Research on the workpiece sorting system based on visual recognition
Fei Lv, Zhuang Yang, Hongmei Ouyang, Chang’an Hu · International Conference on Mechanisms and Robotics (ICMAR 2022) · 2022
Aiming at the characteristics of high intensity and low efficiency of manual sorting of irregular shaped workpieces, a workpiece sorting system based on visual recognition was studied in this paper. A new sorting system based on ROS robot system in Linux environment is proposed. Machine vision technology and ROS method are used in the intelligent sorting of common shape geometry. Firstly, considering the characteristics of large amount of operation and high flexibility of workpiece sorting, the Baxter dual arm robot was selected as the hardware device, an experimental platform for workpiece sorting was constructed. Secondly, the template matching method based on edge information detection realizes image acquisition and processes the collected image to solve the difficult problem of workpiece recognition caused by large background noise and low image feature contrast, Open cv combined with VC + + was used to realize the design of visual program and the motion control function of actuator. The simulation results show that the workpiece sorting method based on visual recognition technology has the characteristics of fast timeliness, strong flexibility and high stability, and can be applied to the rapid sorting of irregular parts.