| 基于颜色掩膜网络和自注意力机制的叶片病害识别方法 |
| |
| 引用本文： | 于明,李若曦,阎刚,王岩,王建春,李扬.基于颜色掩膜网络和自注意力机制的叶片病害识别方法[J].农业机械学报,2022,53(8):337-344. |
| |
| 作者姓名： | 于明 李若曦 阎刚 王岩 王建春 李扬 |
| |
| 作者单位： | 河北工业大学;天津商业大学;天津市农业科学院 |
| |
| 基金项目： | 国家自然科学基金重大研究计划项目(91746207)和国家重点研发计划项目(2018YFC08) |
| |
| 摘 要： | 为了提取到更加准确、丰富的叶片病斑的颜色特征和空间特征，解决病害严重程度细粒度分类粗糙、识别准确率低等问题，提出一种融合颜色掩膜网络和自注意力机制(Fusion color mask and self-attention network, FCMSAN)的病害识别方法。FCMSAN由颜色掩膜网络(Color mask network,CMN)和融合通道自适应的自注意力网络(Channel adaptive self-attention network, CASAN)构成。CMN通过学习叶片病斑颜色区域信息提高模型提取颜色特征的能力；CASAN能够提取全局范围内的病斑特征，同时加入病斑的位置特征和通道自适应特征，可以精确、全面定位叶片病斑区域。最后通过特征转换融合模块（Transfer fusion layer，TFL）将CMN和CASAN进行融合。经实验证明，FCMSAN在61类农作物病虫害细粒度识别中，Top-1的分类准确率达到87.97%，平均F1值达到84.48%。最后通过可视化分析，验证了本文方法在病害识别中的有效性。
|
| 关 键 词： | 农作物病害 自注意力机制 细粒度识别 特征提取 颜色掩膜网络 |
| 收稿时间： | 2021/8/28 0:00:00 |
Crop Diseases Recognition Method via Fusion Color Mask and Self-attention Mechanism |
| |
| YU Ming,LI Ruoxi,YAN Gang,WANG Yan,WANG Jianchun,LI Yang.Crop Diseases Recognition Method via Fusion Color Mask and Self-attention Mechanism[J].Transactions of the Chinese Society of Agricultural Machinery,2022,53(8):337-344. |
| |
| Authors: | YU Ming LI Ruoxi YAN Gang WANG Yan WANG Jianchun LI Yang |
| |
| Institution: | Hebei University of Technology;Tianjin University of Commerce;Tianjin Academy of Agricultural Sciences |
| |
| Abstract: | To reduce the loss of crop diseases, a large number of chemicals are used for disease control. However, due to the untimely and inaccurate judgment of the disease, chemical agents are abused, which also has a great impact on the ecological environment and food safety. Therefore, it is urgent to develop accurate crop disease recognition based on images. In the image recognition of crop diseases, the shape, region, and color of leaf spots are the main indexes to distinguish different types of diseases. In order to extract more accurate and rich color features and spatial features of leaf spots, and solve the problems of coarse fine-grained classification of disease severity and low recognition accuracy, a fusion color mask and self-attention network (FCMSAN) was proposed. FCMSAN was composed of a color mask network (CMN) and a channel adaptive self-attention network (CASAN). CMN can improve the ability of color feature extraction by learning the color features of leaf spots. CASAN can extract the disease spot features in the global scope and add the location features and channel adaptive features of the disease spot, which can locate the leaf disease spot area accurately and comprehensively. Finally, the outputs of CMN and CASAN were fused by transfer fusion layer (TFL). The experimental results showed that the classification Top-1 accuracy reached 87.97% and the average F1 value can reach 84.48% in the fine-grained identification of 61 types of crop diseases. Finally, the effectiveness of the proposed method for crop disease recognition was verified by visualization experiments. |
| |
| Keywords: | crop diseases self-attention mechanism fine-grained identification feature extraction color mask network |
|
| 点击此处可从《农业机械学报》浏览原始摘要信息 |
| 点击此处可从《农业机械学报》下载免费的PDF全文 |
|
