3D human body modeling using range data

Koichiro Yamauchi, Bir Bhanu, Hideo Saito

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

For the 3D modeling of walking humans the determination of body pose and extraction of body parts, from the sensed 3D range data, are challenging image processing problems. Real body data may have holes because of self-occlusions and grazing angle views. Most of the existing modeling methods rely on direct fitting a 3D model into the data without considering the fact that the parts in an image are indeed the human body parts. In this paper, we present a method for 3D human body modeling using range data that attempts to overcome these problems. In our approach the entire human body is first decomposed into major body parts by a parts-based image segmentation method, and then a kinematics model is fitted to the segmented body parts in an optimized manner. The fitted model is adjusted by the iterative closest point (ICP) algorithm to resolve the gaps in the body data. Experimental results and comparisons demonstrate the effectiveness of our approach.

Original languageEnglish
Title of host publicationProceedings - International Conference on Pattern Recognition
Pages3476-3479
Number of pages4
DOIs
Publication statusPublished - 2010
Event2010 20th International Conference on Pattern Recognition, ICPR 2010 - Istanbul, Turkey
Duration: 2010 Aug 232010 Aug 26

Other

Other2010 20th International Conference on Pattern Recognition, ICPR 2010
CountryTurkey
CityIstanbul
Period10/8/2310/8/26

Fingerprint

Image segmentation
Kinematics
Image processing

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Yamauchi, K., Bhanu, B., & Saito, H. (2010). 3D human body modeling using range data. In Proceedings - International Conference on Pattern Recognition (pp. 3476-3479). [5597543] https://doi.org/10.1109/ICPR.2010.849

3D human body modeling using range data. / Yamauchi, Koichiro; Bhanu, Bir; Saito, Hideo.

Proceedings - International Conference on Pattern Recognition. 2010. p. 3476-3479 5597543.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yamauchi, K, Bhanu, B & Saito, H 2010, 3D human body modeling using range data. in Proceedings - International Conference on Pattern Recognition., 5597543, pp. 3476-3479, 2010 20th International Conference on Pattern Recognition, ICPR 2010, Istanbul, Turkey, 10/8/23. https://doi.org/10.1109/ICPR.2010.849
Yamauchi K, Bhanu B, Saito H. 3D human body modeling using range data. In Proceedings - International Conference on Pattern Recognition. 2010. p. 3476-3479. 5597543 https://doi.org/10.1109/ICPR.2010.849
Yamauchi, Koichiro ; Bhanu, Bir ; Saito, Hideo. / 3D human body modeling using range data. Proceedings - International Conference on Pattern Recognition. 2010. pp. 3476-3479
@inproceedings{36b8ece1dec4404daa96c8b73768fe20,
title = "3D human body modeling using range data",
abstract = "For the 3D modeling of walking humans the determination of body pose and extraction of body parts, from the sensed 3D range data, are challenging image processing problems. Real body data may have holes because of self-occlusions and grazing angle views. Most of the existing modeling methods rely on direct fitting a 3D model into the data without considering the fact that the parts in an image are indeed the human body parts. In this paper, we present a method for 3D human body modeling using range data that attempts to overcome these problems. In our approach the entire human body is first decomposed into major body parts by a parts-based image segmentation method, and then a kinematics model is fitted to the segmented body parts in an optimized manner. The fitted model is adjusted by the iterative closest point (ICP) algorithm to resolve the gaps in the body data. Experimental results and comparisons demonstrate the effectiveness of our approach.",
author = "Koichiro Yamauchi and Bir Bhanu and Hideo Saito",
year = "2010",
doi = "10.1109/ICPR.2010.849",
language = "English",
isbn = "9780769541099",
pages = "3476--3479",
booktitle = "Proceedings - International Conference on Pattern Recognition",

}

TY - GEN

T1 - 3D human body modeling using range data

AU - Yamauchi, Koichiro

AU - Bhanu, Bir

AU - Saito, Hideo

PY - 2010

Y1 - 2010

N2 - For the 3D modeling of walking humans the determination of body pose and extraction of body parts, from the sensed 3D range data, are challenging image processing problems. Real body data may have holes because of self-occlusions and grazing angle views. Most of the existing modeling methods rely on direct fitting a 3D model into the data without considering the fact that the parts in an image are indeed the human body parts. In this paper, we present a method for 3D human body modeling using range data that attempts to overcome these problems. In our approach the entire human body is first decomposed into major body parts by a parts-based image segmentation method, and then a kinematics model is fitted to the segmented body parts in an optimized manner. The fitted model is adjusted by the iterative closest point (ICP) algorithm to resolve the gaps in the body data. Experimental results and comparisons demonstrate the effectiveness of our approach.

AB - For the 3D modeling of walking humans the determination of body pose and extraction of body parts, from the sensed 3D range data, are challenging image processing problems. Real body data may have holes because of self-occlusions and grazing angle views. Most of the existing modeling methods rely on direct fitting a 3D model into the data without considering the fact that the parts in an image are indeed the human body parts. In this paper, we present a method for 3D human body modeling using range data that attempts to overcome these problems. In our approach the entire human body is first decomposed into major body parts by a parts-based image segmentation method, and then a kinematics model is fitted to the segmented body parts in an optimized manner. The fitted model is adjusted by the iterative closest point (ICP) algorithm to resolve the gaps in the body data. Experimental results and comparisons demonstrate the effectiveness of our approach.

UR - http://www.scopus.com/inward/record.url?scp=78149490617&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78149490617&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2010.849

DO - 10.1109/ICPR.2010.849

M3 - Conference contribution

AN - SCOPUS:78149490617

SN - 9780769541099

SP - 3476

EP - 3479

BT - Proceedings - International Conference on Pattern Recognition

ER -