CASIA OpenIR  > 学术期刊  > 自动化学报
基于渐进高斯滤波融合的多视角人体姿态估计
杨旭升; 吴江宇; 胡佛; 张文安
Source Publication自动化学报
ISSN0254-4156
2024
Volume50Issue:3Pages:607-616
Abstract针对视觉遮挡引起的人体姿态估计(Human pose estimation, HPE)性能下降问题,提出基于渐进高斯滤波(Progressive Gaussian filtering, PGF)融合的人体姿态估计方法.首先,设计分层性能评估方法对多视觉量测进行分类处理,以适应视觉遮挡引起的量测不确定性问题.其次,构建分布式渐进贝叶斯滤波融合框架,以及设计一种分层分类融合估计方法来提升复杂量测融合的鲁棒性和准确性.特别地,针对量测统计特性变化问题,利用局部估计间的交互信息来引导渐进量测更新,从而隐式地补偿量测不确定性.最后,仿真与实验结果表明,相比于现有的方法,所提的人体姿态估计方法具有更高的准确性和鲁棒性.
Keyword渐进高斯滤波 自适应滤波 分布式融合 人体姿态估计
DOI10.16383/j.aas.c230316
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/55734
Collection学术期刊_自动化学报
Recommended Citation
GB/T 7714
杨旭升,吴江宇,胡佛,等. 基于渐进高斯滤波融合的多视角人体姿态估计[J]. 自动化学报,2024,50(3):607-616.
APA 杨旭升,吴江宇,胡佛,&张文安.(2024).基于渐进高斯滤波融合的多视角人体姿态估计.自动化学报,50(3),607-616.
MLA 杨旭升,et al."基于渐进高斯滤波融合的多视角人体姿态估计".自动化学报 50.3(2024):607-616.
Files in This Item: Download All
File Name/Size DocType Version Access License
AAS-CN-2023-0316.pdf(2670KB)期刊论文出版稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[杨旭升]'s Articles
[吴江宇]'s Articles
[胡佛]'s Articles
Baidu academic
Similar articles in Baidu academic
[杨旭升]'s Articles
[吴江宇]'s Articles
[胡佛]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[杨旭升]'s Articles
[吴江宇]'s Articles
[胡佛]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: AAS-CN-2023-0316.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.