摘要
A high-precision automatic state monitoring and abnormity alarm technique is proposed to solve the process improvement issues of fiber-optic coil winding and splicing. Industrial cameras are used to capture optical and hot images during the assembly of optical components of a fiber-optic gyroscope. A line and contour analysis technique is used to detect abnormal winding. By analyzing the intensity distribution of transmitted light, the graph cut model and multivariate Gaussian mixture model are used to detect and segment the splicing defects. The practical applications indicate the correctness and accuracy of our vision-based technique.
A high-precision automatic state monitoring and abnormity alarm technique is proposed to solve the process improvement issues of fiber-optic coil winding and splicing. Industrial cameras are used to capture optical and hot images during the assembly of optical components of a fiber-optic gyroscope. A line and contour analysis technique is used to detect abnormal winding. By analyzing the intensity distribution of transmitted light, the graph cut model and multivariate Gaussian mixture model are used to detect and segment the splicing defects. The practical applications indicate the correctness and accuracy of our vision-based technique.
基金
supported by the National "973" Program of China under Grant Nos.613186 and 2011CB711000
