文献类型： 外文期刊

作者： Gong, He ¹ ; Liu, Tonghe ¹ ; Luo, Tianye ¹ ; Guo, Jie ¹ ; Feng, Ruilong ¹ ; Li, Ji ¹ ; Ma, Xiaodan ¹ ; Mu, Ye ¹ ; Hu, Tianli ¹ ; Sun, Yu ¹ ; Li, Shijun ⁶ ; Wang, Qinglan ⁸ ; Guo, Ying ¹ ;

作者机构： 1.Jilin Agr Univ, Coll Informat Technol, Changchun 130118, Peoples R China

2.Jilin Prov Agr Internet Things Technol Collaborat, Changchun 130118, Peoples R China

3.Jilin Prov Intelligent Environm Engn Res Ctr, Changchun 130118, Peoples R China

4.Jilin Prov Coll & Univ, Changchun 130118, Peoples R China

5.13th Five Year Engn Res Ctr, Changchun 130118, Peoples R China

6.Wuzhou Univ, Coll Informat Technol, Wuzhou 543003, Peoples R China

7.Guangxi Key Lab Machine Vis & Inteligent Control, Wuzhou 543003, Peoples R China

8.Jilin Acad Agr Sci, Changchun 130033, Peoples R China

关键词： pest identification; FCN; DenseNet; attention mechanism

期刊名称：AGRONOMY-BASEL （ 影响因子：3.7； 五年影响因子：4.0 ）

ISSN：

年卷期： 2023 年 13 卷 2 期

页码：

收录情况： SCI

摘要： One of the most important food crops is rice. For this reason, the accurate identification of rice pests is a critical foundation for rice pest control. In this study, we propose an algorithm for automatic rice pest identification and classification based on fully convolutional networks (FCNs) and select 10 rice pests for experiments. First, we introduce a new encoder-decoder in the FCN and a series of sub-networks connected by jump paths that combine long jumps and shortcut connections for accurate and fine-grained insect boundary detection. Secondly, the network also integrates a conditional random field (CRF) module for insect contour refinement and boundary localization, and finally, a novel DenseNet framework that introduces an attention mechanism (ECA) is proposed to focus on extracting insect edge features for effective rice pest classification. The proposed model was tested on the data set collected in this paper, and the final recognition accuracy was 98.28%. Compared with the other four models in the paper, the proposed model in this paper is more accurate, faster, and has good robustness; meanwhile, it can be demonstrated from our results that effective segmentation of insect images before classification can improve the detection performance of deep-learning-based classification systems.