A Correlated Parts Model for Object Detection in Large 3D Scans. (6th May 2013)

• Record Type: Journal Article
• Authors: Sunkel, M.; Jansen, S.; Wand, M.; Seidel, H.‐P.
• Is Part Of: Computer graphics forum. Volume 32:Number 2(2013)Part 2
• Page Start: 205
• Page End: 214
• Publication Date: 2013-05-06
• Subjects: Computer Graphics [I.3.5]: Computational Geometry and Object Modeling—Object hierarchies -- Image Processing and Computer Vision [I.4.8]: Scene Analysis—Object recognition -- Artificial Intelligence [I.2.10]: Vision and Scene Understanding—Shape; Computer graphics -- Periodicals; 006.605
• DOI: 10.1111/cgf.12040
• Languages: English
• ISSNs: 0167-7055

Abstract

Abstract: 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.