Object Recognition with Stereo Vision and Geometric Hashing

H.A.L. van Dijck

Research output: ThesisPhD Thesis - Research UT, graduation UTAcademic

36 Downloads (Pure)

Abstract

The subject of this thesis is the automatic recognition of objects from digital images. The discussion is restricted to recognition of man made objects that can be described by deterministic, structural models. Applications of this kind of recognition tasks can be found in industry. Object recognition systems are for example used to inspect products and to equip robots with a detection system that allows them to find and handle objects. The thesis discusses a recognition system that is based on a combination of stereo vision and geometric hashing. This combination enables recognition of 3-D objects in a straightforward and relatively simple manner. The recognition relies on local features detected from the images. The stereo images allow these 2-D features to be combined to 3-D features. The 3-D features are matched to 3-D object models using a 3-D variant of the geometric hashing algorithm.
Original languageUndefined
Supervisors/Advisors
  • Regtien, Paulus P.L., Supervisor
  • Houkes, Z., Advisor
Award date5 Feb 1999
Place of PublicationEnschede
Publisher
Print ISBNs90-3651250-6
Publication statusPublished - 5 Feb 1999

Keywords

  • IR-13757
  • METIS-111328

Cite this

van Dijck, H. A. L. (1999). Object Recognition with Stereo Vision and Geometric Hashing. Enschede: Universiteit Twente.
van Dijck, H.A.L.. / Object Recognition with Stereo Vision and Geometric Hashing. Enschede : Universiteit Twente, 1999. 128 p.
@phdthesis{fbb820b4823644daa0d078d4aa275980,
title = "Object Recognition with Stereo Vision and Geometric Hashing",
abstract = "The subject of this thesis is the automatic recognition of objects from digital images. The discussion is restricted to recognition of man made objects that can be described by deterministic, structural models. Applications of this kind of recognition tasks can be found in industry. Object recognition systems are for example used to inspect products and to equip robots with a detection system that allows them to find and handle objects. The thesis discusses a recognition system that is based on a combination of stereo vision and geometric hashing. This combination enables recognition of 3-D objects in a straightforward and relatively simple manner. The recognition relies on local features detected from the images. The stereo images allow these 2-D features to be combined to 3-D features. The 3-D features are matched to 3-D object models using a 3-D variant of the geometric hashing algorithm.",
keywords = "IR-13757, METIS-111328",
author = "{van Dijck}, H.A.L.",
year = "1999",
month = "2",
day = "5",
language = "Undefined",
isbn = "90-3651250-6",
publisher = "Universiteit Twente",

}

Object Recognition with Stereo Vision and Geometric Hashing. / van Dijck, H.A.L.

Enschede : Universiteit Twente, 1999. 128 p.

Research output: ThesisPhD Thesis - Research UT, graduation UTAcademic

TY - THES

T1 - Object Recognition with Stereo Vision and Geometric Hashing

AU - van Dijck, H.A.L.

PY - 1999/2/5

Y1 - 1999/2/5

N2 - The subject of this thesis is the automatic recognition of objects from digital images. The discussion is restricted to recognition of man made objects that can be described by deterministic, structural models. Applications of this kind of recognition tasks can be found in industry. Object recognition systems are for example used to inspect products and to equip robots with a detection system that allows them to find and handle objects. The thesis discusses a recognition system that is based on a combination of stereo vision and geometric hashing. This combination enables recognition of 3-D objects in a straightforward and relatively simple manner. The recognition relies on local features detected from the images. The stereo images allow these 2-D features to be combined to 3-D features. The 3-D features are matched to 3-D object models using a 3-D variant of the geometric hashing algorithm.

AB - The subject of this thesis is the automatic recognition of objects from digital images. The discussion is restricted to recognition of man made objects that can be described by deterministic, structural models. Applications of this kind of recognition tasks can be found in industry. Object recognition systems are for example used to inspect products and to equip robots with a detection system that allows them to find and handle objects. The thesis discusses a recognition system that is based on a combination of stereo vision and geometric hashing. This combination enables recognition of 3-D objects in a straightforward and relatively simple manner. The recognition relies on local features detected from the images. The stereo images allow these 2-D features to be combined to 3-D features. The 3-D features are matched to 3-D object models using a 3-D variant of the geometric hashing algorithm.

KW - IR-13757

KW - METIS-111328

M3 - PhD Thesis - Research UT, graduation UT

SN - 90-3651250-6

PB - Universiteit Twente

CY - Enschede

ER -

van Dijck HAL. Object Recognition with Stereo Vision and Geometric Hashing. Enschede: Universiteit Twente, 1999. 128 p.