DocumentCode :
2189718
Title :
Visual inspection and 3D reconstruction based on image-to-mirror planes
Author :
Martins, Nuno ; Dias, Jorge
Author_Institution :
Dept. de Eng. Inf. e de Sistemas, Inst. Superior de Engenharia de Coimbra, Portugal
Volume :
2
fYear :
2000
fDate :
19-22 Jan. 2000
Firstpage :
329
Abstract :
This article addresses the problem of recovering a tridimensional scene from only one uncalibrated static camera and images from planar mirrors. We present a linear solution for 3D Euclidean reconstruction based on multiocular geometry, epipolar geometry and projective geometric properties. From the recovered points of the scene we can obtain information related with distances, areas, curvatures, dimensions and even volumes of its objects. A system based on this technique could be applied on the industry, in tasks of great importance, such as the quality tests and metrology inspection. The system is simple, low cost and could achieve good performance.
Keywords :
automatic optical inspection; image reconstruction; mirrors; 3D Euclidean reconstruction; 3D reconstruction; epipolar geometry; image-to-mirror planes; metrology inspection; multiocular geometry; projective geometric properties; quality tests; tridimensional scene; uncalibrated static camera; visual inspection; Cameras; Computational geometry; Ear; Image reconstruction; Inspection; Layout; Metrology; Mirrors; Robot vision systems; System testing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Industrial Technology 2000. Proceedings of IEEE International Conference on
Print_ISBN :
0-7803-5812-0
Type :
conf
DOI :
10.1109/ICIT.2000.854175
Filename :
854175
Link To Document :
بازگشت