The key problem in automatic shoe upper spraying system is how to get a reliable trajectory for spraying. To extract information of shoe upper and generate the trajectory for shoe upper spraying quickly, a method based on computer vision with structured light is described. After scanning a shoe lasted upper with the sensor of structured light and CCD camera, basic information of shoe upper rendered by three-dimensional point-cloud, which are located on the underside of shoe upper, can be extracted. To render the underside of shoe upper more obviously, 3D scan curves and a closed contour line are interpolated as B-spline curves. After approximately calculating the offset curve of contour line on the underside of shoe upper, the trajectory for shoe upper spraying could be generated. According to the above mentioned method, an experimental facility system is constructed and corresponding software is developed. Results show that the trajectory can be generated quickly and steadily. Moreover, the trajectory is successfully applied in a shoe upper spraying system with Staubli industrial robot. Thus, this method is validated effectively and feasibly.
[1]
M.A.G. Izquierdo,et al.
Sub-pixel measurement of 3D surfaces by laser scanning
,
1999
.
[2]
J. Y. Kim.
CAD-based automated robot programming in adhesive spray systems for shoe outsoles and uppers
,
2004,
J. Field Robotics.
[3]
Guangjun Zhang,et al.
A novel calibration approach to structured light 3D vision inspection
,
2002
.
[4]
Roger Y. Tsai,et al.
A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf TV cameras and lenses
,
1987,
IEEE J. Robotics Autom..
[5]
Zhongxu Hu,et al.
Computer vision for shoe upper profile measurement via upper and sole conformal matching
,
2007
.
[6]
Zhengyou Zhang,et al.
A Flexible New Technique for Camera Calibration
,
2000,
IEEE Trans. Pattern Anal. Mach. Intell..