Object recognition from range images using superquadric representations

Erik van Dop; Paul Regtien

Object recognition from range images using superquadric representations

Erik van Dop
, Paul Regtien

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

4 Citations (Scopus)

29 Downloads (Pure)

Abstract

Segmentation of range images using superquadric entities has been pointed out by a number of researchers as a powerful approach towards object recognition. Problems exist in finding an unbiased decision function for the assignment of a superquadric representation with an object prototype. This paper discusses current distance measures between recovered models and prototypes and presents a novel method for classification of uncertain superquadric representations using a maximum likelihood criterium and incorporating the range image characteristics of an active optical triangulation sensor. The main advantage of this probabilistic method is its inherent minimisation of the classification error rate. The approach is applied to recognition of electronic components for printed circuit board waste management.

Original language	English
Title of host publication	Proceedings of MVA '96
Subtitle of host publication	IAPR Workshop on Machine Vision Applications : November 12-14 1996, Tokyo, Japan
Place of Publication	Tokyo, Japan
Publisher	Keio University
Pages	267-270
Publication status	Published - 12 Nov 1996
Event	IAPR Workshop on Machine Vision Applications, MVA 1996 - Tokyo, Japan Duration: 12 Nov 1996 → 14 Nov 1996

Workshop

Workshop	IAPR Workshop on Machine Vision Applications, MVA 1996
Country/Territory	Japan
City	Tokyo
Period	12/11/96 → 14/11/96

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 12 Responsible Consumption and Production

Keywords

METIS-113418

Access to Document

VanDop1996objectFinal published version, 855 KB

Cite this

@inproceedings{9fc4207ad9684c0ab39370c74f9f177d,

title = "Object recognition from range images using superquadric representations",

abstract = "Segmentation of range images using superquadric entities has been pointed out by a number of researchers as a powerful approach towards object recognition. Problems exist in finding an unbiased decision function for the assignment of a superquadric representation with an object prototype. This paper discusses current distance measures between recovered models and prototypes and presents a novel method for classification of uncertain superquadric representations using a maximum likelihood criterium and incorporating the range image characteristics of an active optical triangulation sensor. The main advantage of this probabilistic method is its inherent minimisation of the classification error rate. The approach is applied to recognition of electronic components for printed circuit board waste management.",

keywords = "METIS-113418",

author = "\{van Dop\}, Erik and Paul Regtien",

year = "1996",

month = nov,

day = "12",

language = "English",

pages = "267--270",

booktitle = "Proceedings of MVA '96",

publisher = "Keio University",

address = "Japan",

note = "IAPR Workshop on Machine Vision Applications, MVA 1996 ; Conference date: 12-11-1996 Through 14-11-1996",

}

Object recognition from range images using superquadric representations. / van Dop, Erik; Regtien, Paul.
Proceedings of MVA '96 : IAPR Workshop on Machine Vision Applications : November 12-14 1996, Tokyo, Japan. Tokyo, Japan: Keio University, 1996. p. 267-270.

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

TY - GEN

T1 - Object recognition from range images using superquadric representations

AU - van Dop, Erik

AU - Regtien, Paul

PY - 1996/11/12

Y1 - 1996/11/12

N2 - Segmentation of range images using superquadric entities has been pointed out by a number of researchers as a powerful approach towards object recognition. Problems exist in finding an unbiased decision function for the assignment of a superquadric representation with an object prototype. This paper discusses current distance measures between recovered models and prototypes and presents a novel method for classification of uncertain superquadric representations using a maximum likelihood criterium and incorporating the range image characteristics of an active optical triangulation sensor. The main advantage of this probabilistic method is its inherent minimisation of the classification error rate. The approach is applied to recognition of electronic components for printed circuit board waste management.

AB - Segmentation of range images using superquadric entities has been pointed out by a number of researchers as a powerful approach towards object recognition. Problems exist in finding an unbiased decision function for the assignment of a superquadric representation with an object prototype. This paper discusses current distance measures between recovered models and prototypes and presents a novel method for classification of uncertain superquadric representations using a maximum likelihood criterium and incorporating the range image characteristics of an active optical triangulation sensor. The main advantage of this probabilistic method is its inherent minimisation of the classification error rate. The approach is applied to recognition of electronic components for printed circuit board waste management.

KW - METIS-113418

M3 - Conference contribution

SP - 267

EP - 270

BT - Proceedings of MVA '96

PB - Keio University

CY - Tokyo, Japan

T2 - IAPR Workshop on Machine Vision Applications, MVA 1996

Y2 - 12 November 1996 through 14 November 1996

ER -

Object recognition from range images using superquadric representations

Abstract

Workshop

UN SDGs

Keywords

Access to Document

Fingerprint

Cite this