Outdoor Plant Segmentation With Deep Learning for High-Throughput Field Phenotyping on a Diverse Wheat Dataset.
Ontology highlight
ABSTRACT:
SUBMITTER: Zenkl R
PROVIDER: S-EPMC8765702 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundDeep learning methods have outperformed previous techniques in most computer vision tasks, including image-based plant phenotyping. However, massive data collection of root traits and the development of associated artificial intelligence approaches have been hampered by the inaccessibility of the rhizosphere. Here we present ChronoRoot, a system that combines 3D-printed open-hardware with deep segmentation networks for high temporal resolution phenotyping of plant roots in agarized medium.ResultsWe developed a novel deep learning-based root extraction method that leverages the latest advances in convolutional neural networks for image segmentation and incorporates temporal consistency into the root system architecture reconstruction process. Automatic extraction of phenotypic parameters from sequences of images allowed a comprehensive characterization of the root system growth dynamics. Furthermore, novel time-associated parameters emerged from the analysis of spectral features derived from temporal signals.ConclusionsOur work shows that the combination of machine intelligence methods and a 3D-printed device expands the possibilities of root high-throughput phenotyping for genetics and natural variation studies, as well as the screening of clock-related mutants, revealing novel root traits.
| S-EPMC8290196 | biostudies-literature
Project description:The abilities of plant biologists and breeders to characterize the genetic basis of physiological traits are limited by their abilities to obtain quantitative data representing precise details of trait variation, and particularly to collect this data at a high-throughput scale with low cost. Although deep learning methods have demonstrated unprecedented potential to automate plant phenotyping, these methods commonly rely on large training sets that can be time-consuming to generate. Intelligent algorithms have therefore been proposed to enhance the productivity of these annotations and reduce human efforts. We propose a high-throughput phenotyping system which features a Graphical User Interface (GUI) and a novel interactive segmentation algorithm: Semantic-Guided Interactive Object Segmentation (SGIOS). By providing a user-friendly interface and intelligent assistance with annotation, this system offers potential to streamline and accelerate the generation of training sets, reducing the effort required by the user. Our evaluation shows that our proposed SGIOS model requires fewer user inputs compared to the state-of-art models for interactive segmentation. As a case study of the use of the GUI applied for genetic discovery in plants, we present an example of results from a preliminary genome-wide association study (GWAS) of in planta regeneration in Populus trichocarpa (poplar). We further demonstrate that the inclusion of a semantic prior map with SGIOS can accelerate the training process for future GWAS, using a sample of a dataset extracted from a poplar GWAS of in vitro regeneration. The capabilities of our phenotyping system surpass those of unassisted humans to rapidly and precisely phenotype our traits of interest. The scalability of this system enables large-scale phenomic screens that would otherwise be time-prohibitive, thereby providing increased power for GWAS, mutant screens, and other studies relying on large sample sizes to characterize the genetic basis of trait variation. Our user-friendly system can be used by researchers lacking a computational background, thus helping to democratize the use of deep segmentation as a tool for plant phenotyping.
| S-EPMC9394117 | biostudies-literature
Project description:Plant height (PH) is an essential trait in the screening of most crops. While in crops such as wheat, medium stature helps reduce lodging, tall plants are preferred to increase total above-ground biomass. PH is an easy trait to measure manually, although it can be labor-intense depending on the number of plots. There is an increasing demand for alternative approaches to estimate PH in a higher throughput mode. Crop surface models (CSMs) derived from dense point clouds generated via aerial imagery could be used to estimate PH. This study evaluates PH estimation at different phenological stages using plot-level information from aerial imaging-derived 3D CSM in wheat inbred lines during two consecutive years. Multi-temporal and high spatial resolution images were collected by fixed-wing (P l a t F W ) and multi-rotor (P l a t M R ) unmanned aerial vehicle (UAV) platforms over two wheat populations (50 and 150 lines). The PH was measured and compared at four growth stages (GS) using ground-truth measurements (PHground) and UAV-based estimates (PHaerial). The CSMs generated from the aerial imagery were validated using ground control points (GCPs) as fixed reference targets at different heights. The results show that PH estimations using P l a t F W were consistent with those obtained from P l a t M R , showing some slight differences due to image processing settings. The GCPs heights derived from CSM showed a high correlation and low error compared to their actual heights (R 2 ? 0.90, RMSE ? 4 cm). The coefficient of determination (R 2) between PHground and PHaerial at different GS ranged from 0.35 to 0.88, and the root mean square error (RMSE) from 0.39 to 4.02 cm for both platforms. In general, similar and higher heritability was obtained using PHaerial across different GS and years and ranged according to the variability, and environmental error of the PHground observed (0.06-0.97). Finally, we also observed high Spearman rank correlations (0.47-0.91) and R 2 (0.63-0.95) of PHaerial adjusted and predicted values against PHground values. This study provides an example of the use of UAV-based high-resolution RGB imagery to obtain time-series estimates of PH, scalable to tens-of-thousands of plots, and thus suitable to be applied in plant wheat breeding trials.
| S-EPMC7921806 | biostudies-literature
Project description:Plant breeding programs and a wide range of plant science applications would greatly benefit from the development of in-field high throughput phenotyping technologies. In this study, a terrestrial LiDAR-based high throughput phenotyping system was developed. A 2D LiDAR was applied to scan plants from overhead in the field, and an RTK-GPS was used to provide spatial coordinates. Precise 3D models of scanned plants were reconstructed based on the LiDAR and RTK-GPS data. The ground plane of the 3D model was separated by RANSAC algorithm and a Euclidean clustering algorithm was applied to remove noise generated by weeds. After that, clean 3D surface models of cotton plants were obtained, from which three plot-level morphologic traits including canopy height, projected canopy area, and plant volume were derived. Canopy height ranging from 85th percentile to the maximum height were computed based on the histogram of the z coordinate for all measured points; projected canopy area was derived by projecting all points on a ground plane; and a Trapezoidal rule based algorithm was proposed to estimate plant volume. Results of validation experiments showed good agreement between LiDAR measurements and manual measurements for maximum canopy height, projected canopy area, and plant volume, with R2-values of 0.97, 0.97, and 0.98, respectively. The developed system was used to scan the whole field repeatedly over the period from 43 to 109 days after planting. Growth trends and growth rate curves for all three derived morphologic traits were established over the monitoring period for each cultivar. Overall, four different cultivars showed similar growth trends and growth rate patterns. Each cultivar continued to grow until ~88 days after planting, and from then on varied little. However, the actual values were cultivar specific. Correlation analysis between morphologic traits and final yield was conducted over the monitoring period. When considering each cultivar individually, the three traits showed the best correlations with final yield during the period between around 67 and 109 days after planting, with maximum R2-values of up to 0.84, 0.88, and 0.85, respectively. The developed system demonstrated relatively high throughput data collection and analysis.
| S-EPMC5786533 | biostudies-literature
Project description:Field-based high-throughput plant phenotyping (FB-HTPP) has been a primary focus for crop improvement to meet the demands of a growing population in a changing environment. Over the years, breeders, geneticists, physiologists, and agronomists have been able to improve the understanding between complex dynamic traits and plant response to changing environmental conditions using FB-HTPP. However, the volume, velocity, and variety of data captured by FB-HTPP can be problematic, requiring large data stores, databases, and computationally intensive data processing pipelines. To be fully effective, FB-HTTP data workflows including applications for database implementation, data processing, and data interpretation must be developed and optimized. At the US Arid Land Agricultural Center in Maricopa Arizona, USA a data workflow was developed for a terrestrial FB-HTPP platform that utilized a custom Python application and a PostgreSQL database. The workflow developed for the HTPP platform enables users to capture and organize data and verify data quality before statistical analysis. The data from this platform and workflow were used to identify plant lodging and heat tolerance, enhancing genetic gain by improving selection accuracy in an upland cotton breeding program. An advantage of this platform and workflow was the increased amount of data collected throughout the season, while a main limitation was the start-up cost.
| S-EPMC7364621 | biostudies-literature
Project description:BackgroundMaize (Zea mays L.) is one of the most important food sources in the world and has been one of the main targets of plant genetics and phenotypic research for centuries. Observation and analysis of various morphological phenotypic traits during maize growth are essential for genetic and breeding study. The generally huge number of samples produce an enormous amount of high-resolution image data. While high throughput plant phenotyping platforms are increasingly used in maize breeding trials, there is a reasonable need for software tools that can automatically identify visual phenotypic features of maize plants and implement batch processing on image datasets.ResultsOn the boundary between computer vision and plant science, we utilize advanced deep learning methods based on convolutional neural networks to empower the workflow of maize phenotyping analysis. This paper presents Maize-IAS (Maize Image Analysis Software), an integrated application supporting one-click analysis of maize phenotype, embedding multiple functions: (I) Projection, (II) Color Analysis, (III) Internode length, (IV) Height, (V) Stem Diameter and (VI) Leaves Counting. Taking the RGB image of maize as input, the software provides a user-friendly graphical interaction interface and rapid calculation of multiple important phenotypic characteristics, including leaf sheath points detection and leaves segmentation. In function Leaves Counting, the mean and standard deviation of difference between prediction and ground truth are 1.60 and 1.625.ConclusionThe Maize-IAS is easy-to-use and demands neither professional knowledge of computer vision nor deep learning. All functions for batch processing are incorporated, enabling automated and labor-reduced tasks of recording, measurement and quantitative analysis of maize growth traits on a large dataset. We prove the efficiency and potential capability of our techniques and software to image-based plant research, which also demonstrates the feasibility and capability of AI technology implemented in agriculture and plant science.
| S-EPMC8086349 | biostudies-literature
Project description:BackgroundAutomated segmentation of large amount of image data is one of the major bottlenecks in high-throughput plant phenotyping. Dynamic optical appearance of developing plants, inhomogeneous scene illumination, shadows and reflections in plant and background regions complicate automated segmentation of unimodal plant images. To overcome the problem of ambiguous color information in unimodal data, images of different modalities can be combined to a virtual multispectral cube. However, due to motion artefacts caused by the relocation of plants between photochambers the alignment of multimodal images is often compromised by blurring artifacts.ResultsHere, we present an approach to automated segmentation of greenhouse plant images which is based on co-registration of fluorescence (FLU) and of visible light (VIS) camera images followed by subsequent separation of plant and marginal background regions using different species- and camera view-tailored classification models. Our experimental results including a direct comparison with manually segmented ground truth data show that images of different plant types acquired at different developmental stages from different camera views can be automatically segmented with the average accuracy of 93 % ( S D = 5 % ) using our two-step registration-classification approach.ConclusionAutomated segmentation of arbitrary greenhouse images exhibiting highly variable optical plant and background appearance represents a challenging task to data classification techniques that rely on detection of invariances. To overcome the limitation of unimodal image analysis, a two-step registration-classification approach to combined analysis of fluorescent and visible light images was developed. Our experimental results show that this algorithmic approach enables accurate segmentation of different FLU/VIS plant images suitable for application in fully automated high-throughput manner.
| S-EPMC7346525 | biostudies-literature
Project description:BACKGROUND:Measurement of plant traits with precision and speed on large populations has emerged as a critical bottleneck in connecting genotype to phenotype in genetics and breeding. This bottleneck limits advancements in understanding plant genomes and the development of improved, high-yielding crop varieties. RESULTS:Here we demonstrate the application of deep learning on proximal imaging from a mobile field vehicle to directly estimate plant morphology and developmental stages in wheat under field conditions. We developed and trained a convolutional neural network with image datasets labeled from expert visual scores and used this "breeder-trained" network to classify wheat morphology and developmental stages. For both morphological (awned) and phenological (flowering time) traits, we demonstrate high heritability and very high accuracy against the "ground-truth" values from visual scoring. Using the traits predicted by the network, we tested genotype-to-phenotype association using the deep learning phenotypes and uncovered novel epistatic interactions for flowering time. Enabled by the time-series high-throughput phenotyping, we describe a new phenotype as the rate of flowering and show heritable genetic control for this trait. CONCLUSIONS:We demonstrated a field-based high-throughput phenotyping approach using deep learning that can directly measure morphological and developmental phenotypes in genetic populations from field-based imaging. The deep learning approach presented here gives a conceptual advancement in high-throughput plant phenotyping because it can potentially estimate any trait in any plant species for which the combination of breeder scores and high-resolution images can be obtained, capturing the expert knowledge from breeders, geneticists, pathologists, and physiologists to train the networks.
| S-EPMC6862935 | biostudies-literature
Project description:Background Automated analysis of large image data is highly demanded in high-throughput plant phenotyping. Due to large variability in optical plant appearance and experimental setups, advanced machine and deep learning techniques are required for automated detection and segmentation of plant structures in complex optical scenes. Methods Here, we present a GUI-based software tool (DeepShoot) for efficient, fully automated segmentation and quantitative analysis of greenhouse-grown shoots which is based on pre-trained U-net deep learning models of arabidopsis, maize, and wheat plant appearance in different rotational side- and top-views. Results Our experimental results show that the developed algorithmic framework performs automated segmentation of side- and top-view images of different shoots acquired at different developmental stages using different phenotyping facilities with an average accuracy of more than 90% and outperforms shallow as well as conventional and encoder backbone networks in cross-validation tests with respect to both precision and performance time. Conclusion The DeepShoot tool presented in this study provides an efficient solution for automated segmentation and phenotypic characterization of greenhouse-grown plant shoots suitable also for end-users without advanced IT skills. Primarily trained on images of three selected plants, this tool can be applied to images of other plant species exhibiting similar optical properties.
| S-EPMC9328757 | biostudies-literature
Project description:Heliaphen is an outdoor platform designed for high-throughput phenotyping. It allows the automated management of drought scenarios and monitoring of plants throughout their lifecycles. A robot moving between plants growing in 15-L pots monitors the plant water status and phenotypes the leaf or whole-plant morphology. From these measurements, we can compute more complex traits, such as leaf expansion (LE) or transpiration rate (TR) in response to water deficit. Here, we illustrate the capabilities of the platform with two practical cases in sunflower (Helianthus annuus): a genetic and genomic study of the response of yield-related traits to drought, and a modeling study using measured parameters as inputs for a crop simulation. For the genetic study, classical measurements of thousand-kernel weight (TKW) were performed on a biparental population under automatically managed drought stress and control conditions. These data were used for an association study, which identified five genetic markers of the TKW drought response. A complementary transcriptomic analysis identified candidate genes associated with these markers that were differentially expressed in the parental backgrounds in drought conditions. For the simulation study, we used a crop simulation model to predict the impact on crop yield of two traits measured on the platform (LE and TR) for a large number of environments. We conducted simulations in 42 contrasting locations across Europe using 21 years of climate data. We defined the pattern of abiotic stresses occurring at the continental scale and identified ideotypes (i.e., genotypes with specific trait values) that are more adapted to specific environment types. This study exemplifies how phenotyping platforms can assist the identification of the genetic architecture controlling complex response traits and facilitate the estimation of ecophysiological model parameters to define ideotypes adapted to different environmental conditions.
| S-EPMC6343525 | biostudies-literature