An Automated Inspection System |
| |
| Authors: | F. Prieto T. Redarce R. Lepage P. Boulanger |
| |
| Affiliation: | (1) Universidad Nacional de Colombia Sede Manizales, Grupo de Percepción y Control Inteligente. Manizales (Caldas), Colombia, CO;(2) INSA, Laboratoire d’Automatique Industrielle, 20 avenue Albert Einstein, Cedex, France, FR;(3) éTS, Laboratoire d’Imagerie, de Vision et d’Intelligence Artificielle, 1100 rue Notre-Dame Ouest, Montréal, Québec, Canada, CA;(4) University of Alberta, Department of Computing Science, 2–21 Athabasca Hall, Edmonton, Alberta, Canada, CA |
| |
| Abstract: | An automated inspection system for manufactured parts is proposed using a cloud of 3D measured points of a part provided by a range sensor, and its CAD model. In spite of the high precision attained by coordinate measuring machines (CMM), range sensors offer significant advantages for dimensional inspection: a high speed of digitisation and the capacity to take 3D measurements on the whole surfaces of a part without physical contact. The system first registers a cloud of 3D points with a CAD model of the part, then segments the 3D points in different surfaces by using the CAD model, and finally measures the control of the specified tolerances on the part. Results of the inspection are displayed in two ways: visually, using a colour map to display the level of discrepancy between the measured points and the CAD model, and a hardcopy report of the evaluation results of the tolerance specifications. Two range sensor technologies have been tested and inspection results are compared with the results obtained with a CMM. |
| |
| Keywords: | : CAD based vision Inspection Range image Registration Segmentation |
| 本文献已被 SpringerLink 等数据库收录！ |
|
