标题:Accurate 3D head pose estimation with noisy RGBD images
作者:Li, Chenglong ;Zhong, Fan ;Qin, Xueying
作者机构:[Li, Chenglong ;Zhong, Fan ;Qin, Xueying ] School of Computer Science and Technology, Shandong University, Engineering Research Center of Digital Medi 更多
会议名称:33rd Computer Graphics International Conference, CGI 2016
会议日期:28 June 2016 through 1 July 2016
来源:ACM International Conference Proceeding Series
出版年:2016
卷:28-June-01-July-2016
页码:37-40
DOI:10.1145/2949035.2949045
关键词:Depth Feature Points; Head Pose Estimation; Kinect; Point Cloud Matching
摘要:In this paper we propose a novel method for accurate 3D head pose estimation with noisy depth map and higher-resolution color image, which typically produced by popular RGBD cameras such as Kinect. Our method combines the benefit of higher-resolution RGB image and 3D information of depth image. For better accuracy and robustneb, features are detected and matched with only color images, the outliers are filtered with depth information. In this way it effectively avoids the influence of depth noise. Several effective outlier filtering rules are introduced. Finally the pose parameters are optimized iteratively using Extended LM (Levenberg-Marquardt) method. To evaluate our method, we built a database of more than 10K RGBD images, with ground-truth poses recorded using motion capture. Both qualitative and quantitative evaluations show that our method produces significant leb error than previous methods. © 2016 ACM.
收录类别:EI;SCOPUS
Scopus被引频次:1
资源类型:会议论文;期刊论文
原文链接:https://www.scopus.com/inward/record.uri?eid=2-s2.0-84978858569&doi=10.1145%2f2949035.2949045&partnerID=40&md5=f096e983bed04326ed6693e9cafb9abc
TOP