Global Automatic Recognition and Localization of Multi Screws Based on Image Mosaic

In the tuning system based on vision sensor, the object recognition and localization is very important. In order to meet the practical tuning of the microwave cavity filter by the mechanical arm, a global recognition and localization method of multiple adjustable screws is proposed, which combines image mosaic and template matching. A high-definition global image of microwave cavity filter is composed of multiple local images according to feature point registration, and then all adjustable screws in the global image are recognized by template matching algorithm based on shape feature, which solves the problem of limited field of vision of a single industrial camera. It realizes the recognition, localization and numbering of all tuning objects in the whole tuning range, and transmits the coordinate information corresponding to the number to the mechanical arm. This method can be used to tune various types of microwave cavity filters, and it has certain versatility. The experimental results show that the recognition effect of the screws is favorable when the above method is applied to the actual tuning of 12-step microwave cavity filter with the hand-eye integrated four-axis mechanical arm. And it meets the requirements of tuning accuracy.