physiological traits. Helios offers a simulated environment that enables generation of 3D geometric models of plants and soil with random variation, and specification or simulation of their properties and function. This approach differs from traditional computer graphics rendering by explicitly modeling radiation transfer physics, which provides a critical link to underlying plant biophysical processes. Results indicate that the framework is capable of generating high-quality, labeled synthetic plant images under given lighting scenarios, which can lessen or remove the need for manually collected and annotated data. Two example applications are presented that demonstrate the feasibility of using the model to enable unsupervised learning by training deep learning models exclusively with simulated images and performing prediction tasks using real images.

Funder

Bill and Melinda Gates Foundation

National Institute of Food and Agriculture

Publisher

American Association for the Advancement of Science (AAAS)

Reference60 articles.

1. Accuracy and limitations for spectroscopic prediction of leaf traits in seasonally dry tropical environments;Streher AS;Remote Sens Environ,2020

2. Remote sensing for agricultural applications: A meta-review;Weiss M;Remote Sens Environ,2020

3. A direct comparison of remote sensing approaches for high-throughput phenotyping in plant breeding;Tattaris M;Front Plant Sci,2016

4. Yield sensing technologies for perennial and annual horticultural crops: A review;Longchamps L;Precis Agric,2022

5. Machine learning for high-throughput stress phenotyping in plants;Singh A;Trends Plant Sci,2016

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3