Reconstruction of 3D human body pose from stereo image sequences based on top-down learning

Hee Deok Yang, Seong Whan Lee

Research output: Contribution to journalArticle

38 Citations (Scopus)

Abstract

This paper presents a novel method for reconstructing a 3D human body pose from stereo image sequences based on a top-down learning method. However, it is inefficient to build a statistical model using all training data. Therefore, the training data is hierarchically divided into several clusters to reduce the complexity of the learning problem. In the learning stage, the human body model database is hierarchically constructed by classifying the training data into several sub-clusters with silhouette images. The data of each cluster in the bottom level is represented by a linear combination of examples. In the reconstruction stage, the proposed method hierarchically searches a cluster for the best matching silhouette image using a silhouette history image (SHI). Then, the 3D human body pose is reconstructed from a depth image using a linear combination of examples method. By using depth information to reconstruct 3D human body pose, the similar poses in silhouette images are estimated as different 3D human body poses. The experimental results demonstrate that the proposed method is efficient and effective for reconstructing 3D human body poses.

Original languageEnglish
Pages (from-to)3120-3131
Number of pages12
JournalPattern Recognition
Volume40
Issue number11
DOIs
Publication statusPublished - 2007 Nov 1

Fingerprint

Image matching
Statistical Models

Keywords

  • 3D human modeling
  • Depth information
  • Reconstruction of 3D human body pose
  • Spatio-temporal features

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Reconstruction of 3D human body pose from stereo image sequences based on top-down learning. / Yang, Hee Deok; Lee, Seong Whan.

In: Pattern Recognition, Vol. 40, No. 11, 01.11.2007, p. 3120-3131.

Research output: Contribution to journalArticle

@article{2964e0fbadd04d11ae433aefe8a3d475,
title = "Reconstruction of 3D human body pose from stereo image sequences based on top-down learning",
abstract = "This paper presents a novel method for reconstructing a 3D human body pose from stereo image sequences based on a top-down learning method. However, it is inefficient to build a statistical model using all training data. Therefore, the training data is hierarchically divided into several clusters to reduce the complexity of the learning problem. In the learning stage, the human body model database is hierarchically constructed by classifying the training data into several sub-clusters with silhouette images. The data of each cluster in the bottom level is represented by a linear combination of examples. In the reconstruction stage, the proposed method hierarchically searches a cluster for the best matching silhouette image using a silhouette history image (SHI). Then, the 3D human body pose is reconstructed from a depth image using a linear combination of examples method. By using depth information to reconstruct 3D human body pose, the similar poses in silhouette images are estimated as different 3D human body poses. The experimental results demonstrate that the proposed method is efficient and effective for reconstructing 3D human body poses.",
keywords = "3D human modeling, Depth information, Reconstruction of 3D human body pose, Spatio-temporal features",
author = "Yang, {Hee Deok} and Lee, {Seong Whan}",
year = "2007",
month = "11",
day = "1",
doi = "10.1016/j.patcog.2007.01.033",
language = "English",
volume = "40",
pages = "3120--3131",
journal = "Pattern Recognition",
issn = "0031-3203",
publisher = "Elsevier Limited",
number = "11",

}

TY - JOUR

T1 - Reconstruction of 3D human body pose from stereo image sequences based on top-down learning

AU - Yang, Hee Deok

AU - Lee, Seong Whan

PY - 2007/11/1

Y1 - 2007/11/1

N2 - This paper presents a novel method for reconstructing a 3D human body pose from stereo image sequences based on a top-down learning method. However, it is inefficient to build a statistical model using all training data. Therefore, the training data is hierarchically divided into several clusters to reduce the complexity of the learning problem. In the learning stage, the human body model database is hierarchically constructed by classifying the training data into several sub-clusters with silhouette images. The data of each cluster in the bottom level is represented by a linear combination of examples. In the reconstruction stage, the proposed method hierarchically searches a cluster for the best matching silhouette image using a silhouette history image (SHI). Then, the 3D human body pose is reconstructed from a depth image using a linear combination of examples method. By using depth information to reconstruct 3D human body pose, the similar poses in silhouette images are estimated as different 3D human body poses. The experimental results demonstrate that the proposed method is efficient and effective for reconstructing 3D human body poses.

AB - This paper presents a novel method for reconstructing a 3D human body pose from stereo image sequences based on a top-down learning method. However, it is inefficient to build a statistical model using all training data. Therefore, the training data is hierarchically divided into several clusters to reduce the complexity of the learning problem. In the learning stage, the human body model database is hierarchically constructed by classifying the training data into several sub-clusters with silhouette images. The data of each cluster in the bottom level is represented by a linear combination of examples. In the reconstruction stage, the proposed method hierarchically searches a cluster for the best matching silhouette image using a silhouette history image (SHI). Then, the 3D human body pose is reconstructed from a depth image using a linear combination of examples method. By using depth information to reconstruct 3D human body pose, the similar poses in silhouette images are estimated as different 3D human body poses. The experimental results demonstrate that the proposed method is efficient and effective for reconstructing 3D human body poses.

KW - 3D human modeling

KW - Depth information

KW - Reconstruction of 3D human body pose

KW - Spatio-temporal features

UR - http://www.scopus.com/inward/record.url?scp=34250844335&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34250844335&partnerID=8YFLogxK

U2 - 10.1016/j.patcog.2007.01.033

DO - 10.1016/j.patcog.2007.01.033

M3 - Article

AN - SCOPUS:34250844335

VL - 40

SP - 3120

EP - 3131

JO - Pattern Recognition

JF - Pattern Recognition

SN - 0031-3203

IS - 11

ER -