Back to Search
Start Over
A novel NIR-image segmentation method for the precise estimation of above-ground biomass in rice crops
- Source :
- PLoS ONE, PLoS ONE, Public Library of Science, 2020, 15 (10), ⟨10.1371/journal.pone.0239591⟩, PLoS ONE, Vol 15, Iss 10, p e0239591 (2020), PloS One
- Publication Year :
- 2020
- Publisher :
- HAL CCSD, 2020.
-
Abstract
- International audience; Traditional methods to measure spatio-temporal variations in biomass rely on a labor-intensive destructive sampling of the crop. In this paper, we present a high-throughput phenotyping approach for the estimation of Above-Ground Biomass Dynamics (AGBD) using an unmanned aerial system. Multispectral imagery was acquired and processed by using the proposed segmentation method called GFKuts, that optimally labels the plot canopy based on a Gaussian mixture model, a Montecarlo based K-means, and a guided image filtering. Accurate plot segmentation results enabled the extraction of several canopy features associated with biomass yield. Machine learning algorithms were trained to estimate the AGBD according to the growth stages of the crop and the physiological response of two rice genotypes under lowland and upland production systems. Results report AGBD estimation correlations with an average of r = 0.95 and R 2 = 0.91 according to the experimental data. We compared our segmentation method against a traditional technique based on clustering. A comprehensive improvement of 13% in the biomass correlation was obtained thanks to the segmentation method proposed herein.
- Subjects :
- Canopy
010504 meteorology & atmospheric sciences
Image Processing
[SDV]Life Sciences [q-bio]
Multispectral image
0211 other engineering and technologies
Biomass
02 engineering and technology
01 natural sciences
Imagerie multispectrale
Machine Learning
Spectrum Analysis Techniques
F01 - Culture des plantes
Biomasse
Image Processing, Computer-Assisted
Segmentation
Mathematics
2. Zero hunger
Multidisciplinary
Applied Mathematics
Simulation and Modeling
near-Infrared Spectroscopy
Eukaryota
Agriculture
Plants
agriculture de précision
Experimental Organism Systems
Physical Sciences
Engineering and Technology
Medicine
Biomasse aérienne
Algorithms
Research Article
Optimization
Crops, Agricultural
Imaging Techniques
Infrared Rays
Traitement d'images
Science
Spectroscopie infrarouge
Crops
Infrared Spectroscopy
Oryza sativa
Image processing
Colombia
Research and Analysis Methods
Phenotypage
Spatio-Temporal Analysis
Plant and Algal Models
Grasses
Cluster analysis
021101 geological & geomatics engineering
0105 earth and related environmental sciences
business.industry
Organisms
Biology and Life Sciences
Oryza
Pattern recognition
Image segmentation
15. Life on land
Mixture model
Signal Processing
Remote Sensing Technology
Animal Studies
Geographic Information Systems
Rice
Artificial intelligence
U30 - Méthodes de recherche
business
Crop Science
Cereal Crops
Subjects
Details
- Language :
- English
- ISSN :
- 19326203
- Database :
- OpenAIRE
- Journal :
- PLoS ONE, PLoS ONE, Public Library of Science, 2020, 15 (10), ⟨10.1371/journal.pone.0239591⟩, PLoS ONE, Vol 15, Iss 10, p e0239591 (2020), PloS One
- Accession number :
- edsair.doi.dedup.....497c3726b48358bc00b5730d2f6055c5