Next Article in Journal
A Review of Precision Irrigation Water-Saving Technology under Changing Climate for Enhancing Water Use Efficiency, Crop Yield, and Environmental Footprints
Previous Article in Journal
Analysis of Vibration Characteristics of Tractor–Rotary Cultivator Combination Based on Time Domain and Frequency Domain
Previous Article in Special Issue
Loop Closure Detection with CNN in RGB-D SLAM for Intelligent Agricultural Equipment
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Semi-Supervised One-Stage Object Detection for Maize Leaf Disease

1
School of Computer Science and Engineering, Changchun University Of Technology, Changchun 130102, China
2
Institute of Plant Protection, Jilin Academy of Agricultural Sciences (Northeast Agricultural Research Center of China), Changchun 130033, China
3
Jilin Province Data Service Industry Public Technology Research Centre, Changchun 130102, China
*
Author to whom correspondence should be addressed.
Agriculture 2024, 14(7), 1140; https://doi.org/10.3390/agriculture14071140
Submission received: 13 June 2024 / Revised: 8 July 2024 / Accepted: 12 July 2024 / Published: 14 July 2024
(This article belongs to the Special Issue Advanced Image Processing in Agricultural Applications)

Abstract

Maize is one of the most important crops globally, and accurate diagnosis of leaf diseases is crucial for ensuring increased yields. Despite the continuous progress in computer vision technology, detecting maize leaf diseases based on deep learning still relies on a large amount of manually labeled data, and the labeling process is time-consuming and labor-intensive. Moreover, the detectors currently used for identifying maize leaf diseases have relatively low accuracy in complex experimental fields. Therefore, the proposed Agronomic Teacher, an object detection algorithm that utilizes limited labeled and abundant unlabeled data, is applied to maize leaf disease recognition. In this work, a semi-supervised object detection framework is built based on a single-stage detector, integrating the Weighted Average Pseudo-labeling Assignment (WAP) strategy and AgroYOLO detector combining Agro-Backbone network with Agro-Neck network. The WAP strategy uses weight adjustments to set objectness and classification scores as evaluation criteria for pseudo-labels reliability assignment. Agro-Backbone network accurately extracts features of maize leaf diseases and obtains richer semantic information. Agro-Neck network enhances feature fusion by utilizing multi-layer features for collaborative combinations. The effectiveness of the proposed method is validated on the MaizeData and PascalVOC datasets at different annotation ratios. Compared to the baseline model, Agronomic Teacher leverages abundant unlabeled data to achieve a 6.5% increase in mAP (0.5) on the 30% labeled MaizeData. On the 30% labeled PascalVOC dataset, the mAP (0.5) improved by 8.2%, demonstrating the method’s potential for generalization.
Keywords: maize disease detection; semi-supervised learning; object detection maize disease detection; semi-supervised learning; object detection

Share and Cite

MDPI and ACS Style

Liu, J.; Hu, Y.; Su, Q.; Guo, J.; Chen, Z.; Liu, G. Semi-Supervised One-Stage Object Detection for Maize Leaf Disease. Agriculture 2024, 14, 1140. https://doi.org/10.3390/agriculture14071140

AMA Style

Liu J, Hu Y, Su Q, Guo J, Chen Z, Liu G. Semi-Supervised One-Stage Object Detection for Maize Leaf Disease. Agriculture. 2024; 14(7):1140. https://doi.org/10.3390/agriculture14071140

Chicago/Turabian Style

Liu, Jiaqi, Yanxin Hu, Qianfu Su, Jianwei Guo, Zhiyu Chen, and Gang Liu. 2024. "Semi-Supervised One-Stage Object Detection for Maize Leaf Disease" Agriculture 14, no. 7: 1140. https://doi.org/10.3390/agriculture14071140

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop