scholarly journals Plant biomass estimation using image analysis and machine learning technique

2020 ◽  
Vol 35 (1-2) ◽  
Author(s):  
Alka Arora ◽  
Tanuj Mishra ◽  
Sudeep Marwaha ◽  
Mrinmoy Ray ◽  
R. S. Tomar
Keyword(s):  
Image Analysis ◽  
Plant Biomass ◽  
Net Primary Production ◽  
Plant Phenotyping ◽  
Biomass Estimation ◽  
Test Case ◽  
New Delhi ◽  
Fresh Biomass ◽  
Nir Imaging ◽  
Plant Phenomics

Plant biomass is the basis for the calculation of net primary production. Estimation of fresh biomass in high throughput way is critical for plant phenotyping. Conventional phenotyping approaches for measuring the fresh biomass is time consuming, laborious and destructive in nature. Image analysis based plant phenotyping is very popular nowadays. Most of the approaches used projected shoot area from visual images (VIS) to estimate the fresh biomass. As water content has a significant effect on fresh biomass and water absorbs radiation at near infra-red (NIR) region (900nm to 1700nm), we have hypothesized that the combined use of VIS and NIR imaging can predict the fresh biomass more accurately that the VIS image alone. In this study, VIS and NIR images were collected using LemaTec facility installed at Nanaji Deshmukh Plant Phenomics Center, ICAR-IARI, New Delhi-12. In this study, VIS and NIR imaging were captured for rice leaves with different moisture content as a test case. MATLAB software (version 2015b) was used for image analysis. The two image derived parameter viz. Green Leaf Proportion (GPR) from VIS image and mean gray value/intensity (MGV_NIR) from NIR image were used to develop the statistical model to estimate the fresh biomass in the form of Leaf Fresh Weight (LFW). The proposed approach significantly enhanced the fresh biomass estimation.

scholarly journals Digital Biomass Accumulation Using High-Throughput Plant Phenotype Data Analysis

2017 ◽  
Vol 14 (3) ◽  
Author(s):  
Md. Matiur Rahaman ◽  
Md. Asif Ahsan ◽  
Zeeshan Gillani ◽  
Ming Chen
Keyword(s):  
High Throughput ◽  
Plant Biomass ◽  
Biomass Accumulation ◽  
Repeated Measurements ◽  
Functional Ecology ◽  
Plant Phenotyping ◽  
Biomass Estimation ◽  
Phenotypic Trait ◽  
Phenotypic Traits ◽  
Plant Area

AbstractBiomass is an important phenotypic trait in functional ecology and growth analysis. The typical methods for measuring biomass are destructive, and they require numerous individuals to be cultivated for repeated measurements. With the advent of image-based high-throughput plant phenotyping facilities, non-destructive biomass measuring methods have attempted to overcome this problem. Thus, the estimation of plant biomass of individual plants from their digital images is becoming more important. In this paper, we propose an approach to biomass estimation based on image derived phenotypic traits. Several image-based biomass studies state that the estimation of plant biomass is only a linear function of the projected plant area in images. However, we modeled the plant volume as a function of plant area, plant compactness, and plant age to generalize the linear biomass model. The obtained results confirm the proposed model and can explain most of the observed variance during image-derived biomass estimation. Moreover, a small difference was observed between actual and estimated digital biomass, which indicates that our proposed approach can be used to estimate digital biomass accurately.

scholarly journals Maize-IAS: a maize image analysis software using deep learning for high-throughput plant phenotyping

Plant Methods ◽  
2021 ◽  
Vol 17 (1) ◽  
Author(s):  
Shuo Zhou ◽  
Xiujuan Chai ◽  
Zixuan Yang ◽  
Hongwu Wang ◽  
Chenxue Yang ◽  
...  
Keyword(s):  
Computer Vision ◽  
Image Analysis ◽  
Deep Learning ◽  
High Throughput ◽  
Batch Processing ◽  
Plant Phenotyping ◽  
Plant Science ◽  
Analysis Software ◽  
Image Analysis Software ◽  
Maize Growth

Abstract Background Maize (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. Results On 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. Conclusion The 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.

scholarly journals PlantCV v2: Image analysis software for high-throughput plant phenotyping

PeerJ ◽  
2017 ◽  
Vol 5 ◽  
pp. e4088 ◽  
Author(s):  
Malia A. Gehan ◽  
Noah Fahlgren ◽  
Arash Abbasi ◽  
Jeffrey C. Berry ◽  
Steven T. Callen ◽  
...  
Keyword(s):  
Image Processing ◽  
Computer Vision ◽  
Image Analysis ◽  
Image Data ◽  
Plant Phenotyping ◽  
Analysis Software ◽  
Computational Tools ◽  
Landmark Identification ◽  
Plant Image ◽  
Leaf Segmentation

Systems for collecting image data in conjunction with computer vision techniques are a powerful tool for increasing the temporal resolution at which plant phenotypes can be measured non-destructively. Computational tools that are flexible and extendable are needed to address the diversity of plant phenotyping problems. We previously described the Plant Computer Vision (PlantCV) software package, which is an image processing toolkit for plant phenotyping analysis. The goal of the PlantCV project is to develop a set of modular, reusable, and repurposable tools for plant image analysis that are open-source and community-developed. Here we present the details and rationale for major developments in the second major release of PlantCV. In addition to overall improvements in the organization of the PlantCV project, new functionality includes a set of new image processing and normalization tools, support for analyzing images that include multiple plants, leaf segmentation, landmark identification tools for morphometrics, and modules for machine learning.

Plant Biomass Estimation Using Dielectric Properties

2006 ◽  
Author(s):  
Carol L. Jones ◽  
Marvin L. Stone ◽  
Niels O. Maness ◽  
John B. Solie ◽  
Gerald H. Brusewitz
Keyword(s):  
Dielectric Properties ◽  
Plant Biomass ◽  
Biomass Estimation

An analysis of primary production in the Daly River, a relatively unimpacted tropical river in northern Australia

2005 ◽  
Vol 56 (3) ◽  
pp. 303 ◽  
Author(s):  
I. T. Webster ◽  
N. Rea ◽  
A. V. Padovan ◽  
P. Dostine ◽  
S. A. Townsend ◽  
...  
Keyword(s):  
Primary Production ◽  
Plant Biomass ◽  
Net Primary Production ◽  
Low Flow ◽  
Nutrient Concentrations ◽  
Tight Coupling ◽  
Tropical River ◽  
Rate Of Photosynthesis ◽  
Curve Method ◽  
Tropical Australia

In this paper, the dynamics of primary production in the Daly River in tropical Australia are investigated. We used the diurnal-curve method for both oxygen and pH to calculate photosynthesis and respiration rates as indicators of whole-river productivity. The Daly River has maximum discharges during the summer, monsoonal season. Flow during the dry season is maintained by groundwater discharge via springs. The study investigated how primary production and respiration evolve during the period of low flow in the river (April–November). The relationship between primary production and the availability of light and nutrients enabled the role of these factors to be assessed in a clear, oligotrophic tropical river. The measured rate of photosynthesis was broadly consistent with the estimated mass of chlorophyll associated with the main primary producers in the river (phytoplankton, epibenthic algae, macroalgae, macrophytes). A significant result of the analysis is that during the time that plant biomass re-established after recession of the flows, net primary production proved to be ~4% of the rate of photosynthesis. This result and the observed low-nutrient concentrations in the river suggest a tight coupling between photosynthetic fixation of carbon and the microbial degradation of photosynthetic products comprising plant material and exudates.

Image analysis of wheat grains developed in different environments and its implications for identification

2006 ◽  
Vol 144 (3) ◽  
pp. 221-227 ◽  
Author(s):  
J. K. SAINIS ◽  
S. P. SHOUCHE ◽  
S. G. BHAGWAT
Keyword(s):  
Image Analysis ◽  
Environmental Conditions ◽  
Environmental Changes ◽  
Grain Filling ◽  
Test Case ◽  
Wheat Varieties ◽  
Varietal Identification ◽  
Computer Based ◽  
Euclidean Distances ◽  
Grain Size And Shape

Varietal identification is an important aspect of crop research and utilization. Identification using computer-based image analysis could be an alternative to visual identification. However, the effectiveness of image analysis systems needs to be established under various real conditions. Three wheat varieties were sown on three different dates. Variation in the grain size and shape of these varieties, brought about by changes in the environmental conditions, was measured using Comprehensive Image Processing Software (CIPS). Some parameters showed considerable grain-to-grain variation, which was either inherent or due to environmental changes during grain filling. Euclidean distances were calculated using either means of all the parameters (ED1), or using only those parameters that did not show a high coefficient of variation (ED2). For samples of the same variety sown at different times, Euclidean distances were smaller compared with samples of different varieties, indicating that grains of the same variety resembled one another. By using the criterion of minimum Euclidean distance it was possible to distinguish between varieties, in spite of variation in grain shape and size due to environmental conditions. It was possible to identify correctly an unknown sample, taken as a test case.

Sign in / Sign up

Export Citation Format

Share Document