Estimating litchi flower number using a multicolumn convolutional neural network based on a density map
文献类型: 外文期刊
作者: Lin, Jiaquan 1 ; Li, Jun 1 ; Yang, Zhou 2 ; Lu, Huazhong 2 ; Ding, Yunhe 1 ; Cui, Huajun 1 ;
作者机构: 1.South China Agr Univ, Coll Engn, Guangzhou 510642, Peoples R China
2.South China Agr Univ, Key Lab Key Technol Agr Machine & Equipment, Minist Educ, Guangzhou 510642, Peoples R China
3.Jiaying Univ, Guangdong Prov Key Lab Conservat & Precis Utiliza, Meizhou 514015, Peoples R China
4.Guangdong Acad Agr Sci, Guangzhou 510640, Peoples R China
关键词: Flowering intensity estimation; Multicolumn convolutional neural network; Density map; Flower number; Male litchi flower
期刊名称:PRECISION AGRICULTURE ( 影响因子:5.767; 五年影响因子:5.875 )
ISSN: 1385-2256
年卷期: 2022 年 23 卷 4 期
页码:
收录情况: SCI
摘要: To ensure litchi fruit yield and quality, reasonable blooming period management such as flower thinning is required during the early flowering period. A combination of the number of litchi flowers and their density map can provide a reference for blooming period management decisions during the flowering period. Flowering intensity is currently largely estimated manually by humans observing the trees in the orchard. Although some automatic computer vision systems have been proposed for estimating flowering intensity, their overall performance is inadequate to meet current flower-thinning needs, and these systems are weak in some situations such as in varying environments and when the target object has a low-density distribution. With male litchi flowers as the research object, the goal of this study was to design a method for calculating the number of flowers. By using an image of the male litchi flower as input to a multicolumn convolutional neural network, a final density map and the number of flowers were generated. Experimental results using a self-constructed male litchi flower dataset demonstrated the feasibility of outputting a density map and flower count. The flower number was estimated from the model with a mean absolute error (MAE) that reached 16.29 and a mean square error (MSE) reaching 25.40 on the test set, which was better than counting by target detection. The proposed method can be used to perform time-saving analyses to help estimate yield and implement follow-up orchard management, and it demonstrates the potential of using density maps as outputs for estimating flowering intensity.
- 相关文献
作者其他论文 更多>>
-
Formulation and stabilization of high internal phase emulsions via mechanical cellulose nanofibrils/ethyl lauroyl arginate complexes
作者:Huang, Luyao;Xu, Chuan;Gao, Wenhua;Guo, Shasha;Li, Jun;Rojas, Orlando J.;Jiao, Wenjuan;Jiao, Wenjuan
关键词:Cellulose nanofibrils; Ethyl lauroyl arginate; High internal phase emulsions; 3D printing
-
Advancements and Applications of Raman Spectroscopy in Rapid Quality and Safety Detection of Fruits and Vegetables
作者:Xu, Sai;Huang, Xiongmei;Xu, Sai;Xu, Sai;Lu, Huazhong
关键词:Raman spectroscopy; fruit and vegetable quality; safety testing; surface pesticide residues; nondestructive testing
-
Comparison of different pretreatments on drying characteristics, physical properties, nutritional compounds and antioxidant activity of heat pump-dried longan pulp
作者:Zhu, Jingnan;Peng, Jian;Li, Jun;Li, Lu;Xu, Yujuan;Zhu, Jingnan;Gu, Qingqing;Bi, Jinfeng;Yi, Jianyong;Yang, Wanyuan;Chen, Shupeng
关键词:drying characteristics; longan pulp; pretreatments; quality assessment
-
Nondestructive Detecting Maturity of Pineapples Based on Visible and Near-Infrared Transmittance Spectroscopy Coupled with Machine Learning Methodologies
作者:Qiu, Guangjun;Xu, Sai;Liang, Xin;Fan, Changxiang;Qiu, Guangjun;Lu, Huazhong;Xu, Sai;Liang, Xin;Lu, Huazhong;Wang, Xu;Wang, Chen
关键词:transmittance spectrum; maturity; soluble solids content; pineapple; nondestructive; machine learning
-
Visible and near-infrared hyperspectral imaging as an intelligent tool for parasite detection in sashimi
作者:Xu, Sai;Fan, Changxiang;Qiu, Guangjun;Liang, Xin;Peng, Jian;Xu, Sai;Fan, Changxiang;Qiu, Guangjun;Liang, Xin;Peng, Jian;Xu, Sai;Lu, Huazhong;Ference, Christopher
关键词:Sashimi; Parasite; Grass carp; Visible and near-infrared hyperspectral imag; ing; Intelligent detection
-
Research on an Improved Non-Destructive Detection Method for the Soluble Solids Content in Bunch-Harvested Grapes Based on Deep Learning and Hyperspectral Imaging
作者:Zhao, Junhong;Li, Bin;Xie, Yuming;Xu, Sai;Zhao, Junhong;Li, Bin;Xie, Yuming;Lu, Huazhong;Xu, Sai;Hu, Qixiao;Lu, Huazhong
关键词:grape; bunch-harvested; hyperspectral imaging; deep learning; non-destructive detection
-
A multi-omics view of the preservation effect on Camellia sinensis leaves during low temperature postharvest transportation
作者:Chen, Jiahao;Zheng, Peng;Sun, Binmei;Mei, Shuang;Guo, Jiaming;Zeng, Zhixiong;Mei, Shuang;Lu, Huazhong
关键词:Widely targeted secondary metabolomics; Transcriptome; Refrigerated transportation; Postharvest tea leaves; Flavonoids