您好，欢迎访问湖北省农业科学院 机构知识库！
湖北省农业科学院机构知识库

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

An ultra-lightweight efficient network for image-based plant disease and pest infection detection

文献类型： 外文期刊

作者： Wang, Beibei 1 ; Zhang, Chenxiao 2 ; Li, Yanyan 3 ; Cao, Chunxia 1 ; Huang, Daye 1 ; Gong, Yan 1 ;

作者机构： 1.Hubei Acad Agr Sci, Natl Biopesticide Engn Res Ctr, Hubei Biopesticide Engn Res Ctr, Wuhan 430064, Peoples R China

2.Wuhan Univ, Sch Remote Sensing & Informat Engn, Wuhan 430072, Peoples R China

3.Tobacco Res Inst Hubei Prov, Wuhan 430030, Peoples R China

关键词： Plant disease detection; Pest infection detection; Convolutional neural network; Deep learning

期刊名称：PRECISION AGRICULTURE （ 影响因子：6.2； 五年影响因子：6.2 ）

ISSN： 1385-2256

年卷期： 2023 年 24 卷 5 期

页码：

收录情况： SCI

摘要： Plant diseases and pest infections are major factors that undermine the growth of plants along with their life cycle. Optical image-based plant disease detection provides an efficient and low cost way for real-time plant growth monitoring and management. In recent years, the thriving development of deep learning techniques in a variety of communities has validated its great performance in image interpretation and understanding. Existing deep learning-based methods for plant disease classification mostly adopt convolutional neural networks (CNNs) that have been originally developed for general image classification purposes. These CNN architectures consist of a very large volume of training parameters, which severely hinders its applicability under scenarios requiring fast and flexible deployment on compact devices with limited computation powers. In this paper, an ultra-lightweight efficient network (ULEN) is proposed targeting image-based plant disease and pest infection detection. The proposed network consists of two parts, a deep feature extraction module that adopts residual depth-wise convolution and a classification module receiving multi-scale features enhanced by a spatial pyramid pooling layer. The network is constructed in a very compact design with approximately only 100 000 parameters, which greatly favors the demand for a lightweight model for practical needs. Two publicly available plant datasets collected at the indoor and outdoor environments were tested on two compact devices to validate its applicability under different scenarios. Compared with the state-of-the-art architectures, the proposed network showed superior performance with the least computation complexity and compelling classification accuracy.

  • 相关文献
作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：湖北省农业科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台