3D head pose estimation using the Kinect
2011 (English)Conference paper (Refereed)
Head pose estimation plays an essential role for bridging the information gap between humans and computers. Conventional head pose estimation methods are mostly done in images captured by cameras. However accurate and robust pose estimation is often problematic. In this paper we present an algorithm for recovering the six degrees of freedom (DOF) of motion of a head from a sequence of range images taken by the Microsoft Kinect for Xbox 360. The proposed algorithm utilizes a least-squares minimization of the difference between the measured rate of change of depth at a point and the rate predicted by the depth rate constraint equation. We segment the human head from its surroundings and background, and then we estimate the head motion. Our system has the capability to recover the six DOF of the head motion of multiple people in one image. The proposed system is evaluated in our lab and presents superior results.
Place, publisher, year, edition, pages
2011. 1-4 p.
image segmentation;least squares approximations;minimisation;pose estimation;3D head pose estimation;Microsoft Kinect;Xbox 360;degrees of freedom;depth rate constraint equation;human head segmentation;information gap;least-squares minimization;range images;Cameras;Equations;Estimation;Head;Magnetic heads;Three dimensional displays;Tracking
IdentifiersURN: urn:nbn:se:kth:diva-141828DOI: 10.1109/WCSP.2011.6096866ScopusID: 2-s2.0-84555195629ISBN: 978-145771010-0OAI: oai:DiVA.org:kth-141828DiVA: diva2:698791
2011 International Conference on Wireless Communications and Signal Processing, WCSP 2011; Nanjing; China; 9 November 2011 - 11 November 2011
QC 201504292014-02-252014-02-252015-04-29Bibliographically approved