CVGIP: Image Understanding
Machine Vision: Theory, Algorithms, Practicalities
Machine Vision: Theory, Algorithms, Practicalities
A New Kalman-Filter-Based Framework for Fast and Accurate Visual Tracking of Rigid Objects
IEEE Transactions on Robotics
Bayesian modeling of the risk of non-repeatability for the networked robotic system
Computers and Industrial Engineering
Improvement of vision guided robotic accuracy using Kalman filter
Computers and Industrial Engineering
| Hi-index | 0.00 |
EQM integrates a host of advanced technologies to attain a holistic quality control strategy at each stage of the production processes. This differentiates it from conventional quality control practices. A critical problem in EQM is the inaccuracies in vision guided robotic positioning control, especially when the production equipment is situated remotely and controlled over the network. Such a situation introduces many variations in the process that are difficult to control or to eliminate (e.g., network delay, and lens distortion effects). This study applies Kalman Filtering techniques to overcome the shortcomings in the mathematical modeling of vision calibration, in which mathematical equations fail to address the dynamic state of the process. The Kalman Filtering techniques developed in this study effectively reduce the errors in the positioning accuracy of vision-generated robotic control. The Kalman Filtering techniques prove to be a valuable location estimation algorithm for remote robotic control, even when the data contain noise inherent in vision calibration and network-based communication. Experiments validate the proposed scheme; it significantly enhances the accuracy of vision-guided robotic control.