Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

3D pictorial structures for human pose estimation with supervoxels

: Schick, Alexander; Stiefelhagen, R.

Postprint urn:nbn:de:0011-n-3239494 (695 KByte PDF)
MD5 Fingerprint: 4abf669ddead58f8d0930bf9e6f12a96
© IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Created on: 30.1.2015

Institute of Electrical and Electronics Engineers -IEEE-; IEEE Computer Society:
IEEE Winter Conference on Applications of Computer Vision, WACV 2015 : Waikoloa Beach, Hawaii, USA 5-9 January 2015
Piscataway, NJ: IEEE, 2015
ISBN: 978-1-4799-6683-7
Winter Conference on Applications of Computer Vision (WACV) <2015, Waikoloa Beach/Hawaii>
Conference Paper, Electronic Publication
Fraunhofer IOSB ()

Pictorial structures provide a powerful framework for human pose estimation, in particular in the domain of 2D data. However, solving pictorial structures directly in 3D drastically increases its complexity and it quickly exceeds tractable dimensions. In this paper, we propose a discretization-by-segmentation approach by applying supervoxels to 3D pictorial structures which significantly reduces the search space. The proposed 3D pictorial structures approach achieves 3D errors of 115 mm and 135 mm on the HumanEva-I and UMPM datasets and PCP scores of 78% and 75%, respectively. Due to the search space reduction, the overall pose estimation runtime is below 100 ms which is up to four orders of magnitude faster than comparable 3D pictorial structure approaches. The presented approach is not limited to human pose estimation, but provides a general and efficient solution for 3D pictorial structures.