Estimation of 3-D human body posture via co-registration of 3-D human model and sequential stereo information

Nguyen Duc Thang; Tae Seong Kim; Young Koo Lee; Sungyoung Lee

doi:10.1007/s10489-009-0209-4

Estimation of 3-D human body posture via co-registration of 3-D human model and sequential stereo information

Nguyen Duc Thang
, Tae Seong Kim
, Young Koo Lee
, Sungyoung Lee

Research output: Contribution to journal › Article › peer-review

14 Citations (Scopus)

Abstract

In this paper, we present a technique for estimating three-dimensional (3-D) human body posture from a set of sequential stereo images. We estimated the pixel displacements of stereo image pairs to reconstruct 3-D information. We modeled the human body with a set of ellipsoids connected by kinematic chains and parameterized with rotational angles at each body joint. To estimate human posture from the 3-D data, we developed a new algorithm based on expectation maximization (EM) with two-step iterations, assigning the 3-D data to different body parts and refining the kinematic parameters to fit the 3-D model to the data. The algorithm is iterated until it converges on the correct posture. Experimental results with synthetic and real data demonstrate that our method is capable of reconstructing 3-D human posture from stereo images. Our method is robust and generic; any useful information for locating the body parts can be integrated into our framework to improve the outcomes.

Original language	English
Pages (from-to)	163-177
Number of pages	15
Journal	Applied Intelligence
Volume	35
Issue number	2
DOIs	https://doi.org/10.1007/s10489-009-0209-4
Publication status	Published - Oct 2011

Bibliographical note

Funding Information:
Acknowledgements This research was supported by the MKE (Ministry of Knowledge Economy), Korea, under the ITRC (Information Technology Research Center) support program supervised by the IITA (Institute of Information Technology Advancement) (IITA-2009-(C1090-0902-0002)). This work also was supported by a Korea Science and Engineering Foundation (KOSEF) grant funded by the Korea government (MEST No. 2008-1342), and was supported by the Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education, Science, and Technology (2009-0076798).

Keywords

Articulated human body model
Estimation of 3-D human body posture
Stereo images

Access to Document

10.1007/s10489-009-0209-4

Cite this

@article{d4fccbdbb73f42cda8d01e8e2b2143ad,

title = "Estimation of 3-D human body posture via co-registration of 3-D human model and sequential stereo information",

abstract = "In this paper, we present a technique for estimating three-dimensional (3-D) human body posture from a set of sequential stereo images. We estimated the pixel displacements of stereo image pairs to reconstruct 3-D information. We modeled the human body with a set of ellipsoids connected by kinematic chains and parameterized with rotational angles at each body joint. To estimate human posture from the 3-D data, we developed a new algorithm based on expectation maximization (EM) with two-step iterations, assigning the 3-D data to different body parts and refining the kinematic parameters to fit the 3-D model to the data. The algorithm is iterated until it converges on the correct posture. Experimental results with synthetic and real data demonstrate that our method is capable of reconstructing 3-D human posture from stereo images. Our method is robust and generic; any useful information for locating the body parts can be integrated into our framework to improve the outcomes.",

keywords = "Articulated human body model, Estimation of 3-D human body posture, Stereo images",

author = "Thang, \{Nguyen Duc\} and Kim, \{Tae Seong\} and Lee, \{Young Koo\} and Sungyoung Lee",

note = "Funding Information: Acknowledgements This research was supported by the MKE (Ministry of Knowledge Economy), Korea, under the ITRC (Information Technology Research Center) support program supervised by the IITA (Institute of Information Technology Advancement) (IITA-2009-(C1090-0902-0002)). This work also was supported by a Korea Science and Engineering Foundation (KOSEF) grant funded by the Korea government (MEST No. 2008-1342), and was supported by the Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education, Science, and Technology (2009-0076798).",

year = "2011",

month = oct,

doi = "10.1007/s10489-009-0209-4",

language = "English",

volume = "35",

pages = "163--177",

journal = "Applied Intelligence",

issn = "0924-669X",

publisher = "Springer",

number = "2",

}

TY - JOUR

T1 - Estimation of 3-D human body posture via co-registration of 3-D human model and sequential stereo information

AU - Thang, Nguyen Duc

AU - Kim, Tae Seong

AU - Lee, Young Koo

AU - Lee, Sungyoung

N1 - Funding Information: Acknowledgements This research was supported by the MKE (Ministry of Knowledge Economy), Korea, under the ITRC (Information Technology Research Center) support program supervised by the IITA (Institute of Information Technology Advancement) (IITA-2009-(C1090-0902-0002)). This work also was supported by a Korea Science and Engineering Foundation (KOSEF) grant funded by the Korea government (MEST No. 2008-1342), and was supported by the Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education, Science, and Technology (2009-0076798).

PY - 2011/10

Y1 - 2011/10

N2 - In this paper, we present a technique for estimating three-dimensional (3-D) human body posture from a set of sequential stereo images. We estimated the pixel displacements of stereo image pairs to reconstruct 3-D information. We modeled the human body with a set of ellipsoids connected by kinematic chains and parameterized with rotational angles at each body joint. To estimate human posture from the 3-D data, we developed a new algorithm based on expectation maximization (EM) with two-step iterations, assigning the 3-D data to different body parts and refining the kinematic parameters to fit the 3-D model to the data. The algorithm is iterated until it converges on the correct posture. Experimental results with synthetic and real data demonstrate that our method is capable of reconstructing 3-D human posture from stereo images. Our method is robust and generic; any useful information for locating the body parts can be integrated into our framework to improve the outcomes.

AB - In this paper, we present a technique for estimating three-dimensional (3-D) human body posture from a set of sequential stereo images. We estimated the pixel displacements of stereo image pairs to reconstruct 3-D information. We modeled the human body with a set of ellipsoids connected by kinematic chains and parameterized with rotational angles at each body joint. To estimate human posture from the 3-D data, we developed a new algorithm based on expectation maximization (EM) with two-step iterations, assigning the 3-D data to different body parts and refining the kinematic parameters to fit the 3-D model to the data. The algorithm is iterated until it converges on the correct posture. Experimental results with synthetic and real data demonstrate that our method is capable of reconstructing 3-D human posture from stereo images. Our method is robust and generic; any useful information for locating the body parts can be integrated into our framework to improve the outcomes.

KW - Articulated human body model

KW - Estimation of 3-D human body posture

KW - Stereo images

UR - https://www.scopus.com/pages/publications/80052966657

U2 - 10.1007/s10489-009-0209-4

DO - 10.1007/s10489-009-0209-4

M3 - Article

AN - SCOPUS:80052966657

SN - 0924-669X

VL - 35

SP - 163

EP - 177

JO - Applied Intelligence

JF - Applied Intelligence

IS - 2

ER -

Estimation of 3-D human body posture via co-registration of 3-D human model and sequential stereo information

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this