Medical accessory assembly detection method and device based on deep learning

Abstract

The invention discloses a medical accessory assembly detection method and device based on a CenterNet convolutional neural network model. The method comprises the steps of enabling a camera to collecta material receiving image and synchronize the material receiving image to a processing module, and enabling the processing module to carry out the preprocessing of the material receiving image, enabling the processing module to input the preprocessed material receiving image into a medical accessory conveying target detection network and judging whether the medical accessories reach a material receiving seat or not according to the output target category, enabling the camera to collect a medical accessory image and a catheter port image to the processing module to be preprocessed and then inputting the images as a medical accessory assembly target detection network, and acquiring a target frame and a target category of the medical accessory image and a target frame and a target categoryof the catheter port image respectively, and judging whether the position of the target frame is consistent with a preset real frame position or not. Aiming at the problems that whether materials arein place or not and positioning is difficult in the infusion apparatus medical accessory assembling process, accurate positioning and assembling are achieved, the accuracy of visual inspection is improved, and the production efficiency of products is effectively improved.

Description

technical field [0001] The invention belongs to the technical field of medical equipment and deep learning, and in particular relates to a method and device for assembling and detecting medical accessories based on deep learning. Background technique [0002] During the assembly process of the disposable infusion set, some medical accessories (such as the flow rate regulator) need to pass through the catheter for assembly. Most of the existing infusion set medical accessories assembly technology pre-sets a fixed insertion rod, and then the insertion rod needs to pass through the medical accessories until it reaches the catheter. This method of assembling medical accessories has higher requirements for guiding and positioning. Once there is a position deviation, it is easy to cause the insertion rod to collide with the medical accessories and catheters, thereby damaging the assembly of the infusion set. [0003] Before assembling the medical accessories of the infusion set,...

AI Technical Summary

Problems solved by technology

[0004] One of the objectives of the present invention is to provide a deep learning-based method and device for assembly and detection of medical accessories, so as to solve the high cost of optical fiber detection used in the existing assembly of medical accessories in the background art and the balance requirements during detection by gravity balance method higher question

Images