Good Vibrations: A Modal Analysis Approach for Sequential Non-rigid Structure from Motion

Antonio Agudo, L. Agapito, B. Calvo, J. Montiel
{"title":"Good Vibrations: A Modal Analysis Approach for Sequential Non-rigid Structure from Motion","authors":"Antonio Agudo, L. Agapito, B. Calvo, J. Montiel","doi":"10.1109/CVPR.2014.202","DOIUrl":null,"url":null,"abstract":"We propose an online solution to non-rigid structure from motion that performs camera pose and 3D shape estimation of highly deformable surfaces on a frame-by-frame basis. Our method models non-rigid deformations as a linear combination of some mode shapes obtained using modal analysis from continuum mechanics. The shape is first discretized into linear elastic triangles, modelled by means of finite elements, which are used to pose the force balance equations for an undamped free vibrations model. The shape basis computation comes down to solving an eigenvalue problem, without the requirement of a learning step. The camera pose and time varying weights that define the shape at each frame are then estimated on the fly, in an online fashion, using bundle adjustment over a sliding window of image frames. The result is a low computational cost method that can run sequentially in real-time. We show experimental results on synthetic sequences with ground truth 3D data and real videos for different scenarios ranging from sparse to dense scenes. Our system exhibits a good trade-off between accuracy and computational budget, it can handle missing data and performs favourably compared to competing methods.","PeriodicalId":319578,"journal":{"name":"2014 IEEE Conference on Computer Vision and Pattern Recognition","volume":"11 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"71","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2014 IEEE Conference on Computer Vision and Pattern Recognition","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CVPR.2014.202","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 71

Abstract

We propose an online solution to non-rigid structure from motion that performs camera pose and 3D shape estimation of highly deformable surfaces on a frame-by-frame basis. Our method models non-rigid deformations as a linear combination of some mode shapes obtained using modal analysis from continuum mechanics. The shape is first discretized into linear elastic triangles, modelled by means of finite elements, which are used to pose the force balance equations for an undamped free vibrations model. The shape basis computation comes down to solving an eigenvalue problem, without the requirement of a learning step. The camera pose and time varying weights that define the shape at each frame are then estimated on the fly, in an online fashion, using bundle adjustment over a sliding window of image frames. The result is a low computational cost method that can run sequentially in real-time. We show experimental results on synthetic sequences with ground truth 3D data and real videos for different scenarios ranging from sparse to dense scenes. Our system exhibits a good trade-off between accuracy and computational budget, it can handle missing data and performs favourably compared to competing methods.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
良好振动:序列非刚性结构的运动模态分析方法
我们提出了一种基于运动的非刚性结构的在线解决方案,该解决方案可以逐帧地对高度可变形的表面进行相机姿态和3D形状估计。我们的方法将非刚性变形建模为使用连续介质力学的模态分析得到的一些模态振型的线性组合。该形状首先被离散成线性弹性三角形,用有限元方法建模,用来建立无阻尼自由振动模型的力平衡方程。形状基计算可以归结为求解特征值问题,不需要学习步骤。相机的姿势和时间变化的权重,定义了每一帧的形状,然后在飞行中估计,以在线的方式,使用图像帧滑动窗口的捆绑调整。结果是一种计算成本低的方法,可以按顺序实时运行。我们展示了从稀疏到密集场景的不同场景的合成序列与地面真实3D数据和真实视频的实验结果。我们的系统在精度和计算预算之间表现出良好的平衡,它可以处理丢失的数据,并且与竞争方法相比表现良好。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Enriching Visual Knowledge Bases via Object Discovery and Segmentation Multiple Structured-Instance Learning for Semantic Segmentation with Uncertain Training Data Parsing Occluded People L0 Norm Based Dictionary Learning by Proximal Methods with Global Convergence Generalized Pupil-centric Imaging and Analytical Calibration for a Non-frontal Camera
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1