Point fingerprint: A new 3-D object representation scheme

Yiyong Sun; Joonki Paik; Andreas Koschan; David L. Page; Mongi A. Abidi

doi:10.1109/TSMCB.2003.814295

Point fingerprint: A new 3-D object representation scheme

Yiyong Sun, Joonki Paik, Andreas Koschan, David L. Page, Mongi A. Abidi

Geospatial Science and Human Security Di

Research output: Contribution to journal › Letter › peer-review

58 Scopus citations

Abstract

This paper proposes a new, efficient surface representation method for surface matching. A feature carrier for a surface point, which is a set of two-dimensional (2-D) contours that are the projections of geodesic circles on the tangent plane, is generated. The carrier is named point fingerprint because its pattern is similar to human fingerprints and plays a role in discriminating surface points. Corresponding points on surfaces from different views are found by comparing their fingerprints. The point fingerprint is able to carry curvature, color, and other information which can improve matching accuracy, and the matching process is faster than 2-D image comparison. A novel candidate point selection method based on the fingerprint irregularity is introduced. Point fingerprint is successfully applied to pose estimation of real range data.

Original language	English
Pages (from-to)	712-717
Number of pages	6
Journal	IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Volume	33
Issue number	4
DOIs	https://doi.org/10.1109/TSMCB.2003.814295
State	Published - Aug 2003

Funding

Manuscript received November 9, 2001; revised January 20, 2003. This work was supported by the University Research Program in Robotics under Grant DOE-DE-FG02-86NE37968, by the DOD/TACOM/NAC/ARC Program under Grant R01-1344-18, and by FAA/NSSA Program under Grant R01-1344-48/49. This paper was recommended by Guest Editor A. Fusiello.

Keywords

Exponential map
Geodesic distance
Pose estimation
Surface matching
Surface registration
Triangle mesh

Access to Document

10.1109/TSMCB.2003.814295

Cite this

@article{5318c52287a847f69a6da1b5cc9df252,

title = "Point fingerprint: A new 3-D object representation scheme",

abstract = "This paper proposes a new, efficient surface representation method for surface matching. A feature carrier for a surface point, which is a set of two-dimensional (2-D) contours that are the projections of geodesic circles on the tangent plane, is generated. The carrier is named point fingerprint because its pattern is similar to human fingerprints and plays a role in discriminating surface points. Corresponding points on surfaces from different views are found by comparing their fingerprints. The point fingerprint is able to carry curvature, color, and other information which can improve matching accuracy, and the matching process is faster than 2-D image comparison. A novel candidate point selection method based on the fingerprint irregularity is introduced. Point fingerprint is successfully applied to pose estimation of real range data.",

keywords = "Exponential map, Geodesic distance, Pose estimation, Surface matching, Surface registration, Triangle mesh",

author = "Yiyong Sun and Joonki Paik and Andreas Koschan and Page, {David L.} and Abidi, {Mongi A.}",

year = "2003",

month = aug,

doi = "10.1109/TSMCB.2003.814295",

language = "English",

volume = "33",

pages = "712--717",

journal = "IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics",

issn = "1083-4419",

number = "4",

}

TY - JOUR

T1 - Point fingerprint

T2 - A new 3-D object representation scheme

AU - Sun, Yiyong

AU - Paik, Joonki

AU - Koschan, Andreas

AU - Page, David L.

AU - Abidi, Mongi A.

PY - 2003/8

Y1 - 2003/8

N2 - This paper proposes a new, efficient surface representation method for surface matching. A feature carrier for a surface point, which is a set of two-dimensional (2-D) contours that are the projections of geodesic circles on the tangent plane, is generated. The carrier is named point fingerprint because its pattern is similar to human fingerprints and plays a role in discriminating surface points. Corresponding points on surfaces from different views are found by comparing their fingerprints. The point fingerprint is able to carry curvature, color, and other information which can improve matching accuracy, and the matching process is faster than 2-D image comparison. A novel candidate point selection method based on the fingerprint irregularity is introduced. Point fingerprint is successfully applied to pose estimation of real range data.

AB - This paper proposes a new, efficient surface representation method for surface matching. A feature carrier for a surface point, which is a set of two-dimensional (2-D) contours that are the projections of geodesic circles on the tangent plane, is generated. The carrier is named point fingerprint because its pattern is similar to human fingerprints and plays a role in discriminating surface points. Corresponding points on surfaces from different views are found by comparing their fingerprints. The point fingerprint is able to carry curvature, color, and other information which can improve matching accuracy, and the matching process is faster than 2-D image comparison. A novel candidate point selection method based on the fingerprint irregularity is introduced. Point fingerprint is successfully applied to pose estimation of real range data.

KW - Exponential map

KW - Geodesic distance

KW - Pose estimation

KW - Surface matching

KW - Surface registration

KW - Triangle mesh

UR - http://www.scopus.com/inward/record.url?scp=0041765086&partnerID=8YFLogxK

U2 - 10.1109/TSMCB.2003.814295

DO - 10.1109/TSMCB.2003.814295

M3 - Letter

AN - SCOPUS:0041765086

SN - 1083-4419

VL - 33

SP - 712

EP - 717

JO - IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

JF - IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

IS - 4

ER -

Point fingerprint: A new 3-D object representation scheme

Abstract

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this