A Complete System for 3D Reconstruction of Roots for Phenotypic Analysis

Kumar, Pankaj; Cai, Jinhai; Miklavcic, Stanley J.

doi:10.1007/978-3-319-10984-8_14

Cited by 7 publications

(6 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning has been adopted as the method of choice in many recent image analysis applications to address a number of plant phenotyping problems. These include the study of wheat spikes in controlled environments [ 2 ], the classification of leaf species and leaf venation [ 22 ], the analysis of the architecture of root systems [ 23 , 24 ], the measurement of plant stress levels [ 25 ] and the determination of wheat growth stages [ 26 ]. More recently, deep learning has begun to outperform previous image analysis and machine learning approaches and promises a step-change in the performance of image-based phenotyping.…”

Section: Introductionmentioning

confidence: 99%

Detection and analysis of wheat spikes using Convolutional Neural Networks

et al. 2018

Self Cite

View full text Add to dashboard Cite

BackgroundField phenotyping by remote sensing has received increased interest in recent years with the possibility of achieving high-throughput analysis of crop fields. Along with the various technological developments, the application of machine learning methods for image analysis has enhanced the potential for quantitative assessment of a multitude of crop traits. For wheat breeding purposes, assessing the production of wheat spikes, as the grain-bearing organ, is a useful proxy measure of grain production. Thus, being able to detect and characterize spikes from images of wheat fields is an essential component in a wheat breeding pipeline for the selection of high yielding varieties. ResultsWe have applied a deep learning approach to accurately detect, count and analyze wheat spikes for yield estimation. We have tested the approach on a set of images of wheat field trial comprising 10 varieties subjected to three fertilizer treatments. The images have been captured over one season, using high definition RGB cameras mounted on a land-based imaging platform, and viewing the wheat plots from an oblique angle. A subset of in-field images has been accurately labeled by manually annotating all the spike regions. This annotated dataset, called SPIKE, is then used to train four region-based Convolutional Neural Networks (R-CNN) which take, as input, images of wheat plots, and accurately detect and count spike regions in each plot. The CNNs also output the spike density and a classification probability for each plot. Using the same R-CNN architecture, four different models were generated based on four different datasets of training and testing images captured at various growth stages. Despite the challenging field imaging conditions, e.g., variable illumination conditions, high spike occlusion, and complex background, the four R-CNN models achieve an average detection accuracy ranging from 88 to across different sets of test images. The most robust R-CNN model, which achieved the highest accuracy, is then selected to study the variation in spike production over 10 wheat varieties and three treatments. The SPIKE dataset and the trained CNN are the main contributions of this paper.ConclusionWith the availability of good training datasets such us the SPIKE dataset proposed in this article, deep learning techniques can achieve high accuracy in detecting and counting spikes from complex wheat field images. The proposed robust R-CNN model, which has been trained on spike images captured during different growth stages, is optimized for application to a wider variety of field scenarios. It accurately quantifies the differences in yield produced by the 10 varieties we have studied, and their respective responses to fertilizer treatment. We have also observed that the other R-CNN models exhibit more specialized performances. The data set and the R-CNN model, which we make publicly available, have the potential to greatly benefit plant breeders by facilitating the high throughput selection of high yielding varieties.Electronic su...

show abstract

Section: Introductionmentioning

confidence: 99%

Detection and analysis of wheat spikes using Convolutional Neural Networks

et al. 2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…For instance, root system architecture can be studied in a non-destructive manner by either imaging plants grown in soils using X-ray CT scanning devices, or by using standard RGB sensors when the plants are grown in transparent media. With the introduction of these methods has come a steady increase in focus on the 3D modeling of root architecture systems [ 9 – 12 ]. In contrast, methods for studying the anatomy of plant roots are less prevalent [ 13 ].…”

Section: Introductionmentioning

confidence: 99%

RootAnalyzer: A Cross-Section Image Analysis Tool for Automated Characterization of Root Cells and Tissues

et al. 2015

Self Cite

View full text Add to dashboard Cite

The morphology of plant root anatomical features is a key factor in effective water and nutrient uptake. Existing techniques for phenotyping root anatomical traits are often based on manual or semi-automatic segmentation and annotation of microscopic images of root cross sections. In this article, we propose a fully automated tool, hereinafter referred to as RootAnalyzer, for efficiently extracting and analyzing anatomical traits from root-cross section images. Using a range of image processing techniques such as local thresholding and nearest neighbor identification, RootAnalyzer segments the plant root from the image’s background, classifies and characterizes the cortex, stele, endodermis and epidermis, and subsequently produces statistics about the morphological properties of the root cells and tissues. We use RootAnalyzer to analyze 15 images of wheat plants and one maize plant image and evaluate its performance against manually-obtained ground truth data. The comparison shows that RootAnalyzer can fully characterize most root tissue regions with over 90% accuracy.

show abstract

“…Although image analysis has improved with time, the extraction of roots from the soil produces damage that can affect the evaluation of the actual plant response. The 3D reconstruction systems that are currently under development perform nondestructive evaluations of the root system, as they do for aboveground organs, to address this problem [ 93 ].…”

Section: Methods and Approaches To Improve Crop Tolerance To Drougmentioning

confidence: 99%

A Dual Strategy of Breeding for Drought Tolerance and Introducing Drought-Tolerant, Underutilized Crops into Production Systems to Enhance Their Resilience to Water Deficiency

Rosero

Granda

Berdugo-Cely

et al. 2020

Plants

View full text Add to dashboard Cite

Water scarcity is the primary constraint on crop productivity in arid and semiarid tropical areas suffering from climate alterations; in accordance, agricultural systems have to be optimized. Several concepts and strategies should be considered to improve crop yield and quality, particularly in vulnerable regions where such environmental changes cause a risk of food insecurity. In this work, we review two strategies aiming to increase drought stress tolerance: (i) the use of natural genes that have evolved over time and are preserved in crop wild relatives and landraces for drought tolerance breeding using conventional and molecular methods and (ii) exploiting the reservoir of neglected and underutilized species to identify those that are known to be more drought-tolerant than conventional staple crops while possessing other desired agronomic and nutritive characteristics, as well as introducing them into existing cropping systems to make them more resilient to water deficiency conditions. In the past, the existence of drought tolerance genes in crop wild relatives and landraces was either unknown or difficult to exploit using traditional breeding techniques to secure potential long-term solutions. Today, with the advances in genomics and phenomics, there are a number of new tools available that facilitate the discovery of drought resistance genes in crop wild relatives and landraces and their relatively easy transfer into advanced breeding lines, thus accelerating breeding progress and creating resilient varieties that can withstand prolonged drought periods. Among those tools are marker-assisted selection (MAS), genomic selection (GS), and targeted gene editing (clustered regularly interspaced short palindromic repeat (CRISPR) technology). The integration of these two major strategies, the advances in conventional and molecular breeding for the drought tolerance of conventional staple crops, and the introduction of drought-tolerant neglected and underutilized species into existing production systems has the potential to enhance the resilience of agricultural production under conditions of water scarcity.

show abstract

A Complete System for 3D Reconstruction of Roots for Phenotypic Analysis

Cited by 7 publications

References 44 publications

Detection and analysis of wheat spikes using Convolutional Neural Networks

Detection and analysis of wheat spikes using Convolutional Neural Networks

RootAnalyzer: A Cross-Section Image Analysis Tool for Automated Characterization of Root Cells and Tissues

A Dual Strategy of Breeding for Drought Tolerance and Introducing Drought-Tolerant, Underutilized Crops into Production Systems to Enhance Their Resilience to Water Deficiency

Contact Info

Product

Resources

About