您好，欢迎访问新疆农业科学院 机构知识库！
新疆农业科学院机构知识库

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

DLML-PC: an automated deep learning and metric learning approach for precise soybean pod classification and counting in intact plants

文献类型： 外文期刊

作者： Guo, Yixin 1 ; Pan, Jinchao 1 ; Wang, Xueying 1 ; Deng, Hong 2 ; Yang, Mingliang 3 ; Liu, Enliang 5 ; Chen, Qingshan 3 ; Zhu, Rongsheng 2 ;

作者机构： 1.Northeast Agr Univ, Coll Engn, Harbin, Peoples R China

2.Northeast Agr Univ, Coll Arts & Sci, Harbin, Peoples R China

3.Northeast Agr Univ, Natl Key Lab Smart Farm Technol & Syst, Harbin, Peoples R China

4.Northeast Agr Univ, Coll Agr, Harbin, Peoples R China

5.Xinjiang Acad Agr Sci, Grain Crops Inst, Urumqi, Peoples R China

关键词： soybean; pod type; deep learning; metric learning; non-disassembled plants

期刊名称：FRONTIERS IN PLANT SCIENCE （ 影响因子：4.8； 五年影响因子：5.7 ）

ISSN： 1664-462X

年卷期： 2025 年 16 卷

页码：

收录情况： SCI

摘要： Pod numbers are important for assessing soybean yield. How to simplify the traditional manual process and determine the pod number phenotype of soybean maturity more quickly and accurately is an urgent challenge for breeders. With the development of smart agriculture, numerous scientists have explored the phenotypic information related to soybean pod number and proposed corresponding methods. However, these methods mainly focus on the total number of pods, ignoring the differences between different pod types and do not consider the time-consuming and labor-intensive problem of picking pods from the whole plant. In this study, a deep learning approach was used to directly detect the number of different types of pods on non-disassembled plants at the maturity stage of soybean. Subsequently, the number of pods wascorrected by means of a metric learning method, thereby improving the accuracy of counting different types of pods. After 200 epochs, the recognition results of various object detection algorithms were compared to obtain the optimal model. Among the algorithms, YOLOX exhibited the highest mean average precision (mAP) of 83.43% in accurately determining the counts of diverse pod categories within soybean plants. By improving the Siamese Network in metric learning, the optimal Siamese Network model was obtained. SE-ResNet50 was used as the feature extraction network, and its accuracy on the test set reached 93.7%. Through the Siamese Network model, the results of object detection were further corrected and counted. The correlation coefficients between the number of one-seed pods, the number of two-seed pods, the number of three-seed pods, the number of four-seed pods and the total number of pods extracted by the algorithm and the manual measurement results were 92.62%, 95.17%, 96.90%, 94.93%, 96.64%,respectively. Compared with the object detection algorithm, the recognition of soybean mature pods was greatly improved, evolving into a high-throughput and universally applicable method. The described results show that the proposed method is a robust measurement and counting algorithm, which can reduce labor intensity, improve efficiency and accelerate the process of soybean breeding.

  • 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：新疆农业科学院

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