Answers are grounded in this paper and cite their sources.
Image-derived phenotyping at individual plant level can provide more accurate and more comprehensive information than manual measuring for quantitative traits related to canopy growth in field environment. Aims of this study were to: (i) assess smartphone image-derived canopy parameter at early stage of sunflower, and (ii) to evaluate performance of predictive models for morphological and biomass traits related to canopy growth using smartphone image-derived parameter. Original top-view image datasets taken with a smartphone camera were processed, and necessary information was extracted with image analysis software developed using fuzzy c-means clustering algorithm. Canopy cover rate per plant (CCR) was not only the relative value but also image-derived phenotyping feature. CCR were significantly and positively correlated (r ≧ 0.90; **P < 0.01) with plant height, total leaf area per plant, plant dry mass, aboveground plant dry and leaf dry mass, respectively. Ground measured and predicted values from linear regression model for plant height, total leaf area per plant, plant dry mass, aboveground total dry mass, leaf dry mass per plant with CCR showed an accurate prediction with high coefficients of determination (R ) of more than 0.8063, respectively. The present study documented the robustness of predictive models using several metrics.
No takes yet. Share an insight, caveat, or question.
Jong et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: