Distance transform templates for object detection and pose estimation

Stefan Holzer, Stefan Hinterstoisser, Slobodan Ilic, Nassir Navab

Publikation: Beitrag in Buch/Bericht/KonferenzbandKonferenzbeitragBegutachtung

29 Zitate (Scopus)

Abstract

We propose a new approach for detecting low textured planar objects and estimating their 3D pose. Standard matching and pose estimation techniques often depend on texture and feature points. They fail when there is no or only little texture available. Edge-based approaches mostly can deal with these limitations but are slow in practice when they have to search for six degrees of freedom. We overcome these problems by introducing the Distance Transform Templates, generated by applying the distance transform to standard edge based templates. We obtain robustness against perspective transformations by training a classifier for various template poses. In addition, spatial relations between multiple contours on the template are learnt and later used for outlier removal. At runtime, the classifier provides the identity and a rough 3D pose of the Distance Transform Template, which is further refined by a modified template matching algorithm that is also based on the distance transform. We qualitatively and quantitatively evaluate our approach on synthetic and real-life examples and demonstrate robust real-time performance.

OriginalspracheEnglisch
Titel2009 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2009
Herausgeber (Verlag)IEEE Computer Society
Seiten1177-1184
Seitenumfang8
ISBN (Print)9781424439935
DOIs
PublikationsstatusVeröffentlicht - 2009
Veranstaltung2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009 - Miami, FL, USA/Vereinigte Staaten
Dauer: 20 Juni 200925 Juni 2009

Publikationsreihe

Name2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009

Konferenz

Konferenz2009 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2009
Land/GebietUSA/Vereinigte Staaten
OrtMiami, FL
Zeitraum20/06/0925/06/09

Fingerprint

Untersuchen Sie die Forschungsthemen von „Distance transform templates for object detection and pose estimation“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren