Identification Method of Cotton Leaf Diseases Based on Bilinear Coordinate Attention Enhancement Module
Identification Method of Cotton Leaf Diseases Based on Bilinear Coordinate Attention Enhancement Module
复制标题
基于双线性坐标注意力增强模块的棉花叶部病害识别方法
DOI：
10.3390/agronomy13010088
复制
发表时间：
2022-12
期刊：
影响因子：
--
通讯作者：
Jianhua Zhang
中科院分区：
文献类型：
--
作者：
Mingyue Shao;Peitong He;Yanqi Zhang;Shuo Zhou;Ning Zhang;Jianhua Zhang
棉花是重要的经济作物。棉花病害对棉花产量和品质有相当大的不利影响。及时准确地鉴定棉花病害类型是十分重要的。棉花叶部病害鉴定的准确性受到自然环境中不可预测因素的限制，例如复杂背景的存在。因此，本文提出了一种基于双线性坐标注意力增强模块的棉花叶部病害识别模型。通过双线性坐标注意、嵌入特征映射、空间坐标信息和特征融合来减少特征信息的丢失。因此，该模型更专注于叶片疾病区域，并减少了对健康区域等冗余信息的关注。并通过数据增强实现了对叶部病害区域的精确定位和注意力放大，有效提高了自然环境下棉花叶部病害的识别准确率。实验表明，该模型的辨识精度为96.61%，参数大小为21.55 × 106。与已有的模型相比，该模型在不增加参数大小的情况下，辨识精度得到了很大的提高。该研究不仅可以为棉花叶部病害的及时诊断和防治提供决策支持，而且可以为其他作物叶部病害的识别提供范例。
Cotton is an important cash crop. Cotton diseases have a considerable adverse influence on cotton yield and quality. Timely and accurate identification of cotton disease types is important. The accuracy of cotton leaf disease identification is limited by unpredictable factors in natural settings, such as the presence of a complex background. Therefore, this paper proposes a cotton leaf disease identification model based on a bilinear coordinate attention enhancement module. It reduces the loss of feature information by bilinear coordinate attention embedding feature maps spatial coordinate information and feature fusion. Hence the model is more focused on the leaf disease region and reduces the attention to redundant information such as healthy regions. It also achieves the precise localization and amplification of attention to the leaf disease region through data enhancement, which effectively improves the recognition accuracy of cotton leaf diseases in a natural setting. By experiments, the identification accuracy of the proposed model is 96.61% and the parameter size is 21.55 × 106. Compared with other existing models, the identification accuracy of the proposed model is greatly improved without increasing the parameter size. This study can not only provide decision support for the timely diagnosis and prevention of cotton leaf diseases but also validate a paradigm for the identification of other crop leaf diseases.
登录
查看更多内容
DOI：
10.1016/j.compag.2021.106644
发表时间：
2022-02
期刊：
Comput. Electron. Agric.
影响因子：
--
作者：
Yun Zhao;Chengda Sun;Xing Xu;Jiagui Chen
通讯作者：
Yun Zhao;Chengda Sun;Xing Xu;Jiagui Chen
影响因子：
8.3
作者：
Too, Edna Chebet;Li Yujian;Liu Yingchun
通讯作者：
Liu Yingchun
影响因子：
8.3
作者：
Jiang, Feng;Lu, Yang;Li, Gongfa
通讯作者：
Li, Gongfa
影响因子：
4.8
作者：
Jianhua Zhang;Fantao Kong;Jianzhai Wu;Shuqing Han;Zhifen Zhai
通讯作者：
Jianhua Zhang;Fantao Kong;Jianzhai Wu;Shuqing Han;Zhifen Zhai
影响因子：
8.3
作者：
Abbas, Amreen;Jain, Sweta;Vankudothu, Swetha
通讯作者：
Vankudothu, Swetha