Disease Detection and Identification of Rice Leaf Based on Improved Detection Transformer

Author:

Yang Hua1,Deng Xingquan1,Shen Hao2,Lei Qingfeng1,Zhang Shuxiang1,Liu Neng1

Affiliation:

1. School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan 430040, China

2. Baijuncheng Technology Co., Ltd., Wuhan 434000, China

Abstract

In recent years, the domain of diagnosing plant afflictions has predominantly relied upon the utilization of deep learning techniques for classifying images of diseased specimens; however, these classification algorithms remain insufficient for instances where a single plant exhibits multiple ailments. Consequently, we view the region afflicted by the malady of rice leaves as a minuscule issue of target detection, and then avail ourselves of a computational approach to vision to identify the affected area. In this paper, we advance a proposal for a Dense Higher-Level Composition Feature Pyramid Network (DHLC-FPN) that is integrated into the Detection Transformer (DETR) algorithm, thereby proffering a novel Dense Higher-Level Composition Detection Transformer (DHLC-DETR) methodology which can effectively detect three diseases: sheath blight, rice blast, and flax spot. Initially, the proposed DHLC-FPN is utilized to supersede the backbone network of DETR through amalgamation with Res2Net, thus forming a feature extraction network. Res2Net then extracts five feature scales, which are coalesced through the deployment of high-density rank hybrid sampling by the DHLC-FPN architecture. The fused features, in concert with the location encoding, are then fed into the transformer to produce predictions of classes and prediction boxes. Lastly, the prediction classes and the prediction boxes are subjected to binary matching through the application of the Hungarian algorithm. On the IDADP datasets, the DHLC-DETR model, through the utilization of data enhancement, elevated mean Average Precision (mAP) by 17.3% in comparison to the DETR model. Additionally, mAP for small target detection was improved by 9.5%, and the magnitude of hyperparameters was reduced by 324.9 M. The empirical outcomes demonstrate that the optimized structure for feature extraction can significantly enhance the average detection accuracy and small target detection accuracy of the model, achieving an average accuracy of 97.44% on the IDADP rice disease dataset.

Funder

School enterprise cooperation project

Hubei Provincial Teaching and Research Project

Ministry of Education Industry-University Cooperation Collaborative Education Project

Publisher

MDPI AG

Subject

Plant Science,Agronomy and Crop Science,Food Science

Reference41 articles.

1. Shi, J., and Yang, X. (2022). Sustainable development levels and influence factors in rural china based on rural revitalization strategy. Sustainability, 14.

2. Deep feature based rice leaf disease identification using support vector machine;Sethy;Comput. Electron. Agric.,2020

3. Maize leaf disease identification based on feature enhancement and dms-robust alexnet;Lv;IEEE Access,2020

4. Classification and identification of primitive kharif crops using supervised deep convolutional networks;Khamparia;Sustain. Comput. Inform. Syst.,2020

5. Ge, Z., Liu, S., Wang, F., Li, Z., and Sun, J. (2021). Yolox: Exceeding yolo series in 2021. arXiv.

Cited by 12 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. An interpretable fusion model integrating lightweight CNN and transformer architectures for rice leaf disease identification;Ecological Informatics;2024-09

2. Integration of Diffusion Transformer and Knowledge Graph for Efficient Cucumber Disease Detection in Agriculture;Plants;2024-08-31

3. LWSDNet: A Lightweight Wheat Scab Detection Network Based on UAV Remote Sensing Images;Remote Sensing;2024-07-31

4. Rice Leaf Disease Stages Classification Using Few-shot Learning Techniques;2024 International Conference on Smart Systems for Electrical, Electronics, Communication and Computer Engineering (ICSSEECC);2024-06-28

5. Tomato Plant Disease Classification Using Transfer Learning;2024 5th International Conference for Emerging Technology (INCET);2024-05-24

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3