PoseestimationwithmotionletLLCcoding资源-CSDN文库

21 浏览量 2021-02-09 00:00:57 上传评论收藏 453KB PDF 举报

资源推荐

资源详情

资源评论

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.

 Springer-Verlag Berlin Heidelberg 2012

436 L. Sun et al.

learn a nonlinear mapping from image descriptors to 3D human pose conﬁgura-

tions. This is challenging due to high-dimensionality and multimodality of the

mapping. Moreover, the mapping is highly noisy because of image ambiguities

and subject variations.

In this paper we present a novel discriminative framework that can learn a

complex mapping from image descriptors to 3D human pose conﬁgurations. We

propose a local online approach to select most informative and helpful training

examples for the query frame, and then group them into motionlets. As depicted

by ﬁg. 1, every motionlet consists of training examples that covers a local area

with respect to image space, pose space and time stream. The concept of mo-

tionlets is a natural embodiment of the local motion similarity of human motion,

which is the basis assumption of discriminative human pose estimation. We take

advantage of Locality-constrained Linear Coding (LLC) algorithm [7] to recon-

struct 3D human poses using motionlets as codebooks. LLC oﬀers an eﬃcient

local smooth sparse projection of an image descriptor into its local-coordinate

system with good reconstruction. Each motionlet contributes a candidate pose.

We handle the problem of multimodality through selecting the most appropri-

ate pose from these candidate poses. To further eliminate inference ambiguities,

we extend our framework to incorporate multiviews and retain an accurate and

robust inference from image descriptors to 3D human poses.

We review related work in the next section, and then present our online frame-

work of motionlet LLC coding. We deﬁne local neighborhoods for a query frame,

and then show that multimodality of the mapping is mainly caused by the multi-

ple instances of motionlets. We demonstrate how to choose from candidate poses

recovered by LLC coding and how to incorporate multiviews into our framework.

Fig. 1. Motionlets for a query frame. Each motionlet consists of training examples that

cover a local region in terms of appearance space, pose space and time stream.

剩余8页未读，继续阅读

评论收藏

内容反馈

weixin_38746926

粉丝: 12
资源: 994

Pose estimation with motionlet LLC coding

最新资源

Pose estimation with motionlet LLC coding

Motionlet LLC coding for discriminative human pose estimation

3D Human Pose Estimation with 2D Marginal Heatmaps.pdf

Real Time Head Pose Estimation with Random Regression Forests

Learning a Deep Network with Spherical Part Model for 3D Hand Pose Estimation

Human Pose Estimation with Deep Learning:Human Pose Estimation with Deep Learning-matlab开发

2D/3D Pose Estimation and Action Recognition using Multitask Deep Learning

Introduction to Camera Pose Estimation with Deep Learning

Depth-Based Hand Pose Estimation: Methods, Data, and Challenges

3D Human Pose Estimation = 2D Pose Estimation + Matching(2017)

Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields ∗ 源代码

轻量级人体姿态估计lightweight-human-pose-estimation.rar

ssd_pose_estimation

tf-pose-estimation-master.zip

Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields.docx

Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields中文翻译

DeepPose: Human Pose Estimation via Deep Neural Networks

DeepPose-Human Pose Estimation via Deep Neural Networks

Estimation with Applications to Tracking and Navigation (PDF) 第一部分（共2部）

Globally Optimal Relative Pose Estimation With Gravity Prior.pdf

Efficient Human Pose Estimation from Single Depth Images

Delving into Unbiased Data Processing for Human Pose Estimation.pdf

3D Pose Estimation and 3D Model Retrieval for Objects in the Wild

Uncertainty-Driven 6D Pose Estimation

Fine-Grained Head Pose Estimation Without Keypoints

Human Pose Estimation Overview.pptx

depth-based 3d hand pose estimation

Conditional regression forests for human pose estimation

最新资源