单深度图像中实时人体姿态识别

需积分: 10 176 浏览量更新于2024-09-12 收藏 4.65MB PDF 举报

"Real-Time Human Pose Recognition in Parts from Single Depth Images" 这篇论文提出了一种新的方法，可以在不使用时间信息的情况下，仅通过单个深度图像快速而准确地预测人体关节的3D位置。研究团队由微软剑桥研究院和Xbox孵化器的成员组成，包括Jamie Shotton、Andrew Fitzgibbon等人。在论文中，他们采用了一种物体识别的方法，设计了一个中间的体部位表示，将复杂的姿态估计问题转化为更简单的像素级分类问题。这一策略的关键在于，通过大量的、高度多样化的训练数据集，使得分类器能够学习到身体部位的特征，这些特征对于不同的姿势、体型、穿着等都是不变的。这样，即使在复杂的环境中，也能保持较高的识别准确性。最后，通过重新投影分类结果并寻找局部极大值，他们生成了具有置信度评分的多个身体关节的3D提议。这种方法在消费级硬件上可以达到每秒200帧的速度，实现了实时性能。评估结果显示，无论是在合成数据集还是真实测试集上，该系统都表现出高精度。论文还深入探讨了几个训练参数对性能的影响，并在与相关工作的比较中取得了最先进的准确性。此外，他们还证明了该方法在泛化能力上的改进，即在未见过的数据上仍能保持良好的表现。该研究对于基于Kinect等深度传感器的人体姿态识别技术有着显著的贡献，尤其适用于实时应用场景，如游戏交互、运动分析、健康监测等领域。通过深度学习和图像处理技术的结合，它开辟了实时三维人体姿态识别的新途径。

Real-Time Human Pose Recognition in Parts from Single Depth Images

Jamie Shotton Andrew Fitzgibbon Mat Cook Toby Sharp Mark Finocchio

Richard Moore Alex Kipman Andrew Blake

Microsoft Research Cambridge & Xbox Incubation

Abstract

We propose a new method to quickly and accurately pre-

dict 3D positions of body joints from a single depth image,

using no temporal information. We take an object recog-

nition approach, designing an intermediate body parts rep-

resentation that maps the difﬁcult pose estimation problem

into a simpler per-pixel classiﬁcation problem. Our large

and highly varied training dataset allows the classiﬁer to

estimate body parts invariant to pose, body shape, clothing,

etc. Finally we generate conﬁdence-scored 3D proposals of

several body joints by reprojecting the classiﬁcation result

and ﬁnding local modes.

The system runs at 200 frames per second on consumer

hardware. Our evaluation shows high accuracy on both

synthetic and real test sets, and investigates the effect of sev-

eral training parameters. We achieve state of the art accu-

racy in our comparison with related work and demonstrate

improved generalization over exact whole-skeleton nearest

neighbor matching.

1. Introduction

Robust interactive human body tracking has applica-

tions including gaming, human-computer interaction, secu-

rity, telepresence, and even health-care. The task has re-

cently been greatly simpliﬁed by the introduction of real-

time depth cameras [16, 19, 44, 37, 28, 13]. However, even

the best existing systems still exhibit limitations. In partic-

ular, until the launch of Kinect [21], none ran at interactive

rates on consumer hardware while handling a full range of

human body shapes and sizes undergoing general body mo-

tions. Some systems achieve high speeds by tracking from

frame to frame but struggle to re-initialize quickly and so

are not robust. In this paper, we focus on pose recognition

in parts: detecting from a single depth image a small set of

3D position candidates for each skeletal joint. Our focus on

per-frame initialization and recovery is designed to comple-

ment any appropriate tracking algorithm [7, 39, 16, 42, 13]

that might further incorporate temporal and kinematic co-

herence. The algorithm presented here forms a core com-

ponent of the Kinect gaming platform [21].

Illustrated in Fig. 1 and inspired by recent object recog-

nition work that divides objects into parts (e.g. [12, 43]),

our approach is driven by two key design goals: computa-

tional efﬁciency and robustness. A single input depth image

is segmented into a dense probabilistic body part labeling,

with the parts deﬁned to be spatially localized near skeletal

CVPR Teaser

seq 1: frame 15

seq 2: frame 236

seq 5: take 1, 72

depth image body parts 3D joint proposals

Figure 1. Overview. From an single input depth image, a per-pixel

body part distribution is inferred. (Colors indicate the most likely

part labels at each pixel, and correspond in the joint proposals).

Local modes of this signal are estimated to give high-quality pro-

posals for the 3D locations of body joints, even for multiple users.

joints of interest. Reprojecting the inferred parts into world

space, we localize spatial modes of each part distribution

and thus generate (possibly several) conﬁdence-weighted

proposals for the 3D locations of each skeletal joint.

We treat the segmentation into body parts as a per-pixel

classiﬁcation task (no pairwise terms or CRF have proved

necessary). Evaluating each pixel separately avoids a com-

binatorial search over the different body joints, although

within a single part there are of course still dramatic dif-

ferences in the contextual appearance. For training data,

we generate realistic synthetic depth images of humans of

many shapes and sizes in highly varied poses sampled from

a large motion capture database. We train a deep ran-

domized decision forest classiﬁer which avoids overﬁtting

by using hundreds of thousands of training images. Sim-

ple, discriminative depth comparison image features yield

3D translation invariance while maintaining high computa-

tional efﬁciency. For further speed, the classiﬁer can be run

in parallel on each pixel on a GPU [34]. Finally, spatial

modes of the inferred per-pixel distributions are computed

using mean shift [10] resulting in the 3D joint proposals.

An optimized implementation of our algorithm runs in

under 5ms per frame (200 frames per second) on the Xbox

360 GPU, at least one order of magnitude faster than exist-

ing approaches. It works frame-by-frame across dramati-

cally differing body shapes and sizes, and the learned dis-

criminative approach naturally handles self-occlusions and

下载后可阅读完整内容，剩余7页未读，立即下载

月小夏

粉丝: 17

单深度图像中实时人体姿态识别

Real-time human pose recognition in parts from single depth images 中文翻译

Real-time Human Pose Recognition in Parts from Single Depth Images.pdf

cole_02_0507.pdf

工程硕士开题报告：无线传感器网络路由技术及能量优化LEACH协议研究

【东海期货-2025研报】东海贵金属周度策略：金价高位回落，阶段性回调趋势初现.pdf

图像数据处理工具+数据(帮助用户快速划分数据集并增强图像数据集。通过自动化数据处理流程，简化了深度学习项目的数据准备工作)

diminico_02_0709.pdf

agenda_3cd_01_0716.pdf

A课件Python全栈开发线下班.zip

diminico_02_1108.pdf

最新资源