{"title":"Markerless human body motion capture using multiple cameras","authors":"Li Jia, M. Zhenjiang, Wang Chengkai","doi":"10.1109/ICOSP.2008.4697410","DOIUrl":null,"url":null,"abstract":"In this paper, we present an approach for markerless model-based full human-body motion capture using multi-view images as input. We extract volume data (voxels) representation from the silhouettes extracted from multiple-view video images by the method of shape from Silhouettes (SFS), and match our predefined human body model to the volume data. We construct an energy field in the volume of interest based on the volume data and human body model with pose parameters, and transform the matching to an energy minimizing problem. By dynamic graph cut, we get the minimum energy of certain pose parameters, and at last we optimize the pose parameters using Powell algorithm with a novel approach that uses the linear prediction guiding the optimization process and get the pose recovered. Through the test results on several video sequences of human body movements in an unaugmented office environment, we demonstrate the effectiveness and robustness of our approach.","PeriodicalId":445699,"journal":{"name":"2008 9th International Conference on Signal Processing","volume":"17 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2008-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2008 9th International Conference on Signal Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICOSP.2008.4697410","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
In this paper, we present an approach for markerless model-based full human-body motion capture using multi-view images as input. We extract volume data (voxels) representation from the silhouettes extracted from multiple-view video images by the method of shape from Silhouettes (SFS), and match our predefined human body model to the volume data. We construct an energy field in the volume of interest based on the volume data and human body model with pose parameters, and transform the matching to an energy minimizing problem. By dynamic graph cut, we get the minimum energy of certain pose parameters, and at last we optimize the pose parameters using Powell algorithm with a novel approach that uses the linear prediction guiding the optimization process and get the pose recovered. Through the test results on several video sequences of human body movements in an unaugmented office environment, we demonstrate the effectiveness and robustness of our approach.
在本文中,我们提出了一种使用多视图图像作为输入的基于无标记模型的全身运动捕捉方法。我们利用SFS (shape from silhouette)方法从多视图视频图像中提取的轮廓中提取体数据(体素)表示,并将我们预定义的人体模型与体数据进行匹配。基于体数据和具有位姿参数的人体模型,在感兴趣的体上构造能量场,并将匹配问题转化为能量最小化问题。通过动态图切得到某一姿态参数的最小能量,最后利用Powell算法对姿态参数进行优化,提出了一种利用线性预测指导优化过程并得到姿态恢复的新方法。通过在非增强办公环境中对几个人体运动视频序列的测试结果,我们证明了我们的方法的有效性和鲁棒性。