Facial Tracking by Gaussian Process

WANG Lei; ZOU Beiji; PENG Xiaoning; PAN Li-li

您当前的位置：

首页 >

文章列表页 >

Facial Tracking by Gaussian Process

更新时间：2025-07-16

- Facial Tracking by Gaussian Process
- Acta Electronica Sinica Vol. 35, Issue 11, Pages: 2087-2091(2007)
- 作者机构：
  
  1. 湖南大学计算机与通信学院,湖南,长沙,410082
  2. 中南大学信息科学与工程学院,湖南,长沙,410083
  3. 湖南大学计算机与通信学院湖南长沙,410082
  4. 中南大学信息科学与工程学院湖南长沙,410083
  5. 浙江大学计算机辅助设计与图形学国家重点实验室,浙江,杭州,310058
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP391.41
- Published：2007
- 稿件说明：
移动端阅览
WANG Lei, ZOU Beiji, PENG Xiaoning, et al. Facial Tracking by Gaussian Process[J]. Acta Electronica Sinica, 2007, 35(11): 2087-2091.
DOI：

WANG Lei, ZOU Beiji, PENG Xiaoning, et al. Facial Tracking by Gaussian Process[J]. Acta Electronica Sinica, 2007, 35(11): 2087-2091. DOI：

摘要

在表情动作单元的跟踪中有两个常见问题:一是跟踪结果有小幅而频繁的抖动;二是跟踪过程会产生难以检测的误差.针对这两个问题

本文提出了一种基于高斯过程和粒子滤波的表情动作单元跟踪技术.实验结果表明本文算法比传统的梯度优化和粒子滤波法具有更好的平滑性和跟踪精度

而精度的优势在头部有偏转的情况下尤为突出.

Abstract

Facial Action Units (FAU) tracking is a hard problem for the rigid and non-rigid transformations of human face.The constantly trembling in the tracking result and the tracking failures caused by the absence of constraint remain open problems.This paper presents a novel method to attack these problems by combining Gaussian Process and Particle Filtering.Gradient-based method and particle filtering based method are compared with our method and the experiment results are encouraging.

关键词

Keywords

references

Views

1167

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

A Likelihood-Ratio Detection Method of Radar Target Based on Particle Filtering

A Novel Particle Filtering Algorithm Based on Generalized Unscented Transformation

Reinforcement Learning for Continuous Spaces Based on Gaussian Process Classifier

Related Author

FONT

YU Xing-Wei

WANG Shou-yong

Verdana

FONT face

PAN Quan

FONT face

Verdana

Related Institution

Wuhan Radar Institute

(College of Automation, Northwestern Polytechnical University,,,)

College of ComnputerNanjing University of Posts and TelecommunicationsNanjingJiangshu 210003China

School of Computer Science and TechnologyShanDong UniversityJinanShandong 250022China

School of Information and Science EngineeringUniversity of JinanShandong 250022China

⁰