A Correlated Parts Model for Object Detection in Large 3D Scans

This paper addresses the problem of detecting objects in 3D scans according to object classes learned from sparse user annotation. We model objects belonging to a class by a set of fully correlated parts, encoding dependencies between local shapes of different parts as well as their relative spatial...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Computer graphics forum Ročník 32; číslo 2pt2; s. 205 - 214
Hlavní autori:	Sunkel, M., Jansen, S., Wand, M., Seidel, H.-P.
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Oxford, UK Blackwell Publishing Ltd 01.05.2013
Predmet:	3-D graphics Algorithms Analysis Approximation Artificial Intelligence [I.2.10]: Vision and Scene Understanding-Shape Composite structures Computer graphics Computer Graphics [I.3.5]: Computational Geometry and Object Modeling-Object hierarchies Correlation Image Processing and Computer Vision [I.4.8]: Scene Analysis-Object recognition Image processing systems Inference Studies Three dimensional Training
ISSN:	0167-7055, 1467-8659
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	This paper addresses the problem of detecting objects in 3D scans according to object classes learned from sparse user annotation. We model objects belonging to a class by a set of fully correlated parts, encoding dependencies between local shapes of different parts as well as their relative spatial arrangement. For an efficient and comprehensive retrieval of instances belonging to a class of interest, we introduce a new approximate inference scheme and a corresponding planning procedure. We extend our technique to hierarchical composite structures, reducing training effort and modeling spatial relations between detected instances. We evaluate our method on a number of real‐world 3D scans and demonstrate its benefits as well as the performance of the new inference algorithm.
Bibliografia:	ark:/67375/WNG-XLM99MHJ-9 istex:F607F34F3F019FD69FA6947B749B75BA85F5BCCF ArticleID:CGF12040 SourceType-Scholarly Journals-1 ObjectType-Feature-1 content type line 14 ObjectType-Article-2 content type line 23
ISSN:	0167-7055 1467-8659
DOI:	10.1111/cgf.12040