EFDet: An efficient detection method for cucumber disease under natural complex environments
文献类型： 外文期刊
作者： Liu, Chen 1 ; Zhu, Huaji 1 ; Guo, Wang 1 ; Han, Xiao 1 ; Chen, Cheng 1 ; Wu, Huarui 1 ;
作者机构： 1.Natl Engn Res Ctr Informat Technol Agr, Beijing 100097, Peoples R China
2.Northwest A&F Univ, Coll Informat Engn, Yangling 712100, Shanxi, Peoples R China
3.Beijing Res Ctr Informat Technol Agr, Beijing 100097, Peoples R China
关键词： Precision agriculture; Cucumber disease leaf; Disease detection; Complex environment; ASFF; EfficientNet
期刊名称：COMPUTERS AND ELECTRONICS IN AGRICULTURE （ 影响因子：5.565； 五年影响因子：5.494 ）
ISSN： 0168-1699
年卷期： 2021 年 189 卷
页码：
收录情况： SCI
摘要： Improving the application capability of the disease detection model is a key issue in the field of agricultural informatization. The complex backgrounds, image diversity, and model complexity are the main factors that affect the realization of automatic disease recognition. This study constructs an efficient detection model (EFDet), which mainly consists of the efficient backbone network, a feature fusion module, and a predictor. EFDet improves the detection effect for cucumber leaves in complex backgrounds by fusing feature maps at different levels. We collected three category cucumber leaves including downy mildew, bacterial angular spot, and health to construct the cucumber disease dataset. It contains 7,488 images with three complexity levels for model training and evaluation. YOLO V3-V5, EfficientDet-D1, YOLO V3-ASFF, and other six detection models as the comparison models, we verify the EFDet performance in terms of model size, FLOPs, and mAP. Experimental results show that EFDet has strong robustness for cucumber disease leaf in complex environments. It also has smaller parameters and calculations that are suitable for actual applications.
- 相关文献
作者其他论文 更多>>
-
D-glucose-derived S-doped porous carbon: Sustainable and effective CO2 adsorption
作者：Xu, Qianyu;Wang, Junting;Feng, Jiamin;Liu, Chen;Hu, Xin;Xiao, Qiang;Demir, Muslum;Simsek, Utku Bulut;Demir, Muslum;Kilic, Murat;Wang, Linlin
关键词：S-doped porous carbons; Biomass; CO2 adsorption; Sodium thiosulfate, D-glucose
-
Advanced microporous carbon adsorbents for selective CO2 capture: Insights into heteroatom doping and pore structure optimization
作者：Shao, Jiawei;Wang, Yingyi;Liu, Chen;Hu, Xin;Xiao, Qiang;Demir, Muslum;Demir, Muslum;Al Mesfer, Mohammed K.;Danish, Mohd;Wang, Linlin
关键词：N/S co-doped porous carbons; Resins; Thiourea; CO2 adsorption
-
High-performance CO2 adsorption with P-doped porous carbons from lotus petiole biomass
作者：Zhi, Yue;Shao, Jiawei;Liu, Chen;Hu, Xin;Xiao, Qiang;Demir, Muslum;Demir, Muslum;Al Mesfer, Mohammed K.;Danish, Mohd;Wang, Linlin
关键词：P-doped porous carbons; CO2 adsorption; KOH activation; Phytic acid; Biomass
-
A Joint Knowledge Extraction Model for Tobacco Pest and Disease Prevention Based on BERT plus BA plus CASREL
作者：Liu, Kehan;Zhang, Feng;Wu, Qiulan;Sun, Ziruo;Liu, Kehan;Sun, Xiang;Wu, Huarui;Sun, Ziruo;Zhang, Feng;Wu, Qiulan;Sun, Xiang;Wu, Huarui
关键词：Tobacco pest and disease prevention; knowledge extraction; joint knowledge extraction model; Tobacco pest and disease prevention; knowledge extraction; joint knowledge extraction model
-
Swin-Unet plus plus : a study on phenotypic parameter analysis of cabbage seedling roots
作者：Li, Hongda;Zhao, Yue;Bi, Zeyang;Li, Hongda;Hao, Peng;Wu, Huarui;Zhao, Chunjiang;Hao, Peng;Wu, Huarui;Zhao, Chunjiang
关键词：Cabbage; Root phenotype; Attention mechanism; Semantic segmentation; Unet; Residual networks
-
A high-efficiency regulation method for optimal root zone temperature under different nitrogen fertilizer using discrete curvature
作者：Li, Huimin;Gao, Pan;Sun, Zhangtong;Hu, Jin;Wei, Ziyuan;Lu, Miao;Li, Huimin;Wei, Ziyuan;Lu, Miao;Gao, Pan;Sun, Zhangtong;Hu, Jin;Gao, Pan;Wu, Huarui
关键词：U -chord curvature; Chlorophyll fluorescence; Suitable RZT range; Dynamic regulation; Hydroponic tomato seedlings
-
Appearance quality identification and environmental factors tracing of Lyophyllum decastes for precise environment control using knowledge graph
作者：Zhou, Kai;Yu, Junyuan;Shi, Haotong;Hou, Jialin;Hou, Rui;Wu, Huarui
关键词：Lyophyllum decastes; Appearance identification; Residual neural network; Knowledge graph; Graph attention network
