High-Throughput Rice Density Estimation from Transplantation to Tillering Stages Using Deep Networks.

Abstract

Rice density is closely related to yield estimation, growth diagnosis, cultivated area statistics, and management and damage evaluation. Currently, rice density estimation heavily relies on manual sampling and counting, which is inefficient and inaccurate. With the prevalence of digital imagery, computer vision (CV) technology emerges as a promising alternative to automate this task. However, challenges of an in-field environment, such as illumination, scale, and appearance variations, render gaps for deploying CV methods. To fill these gaps towards accurate rice density estimation, we propose a deep learning-based approach called the Scale-Fusion Counting Classification Network (SFC 2 Net) that integrates several state-of-the-art computer vision ideas. In particular, SFC 2 Net addresses appearance and illumination changes by employing a multicolumn pretrained network and multilayer feature fusion to enhance feature representation. To ameliorate sample imbalance engendered by scale, SFC 2 Net follows a recent blockwise classification idea. We validate SFC 2 Net on a new rice plant counting (RPC) dataset collected from two field sites in China from 2010 to 2013. Experimental results show that SFC 2 Net achieves highly accurate counting performance on the RPC dataset with a mean absolute error (MAE) of 25.51, a root mean square error (MSE) of 38.06, a relative MAE of 3.82%, and a R 2 of 0.98, which exhibits a relative improvement of 48.2% w.r.t. MAE over the conventional counting approach CSRNet. Further, SFC 2 Net provides high-throughput processing capability, with 16.7 frames per second on 1024 × 1024 images. Our results suggest that manual rice counting can be safely replaced by SFC 2 Net at early growth stages. Code and models are available online at https://git.io/sfc2net.

Plant phenotyping relevance

イネ個体数という植物形態・密度形質を画像から自動推定する深層学習手法を開発し、新規データセットで精度検証しているため、方法が中心である。

Code and data availability

The paper's rice plant counting (RPC) dataset (382 field images with 211,971 dot annotations) and the authors' SFC2Net code and trained models are explicitly stated to be publicly available at the authors' URL https://git.io/sfc2net, which matches an allowed URL.