Sensing And Recognition Of Rigid Objects Using Structured Light

George C. Stockman, Sei-Wang Chen, Gongzhu Hu, Neelima Shrikhande

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

Work directed toward the development of a vision system for bin picking rigid threedimensional (3-D) objects is reported. Any such system must have components for sensing, feature extraction, modeling, and matching. A structured light system for 3-D sensing and feature extraction, which attempts to deliver a rich 2–D representation of the scene, is described. Surface patches are evident as connected sets of stripes whose 3-D coordinates are computed via triangulation and constraint propagation across the stripe network. Object edges are detected via intersection of surface patches or by backprojecting image edges to intersect with patches in the 3-D space. Two matching paradigms are given for drawing correspondence between structures in the scene representation and structures in models. Three major contributions are contained in the work. First, original work is given for sensing object surface patches without having to uniquely solve for stripe labels. Second, use of both an intensity image and a striped image allows detected edges to be used along with 3-D surface patches to represent the scene. Finally, a pose clustering algorithm offers a uniform technique to accumulate matching evidence for recognition while, at the same time, averaging out substantial errors of pose computed from individual feature matches.

Original languageEnglish
Pages (from-to)14-22
Number of pages9
JournalIEEE Control Systems Magazine
Volume8
Issue number3
DOIs
Publication statusPublished - 1988 Jan 1

Fingerprint

Structured Light
Patch
Sensing
3D
Feature extraction
Feature Extraction
Bins
Triangulation
Constraint Propagation
Clustering algorithms
Connected Set
Labels
Vision System
Accumulate
Intersect
Clustering Algorithm
Averaging
Correspondence
Intersection
Paradigm

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Modelling and Simulation
  • Electrical and Electronic Engineering

Cite this

Sensing And Recognition Of Rigid Objects Using Structured Light. / Stockman, George C.; Chen, Sei-Wang; Hu, Gongzhu; Shrikhande, Neelima.

In: IEEE Control Systems Magazine, Vol. 8, No. 3, 01.01.1988, p. 14-22.

Research output: Contribution to journalArticle

Stockman, George C. ; Chen, Sei-Wang ; Hu, Gongzhu ; Shrikhande, Neelima. / Sensing And Recognition Of Rigid Objects Using Structured Light. In: IEEE Control Systems Magazine. 1988 ; Vol. 8, No. 3. pp. 14-22.
@article{7f2305d340154f1183e9545bcca8724f,
title = "Sensing And Recognition Of Rigid Objects Using Structured Light",
abstract = "Work directed toward the development of a vision system for bin picking rigid threedimensional (3-D) objects is reported. Any such system must have components for sensing, feature extraction, modeling, and matching. A structured light system for 3-D sensing and feature extraction, which attempts to deliver a rich 2–D representation of the scene, is described. Surface patches are evident as connected sets of stripes whose 3-D coordinates are computed via triangulation and constraint propagation across the stripe network. Object edges are detected via intersection of surface patches or by backprojecting image edges to intersect with patches in the 3-D space. Two matching paradigms are given for drawing correspondence between structures in the scene representation and structures in models. Three major contributions are contained in the work. First, original work is given for sensing object surface patches without having to uniquely solve for stripe labels. Second, use of both an intensity image and a striped image allows detected edges to be used along with 3-D surface patches to represent the scene. Finally, a pose clustering algorithm offers a uniform technique to accumulate matching evidence for recognition while, at the same time, averaging out substantial errors of pose computed from individual feature matches.",
author = "Stockman, {George C.} and Sei-Wang Chen and Gongzhu Hu and Neelima Shrikhande",
year = "1988",
month = "1",
day = "1",
doi = "10.1109/37.472",
language = "English",
volume = "8",
pages = "14--22",
journal = "IEEE Control Systems",
issn = "1066-033X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

TY - JOUR

T1 - Sensing And Recognition Of Rigid Objects Using Structured Light

AU - Stockman, George C.

AU - Chen, Sei-Wang

AU - Hu, Gongzhu

AU - Shrikhande, Neelima

PY - 1988/1/1

Y1 - 1988/1/1

N2 - Work directed toward the development of a vision system for bin picking rigid threedimensional (3-D) objects is reported. Any such system must have components for sensing, feature extraction, modeling, and matching. A structured light system for 3-D sensing and feature extraction, which attempts to deliver a rich 2–D representation of the scene, is described. Surface patches are evident as connected sets of stripes whose 3-D coordinates are computed via triangulation and constraint propagation across the stripe network. Object edges are detected via intersection of surface patches or by backprojecting image edges to intersect with patches in the 3-D space. Two matching paradigms are given for drawing correspondence between structures in the scene representation and structures in models. Three major contributions are contained in the work. First, original work is given for sensing object surface patches without having to uniquely solve for stripe labels. Second, use of both an intensity image and a striped image allows detected edges to be used along with 3-D surface patches to represent the scene. Finally, a pose clustering algorithm offers a uniform technique to accumulate matching evidence for recognition while, at the same time, averaging out substantial errors of pose computed from individual feature matches.

AB - Work directed toward the development of a vision system for bin picking rigid threedimensional (3-D) objects is reported. Any such system must have components for sensing, feature extraction, modeling, and matching. A structured light system for 3-D sensing and feature extraction, which attempts to deliver a rich 2–D representation of the scene, is described. Surface patches are evident as connected sets of stripes whose 3-D coordinates are computed via triangulation and constraint propagation across the stripe network. Object edges are detected via intersection of surface patches or by backprojecting image edges to intersect with patches in the 3-D space. Two matching paradigms are given for drawing correspondence between structures in the scene representation and structures in models. Three major contributions are contained in the work. First, original work is given for sensing object surface patches without having to uniquely solve for stripe labels. Second, use of both an intensity image and a striped image allows detected edges to be used along with 3-D surface patches to represent the scene. Finally, a pose clustering algorithm offers a uniform technique to accumulate matching evidence for recognition while, at the same time, averaging out substantial errors of pose computed from individual feature matches.

UR - http://www.scopus.com/inward/record.url?scp=0024033945&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024033945&partnerID=8YFLogxK

U2 - 10.1109/37.472

DO - 10.1109/37.472

M3 - Article

AN - SCOPUS:0024033945

VL - 8

SP - 14

EP - 22

JO - IEEE Control Systems

JF - IEEE Control Systems

SN - 1066-033X

IS - 3

ER -