Deep learning-based work step specification visual recognition and judgment method and system

Abstract

The invention discloses a step specification visual recognition judgment method and system based on deep learning. The method comprises the steps: obtaining a standard operation video of a worker, extracting a standard operation track in a corresponding monitoring region according to a target detection model, and segmenting the standard operation track into a plurality of steps according to an operation specification; obtaining a current worker operation video, and judging whether the current operation track of the worker in the monitoring area is matched with the standard operation track or not; giving a corresponding judgment result and / or information prompt according to the matching result; the system comprises a video stream receiving module, a client configurator module, a video stream analysis module, a step guide client and a main control computer, according to the embodiment of the invention, the system executes the method, compares the current operation track of the worker with the standard operation track, gives the corresponding judgment result and / or information prompt to guide the operation process of the worker and judge and standardize the operation omission and errors, effectively prevents the operation error problem, and improves the yield.

Description

technical field [0001] The invention relates to the technical field of machine vision, in particular to a method and system for visual recognition and judgment of work step specifications based on deep learning. Background technique [0002] With the development of artificial intelligence technology, in the production operations of the workshop, especially for the manual transfer stations, the initial workers' operations are carried out according to the paper operation instructions, and the traditional paper instructions cannot be intuitive. How to instruct the workers how to work, and it is impossible to detect whether each step of the workers is carried out in accordance with the specifications. Therefore, it has been increasingly unable to meet the process quality management and production index requirements of existing manufacturing production. [0003] At present, the recognition and judgment method that relies on traditional machine vision to standardize the operation...

AI Technical Summary

Problems solved by technology

[0005] The present invention aims at the technical problem that the traditional machine vision method in the prior art extracts the feature value of the collected video image and the recognition accuracy is not high. The present invention provides a method and system for visual recognition and judgment of work step specifications based on deep learning

Images