Geometric optimization for 3D pose estimation of quadratic surfaces

Pei Yean Lee; John B. Moore

Geometric optimization for 3D pose estimation of quadratic surfaces

Pei Yean Lee^*, John B. Moore

^*Corresponding author for this work

Research output: Contribution to journal › Conference article › peer-review

9 Citations (Scopus)

Abstract

Our task is 3D pose estimation for on-line application in industrial robotics and machine vision. It involves the estimation of object position and orientation relative to a known model. Since most man made objects can be approximated by a small set of quadratic surfaces, in this paper we focus on pose estimation of such surfaces. Our optimization is of an error measure between the CAD model and the measured data. Most existing algorithms are sensitive to noise and occlusion or only converge linearly. Our optimization involves iterative cost function reduction on the smooth manifold of the Special Euclidean Group, SE₃. The optimization is based on locally quadratically convergent Newton-type iterations on this constraint manifold. A careful analysis of the underlying geometric constraint is required.

Original language	English
Pages (from-to)	131-135
Number of pages	5
Journal	Conference Record of the Asilomar Conference on Signals, Systems and Computers
Volume	1
Publication status	Published - 2004
Event	Conference Record of the Thirty-Eighth Asilomar Conference on Signals, Systems and Computers - Pacific Grove, CA, United States Duration: 7 Nov 2004 → 10 Nov 2004

Cite this

@article{3cbad89ee0d94d9f878496a8c7f08770,

title = "Geometric optimization for 3D pose estimation of quadratic surfaces",

abstract = "Our task is 3D pose estimation for on-line application in industrial robotics and machine vision. It involves the estimation of object position and orientation relative to a known model. Since most man made objects can be approximated by a small set of quadratic surfaces, in this paper we focus on pose estimation of such surfaces. Our optimization is of an error measure between the CAD model and the measured data. Most existing algorithms are sensitive to noise and occlusion or only converge linearly. Our optimization involves iterative cost function reduction on the smooth manifold of the Special Euclidean Group, SE3. The optimization is based on locally quadratically convergent Newton-type iterations on this constraint manifold. A careful analysis of the underlying geometric constraint is required.",

author = "Lee, {Pei Yean} and Moore, {John B.}",

year = "2004",

language = "English",

volume = "1",

pages = "131--135",

journal = "Conference Record of the Asilomar Conference on Signals, Systems and Computers",

issn = "1058-6393",

publisher = "IEEE Computer Society",

note = "Conference Record of the Thirty-Eighth Asilomar Conference on Signals, Systems and Computers ; Conference date: 07-11-2004 Through 10-11-2004",

}

TY - JOUR

T1 - Geometric optimization for 3D pose estimation of quadratic surfaces

AU - Lee, Pei Yean

AU - Moore, John B.

PY - 2004

Y1 - 2004

N2 - Our task is 3D pose estimation for on-line application in industrial robotics and machine vision. It involves the estimation of object position and orientation relative to a known model. Since most man made objects can be approximated by a small set of quadratic surfaces, in this paper we focus on pose estimation of such surfaces. Our optimization is of an error measure between the CAD model and the measured data. Most existing algorithms are sensitive to noise and occlusion or only converge linearly. Our optimization involves iterative cost function reduction on the smooth manifold of the Special Euclidean Group, SE3. The optimization is based on locally quadratically convergent Newton-type iterations on this constraint manifold. A careful analysis of the underlying geometric constraint is required.

AB - Our task is 3D pose estimation for on-line application in industrial robotics and machine vision. It involves the estimation of object position and orientation relative to a known model. Since most man made objects can be approximated by a small set of quadratic surfaces, in this paper we focus on pose estimation of such surfaces. Our optimization is of an error measure between the CAD model and the measured data. Most existing algorithms are sensitive to noise and occlusion or only converge linearly. Our optimization involves iterative cost function reduction on the smooth manifold of the Special Euclidean Group, SE3. The optimization is based on locally quadratically convergent Newton-type iterations on this constraint manifold. A careful analysis of the underlying geometric constraint is required.

UR - http://www.scopus.com/inward/record.url?scp=21644433176&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:21644433176

SN - 1058-6393

VL - 1

SP - 131

EP - 135

JO - Conference Record of the Asilomar Conference on Signals, Systems and Computers

JF - Conference Record of the Asilomar Conference on Signals, Systems and Computers

T2 - Conference Record of the Thirty-Eighth Asilomar Conference on Signals, Systems and Computers

Y2 - 7 November 2004 through 10 November 2004

ER -

Geometric optimization for 3D pose estimation of quadratic surfaces

Abstract

Other files and links

Fingerprint

Cite this