DeepWheat: Estimating Phenotypic Traits from Crop Images with Deep Learning

TL;DR

DeepWheat employs advanced deep learning models to accurately estimate wheat emergence and biomass traits from field images, outperforming previous methods even with limited data.

Contribution

The paper introduces a novel deep learning framework for phenotypic trait estimation from crop images, demonstrating superior accuracy over existing approaches.

Findings

Achieved mean absolute difference of 1.05 counts for emergence

Achieved mean absolute difference of 1.45 for biomass estimation

Outperformed previous methods in biomass prediction accuracy

Abstract

In this paper, we investigate estimating emergence and biomass traits from color images and elevation maps of wheat field plots. We employ a state-of-the-art deconvolutional network for segmentation and convolutional architectures, with residual and Inception-like layers, to estimate traits via high dimensional nonlinear regression. Evaluation was performed on two different species of wheat, grown in field plots for an experimental plant breeding study. Our framework achieves satisfactory performance with mean and standard deviation of absolute difference of 1.05 and 1.40 counts for emergence and 1.45 and 2.05 for biomass estimation. Our results for counting wheat plants from field images are better than the accuracy reported for the similar, but arguably less difficult, task of counting leaves from indoor images of rosette plants. Our results for biomass estimation, even with a very small dataset, improve upon all previously proposed approaches in the literature.