Authors:
Andrei Hossu
and
Daniela Hossu
Affiliation:
University Politehnica of Bucharest, Faculty of Control and Computers, Romania
Keyword(s):
Industrial Vision System, Line-Scan Camera, Dual-Camera Vision System, and Moving Scene in Robotic Automation.
Related
Ontology
Subjects/Areas/Topics:
Informatics in Control, Automation and Robotics
;
Robotics and Automation
;
Vision, Recognition and Reconstruction
Abstract:
The System Set-up Time it is one of the characteristics of an Industrial Vision System, besides the accuracy performances and response time. Minimizing the set-up time while keeping the performances in accuracy and in response time is one of the goals of any advanced Vision System. Starting from the purpose and the required performances of the proposed Industrial Vision System, in the paper is presented a calibration method developed for a multiple line-scan camera Vision System (in particular for a dual line-scan camera system). The calibration method presented is based on analyzing the image of a calibration tool exposed to the Vision System. There are presented the type of dimensional distortions identified from the experimental results. The second part of the paper presents the calibration method. The Industrial Vision System described in the paper is designed for silhouette inspection of planar objects located on a moving scene (transport conveyor), in a robotic handling applica
tion (it is a pure 2D Vision System, the volumetric characteristics of the analyzed objects being not relevant for the application). However the height of the object is varying in time (from one set of objects to another). Due to the fact the distance between the cameras and the objects is changing, the measuring results are affected. The proposed calibration method allows the Vision System to self adjust the calibration parameters for a known change in height of the objects, without affecting the accuracy system performances. In the final section of the paper are presented some practical aspects of the proposed calibration method, and the balance between the off-line and the on-line required computational efforts from the Vision System.
(More)