Tiller estimation method using deep neural networks

Abstract

Abstract Background: A tiller is a branch on a grass plant, and the number of tillers is one of the most important determinants of yield. Traditionally, the tiller number is usually counted by hand, and so an automated approach is necessary for high-throughput phenotyping. Conventional methods use heuristic features to estimate the tiller number. Based on the successful application of DNNs in the field of computer vision, the use of DNN-based features instead of heuristic features is expected to improve the estimation accuracy. However, as DNNs generally require large volumes of data for training, it is difficult to apply them to estimation problems for which large training datasets are unavailable. In this paper, we use two strategies to overcome the problem of insufficient training data: the use of a pretrained DNN model and the use of pretext tasks for learning the feature representation. We extract features using the resulting DNNs and estimate the tiller numbers through a regression technique. Results: We conducted experiments using a dataset of Setaria viridis. Experiments show that the proposed methods using a pretrained model and specific pretext tasks achieve better performance than the conventional method. The best mean absolute error between the hand-labeled and estimated tiller numbers by the proposed method is 0.57. Conclusions: We realized applying DNN methods to tiller number estimation methods by using pretext tasks. The proposed method outperformed the conventional approach.

Code and data availability

The paper's tiller estimation experiments use the Setaria viridis image dataset (25,570 images, 576 with hand-labeled tiller numbers), which the authors explicitly state is publicly available in the figshare repository. No author analysis code or trained models are reported as deposited.