一种新颖的人类行为自动分割方法资源-CSDN文库

研究论文

126 浏览量 2021-04-01 22:41:20 上传评论收藏 896KB PDF 举报

资源详情

资源评论

COMPUTER ANIMATION AND VIRTUAL WORLDS

Comp. Anim. Virtual Worlds

2016; 27:501–514

Published online 12 April 2016 in Wiley Online Library (wileyonlinelibrary.com). DOI: 10.1002/cav.1690

RESEARCH ARTICLE

A novel method for automated human

behavior segmentation

Xing Weiwei*, Wang Weiqiang, Bao Peng, Sun Liya and Tong Leiming

School of Software Engineering,Beijing Jiaotong University, Beijing, China

ABSTRACT

In order to conveniently classify, retrieve, and synthesize human motion, motion capture (MoCap) data need to be properly

segmented into distinct behaviors. In this paper, we propose a novel automated segmentation method based on posture

histograms in sliding window. Firstly, a set of new posture features are proposed and deﬁned to construct the posture

histogram, which is a new compact representation of behavioral features. Then, by executing the sliding window, especially

in this paper, the behavior features are analyzed in subsequence level to reduce noise sensitivity. We open up a novel way

to tune sliding window by studying steady states of human behaviors, so that conspicuous and stable behavioral features

can be obtained. Finally, by analyzing the clustering property of posture histograms of the subsequences, the behavior

segmentation problem is tactfully simpliﬁed to the detection of outlier subsequence. In particular, the local outlier factor

algorithm is adopted to solve outlier subsequence detection, and good results are achieved. Extensive experiments are

conducted on 14 pieces of multi-behavior MoCap data from the CMU database,

†

and the experimental results demonstrate

KEYWORDS

motion capture; human behavior segmentation; posture histogram; sliding window; posture features; outlier detection

*Correspondence

Xing Weiwei, School of Software Engineering, Beijing Jiaotong University, Beijing, China.

E-mail: wwxing@bjtu.edu.cn

1. INTRODUCTION

With the increasing demand for realistic human motion

data, masses of motion capture (MoCap) datasets [1] have

been springing up in the last few years. These MoCap

datasets can be utilized in many ﬁelds, such as produc-

tion of video games and animation movies [2–5], physical

rehabilitation [6–8], and ergonomic analysis [9–11]. For a

motion sequence, that is, a piece of MoCap data, it is often

composed of multiple types of behaviors. For instance, per-

formers are told to ﬁnish a speciﬁed task in a scenario by

consecutively acting out several distinct behaviors. In order

to effectively and efﬁciently take advantage of MoCap

data, they are required to be segmented based on their

behavioral semantics, such as walking, running, and jump-

ing, as illustrated in Figure 1. However, automated behav-

ior segmentation is still a challenge. And several issues

contribute to the challenge, such as the incalculable varia-

tion in behavioral periodicities, the intricate representation

†

CMU Graphics Lab Motion Capture Database: http://mocap.cs.

cmu.edu

of articulated body postures, and the countless combina-

tions of all possible behaviors.

Supervised learning strategies have been employed to

this problem by training behavioral classiﬁers from a care-

fully selected training dataset [12–17]. However, the results

heavily relied on the training set, and it would fail to

pick up the segments whose corresponding behaviors were

not contained. To improve extensibility, some researchers

applied unsupervised learning methods, mostly cluster-

ing methods [18–22]. Behavioral features extracted from

motion sequences play a critical role in the process of

clustering. But conventional representation of behavioral

features keeps posture details in all motion frames and

suffers from the overly high dimensionality. The same

issue exists in non-learning-based methods, which formal-

ize segmentation problem as a curve analysis problem

[23–25]. And the analysis of feature curve is executed

frame by frame. Therefore, they are more sensitive to noise

and may produce some false cuts.

From a different perspective, we deﬁne a set of new

posture features and construct a new compact representa-

tion of behavior features, posture histogram, by calculating

proportions of motion frames in subintervals of posture

PHSW-based automated human behavior segmentation X. Weiwei

et al.

Figure 1. Behavior segmentation.

features. Moreover, a selective combination of posture fea-

tures is proposed for the ﬁrst time to derive the posture

histogram. To reduce noise sensitivity, we try to analyze

behavioral features in subsequence level by applying slid-

ing window. And in order to obtain conspicuous and stable

behavioral characteristics of the extracted subsequences, a

novel way is put forward to tune sliding window by ana-

lyzing steady states of human behaviors. Beneﬁting from

the great clustering property of posture histograms in slid-

ing window, behavior segmentation problem is tactfully

simpliﬁed to the detection of outlier subsequence whose

central frame is taken as the segmenting point. And the

local outlier factor (LOF) algorithm [26] is ﬁrst adopted

to pick up the outlier subsequences. CMU MoCap dataset

is used as our dataset for the analysis and experiments.

As shown in the experiment results, our proposed method

achieves great performance in precision and recall, which

outperforms other state-of-the-art methods. The main con-

tributions of this paper can be concluded as follows:

(1) A set of novel features including bone–bone

angles (BBAs), joint–plane distances (JPDs), and

bone–plane angles (BPAs) is proposed and deﬁned

to represent the human body postures. Based on

these novel features, a compact representation

of behavioral features, posture histogram,ispre-

sented for behavior segmentation. It can effectively

decrease the computation cost of segmentation

without loss of accuracy.

(2) As subsequence contains more conspicuous and sta-

ble behavioral features, we construct sliding window

and propose a novel way to tune it by analyzing

steady states of human behaviors. Thus, the behav-

ior features are analyzed in subsequence level. Com-

pared with the frame-based method, our method is

robust to noise.

(3) Regarding the behavior segmentation problem, we

tactfully simplify it to the detection of outlier sub-

sequence, and the LOF algorithm is ﬁrst adopted to

solve this problem and achieves good performance.

The remainder of this paper is organized as follows.

After reviewing related works in Section 2, we construct

posture histogram from a selective feature set in Section 3.

In Section 4, we extract subsequences by a well-tuned slid-

ing window, and then the LOF algorithm is implemented to

pick up the outlier subsequences. In Section 5, experiments

are conducted on 14 multi-behavior motion sequences

from the CMU MoCap database. Finally, Section 6 con-

cludes this paper and discusses the future work.

2. RELATED WORKS

Over the past decades, several techniques have been pro-

posed for behavior segmentation, which can be generally

categorized into two types: learning and non-learning. As

for learning-based methods, they can be further divided

into two groups: supervised learning and unsupervised

learning.

Supervised learning methods generally formulize behav-

ior segmentation as a classiﬁcation problem, where clas-

siﬁers are trained from a carefully selected training set.

Some behavior classiﬁers were trained based on existing

models, such as support vector machine [ 12] and hid-

den Markov model [ 13]. In addition, some custom models

were also proposed to solve the problem [14–17]. Müller

et al. deﬁned motion template to characterize behaviors

[14]. Barnachon et al. proposed behavior histogram as the

behavior classiﬁer [15]. However, segmenting results heav-

ily relied on the training set, and it would fail to pick

up the segments whose corresponding behaviors were not

contained in the training set.

In order to overcome this limitation, it is natural

for researchers to use an unsupervised learning strat-

egy. In unsupervised learning methods, behavior segments

are located by clustering motion frames. Barbi

c et al.

employed Gaussian mixture model (GMM) to model the

motion sequence [18]. The segmenting point was located

as the frame on both sides in which two sets of frames

belong to different Gaussian distributions. Yet manually

setting the number of clusters is not practical when motion

502

Comp. Anim. Virtual Worlds

DOI: 10.1002/cav

X. Weiwei

et al.

PHSW-based automated human behavior segmentation

sequences in a dataset have an unknown number of behav-

iors. Besides, Souvenir et al. and Goh et al. attempted

to formalize behavior segmentation as manifold learn-

ing and clustering [19,20]. And Zhou et al. implemented

an unsupervised hierarchical bottom-up framework called

hierarchical aligned cluster analysis (HACA) [21], which

is based on his previous non-hierarchical work, aligned

cluster analysis [27].

On the other line of enquiry, researchers attempt to solve

the problem of behavior segmentation in the non-learning

way. In the early stage, curve analysis was employed to

segment motion sequence by ﬁnding the zero crossing

or extreme points of the feature curve [23–25]. There

are other methods lying in the non-learning category

[18,28–30]. Barbi

c et al. assumed that different behav-

iors should have different intrinsic dimensionality obtained

by the linear dimension reduction technique probabilistic

principal components analysis (PPCA) [18], so a segment-

ing frame was assigned when the intrinsic dimensional-

ity of a local subsequence suddenly increases. Compared

with learning style methods, conventional non-learning

approaches are more extensible and time-saving. Never-

theless, they are more sensitive to noise and may produce

some false cuts.

3. POSTURE HISTOGRAM

CONSTRUCTION

In order to segment MoCap data into distinct behaviors by

analyzing abrupt change of behavioral features, we need

to accurately characterize different behaviors. Enlightened

by the fact that people identify a behavior by observing the

included body postures, we try to capture characteristics of

behaviors by statistics of posture features. In other words,

we want to extract features of not only per posture but also

permutation of all postures.

To characterize behavioral features of motions, pos-

ture histogram has advantages over existing methods in

three aspects. Firstly, it has uniﬁed feature dimensions for

behaviors with varying sequence length, which is very

convenient for comparing motions without any time warp-

ing algorithms. Then, posture histogram keeps far fewer

dimensions than some conventional methods that often

need to be further applied with a dimension reduction algo-

rithm. Most importantly, posture histogram is accurate in

characterizing behavioral features of motions based on the

results of experiments.

In this section, we introduce the proposed posture his-

togram as a way to characterize behaviors. First, we deﬁne

three groups of posture features to describe body posture

of each motion frame and then construct posture histogram

to encapsulate characteristics of the behavior by the dis-

tribution of motion frames in the subintervals of each

posture feature.

3.1. Posture Feature Deﬁnition

Before characterizing a behavior in a motion sequence, we

need to describe the body posture of each motion frame.

Human body posture is the relative ubiety of body parts

including head, trunk, and limbs, as illustrated in Figure 2.

The common way of depicting body posture is to specify

the angles between bones ( BBA). However, some different

postures share the same BBA, which will cause missing

segmenting frames. So we meticulously deﬁne two more

Figure 2. Human skeleton.

Comp. Anim. Virtual Worlds

DOI: 10.1002/cav

剩余13页未读，继续阅读

评论收藏

内容反馈

一种新颖的人类行为自动分割方法

评论0

最新资源

一种新颖的人类行为自动分割方法

评论0

最新资源

相关推荐

爬虫，爬取文本信息，进行中文分割.zip

利用爬虫爬取文本，进行中文分割，统计词频.zip

基于Unet模型和并联注意力机制实现猫和老鼠动画片的语义分割.zip

关于人工智能的一些介绍与看法.docx

对人工智能的看法作文.docx

对人工智能的看法作文(1).docx

PHP 面向对象技术(全面讲解).txt

C#微软培训资料

人工智能时代的隐私困境.doc

行人惯性导航零速检测算法

基于CORDIC的反正弦和反余弦计算的FPGA实现

混合动力汽车基于规则的控制和ECMS与优化等效因子的实时能源管理策略

BA无标度网络中的SIR模型

使用3DCNN和卷积LSTM进行手势识别学习时空特征

基于三次贝塞尔曲线的类汽车曲率连续路径平滑

基于机器学习的设备剩余寿命预测方法综述

基于无差拍预测控制和扰动观测器的永磁同步电机电流控制

基于FPGA的奇异值和特征值分解的快速实现。

基于BP神经网络的人口预测

无人机协同目标的多无人机协同搜索方法

两轮平衡车的建模与控制研究

基于改进遗传算法的六自由度机器人时间最优轨迹规划

一种基于深度学习的机械臂抓取方法

基于深度神经网络的交通流量预测

一种去除ECG中基线漂移和工频干扰的高效滤波方法