3D articulated model retrieval using depth image input

Jun Yang Lin; May Fang She; Ming Han Tsai; I-Chen Lin; Yo Chung Lau; Hsu Hang Liu

doi:10.1007/978-3-030-26756-8_2

3D articulated model retrieval using depth image input

Jun Yang Lin, May Fang She, Ming Han Tsai^*, I-Chen Lin, Yo Chung Lau, Hsu Hang Liu

^*Corresponding author for this work

Institute of Multimedia Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

In this paper, a novel framework to retrieve 3D articulated models from a database based on one or few depth images is presented. Existing state-of-the-arts retrieval approaches usually constrain the view points of query images or assume that the target models are rigid-body. When they are applied to retrieving articulated models, the retrieved results are substantially influenced by the model postures. In our work, we extracts the limbs and torso regions from projections and analyzes the features of local regions. The use of both global and local features can alleviate the disturbance of model postures in model retrieval. Experiments show that the proposed method can efficiently retrieve relevant models within a second, and provides higher retrieval accuracy than those of compared methods for not only rigid body 3D models but also models with articulated limbs.

Original language	English
Title of host publication	Computer Vision, Imaging and Computer Graphics Theory and Applications - 13th International Joint Conference, VISIGRAPP 2018, Revised Selected Papers
Editors	Dominique Bechmann, Manuela Chessa, Ana Paula Cláudio, Francisco Imai, Andreas Kerren, Paul Richard, Alexandru Telea, Alain Tremeau
Publisher	Springer Verlag
Pages	25-47
Number of pages	23
ISBN (Print)	9783030267551
DOIs	https://doi.org/10.1007/978-3-030-26756-8_2
State	Published - 27 Jan 2018
Event	13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2018 - Funchal, Madeira, Portugal Duration: 27 Jan 2018 → 29 Jan 2018

Publication series

Name	Communications in Computer and Information Science
Volume	997
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2018
Country/Territory	Portugal
City	Funchal, Madeira
Period	27/01/18 → 29/01/18

Keywords

3D object retrieval
Depth image analysis
Shape matching

Access to Document

10.1007/978-3-030-26756-8_2

Cite this

Lin, J. Y., She, M. F., Tsai, M. H., Lin, I.-C., Lau, Y. C., & Liu, H. H. (2018). 3D articulated model retrieval using depth image input. In D. Bechmann, M. Chessa, A. P. Cláudio, F. Imai, A. Kerren, P. Richard, A. Telea, & A. Tremeau (Eds.), Computer Vision, Imaging and Computer Graphics Theory and Applications - 13th International Joint Conference, VISIGRAPP 2018, Revised Selected Papers (pp. 25-47). (Communications in Computer and Information Science; Vol. 997). Springer Verlag. https://doi.org/10.1007/978-3-030-26756-8_2

Lin, Jun Yang ; She, May Fang ; Tsai, Ming Han et al. / 3D articulated model retrieval using depth image input. Computer Vision, Imaging and Computer Graphics Theory and Applications - 13th International Joint Conference, VISIGRAPP 2018, Revised Selected Papers. editor / Dominique Bechmann ; Manuela Chessa ; Ana Paula Cláudio ; Francisco Imai ; Andreas Kerren ; Paul Richard ; Alexandru Telea ; Alain Tremeau. Springer Verlag, 2018. pp. 25-47 (Communications in Computer and Information Science).

@inproceedings{cf74ab0671f54e8f89f0f48015869be6,

title = "3D articulated model retrieval using depth image input",

abstract = "In this paper, a novel framework to retrieve 3D articulated models from a database based on one or few depth images is presented. Existing state-of-the-arts retrieval approaches usually constrain the view points of query images or assume that the target models are rigid-body. When they are applied to retrieving articulated models, the retrieved results are substantially influenced by the model postures. In our work, we extracts the limbs and torso regions from projections and analyzes the features of local regions. The use of both global and local features can alleviate the disturbance of model postures in model retrieval. Experiments show that the proposed method can efficiently retrieve relevant models within a second, and provides higher retrieval accuracy than those of compared methods for not only rigid body 3D models but also models with articulated limbs.",

keywords = "3D object retrieval, Depth image analysis, Shape matching",

author = "Lin, {Jun Yang} and She, {May Fang} and Tsai, {Ming Han} and I-Chen Lin and Lau, {Yo Chung} and Liu, {Hsu Hang}",

note = "Publisher Copyright: {\textcopyright} Springer Nature Switzerland AG 2019.; 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2018 ; Conference date: 27-01-2018 Through 29-01-2018",

year = "2018",

month = jan,

day = "27",

doi = "10.1007/978-3-030-26756-8_2",

language = "English",

isbn = "9783030267551",

series = "Communications in Computer and Information Science",

publisher = "Springer Verlag",

pages = "25--47",

editor = "Dominique Bechmann and Manuela Chessa and Cl{\'a}udio, {Ana Paula} and Francisco Imai and Andreas Kerren and Paul Richard and Alexandru Telea and Alain Tremeau",

booktitle = "Computer Vision, Imaging and Computer Graphics Theory and Applications - 13th International Joint Conference, VISIGRAPP 2018, Revised Selected Papers",

address = "德國",

}

Lin, JY, She, MF, Tsai, MH, Lin, I-C, Lau, YC & Liu, HH 2018, 3D articulated model retrieval using depth image input. in D Bechmann, M Chessa, AP Cláudio, F Imai, A Kerren, P Richard, A Telea & A Tremeau (eds), Computer Vision, Imaging and Computer Graphics Theory and Applications - 13th International Joint Conference, VISIGRAPP 2018, Revised Selected Papers. Communications in Computer and Information Science, vol. 997, Springer Verlag, pp. 25-47, 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2018, Funchal, Madeira, Portugal, 27/01/18. https://doi.org/10.1007/978-3-030-26756-8_2

3D articulated model retrieval using depth image input. / Lin, Jun Yang; She, May Fang; Tsai, Ming Han et al.
Computer Vision, Imaging and Computer Graphics Theory and Applications - 13th International Joint Conference, VISIGRAPP 2018, Revised Selected Papers. ed. / Dominique Bechmann; Manuela Chessa; Ana Paula Cláudio; Francisco Imai; Andreas Kerren; Paul Richard; Alexandru Telea; Alain Tremeau. Springer Verlag, 2018. p. 25-47 (Communications in Computer and Information Science; Vol. 997).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - 3D articulated model retrieval using depth image input

AU - Lin, Jun Yang

AU - She, May Fang

AU - Tsai, Ming Han

AU - Lin, I-Chen

AU - Lau, Yo Chung

AU - Liu, Hsu Hang

N1 - Publisher Copyright: © Springer Nature Switzerland AG 2019.

PY - 2018/1/27

Y1 - 2018/1/27

N2 - In this paper, a novel framework to retrieve 3D articulated models from a database based on one or few depth images is presented. Existing state-of-the-arts retrieval approaches usually constrain the view points of query images or assume that the target models are rigid-body. When they are applied to retrieving articulated models, the retrieved results are substantially influenced by the model postures. In our work, we extracts the limbs and torso regions from projections and analyzes the features of local regions. The use of both global and local features can alleviate the disturbance of model postures in model retrieval. Experiments show that the proposed method can efficiently retrieve relevant models within a second, and provides higher retrieval accuracy than those of compared methods for not only rigid body 3D models but also models with articulated limbs.

AB - In this paper, a novel framework to retrieve 3D articulated models from a database based on one or few depth images is presented. Existing state-of-the-arts retrieval approaches usually constrain the view points of query images or assume that the target models are rigid-body. When they are applied to retrieving articulated models, the retrieved results are substantially influenced by the model postures. In our work, we extracts the limbs and torso regions from projections and analyzes the features of local regions. The use of both global and local features can alleviate the disturbance of model postures in model retrieval. Experiments show that the proposed method can efficiently retrieve relevant models within a second, and provides higher retrieval accuracy than those of compared methods for not only rigid body 3D models but also models with articulated limbs.

KW - 3D object retrieval

KW - Depth image analysis

KW - Shape matching

UR - http://www.scopus.com/inward/record.url?scp=85073910312&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-26756-8_2

DO - 10.1007/978-3-030-26756-8_2

M3 - Conference contribution

AN - SCOPUS:85073910312

SN - 9783030267551

T3 - Communications in Computer and Information Science

SP - 25

EP - 47

BT - Computer Vision, Imaging and Computer Graphics Theory and Applications - 13th International Joint Conference, VISIGRAPP 2018, Revised Selected Papers

A2 - Bechmann, Dominique

A2 - Chessa, Manuela

A2 - Cláudio, Ana Paula

A2 - Imai, Francisco

A2 - Kerren, Andreas

A2 - Richard, Paul

A2 - Telea, Alexandru

A2 - Tremeau, Alain

PB - Springer Verlag

T2 - 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2018

Y2 - 27 January 2018 through 29 January 2018

ER -

Lin JY, She MF, Tsai MH, Lin IC, Lau YC, Liu HH. 3D articulated model retrieval using depth image input. In Bechmann D, Chessa M, Cláudio AP, Imai F, Kerren A, Richard P, Telea A, Tremeau A, editors, Computer Vision, Imaging and Computer Graphics Theory and Applications - 13th International Joint Conference, VISIGRAPP 2018, Revised Selected Papers. Springer Verlag. 2018. p. 25-47. (Communications in Computer and Information Science). doi: 10.1007/978-3-030-26756-8_2

3D articulated model retrieval using depth image input

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this