Shape measure for identifying perceptually informative parts of 3D objects

Sreenivas Sukumar; David Page; Andrei Gribok; Andreas Koschan; Mongi Abidi

doi:10.1109/3DPVT.2006.127

Shape measure for identifying perceptually informative parts of 3D objects

Sreenivas Sukumar
, David Page
, Andrei Gribok
, Andreas Koschan
, Mongi Abidi

Geospatial Science and Human Security Di

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

19 Scopus citations

Abstract

We propose a mathematical approach for quantifying shape complexity of 3D surfaces based on perceptual principles of visual saliency. Our curvature variation measure (CVM), as a 3D feature, combines surface curvature and information theory by leveraging bandwidth-optimized kernel density estimators. Using a part decomposition algorithm for digitized 3D objects, represented as triangle meshes, we apply our shape measure to transform the low level mesh representation into a perceptually informative form. Further, we analyze the effects of noise, sensitivity to digitization, occlusions, and descriptiveness to demonstrate our shape measure on laser-scanned real world 3D objects.

Original language	English
Title of host publication	Proceedings - 3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006
Publisher	IEEE Computer Society
Pages	679-686
Number of pages	8
ISBN (Print)	0769528252, 9780769528250
DOIs	https://doi.org/10.1109/3DPVT.2006.127
State	Published - 2006
Event	3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006 - Chapel Hill, NC, United States Duration: Jun 14 2006 → Jun 16 2006

Publication series

Name	Proceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006

Conference

Conference	3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006
Country/Territory	United States
City	Chapel Hill, NC
Period	06/14/06 → 06/16/06

Access to Document

10.1109/3DPVT.2006.127

Cite this

Sukumar, S., Page, D., Gribok, A., Koschan, A., & Abidi, M. (2006). Shape measure for identifying perceptually informative parts of 3D objects. In Proceedings - 3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006 (pp. 679-686). Article 4155789 (Proceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006). IEEE Computer Society. https://doi.org/10.1109/3DPVT.2006.127

Sukumar, Sreenivas ; Page, David ; Gribok, Andrei et al. / Shape measure for identifying perceptually informative parts of 3D objects. Proceedings - 3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006. IEEE Computer Society, 2006. pp. 679-686 (Proceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006).

@inproceedings{6a72b95255aa4fc882d664652a8ffa9b,

title = "Shape measure for identifying perceptually informative parts of 3D objects",

abstract = "We propose a mathematical approach for quantifying shape complexity of 3D surfaces based on perceptual principles of visual saliency. Our curvature variation measure (CVM), as a 3D feature, combines surface curvature and information theory by leveraging bandwidth-optimized kernel density estimators. Using a part decomposition algorithm for digitized 3D objects, represented as triangle meshes, we apply our shape measure to transform the low level mesh representation into a perceptually informative form. Further, we analyze the effects of noise, sensitivity to digitization, occlusions, and descriptiveness to demonstrate our shape measure on laser-scanned real world 3D objects.",

author = "Sreenivas Sukumar and David Page and Andrei Gribok and Andreas Koschan and Mongi Abidi",

year = "2006",

doi = "10.1109/3DPVT.2006.127",

language = "English",

isbn = "0769528252",

series = "Proceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006",

publisher = "IEEE Computer Society",

pages = "679--686",

booktitle = "Proceedings - 3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006",

note = "3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006 ; Conference date: 14-06-2006 Through 16-06-2006",

}

Sukumar, S, Page, D, Gribok, A, Koschan, A & Abidi, M 2006, Shape measure for identifying perceptually informative parts of 3D objects. in Proceedings - 3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006., 4155789, Proceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006, IEEE Computer Society, pp. 679-686, 3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006, Chapel Hill, NC, United States, 06/14/06. https://doi.org/10.1109/3DPVT.2006.127

Shape measure for identifying perceptually informative parts of 3D objects. / Sukumar, Sreenivas; Page, David; Gribok, Andrei et al.
Proceedings - 3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006. IEEE Computer Society, 2006. p. 679-686 4155789 (Proceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006).

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

TY - GEN

T1 - Shape measure for identifying perceptually informative parts of 3D objects

AU - Sukumar, Sreenivas

AU - Page, David

AU - Gribok, Andrei

AU - Koschan, Andreas

AU - Abidi, Mongi

PY - 2006

Y1 - 2006

N2 - We propose a mathematical approach for quantifying shape complexity of 3D surfaces based on perceptual principles of visual saliency. Our curvature variation measure (CVM), as a 3D feature, combines surface curvature and information theory by leveraging bandwidth-optimized kernel density estimators. Using a part decomposition algorithm for digitized 3D objects, represented as triangle meshes, we apply our shape measure to transform the low level mesh representation into a perceptually informative form. Further, we analyze the effects of noise, sensitivity to digitization, occlusions, and descriptiveness to demonstrate our shape measure on laser-scanned real world 3D objects.

AB - We propose a mathematical approach for quantifying shape complexity of 3D surfaces based on perceptual principles of visual saliency. Our curvature variation measure (CVM), as a 3D feature, combines surface curvature and information theory by leveraging bandwidth-optimized kernel density estimators. Using a part decomposition algorithm for digitized 3D objects, represented as triangle meshes, we apply our shape measure to transform the low level mesh representation into a perceptually informative form. Further, we analyze the effects of noise, sensitivity to digitization, occlusions, and descriptiveness to demonstrate our shape measure on laser-scanned real world 3D objects.

UR - https://www.scopus.com/pages/publications/47249152765

U2 - 10.1109/3DPVT.2006.127

DO - 10.1109/3DPVT.2006.127

M3 - Conference contribution

AN - SCOPUS:47249152765

SN - 0769528252

SN - 9780769528250

T3 - Proceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006

SP - 679

EP - 686

BT - Proceedings - 3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006

PB - IEEE Computer Society

T2 - 3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006

Y2 - 14 June 2006 through 16 June 2006

ER -

Sukumar S, Page D, Gribok A, Koschan A, Abidi M. Shape measure for identifying perceptually informative parts of 3D objects. In Proceedings - 3rd International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006. IEEE Computer Society. 2006. p. 679-686. 4155789. (Proceedings - Third International Symposium on 3D Data Processing, Visualization, and Transmission, 3DPVT 2006). doi: 10.1109/3DPVT.2006.127

Shape measure for identifying perceptually informative parts of 3D objects

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this