A survey on model based approaches for 2D and 3D visual human pose recovery

Xavier Perez-Sala; Sergio Escalera; Cecilio Angulo; Jordi Gonzàlez

doi:https://doi.org/10.3390/s140304189

A survey on model based approaches for 2D and 3D visual human pose recovery

Xavier Perez-Sala, Sergio Escalera, Cecilio Angulo, Jordi Gonzàlez

Department of Computer Science

Research output: Contribution to journal › Review article › Research › peer-review

33 Citations (Scopus)

Abstract

Human Pose Recovery has been studied in the field of Computer Vision for the last 40 years. Several approaches have been reported, and significant improvements have been obtained in both data representation and model design. However, the problem of Human Pose Recovery in uncontrolled environments is far from being solved. In this paper, we define a general taxonomy to group model based approaches for Human Pose Recovery, which is composed of five main modules: appearance, viewpoint, spatial relations, temporal consistence, and behavior. Subsequently, a methodological comparison is performed following the proposed taxonomy, evaluating current SoA approaches in the aforementioned five group categories. As a result of this comparison, we discuss the main advantages and drawbacks of the reviewed literature. © 2014 by the authors; licensee MDPI, Basel, Switzerland.

Original language	English
Pages (from-to)	4189-4210
Journal	Sensors
Volume	14
Issue number	3
DOIs	https://doi.org/10.3390/s140304189
Publication status	Published - 3 Mar 2014

Keywords

Behavior analysis
Computer vision
Human body modelling
Human pose recovery

Access to Document

https://doi.org/10.3390/s140304189

https://ddd.uab.cat/record/146918

Cite this

@article{9f9f46008c56414cac4c4368f14e9a13,

title = "A survey on model based approaches for 2D and 3D visual human pose recovery",

abstract = "Human Pose Recovery has been studied in the field of Computer Vision for the last 40 years. Several approaches have been reported, and significant improvements have been obtained in both data representation and model design. However, the problem of Human Pose Recovery in uncontrolled environments is far from being solved. In this paper, we define a general taxonomy to group model based approaches for Human Pose Recovery, which is composed of five main modules: appearance, viewpoint, spatial relations, temporal consistence, and behavior. Subsequently, a methodological comparison is performed following the proposed taxonomy, evaluating current SoA approaches in the aforementioned five group categories. As a result of this comparison, we discuss the main advantages and drawbacks of the reviewed literature. {\textcopyright} 2014 by the authors; licensee MDPI, Basel, Switzerland.",

keywords = "Behavior analysis, Computer vision, Human body modelling, Human pose recovery",

author = "Xavier Perez-Sala and Sergio Escalera and Cecilio Angulo and Jordi Gonz{\`a}lez",

year = "2014",

month = mar,

day = "3",

doi = "https://doi.org/10.3390/s140304189",

language = "English",

volume = "14",

pages = "4189--4210",

journal = "Sensors",

issn = "1424-3210",

publisher = "Multidisciplinary Digital Publishing Institute",

number = "3",

}

TY - JOUR

T1 - A survey on model based approaches for 2D and 3D visual human pose recovery

AU - Perez-Sala, Xavier

AU - Escalera, Sergio

AU - Angulo, Cecilio

AU - Gonzàlez, Jordi

PY - 2014/3/3

Y1 - 2014/3/3

N2 - Human Pose Recovery has been studied in the field of Computer Vision for the last 40 years. Several approaches have been reported, and significant improvements have been obtained in both data representation and model design. However, the problem of Human Pose Recovery in uncontrolled environments is far from being solved. In this paper, we define a general taxonomy to group model based approaches for Human Pose Recovery, which is composed of five main modules: appearance, viewpoint, spatial relations, temporal consistence, and behavior. Subsequently, a methodological comparison is performed following the proposed taxonomy, evaluating current SoA approaches in the aforementioned five group categories. As a result of this comparison, we discuss the main advantages and drawbacks of the reviewed literature. © 2014 by the authors; licensee MDPI, Basel, Switzerland.

AB - Human Pose Recovery has been studied in the field of Computer Vision for the last 40 years. Several approaches have been reported, and significant improvements have been obtained in both data representation and model design. However, the problem of Human Pose Recovery in uncontrolled environments is far from being solved. In this paper, we define a general taxonomy to group model based approaches for Human Pose Recovery, which is composed of five main modules: appearance, viewpoint, spatial relations, temporal consistence, and behavior. Subsequently, a methodological comparison is performed following the proposed taxonomy, evaluating current SoA approaches in the aforementioned five group categories. As a result of this comparison, we discuss the main advantages and drawbacks of the reviewed literature. © 2014 by the authors; licensee MDPI, Basel, Switzerland.

KW - Behavior analysis

KW - Computer vision

KW - Human body modelling

KW - Human pose recovery

U2 - https://doi.org/10.3390/s140304189

DO - https://doi.org/10.3390/s140304189

M3 - Review article

VL - 14

SP - 4189

EP - 4210

JO - Sensors

JF - Sensors

SN - 1424-3210

IS - 3

ER -

A survey on model based approaches for 2D and 3D visual human pose recovery

Abstract

Keywords

Access to Document

Fingerprint

Cite this