Pose Estimation with Motionlet LLC Coding
Li Sun, Mingli Song, Jiajun Bu, and Chun Chen
Zhejiang Provincial Key Laboratory of Service Robot,
College of Computer Science, Zhejiang University
{lsun,brooksong,bjj,chenc}@zju.edu.cn
Abstract. 3D human pose estimation is a challenging but important
research topic with abundant applications. As for discriminative human
pose estimation, the main goal is to learn a nonlinear mapping from im-
age descriptors to 3D human pose configurations, which is difficult due
to the high-dimensionality of human pose space and the multimodal-
ity of the distribution. To address these problems, we propose a novel
motionlet LLC coding on a discriminative framework. A motionlet con-
sists of training examples covering a local area in terms of image space,
pose space and time stream. We first group most informative and help-
ful training examples into motionlets, then perform LLC Coding to learn
the nonlinear mapping and get candidate poses, and finally choose the
most appropriate pose as the result estimate. To further eliminate am-
biguities and improve robustness, we extend our framework to incorpo-
rate multiviews. We conduct qualitative evaluation on our Taichi data
set and quantitative evaluation on HumanEva data set, which show that
our approach has gained the-state-of-the-art performance and significant
improvement against previous approaches.
Keywords: human pose estimation, multimodality, multiview, motion-
let, LLC coding.
1 Introduction
3D human pose estimation from images is a challenging but important research
topic with applications in many areas including Human-Computer Interaction,
robotics, surveillance, computer graphics and sport science. Recent approaches
to 3D human pose estimation can be roughly classified into two categories, gen-
erative and discriminative. Generative approaches explicitly model human body
appearance and kinematic constraints and usually concentrate on development
of efficient inference methods that are able to handle the high dimensionality of
human pose. Discriminative approaches directly learn the mapping from image
space to pose space.
Discriminative approaches are popular due to their flexibility of choosing
image descriptors, easy adaptation to different learning methods, no need for
initialization, and most importantly, the ability of fast inference in real-world
databases. The main goal of discriminative 3D human pose estimation is to
W. Lin et al. (Eds.): PCM 2012, LNCS 7674, pp. 435–443, 2012.
c
Springer-Verlag Berlin Heidelberg 2012
剩余8页未读，继续阅读
资源评论
