• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

分数阶变分光流模型的运动估计。

Fractional-order variational optical flow model for motion estimation.

机构信息

College of Information Science and Engineering, Northeastern University, Shenyang 110819, People's Republic of China.

出版信息

Philos Trans A Math Phys Eng Sci. 2013 Apr 1;371(1990):20120148. doi: 10.1098/rsta.2012.0148. Print 2013 May 13.

DOI:10.1098/rsta.2012.0148
PMID:23547225
Abstract

A new class of fractional-order variational optical flow models, which generalizes the differential of optical flow from integer order to fractional order, is proposed for motion estimation in this paper. The corresponding Euler-Lagrange equations are derived by solving a typical fractional variational problem, and the numerical implementation based on the Grünwald-Letnikov fractional derivative definition is proposed to solve these complicated fractional partial differential equations. Theoretical analysis reveals that the proposed fractional-order variational optical flow model is the generalization of the typical Horn and Schunck (first-order) variational optical flow model and the second-order variational optical flow model, which provides a new idea for us to study the optical flow model and has an important theoretical implication in optical flow model research. The experiments demonstrate the validity of the generalization of differential order.

摘要

本文提出了一类新的分数阶变分光流模型,将光流的微分从整数阶推广到分数阶,用于运动估计。通过求解典型的分数变分问题,推导出相应的欧拉-拉格朗日方程,并提出了基于 Grunwald-Letnikov 分数导数定义的数值实现方法来求解这些复杂的分数偏微分方程。理论分析表明,所提出的分数阶变分光流模型是典型的 Horn 和 Schunck(一阶)变分光流模型和二阶变分光流模型的推广,为我们研究光流模型提供了新的思路,在光流模型研究中具有重要的理论意义。实验验证了微分阶数推广的有效性。

相似文献

1
Fractional-order variational optical flow model for motion estimation.分数阶变分光流模型的运动估计。
Philos Trans A Math Phys Eng Sci. 2013 Apr 1;371(1990):20120148. doi: 10.1098/rsta.2012.0148. Print 2013 May 13.
2
Fractional Herglotz variational problems with Atangana-Baleanu fractional derivatives.具有阿坦加纳-巴莱努分数阶导数的分数阶赫格洛茨变分问题。
J Inequal Appl. 2018;2018(1):44. doi: 10.1186/s13660-018-1635-9. Epub 2018 Feb 17.
3
A hybrid fractional optimal control for a novel Coronavirus (2019-nCov) mathematical model.一种新型冠状病毒(2019-nCov)数学模型的混合分数阶最优控制。
J Adv Res. 2021 Sep;32:149-160. doi: 10.1016/j.jare.2020.08.006. Epub 2020 Aug 25.
4
Joint edge detection and motion estimation of cardiac MR image sequence by a phase field method.基于相场方法的心磁图像序列的联合边缘检测和运动估计。
Comput Biol Med. 2010 Jan;40(1):21-8. doi: 10.1016/j.compbiomed.2009.10.004. Epub 2009 Nov 14.
5
Optical flow 3D segmentation and interpretation: a variational method with active curve evolution and level sets.光流三维分割与解释:一种基于活动曲线演化和水平集的变分方法。
IEEE Trans Pattern Anal Mach Intell. 2006 Nov;28(11):1818-29. doi: 10.1109/TPAMI.2006.232.
6
Probabilistic and sequential computation of optical flow using temporal coherence.利用时间相干性进行光流的概率和序列计算。
IEEE Trans Image Process. 1994;3(6):773-88. doi: 10.1109/83.336247.
7
Large displacement optical flow: descriptor matching in variational motion estimation.大位移光流:变分运动估计中的描述子匹配。
IEEE Trans Pattern Anal Mach Intell. 2011 Mar;33(3):500-13. doi: 10.1109/TPAMI.2010.143.
8
A Fractional-Order Variational Framework for Retinex: Fractional-Order Partial Differential Equation-Based Formulation for Multi-Scale Nonlocal Contrast Enhancement with Texture Preserving.分数阶变分框架的 Retinex:基于分数阶偏微分方程的多尺度非局部对比度增强与纹理保持的公式。
IEEE Trans Image Process. 2018 Mar;27(3):1214-1229. doi: 10.1109/TIP.2017.2779601. Epub 2017 Dec 4.
9
Subgrid Variational Optimized Optical Flow Estimation Algorithm for Image Velocimetry.用于图像测速的子网格变分优化光流估计算法。
Sensors (Basel). 2022 Dec 30;23(1):437. doi: 10.3390/s23010437.
10
Variational principles, surface evolution, PDE's, level set methods, and the stereo problem.变分原理、曲面演化、偏微分方程、水平集方法与立体视觉问题
IEEE Trans Image Process. 1998;7(3):336-44. doi: 10.1109/83.661183.

引用本文的文献

1
Dynamic gesture recognition based on 2D convolutional neural network and feature fusion.基于二维卷积神经网络和特征融合的动态手势识别。
Sci Rep. 2022 Mar 14;12(1):4345. doi: 10.1038/s41598-022-08133-z.
2
ARTFLOW: A Fast, Biologically Inspired Neural Network that Learns Optic Flow Templates for Self-Motion Estimation.ARTFLOW:一种快速、受生物启发的神经网络,用于学习用于自运动估计的光流模板。
Sensors (Basel). 2021 Dec 8;21(24):8217. doi: 10.3390/s21248217.
3
Mathematical modelling with experimental validation of viscoelastic properties in non-Newtonian fluids.
用实验验证非牛顿流体粘弹性的数学建模。
Philos Trans A Math Phys Eng Sci. 2020 May 29;378(2172):20190284. doi: 10.1098/rsta.2019.0284. Epub 2020 May 11.
4
Fractional calculus and its applications.分数阶微积分及其应用。
Philos Trans A Math Phys Eng Sci. 2013 Apr 1;371(1990):20130037. doi: 10.1098/rsta.2013.0037. Print 2013 May 13.