数字农科院2.0

Towards improved accuracy of UAV-based wheat ears counting: a transfer learning method of the ground-based fully convolutional network

文献类型： 外文期刊

作者： Juncheng Ma;Yunxia Li;Hongjie Liu;Yongfeng Wu1;Lingxian Zhang

作者机构：

关键词： number of wheat ears; UAV; digital images; convolutional neural network; transfer learning

期刊名称： Expert Systems with Applications

ISSN： 0957-4174

年卷期： 2021 年

页码：

收录情况： JCR（2021版） ; EI（2021版）

摘要： In order to achieve accurate UAV-based wheat ear counting, a transfer learning method of the ground-based fully convolutional network, i.e., EarDensityNet, was proposed in this study. The EarDensityNet, which integrated the filter pyramid block and dilated convolution, was designed to map the wheat canopy images to ear density maps generated by dot annotations. The wheat ear counting can be obtained by summing all the pixel values of the corresponding ear density map. Results showed strong correlations could be observed between the actual number of wheat ears to those estimated by the EarDensityNet, with high coefficient of determination (R2=0.9179) and low Root-Mean-Square-Error (RMSE=17.61 ears, NRMSE=4.47%), outperforming the compared methods. Ground resolution of canopy images had a significant impact on the performance of the EarDensityNet. Transfer learning of the ground-based EarDensityNet could take full advantage of the rich details presented by the ground-based images with high pixel resolution, thus effectively alleviating the degradation of counting performance caused by the decreased ground resolution. Therefore, obtained results showed the fine-tuned EarDensityNet more accurate UAV-based wheat ear counting (R2=0.9570, RMSE=801.34, and NRMSE=22.06%) than one learned from scratch, demonstrating the superiority and applicability. Border effect from splitting digital images with high pixel resolution into sub-images did not make a major problem to the EarDensityNet, demonstrating great potentials to be generalized from plot-wise to field-wise. Wheat ear counting was recommended after the flowering stage since the textures of wheat ears were more obvious for EarDensityNet to learn complex feature representations.

分类号：

  • 相关文献

[1]Finer Classification Of Crops By Fusing Uav Images And Sentinel-2A Data. Zhao, LC, Shi, Y, Liu, B, Hovis, C, Duan, YL, Shi, ZC. 2019

[2]Time-Series Multispectral Indices From Unmanned A.erial Vehicle Imagery Reveal S enescence Rate In Bread Wheat. Hassan, MA, Yang, MJ, Rasheed, A, Jin, XL, Xia, XC, Xiao, YG, He, ZH. 2018

[3]Improvement Of Sugarcane Yield Estimation By Assimilating Uav-Derived Plant Height Observations. Yu, DY, Zha, YY, Shi, LS, Jin, XL, Hu, S, Yang, Q, Huang, K, Zeng, WZ. 2020

[4]Assessment Of Water And Nitrogen Use Efficiencies Through Uav-Based Multispectral Phenotyping In Winter Wheat. Yang, MJ, Hassan, MA, Xu, KJ, Zheng, CY, Rasheed, A, Zhang, Y, Jin, XL, Xia, XC, Xiao, YG, He, ZH. 2020

[5]Establishment of a high-throughput ffeld defoliation data survey strategy combined with genome-wide association studies to reveal the genetic basis of defoliation in cotton. . 2025

[6]YOLO-light-pruned: A lightweight model for monitoring maize seedling count and leaf age using near-ground and UAV RGB images. Tiantian Jiang,Liang Li,Zhen Zhang,Xun Yu,Yanqin Zhu,Liming Li,Yadong Liu,YaliBai, Ziqian Tang , Shuaibing Liu,Yan Zhang,Zheng Duan,Dameng Yin,Xiuliang Jin. 2025

[7]Combining UAV multisensor field phenotyping and genome-wide association studies to reveal the genetic basis of plant height in cotton (Gossypium hirsutum).. . 2025

[8]Screening Verticillium wilt-resistant germplasm by monitoring the time-series chlorophyll content of cotton canopies via a UAV-based high-throughput platform. . 2025

[9]Evaluation of Machine Learning Models for Daily Reference Evapotranspiration Modeling Using Limited Meteorological Data in Eastern Inner Mongolia, North China. Zhang H., Meng F., Xu J., Liu Z., Meng J.. 2022

[10]Maize-IAS: a maize image analysis software using deep learning for high-throughput plant phenotyping. Zhou Shuo,Chai Xiujuan,Yang Zixuan,Wang Hongwu,Yang Chenxue,Sun Tan. 2021

[11]An automated zizania quality grading method based on deep classification model. Jingjun Cao,Tan Sun,Wenrong Zhang,Ming Zhong,Bo Huang,Guomin Zhou,Xiujuan Chai. 2021

[12]Maize-IAS: a maize image analysis software using deep learning for high-throughput plant phenotyping. Zhou Shuo,Chai Xiujuan,Yang Zixuan,Wang Hongwu,Yang Chenxue,Sun Tan. 2021

[13]Learned Features Of Leaf Phenotype To Monitor Maize Water Status In The Fields. Zhuang, S, Wang, P, Jiang, BR, Li, MS. 2020

[14]Prior Knowledge Guided Small Object Detection On High-Resolution Images. Yang, ZX, Chai, XJ, Wang, RP, Guo, WJ, Wang, WX, Pu, L, Chen, XL. 2019

作者其他论文 更多>>