Paper Info
Title
Identification and pose under severe occlusion in range images
Abstract
Object recognition may be a hard computer vision task under severe occlusion circumstances. This problem is efficiently solved in this paper through a new 3D recognition method for free-form objects. The technique uses the Depth Gradient Image Based on Silhouette representation (DGI-BS) and settles the problem of identification-pose under occlusion and noise requirements. DGI-BS synthesizes both surface and contour information of an object avoiding restrictions concerning the layout and visibility. Object recognition is carried out by means of a simple matching algorithm in the DGI-BS space which yields a point-to-point correspondence between scene and model. The method has been successfully tested in real scenes under occlusion and noise circumstances.
Year
DOI
Venue
2008
10.1109/ICPR.2008.4761493
Tampa, FL
Keywords
Field
DocType
image matching,image representation,object recognition,3D recognition method,Silhouette representation,computer vision task,depth gradient image,free-form objects,matching algorithm,object recognition,range images,severe occlusion circumstances
Computer vision,Visibility,Occlusion,3D single-object recognition,Pattern recognition,Silhouette,Computer science,Artificial intelligence,Pixel,Statistical classification,Blossom algorithm,Cognitive neuroscience of visual object recognition
Conference
ISSN
ISBN
Citations 
1051-4651 E-ISBN : 978-1-4244-2175-6
978-1-4244-2175-6
2
PageRank 
References 
Authors
0.37
16
4
Name
Order
Citations
PageRank
Pilar Merchán16311.05
Antonio Adán Oliver2121.46
Santiago Salamanca36311.24
Adan, A.420.37