Engineering in Agriculture, Environment and Food
Online ISSN : 1881-8366
ISSN-L : 1881-8366
Research Article
Estimation of Tiller Number in Rice Using a Field Robot and Deep Learning
─Investigating Effects of Dataset Composition on Tiller Estimation Accuracy─
Dhirendranath SINGH Tomohiro MORIShigeru ICHIURAThanh Tung NGUYENYuka SASAKIMitsuhiko KATAHIRA
Author information

2022 Volume 15 Issue 2 Pages 47-60


Tiller number, an important growth parameter for rice cultivation, is still being assessed manually. This work investigated the influence of dataset composition on performance of deep learning models for tiller number estimation in rice. Four datasets were constructed for early tillering, active tillering, and maximum tillering by applying the concepts of mixed varieties, class balance, and data augmentation. YOLOv4 models were trained to estimate tiller numbers using each constructed dataset. Then their performance was evaluated. Results demonstrated that the models trained with datasets created using a combination of mixed variety, class balance, and augmentation showed the best performance for estimating the tiller number at the three tillering stages with a mAP range of 68.8–86.4 %.

Content from these authors
© 2022 Asian Agricultural and Biological Engineering Association
Next article