Paper Info
Title
Fast and Robust Bore Detection in Range Image Data for Industrial Automation
Abstract
This paper presents a fast and robust method to precisely segment and locate bore holes of 4 to 50mm diameter. The task is solved by a robot moving a compact triangulation scanning sensor to all sides of the object and scanning the bore holes. Exploiting the knowledge about the expected bore diameter and bore pose makes it possible to develop highly robust algorithms for an industrial application. Sparse data of the bore hole is sufficient to segment the bore independent of bore hole chamfer type using a robust normal vector fit and a classification based on the Gaussian image. A sequential algorithm to fit the bore cylinder makes it possible to calculate the bore pose in less than 1 second. Experiments demonstrate that 120 degrees of the bore hole surface are sufficient for robust localization within 0.3mm and 0.5 degrees even in the presence of ghost points and notches in the bore holes.
Year
DOI
Venue
2004
10.1109/3DPVT.2004.60
3DPVT
Keywords
Field
DocType
automatic optical inspection,factory automation,image classification,image segmentation,image sensors,industrial robots,Gaussian image,bore detection,industrial automation,normal vector fit,range image data,sequential algorithm,triangulation scanning sensor
Computer vision,Image sensor,Computer science,Cylinder,Chamfer,Image segmentation,Triangulation (social science),Gaussian,Artificial intelligence,Sequential algorithm,Normal
Conference
ISBN
Citations 
PageRank 
0-7695-2223-8
1
0.37
References 
Authors
0
2
Name
Order
Citations
PageRank
Georg Biegelbauer1667.04
Markus Vincze21343136.87