UAV Image-Based Crop Growth Analysis of 3D-Reconstructed Crop Canopies

Area of Science:

• Agricultural Science
• Plant Science
• Remote Sensing

Background:

• Accurate plant growth rate measurement is crucial for crop productivity.
• Manual field measurements are often inaccurate and time-consuming.
• High-throughput, image-based platforms offer non-destructive, objective plant parameter estimation.

Purpose of the Study:

• To assess the potential of unoccupied aerial vehicle (UAV)-based imagery for quantifying lentil plant growth rate.
• To evaluate image-derived parameters against traditional biomass measurements.
• To explore novel phenotypes for plant breeding programs.

Main Methods:

• Lentil lines were grown in microplots over five site-years with multiple biomass collection time-points.
• UAV-based aerial imagery was collected simultaneously with manual biomass measurements.
• Two-dimensional orthomosaics and three-dimensional point clouds were generated; non-linear logistic models were applied.

Main Results:

• Remotely detected vegetation area and crop volume showed trends comparable to dry weight biomass accumulation.
• UAV-derived vegetation area correlated with early-season leaf area and biomass.
• Plot volume proved a better estimator for mid- to late-season biomass; growth rate and G50 parameters effectively quantified lentil growth.

Conclusions:

• UAV-based imagery provides a powerful tool for non-destructively estimating lentil growth rate and biomass.
• Image-based methods enable the analysis of novel plant parameters, enhancing breeding efficiency.
• This technology offers significant potential for accelerating plant breeding programs through new phenotypes and improved selection intensity.