Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

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

Biomimetic Surface Nanoengineering of Biodegradable Zn-Based Membranes Enables Phase-Specific Metal Ion Delivery for Synergistic Anti-Infection and Bone Regeneration.

Advanced materials (Deerfield Beach, Fla.)·2026

Same author

Dissociation of CCDC25 dimer into NETs-DNA-bound monomer licenses inflammatory activation of fibroblast-like synoviocytes in rheumatoid arthritis.

Cell reports·2026

Same author

Reinforcing the Arsenal: Advanced Antibiotic Adjuvants as Strategic Disruptors of Bacterial Defenses.

Journal of agricultural and food chemistry·2026

Same author

Novel dual-targeting biofilm inhibitors for potentiating antibiotic efficacy against multidrug-resistant Pseudomonas aeruginosa infections.

Journal of advanced research·2026

Same author

Immune and Stem Cell-Mediated Bactericidal Amplification and Bone Remodeling for Infection Clearance and Osteointegration.

Advanced materials (Deerfield Beach, Fla.)·2026

Same author

Cartilage intermediate layer protein inhibits ligamentum flavum hypertrophy mediated by TGF-β1/SMAD3/SERPINE2 signaling pathway.

Cellular and molecular life sciences : CMLS·2026

Search research articles

相关实验视频

Updated: Jul 20, 2025

Visualization of Failure and the Associated Grain-Scale Mechanical Behavior of Granular Soils under Shear using Synchrotron X-Ray Micro-Tomography

Visualization of Failure and the Associated Grain-Scale Mechanical Behavior of Granular Soils under Shear using Synchrotron X-Ray Micro-Tomography

Published on: September 29, 2019

一种基于结构光成像和改进的PointNet+进行填充/不填充谷物分类的新方法.

Shihao Huang^1,2,3, Zhihao Lu¹, Yuxuan Shi¹

¹College of Engineering, Huazhong Agricultural University, Wuhan 430070, China.

Sensors (Basel, Switzerland)

|July 29, 2023

概括

本研究引入了一种改进的深度学习方法,用于使用3D点云数据对填充/未填充的米粒进行分类. 这种新方法显著提高了用于育种和遗传分析的米粒识别的准确性.

关键词:

三维结构光的3D结构光.增强数据的增强数据的增强深度学习是一种深度学习.谷物分类的谷物分类正常向量的正常向量.点云细分分点云细分

更多相关视频

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images

Published on: February 2, 2019

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Published on: February 23, 2024

相关实验视频

Last Updated: Jul 20, 2025

Visualization of Failure and the Associated Grain-Scale Mechanical Behavior of Granular Soils under Shear using Synchrotron X-Ray Micro-Tomography

Visualization of Failure and the Associated Grain-Scale Mechanical Behavior of Granular Soils under Shear using Synchrotron X-Ray Micro-Tomography

Published on: September 29, 2019

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images

Cereal Crop Ear Counting in Field Conditions Using Zenithal RGB Images

Published on: February 2, 2019

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Author Spotlight: Assessment of Visual Acuity in Central Vision Loss Through Motion-Based Peripheral Vision Testing

Published on: February 23, 2024

科学领域:

农业科学农业科学
计算机视觉计算机视觉
生物技术是生物技术.

背景情况:

准确地分类填充/未填充的米粒对于世界上最大的生产国和消费国中国的米育种和遗传分析至关重要.
传统的谷物识别手工方法效率低下,缺乏可重复性,精度低.

研究的目的:

开发一种新的,自动化的方法来分类填充/未填充的米粒.
与传统方法相比,提高米粒分析的效率和准确性.

主要方法:

采用结构化光成像,获取米粒的3D点云数据.
开发了用于单粒细分和基于正常向量的数据增强的算法.
改进了PointNet++深度学习网络,添加了一个Set抽象层,并将正常向量最大聚合用于分类.

主要成果:

改进的PointNet++实现了98.50%的分类准确度.
这种准确性超过了传统的机器学习模型 (例如,XGboost的91.99%) 和其他深度学习模型,如PointNet (93.75%) 和PointConv (92.25%).

结论:

该研究展示了一种新且高效的方法,用于识别填充/未填充的米粒,使用对3D点云数据进行改进的深度学习.
这种自动化方法在农业应用中在精度和效率方面提供了显著的优势.