文献类型： 外文期刊
作者： Wang, Binbin 1 ; Yang, Guijun 1 ; Yang, Hao 1 ; Gu, Jinan 2 ; Xu, Sizhe 1 ; Zhao, Dan 1 ; Xu, Bo 1 ;
作者机构： 1.Beijing Acad Agr & Forestry Sci, Informat Technol Res Ctr, Minist Agr & Rural Affairs, Key Lab Quantitat Remote Sensing Agr, Beijing 100097, Peoples R China
2.Jiangsu Univ, Sch Mech Engn, Zhenjiang 212000, Peoples R China
3.Univ Sci & Technol Beijing, Sch Chem & Bioengn, Beijing 100083, Peoples R China
关键词： deep learning; target detection; maize tassels; UAV; image analysis
期刊名称：REMOTE SENSING （ 影响因子：5.0； 五年影响因子：5.6 ）
ISSN：
年卷期： 2023 年 15 卷 10 期
页码：
收录情况： SCI
摘要： The acquisition of maize tassel phenotype information plays a vital role in studying maize growth and improving yield. Unfortunately, detecting maize tassels has proven challenging because of the complex field environment, including image resolution, varying sunlight conditions, plant varieties, and planting density. To address this situation, the present study uses unmanned aerial vehicle (UAV) remote sensing technology and a deep learning algorithm to facilitate maize tassel identification and counting. UAVs are used to collect maize tassel images in experimental fields, and RetinaNet serves as the basic model for detecting maize tassels. Small maize tassels are accurately identified by optimizing the feature pyramid structure in the model and introducing attention mechanisms. We also study how mapping differences in image resolution, brightness, plant variety, and planting density affect the RetinaNet model. The results show that the improved RetinaNet model is significantly better at detecting maize tassels than the original RetinaNet model. The average precision in this study is 0.9717, the precision is 0.9802, and the recall rate is 0.9036. Compared with the original model, the improved RetinaNet improves the average precision, precision, and recall rate by 1.84%, 1.57%, and 4.6%, respectively. Compared with mainstream target detection models such as Faster R-CNN, YOLOX, and SSD, the improved RetinaNet model more accurately detects smaller maize tassels. For equal-area images of differing resolution, maize tassel detection becomes progressively worse as the resolution decreases. We also analyze how detection depends on brightness in the various models. With increasing image brightness, the maize tassel detection worsens, especially for small maize tassels. This paper also analyzes the various models for detecting the tassels of five maize varieties. Zhengdan958 tassels prove the easiest to detect, with R-2 = 0.9708, 0.9759, and 0.9545 on 5, 9, and 20 August 2021, respectively. Finally, we use the various models to detect maize tassels under different planting densities. At 29,985, 44,978, 67,466, and 89,955 plants/hm(2), the mean absolute errors for detecting Zhengdan958 tassels are 0.18, 0.26, 0.48, and 0.63, respectively. Thus, the detection error increases gradually with increasing planting density. This study thus provides a new method for high-precision identification of maize tassels in farmland and is especially useful for detecting small maize tassels. This technology can be used for high-throughput investigations of maize phenotypic traits.
- 相关文献
作者其他论文 更多>>
-
UssNet: a spatial self-awareness algorithm for wheat lodging area detection
作者：Zhang, Jun;Wu, Qiang;Duan, Fenghui;Liu, Cuiping;Xiong, Shuping;Ma, Xinming;Cheng, Jinpeng;Feng, Mingzheng;Dai, Li;Wang, Xiaochun;Yang, Hao;Yang, Guijun;Chang, Shenglong
关键词：Unmanned aerial vehicle; State space models; Wheat lodging area identification; Semantic segmentation
-
A Comprehensive Evaluation of Monocular Depth Estimation Methods in Low-Altitude Forest Environment
作者：Jia, Jiwen;Kang, Junhua;Gao, Xiang;Zhang, Borui;Yang, Guijun;Chen, Lin;Yang, Guijun
关键词：monocular depth estimation; CNN; vision transformer; forest environment; comparative study
-
Genotyping Identification of Maize Based on Three-Dimensional Structural Phenotyping and Gaussian Fuzzy Clustering
作者：Xu, Bo;Zhao, Chunjiang;Xu, Bo;Zhao, Chunjiang;Yang, Guijun;Zhang, Yuan;Liu, Changbin;Feng, Haikuan;Yang, Xiaodong;Yang, Hao;Xu, Bo;Zhao, Chunjiang;Yang, Guijun;Zhang, Yuan;Liu, Changbin;Feng, Haikuan;Yang, Xiaodong;Yang, Hao
关键词：tassel; 3D phenotyping; TreeQSM; genotyping; clustering
-
Estimation of Leaf Chlorophyll Content of Maize from Hyperspectral Data Using E2D-COS Feature Selection, Deep Neural Network, and Transfer Learning
作者：Chen, Riqiang;Feng, Haikuan;Hu, Haitang;Chen, Riqiang;Ren, Lipeng;Yang, Guijun;Cheng, Zhida;Zhao, Dan;Zhang, Chengjian;Feng, Haikuan;Hu, Haitang;Yang, Hao;Chen, Riqiang;Zhang, Chengjian;Ren, Lipeng;Feng, Haikuan
关键词：maize; chlorophyll; radiative transfer model; feature selection; transfer learning
-
Field-scale irrigated winter wheat mapping using a novel cross-region slope length index in 3D canopy hydrothermal and spectral feature space
作者：Zhang, Youming;Yang, Guijun;Li, Zhenhong;Liu, Miao;Zhang, Jing;Gao, Meiling;Zhu, Wu;Zhang, Youming;Yang, Guijun;Yang, Xiaodong;Song, Xiaoyu;Long, Huiling;Liu, Miao;Meng, Yang;Thenkabail, Prasad S.;Wu, Wenbin;Zuo, Lijun;Meng, Yang
关键词：Winter wheat; Irrigation mapping; Hydrothermal and spectral feature; Cross-region; Rainfed line; Slope Length Index
-
Combining UAV Remote Sensing with Ensemble Learning to Monitor Leaf Nitrogen Content in Custard Apple (Annona squamosa L.)
作者：Jiang, Xiangtai;Xu, Xingang;Wu, Wenbiao;Yang, Guijun;Meng, Yang;Feng, Haikuan;Li, Yafeng;Xue, Hanyu;Chen, Tianen;Jiang, Xiangtai;Xu, Xingang;Gao, Lutao
关键词：canopy nitrogen content; UAV remote sensing; ensemble learning; Lasso model
-
Retrieving the chlorophyll content of individual apple trees by reducing canopy shadow impact via a 3D radiative transfer model and UAV multispectral imagery
作者：Zhang, Chengjian;Chen, Zhibo;Chen, Riqiang;Zhang, Wenjie;Zhang, Chengjian;Chen, Riqiang;Zhang, Wenjie;Zhao, Dan;Yang, Guijun;Xu, Bo;Feng, Haikuan;Yang, Hao
关键词：Chlorophyll content; Shadows; Vegetation index (VI); Radiative transfer models (RTMs); Hybrid inversion model; Individual apple tree crown
