Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关实验视频

Updated: Jan 7, 2026

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images
11:49

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images

Published on: February 2, 2019

9.8K

转移学习模型用于在多源数据集上检测小麦耳朵.

Željana Grbović1, Marko Panić2, Dimitrije Stefanović2

  • 1BioSense Institute, University of Novi Sad, Novi Sad, Serbia. zeljanagrbovic@biosense.rs.

Scientific reports
|December 30, 2025
PubMed
概括
此摘要是机器生成的。

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Quantification of disease-associated RNA tandem repeats by nanopore sensing.

Nature communications·2026
Same author

Evaluation of the INCISIVE Services in Cancer Imaging: A Feasibility Study.

Seminars in oncology nursing·2026
Same author

Detection of Suspicious Lesions in Breast MRI: Radiomics Patch-based Granular Classification Approach.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

Clinical Assessment of Dairy Goats' Udder Health Using Infrared Thermography.

Animals : an open access journal from MDPI·2025
Same author

The first geospatial dataset of irrigated fields (2020-2024) in Vojvodina (Serbia).

Scientific data·2025
Same author

Comprehensive dataset from high resolution UAV land cover mapping of diverse natural environments in Serbia.

Scientific data·2025
Same journal

Clinical crown height changes in mandibular anterior teeth retained with two types of fixed retainers over two years: findings from a randomized clinical trial.

Scientific reports·2026
Same journal

Rethinking water governance through indigenous systems: A comparative assessment of qanat and well irrigation productivity in Sabzevar County, Iran.

Scientific reports·2026
Same journal

Distributed Nash equilibrium seeking for second-order systems with finite/fixed-time convergence in the absence of velocity measurement.

Scientific reports·2026
Same journal

Determinants of pregnancy termination among ever-married women of reproductive age in Bangladesh.

Scientific reports·2026
Same journal

Occurrence and human health risk assessment of organochlorine pesticides in irrigated and non-irrigated agricultural soils of Wondogenet District, Ethiopia.

Scientific reports·2026
Same journal

High angular resolution diffusion imaging of neurodevelopment in children through data creation with deep learning.

Scientific reports·2026
查看所有相关文章

研究人员开发了BioS-Wheat数据集,并评估了用于自动检测小麦耳朵的深度学习模型. 这有助于对全球粮食安全的准确,早期产量预测.

科学领域:

  • 农业科学 农业科学
  • 计算机视觉 计算机视觉
  • 数据科学数据科学数据科学

背景情况:

  • 准确的小麦产量预测对于全球粮食安全至关重要,但目前的方法往往是有偏见的或劳动密集型的.
  • 手动计数小麦穗是精确但耗时的产量预测方法.
  • 自动小麦耳探测可以提高产量估计的准确性和效率.

研究的目的:

  • 介绍BioS-Wheat数据集,这是一个新的,高质量的RGB智能手机图像数据集,用于小麦耳朵检测.
  • 评估六个深度学习模型的性能,用于自动检测小麦耳朵.
  • 为未来的小麦产量预测自动化研究提供基准.

主要方法:

  • 创建BioS-小麦数据集:在四种小麦品种中创建了5,696张注释的RGB图像,种植密度高,行间距最小.
  • 评估六种深度学习模型,包括RetinaNet,YOLOv8和RT-DETR,用于小麦耳朵检测.
  • 使用平均平均精度 (mAP@50) 的性能评估.

主要成果:

  • 在小麦耳检测方面,RetinaNet,YOLOv8和RT-DETR实现了91%的最高mAP@50.
  • 这些表现最好的模型表现出明显更高的计算复杂性.
关键词:
生物小麦数据集 生物小麦数据集基于Mask-RCNN的模型基于视觉变压器的模型小麦耳朵检测检测器这就是Yolov8的原因.

更多相关视频

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology
09:44

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Published on: March 8, 2024

5.7K

相关实验视频

Last Updated: Jan 7, 2026

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images
11:49

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images

Published on: February 2, 2019

9.8K
Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology
09:44

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Published on: March 8, 2024

5.7K
  • 生物-小麦数据集的复杂性,由于密集的安排和封闭,挑战了模型的稳定性.

    • 结论:

    • 生物-小麦数据集为开发强大的自动小麦耳朵检测模型提供了宝贵的资源.
    • 深度学习模型显示了准确,早期小麦产量预测的高潜力.
    • 数据集的农学多样性对于在各种条件下提高模型性能至关重要.