A multi-branch convolutional neural network with density map for aphid counting | |
Li, Rui1,3,6; Wang, Rujing1,3,4,6; Xie, Chengjun1,3,6; Chen, Hongbo1,3,4,6; Long, Qi5; Liu, Liu2; Zhang, Jie1,3,6; Chen, Tianjiao1,3,6; Hu, Haiying1,3,6; Jiao, Lin1,3,4,6 | |
刊名 | BIOSYSTEMS ENGINEERING
![]() |
2022 | |
卷号 | 213 |
关键词 | Density map Aphid counting Convolutional neural network Deep learning |
ISSN号 | 1537-5110 |
DOI | 10.1016/j.biosystemseng.2021.11.020 |
通讯作者 | Xie, Chengjun(cjxie@iim.ac.cn) ; Chen, Hongbo(hbchen@iim.ac.cn) |
英文摘要 | In agriculture, aphids always cause major damage in wheat, corn and rape, which significantly affect the crop yield. Manual aphid counting approaches are often labour consuming and time-costing for Integrated Pest Management (IPM). In addition, the results of existing aphid counting methods based on computer vision are not satisfactory due to the complex background and the dense distribution. In order to address these problems, a novel multi-branch convolutional neural network (Mb-CNN) with density map for aphid counting is developed in this paper. In this approach, the aphid images are firstly fed into multi-branch convolutional neural networks, which have three branches for extracting the feature maps of different scales. Then, an aphid density map is generated via Mb-CNN, which contains the distribution information of aphids. Finally, the counting of aphids is estimated by using the density map. Experiment results on our dataset demonstrate that our Mb-CNN achieves the performance of 10.22 Mean Absolute Error (MAE) and 12.24 Mean Squared Error (MSE) in the aphid counting, which outweighs the state-of-the-art approaches. (c) 2021 IAgrE. Published by Elsevier Ltd. All rights reserved. |
资助项目 | National Key Technology R&D Program of China[ACAIM190101] ; National Natural Science Foundation of China[32171888] ; National Natural Science Foundation of China[61773360] ; Dean's Fund of Hefei Institute of Physical Science, Chinese Academy of Sciences[YZJJ2020QN21] |
WOS研究方向 | Agriculture |
语种 | 英语 |
出版者 | ACADEMIC PRESS INC ELSEVIER SCIENCE |
WOS记录号 | WOS:000793358200007 |
资助机构 | National Key Technology R&D Program of China ; National Natural Science Foundation of China ; Dean's Fund of Hefei Institute of Physical Science, Chinese Academy of Sciences |
内容类型 | 期刊论文 |
源URL | [http://ir.hfcas.ac.cn:8080/handle/334002/130839] ![]() |
专题 | 中国科学院合肥物质科学研究院 |
通讯作者 | Xie, Chengjun; Chen, Hongbo |
作者单位 | 1.Intelligent Agr Engn Lab Anhui Prov, Hefei, Peoples R China 2.Shanghai Jiao Tong Univ, Dept Comp Sci & Engn, Shanghai, Peoples R China 3.Chinese Acad Sci, Hefei Inst Phys Sci, Hefei 230031, Peoples R China 4.Univ Sci & Technol China, Hefei 230026, Peoples R China 5.South China Agr Univ, Coll Engn, Guangzhou, Peoples R China 6.Chinese Acad Sci, Inst Intelligent Machines, Hefei 230031, Peoples R China |
推荐引用方式 GB/T 7714 | Li, Rui,Wang, Rujing,Xie, Chengjun,et al. A multi-branch convolutional neural network with density map for aphid counting[J]. BIOSYSTEMS ENGINEERING,2022,213. |
APA | Li, Rui.,Wang, Rujing.,Xie, Chengjun.,Chen, Hongbo.,Long, Qi.,...&Liu, Haiyun.(2022).A multi-branch convolutional neural network with density map for aphid counting.BIOSYSTEMS ENGINEERING,213. |
MLA | Li, Rui,et al."A multi-branch convolutional neural network with density map for aphid counting".BIOSYSTEMS ENGINEERING 213(2022). |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论