中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 合肥物质科学研究院
  3. 中国科学院合肥物质科学研究院
Auto-adjustment label assignment-based convolutional neural network for oriented wheat diseases detection

文献类型：期刊论文

作者Liu, Haiyun1,2,5; Chen, Hongbo1,2,5; Du, Jianming1,2; Xie, Chengjun1,5; Zhou, Qiong1,2,4,5; Wang, Rujing1,2,5; Jiao, Lin1,2,3
刊名COMPUTERS AND ELECTRONICS IN AGRICULTURE
出版日期2024-07-01
卷号222
关键词Wheat diseases detection Aspect ratio Auto-adjustment label assignment Localization potential assessment
ISSN号0168-1699
DOI10.1016/j.compag.2024.109029
通讯作者Wang, Rujing(rjwang@iim.ac.cn) ; Jiao, Lin(ljiao@ahu.edu.cn)
英文摘要The frequent occurrence of wheat diseases seriously affects the quality and yield of wheat. Thus, the accurate detection of wheat diseases is highly desired in the field of agricultural information. However, for wheat disease with arbitrary-oriented and aspect ratio varies greatly, existing deep learning-based methods adopt defined IoU threshold to assign label and do not consider the differences in localization potential of selected positive samples, resulting in some objects with large aspect ratios could not match enough high potential positive samples. In this paper, we put forward a convolutional neural network-based method for detecting wheat diseases characterized by arbitrary orientation and significant aspect ratio variations. First, we design an auto-adjustment label assignment scheme based on the similarity of aspect ratio between the sample and object to assign high-potential positive samples. Then, a localization potential assessment scheme is proposed to evaluate each positive sample. Finally, we construct a dataset of wheat disease in field (WDF2023) based on oriented annotation. We evaluate the effectiveness of our proposed method and eight oriented object detection detectors. The experimental results showcase that the proposed method attains an mAP of 60.8% and an mRecall of 73.8% on the WDF2023 dataset, surpassing existing advanced oriented object detection detectors. Notably, when contrasted with conventional horizontal object detection detectors, our method demonstrates superior performance in precisely localizing disease regions.
资助项目National Natural Science Foundation of China[32171888] ; Natural Science Foundation of Anhui Higher Education Institutions of China[KJ2021A0025] ; Major Special Science and Technology Project of Anhui Province[2020b06050001] ; Natural Science Foundation of Anhui Province, China[2208085MC57] ; Intergovernmental International Scientific and Technological Innovation Cooperation[2019YFE0125700]
WOS研究方向Agriculture ; Computer Science
语种英语
WOS记录号WOS:001243987400001
出版者ELSEVIER SCI LTD
资助机构National Natural Science Foundation of China ; Natural Science Foundation of Anhui Higher Education Institutions of China ; Major Special Science and Technology Project of Anhui Province ; Natural Science Foundation of Anhui Province, China ; Intergovernmental International Scientific and Technological Innovation Cooperation
源URL[http://ir.hfcas.ac.cn:8080/handle/334002/136248]  
专题中国科学院合肥物质科学研究院
通讯作者Wang, Rujing; Jiao, Lin
作者单位1.Chinese Acad Sci, Inst Intelligent Machines, Hefei Inst Phys Sci, Hefei 230031, Peoples R China
2.Intelligent Agr Engn Lab Anhui Prov, Hefei, Peoples R China
3.Anhui Univ, Sch Internet, Hefei 230601, Peoples R China
4.Anhui Agr Univ, Coll Informat & Comp, Hefei 230036, Peoples R China
5.Univ Sci & Technol China, Hefei 230026, Peoples R China
推荐引用方式
GB/T 7714		 Liu, Haiyun,Chen, Hongbo,Du, Jianming,et al. Auto-adjustment label assignment-based convolutional neural network for oriented wheat diseases detection[J]. COMPUTERS AND ELECTRONICS IN AGRICULTURE,2024,222.
APA Liu, Haiyun.,Chen, Hongbo.,Du, Jianming.,Xie, Chengjun.,Zhou, Qiong.,...&Jiao, Lin.(2024).Auto-adjustment label assignment-based convolutional neural network for oriented wheat diseases detection.COMPUTERS AND ELECTRONICS IN AGRICULTURE,222.
MLA Liu, Haiyun,et al."Auto-adjustment label assignment-based convolutional neural network for oriented wheat diseases detection".COMPUTERS AND ELECTRONICS IN AGRICULTURE 222(2024).

入库方式： OAI收割

来源：合肥物质科学研究院

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。