Human body shape and motion tracking by hierarchical weighted ICP

Jia Chen; Xiaojun Wu; Michael Yu Wang; Fuqin Deng

doi:10.1007/978-3-642-24031-7_41

Human body shape and motion tracking by hierarchical weighted ICP

Jia Chen, Xiaojun Wu, Michael Yu Wang, Fuqin Deng

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Other

6 Citations (Scopus)

Abstract

We present a new approach for tracking both the human body shape and the whole body motion with complete six DOF of each body limb without imposing rotation or translation constraints. First, a surface mesh with highly improved quality is obtained by using our new silhouette-based visual hull reconstruction method for each frame of multi-view videos. Then, a skinned mesh model is fitted to the data using hierarchical weighted ICP (HWICP) algorithm, where an easy-to-adjust strategy for selecting the set of ICP registration points is given based on the weights of the skinned model and the Approximate Nearest Neighbors (ANN) method is applied for fast searching nearest neighbors. By comparing HWICP with the general hierarchical ICP (Iterative Closest Point) method based on synthetic data, we demonstrate the power of weighting corresponding point pairs in HWICP, especially when adjacent body segments of target are near 'cylindrical-shaped'.

Original language	English
Title of host publication	ISVC 2011: Advances in Visual Computing
Publisher	Springer
Pages	408-417
Number of pages	10
Volume	6939 LNCS
Edition	PART 2
DOIs	https://doi.org/10.1007/978-3-642-24031-7_41
Publication status	Published - 2011
Externally published	Yes
Event	International Symposium on Visual Computing 2011 - Las Vegas, United States of America Duration: 26 Sept 2011 → 28 Sept 2011 Conference number: 7th

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
ISSN (Print)	0302-9743

Conference

Conference	International Symposium on Visual Computing 2011
Abbreviated title	ISVC 2011
Country/Territory	United States of America
City	Las Vegas
Period	26/09/11 → 28/09/11

Access to Document

10.1007/978-3-642-24031-7_41

Cite this

@inproceedings{608d0e666a6e4b828b0bfb2201fac144,

title = "Human body shape and motion tracking by hierarchical weighted ICP",

abstract = "We present a new approach for tracking both the human body shape and the whole body motion with complete six DOF of each body limb without imposing rotation or translation constraints. First, a surface mesh with highly improved quality is obtained by using our new silhouette-based visual hull reconstruction method for each frame of multi-view videos. Then, a skinned mesh model is fitted to the data using hierarchical weighted ICP (HWICP) algorithm, where an easy-to-adjust strategy for selecting the set of ICP registration points is given based on the weights of the skinned model and the Approximate Nearest Neighbors (ANN) method is applied for fast searching nearest neighbors. By comparing HWICP with the general hierarchical ICP (Iterative Closest Point) method based on synthetic data, we demonstrate the power of weighting corresponding point pairs in HWICP, especially when adjacent body segments of target are near 'cylindrical-shaped'.",

author = "Jia Chen and Xiaojun Wu and Wang, {Michael Yu} and Fuqin Deng",

year = "2011",

doi = "10.1007/978-3-642-24031-7_41",

language = "English",

volume = "6939 LNCS",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "408--417",

booktitle = "ISVC 2011: Advances in Visual Computing",

edition = "PART 2",

note = "International Symposium on Visual Computing 2011, ISVC 2011 ; Conference date: 26-09-2011 Through 28-09-2011",

}

Chen, J, Wu, X, Wang, MY & Deng, F 2011, Human body shape and motion tracking by hierarchical weighted ICP. in ISVC 2011: Advances in Visual Computing . PART 2 edn, vol. 6939 LNCS, Lecture Notes in Computer Science, Springer, pp. 408-417, International Symposium on Visual Computing 2011, Las Vegas, Nevada, United States of America, 26/09/11. https://doi.org/10.1007/978-3-642-24031-7_41

TY - GEN

T1 - Human body shape and motion tracking by hierarchical weighted ICP

AU - Chen, Jia

AU - Wu, Xiaojun

AU - Wang, Michael Yu

AU - Deng, Fuqin

N1 - Conference code: 7th

PY - 2011

Y1 - 2011

N2 - We present a new approach for tracking both the human body shape and the whole body motion with complete six DOF of each body limb without imposing rotation or translation constraints. First, a surface mesh with highly improved quality is obtained by using our new silhouette-based visual hull reconstruction method for each frame of multi-view videos. Then, a skinned mesh model is fitted to the data using hierarchical weighted ICP (HWICP) algorithm, where an easy-to-adjust strategy for selecting the set of ICP registration points is given based on the weights of the skinned model and the Approximate Nearest Neighbors (ANN) method is applied for fast searching nearest neighbors. By comparing HWICP with the general hierarchical ICP (Iterative Closest Point) method based on synthetic data, we demonstrate the power of weighting corresponding point pairs in HWICP, especially when adjacent body segments of target are near 'cylindrical-shaped'.

AB - We present a new approach for tracking both the human body shape and the whole body motion with complete six DOF of each body limb without imposing rotation or translation constraints. First, a surface mesh with highly improved quality is obtained by using our new silhouette-based visual hull reconstruction method for each frame of multi-view videos. Then, a skinned mesh model is fitted to the data using hierarchical weighted ICP (HWICP) algorithm, where an easy-to-adjust strategy for selecting the set of ICP registration points is given based on the weights of the skinned model and the Approximate Nearest Neighbors (ANN) method is applied for fast searching nearest neighbors. By comparing HWICP with the general hierarchical ICP (Iterative Closest Point) method based on synthetic data, we demonstrate the power of weighting corresponding point pairs in HWICP, especially when adjacent body segments of target are near 'cylindrical-shaped'.

UR - http://www.scopus.com/inward/record.url?scp=80053354192&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-24031-7_41

DO - 10.1007/978-3-642-24031-7_41

M3 - Conference Paper

AN - SCOPUS:80053354192

VL - 6939 LNCS

T3 - Lecture Notes in Computer Science

SP - 408

EP - 417

BT - ISVC 2011: Advances in Visual Computing

PB - Springer

T2 - International Symposium on Visual Computing 2011

Y2 - 26 September 2011 through 28 September 2011

ER -

Human body shape and motion tracking by hierarchical weighted ICP

Abstract

Publication series

Conference

Access to Document

Other files and links

Cite this