An Instance Segmentation-Based Method to Obtain the Leaf Age and Plant Centre of Weeds in Complex Field Environments.

Longzhe Quan,Hengda Li,Bing Wu,Chunjie Yang,Shouren Mao

doi:10.3390/s21103389

Longzhe Quan, Hengda Li + Show 3 more

Open Access

https://doi.org/10.3390/s21103389

Copy DOI

Abstract

Leaf age and plant centre are important phenotypic information of weeds, and accurate identification of them plays an important role in understanding the morphological structure of weeds, guiding precise targeted spraying and reducing the use of herbicides. In this work, a weed segmentation method based on BlendMask is proposed to obtain the phenotypic information of weeds under complex field conditions. This study collected images from different angles (front, side, and top views) of three kinds of weeds (Solanum nigrum, barnyard grass (Echinochloa crus-galli), and Abutilon theophrasti Medicus) in a maize field. Two datasets (with and without data enhancement) and two backbone networks (ResNet50 and ResNet101) were replaced to improve model performance. Finally, seven evaluation indicators are used to evaluate the segmentation results of the model under different angles. The results indicated that data enhancement and ResNet101 as the backbone network could enhance the model performance. The F1 value of the plant centre is 0.9330, and the recognition accuracy of leaf age can reach 0.957. The mIOU value of the top view is 0.642. Therefore, deep learning methods can effectively identify weed leaf age and plant centre, which is of great significance for variable spraying.

Highlights

IntroductionThe control of weeds is mainly based on the traditional uniform spraying of herbicides
In view of the above research, our goal is to propose a weed phenotype acquisition method based on an instance segmentation model that can provide weed species, leaf age, and plant centres in a complex field environment
The performance of instance segmentation will determine the effect of weed recognition, so the following research is carried out for instance segmentation networks

Summary

Introduction

The control of weeds is mainly based on the traditional uniform spraying of herbicides. This method has caused excessive use of herbicides and environmental pollution. The plant centre is the area formed by the overlapping of the petiole and stem of the top leaves of the weed. Accurate identification of weed leaf age and plant centre is of great significance to reduce the use of herbicides, improve the utilization rate of herbicides, and avoid environmental pollution

Objectives

Methods

Results

Conclusion