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

A Predictive Model for Major Adverse Aortic Events in Patients with Abdominal Aortic Aneurysm Using Clinical and Biomarker Data.

International journal of molecular sciences·2026

Same author

A Prospective Head-to-Head Comparison of HER2-Targeted and 18F-FDG PET/CT for Detecting Axillary Lymph Node Metastases Among Newly Diagnosed HER2-Positive and HER2-Low Breast Cancer.

Clinical nuclear medicine·2026

Same author

Dual-Metal MOF-Derived Carbon Fibers Achieve Efficient Polysulfide Anchoring and Conversion Simultaneously in Li-S Batteries.

Small (Weinheim an der Bergstrasse, Germany)·2026

Same author

Trefoil Factor 3 as a Biomarker for Peripheral Artery Disease.

Biomolecules·2026

Same author

The Association Between Abnormal Electrocardiogram Findings and the Ankle Brachial Index.

Medicina (Kaunas, Lithuania)·2026

Same author

Navigating the Evolution of Urothelial Carcinoma Treatment: From Chemotherapy to Immunotherapy.

Cancer medicine·2026

Search research articles

相关实验视频

Updated: Jul 9, 2025

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

LMFD:用于图像拼接的轻量级多功能描述符.

Yingbo Fan¹, Shanjun Mao², Mei Li¹

¹Institute of Remote Sensing and Geographic Information Systems, Peking University, No.5 Summer Palace Road, Beijing, 100000, China.

Scientific reports

|November 30, 2023

概括

本研究介绍了用于强大的图像拼接的轻量级多功能描述器 (LMFD). LMFD提高了精度和计算效率,在关键计算机视觉任务中表现优于现有方法.

更多相关视频

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

Author Spotlight: Improved Methods for Preparing Transverse Sections and Unrolled Whole Mounts of Maize Leaf Primordia for Fluorescence and Confocal Imaging

Author Spotlight: Improved Methods for Preparing Transverse Sections and Unrolled Whole Mounts of Maize Leaf Primordia for Fluorescence and Confocal Imaging

Published on: September 22, 2023

相关实验视频

Last Updated: Jul 9, 2025

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Combining Eye-tracking Data with an Analysis of Video Content from Free-viewing a Video of a Walk in an Urban Park Environment

Published on: May 7, 2019

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

Author Spotlight: Improved Methods for Preparing Transverse Sections and Unrolled Whole Mounts of Maize Leaf Primordia for Fluorescence and Confocal Imaging

Author Spotlight: Improved Methods for Preparing Transverse Sections and Unrolled Whole Mounts of Maize Leaf Primordia for Fluorescence and Confocal Imaging

Published on: September 22, 2023

科学领域:

计算机视觉计算机视觉
图像处理图像处理
模式识别模式识别

背景情况:

图像拼接严重依赖特征描述符,但目前的方法缺乏对噪声和旋转的稳定性.
现有的描述符对硬件部署的适应性有限,阻碍了实际应用.

研究的目的:

为改进图像拼接提出轻量级多功能描述器 (LMFD).
在特征描述器中增强旋转不变性,抗噪声和计算效率.

主要方法:

在特征点周围提取了梯度,平均值和全局信息.
使用各种组合生成特征描述符,形成二进制矩阵 (0s和1s).
对Hpatches和2D-HeLa数据集进行LMFD评估,并与最先进的算法对比.

主要成果:

与现有方法相比,LMFD在图像匹配方面表现出更高的准确性.
LMFD的二进制矩阵格式促进了高效的硬件部署,并降低了计算复杂性.
实现了强大的旋转不变性和抗噪力.

结论:

LMFD在图像拼接的特征描述器技术中取得了重大进展.
拟议的描述符为计算机视觉应用提供了强大,高效和准确的解决方案.
在各种现实世界的场景中,LMFD显示出强大的实际实施潜力.