您好，欢迎访问中国农业科学院 机构知识库！

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

Soybean yield estimation and lodging classification based on UAV multi-source data and self-supervised contrastive learning

文献类型： 外文期刊

作者： Zhou, Longyu 1 ; Zhang, Yong 2 ; Chen, Haochong 1 ; Sun, Guangyao 3 ; Wang, Lei 2 ; Li, Mingxue 2 ; Sun, Xuhong 2 ; Feng, Puyu 1 ; Yan, Long 4 ; Qiu, Lijuan 5 ; Li, Yinghui 5 ; Ma, Yuntao 1 ;

作者机构： 1.China Agr Univ, Coll Land Sci & Technol, Beijing 100193, Peoples R China

2.Heilongjiang Acad Agr Sci, Keshan Branch, Qiqihar, Peoples R China

3.China Agr Univ, Coll Informat & Elect Engn, Beijing 100193, Peoples R China

4.Hebei Acad Agr & Forestry Sci, Inst Cereal & Oil Crops, Shijiazhuang 050035, Hebei, Peoples R China

5.Chinese Acad Agr Sci, Inst Crop Sci, State Key Lab Crop Gene Resources & Breeding, Beijing 100081, Peoples R China

关键词： Remote sensing; 3D reconstruction; Point cloud; Multispectral; Structure from motion

期刊名称：COMPUTERS AND ELECTRONICS IN AGRICULTURE （ 影响因子：8.9； 五年影响因子：9.3 ）

ISSN： 0168-1699

年卷期： 2025 年 230 卷

页码：

收录情况： SCI

摘要： Unmanned aerial vehicle (UAV) platforms are increasingly used to obtain plant phenotypes in crop breeding for their efficiency and versatility. A lightweight UAV was used to collect high-precision RGB images, multispectral and point cloud data of soybeans (Glycine max (L.) Merr.) across fields at various growth stages, utilizing an innovative cross-circling oblique (CCO) route. A multi-modal data fusion deep learning model was proposed based on the self-supervised contrastive learning strategy with fine-tuning for yield estimation and lodging discrimination in soybean germplasm resources. During the soybean growth stages of flowering (R1) to maturity (R8), the contrastive learning effectively captured the decoupling characteristics of different soybean varieties in the feature space. Higher accuracy in yield estimation was obtained combined contrastive learning with the traditional features. Correlations were significantly reduced between features among varieties (Pearson's mean 0.27-0.62) and feature separations were achieved after dimension reduction (R8: CH = 12.4, DB = 51.8). RMSE of yield estimation was 591.39 kg ha-1 at high density and 532.75 kg ha-1 at low density at R8 growth stages. Lodging discrimination achieved the highest accuracy with an F1-score of 0.57 at high density and 0.64 at low density. The results demonstrated that utilizing contrastive learning for extraction of deep soybean features holds significant potential in supporting traditional features for yield estimation and lodging discrimination.

  • 相关文献
作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：中国农业科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台