A Study of Shape Similarity for Temporal Surface Sequences of People

Sixth International Conference on 3-D Digital Imaging and Modeling (3DIM 2007) Pub Date : 2007-08-21 DOI:10.1109/3DIM.2007.8

Peng Huang, J. Starck, A. Hilton

{"title":"A Study of Shape Similarity for Temporal Surface Sequences of People","authors":"Peng Huang, J. Starck, A. Hilton","doi":"10.1109/3DIM.2007.8","DOIUrl":null,"url":null,"abstract":"The problem of 3D shape matching is typically restricted to static objects to classify similarity for shape retrieval. In this paper we consider 3D shape matching in temporal sequences where the goal is instead to find similar shapes for a single time-varying object, here the human body. Local- feature distribution descriptors are adopted to provide a rich object description that is invariant to changes in surface topology. Two contributions are made, (i) a comparison of descriptors for shape similarity in temporal sequences of a dynamic free-form object and (ii) a quantitative evaluation based on the Receiver-Operator Characteristic (ROC) curve for the descriptors using a ground-truth data set for synthetic motion sequences. Shape Distribution [25], Spin Image [15], Shape Histogram [1] and Spherical Harmonic [17] descriptors are compared. The highest performance is obtained by volume-sampling shape-histogram descriptors. The descriptors also demonstrate relative in- sensitivity to parameter setting. The application is demonstrated in captured sequences of 3D human surface motion.","PeriodicalId":442311,"journal":{"name":"Sixth International Conference on 3-D Digital Imaging and Modeling (3DIM 2007)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2007-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"12","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Sixth International Conference on 3-D Digital Imaging and Modeling (3DIM 2007)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/3DIM.2007.8","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 12

Abstract

The problem of 3D shape matching is typically restricted to static objects to classify similarity for shape retrieval. In this paper we consider 3D shape matching in temporal sequences where the goal is instead to find similar shapes for a single time-varying object, here the human body. Local- feature distribution descriptors are adopted to provide a rich object description that is invariant to changes in surface topology. Two contributions are made, (i) a comparison of descriptors for shape similarity in temporal sequences of a dynamic free-form object and (ii) a quantitative evaluation based on the Receiver-Operator Characteristic (ROC) curve for the descriptors using a ground-truth data set for synthetic motion sequences. Shape Distribution [25], Spin Image [15], Shape Histogram [1] and Spherical Harmonic [17] descriptors are compared. The highest performance is obtained by volume-sampling shape-histogram descriptors. The descriptors also demonstrate relative in- sensitivity to parameter setting. The application is demonstrated in captured sequences of 3D human surface motion.

查看原文本刊更多论文

人的时间表面序列的形状相似性研究

三维形状匹配问题通常局限于静态物体的形状检索，需要对物体的相似度进行分类。在本文中，我们考虑在时间序列中的三维形状匹配，其目标是为单个时变物体(这里是人体)找到相似的形状。采用局部特征分布描述符，提供丰富的对象描述，且不受表面拓扑变化的影响。本文做出了两项贡献，(i)对动态自由形状物体的时间序列中形状相似性的描述符进行了比较，(ii)使用合成运动序列的真值数据集对描述符进行了基于接收算子特征(ROC)曲线的定量评估。比较了形状分布[25]、自旋图像[15]、形状直方图[1]和球面谐波[17]描述符。体积采样形状直方图描述符获得了最高的性能。描述符还显示了对参数设置的相对敏感性。在三维人体表面运动的捕获序列中演示了该应用程序。

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分钟内获得全文求助全文

来源期刊

Sixth International Conference on 3-D Digital Imaging and Modeling (3DIM 2007)

自引率

0.00%

发文量