Intelligent data acquisition mode based on computer vision

Abstract

An intelligent data acquisition mode based on computer vision comprises the following steps: (1) image pre-acquisition; (2) image feature matching; (3) character recognition; (4) data acquisition software intervention; (5) system debugging. According to the method, an image feature matching algorithm is utilized to locate a character area needing to be acquired in an image, and then a crnn algorithm is utilized to identify characters, so that acquisition of test bed data is realized. According to the method, an original test bed does not need to be changed, the production process is not affected, only a camera needs to be erected in front of a test bed to be used for collecting test bed image information, an image processing server and a camera are added to form a local area network for image processing, and development software can control data collection of a production field according to the technological process.

Description

technical field [0001] The invention relates to an intelligent data collection method based on computer vision. Background technique [0002] In industrial production sites, there are a large number of test benches that undertake various experimental tasks. Many test benches are not highly informatized and cannot export test data. The records of test data are manually filled in by operators. The cost of upgrading and transforming the entire test bench equipment is high, and the existing equipment can be used normally. Directly upgrading the equipment will cause a great waste of resources, and the construction and transformation on site will also affect the production progress. Contents of the invention [0003] The purpose of the present invention is to solve the above deficiencies in the prior art, and proposes a computer vision-based intelligent data collection method, [0004] An intelligent data acquisition method based on computer vision, comprising the following ste...

AI Technical Summary

Problems solved by technology

[0002] In industrial production sites, there are a large number of test benches that undertake various experimental tasks. Many test benches are not highly informatized and cannot export test data. The records of test data are manually filled in by operators. The cost of upgrading the entire test bench equipment is high, and the existing equipment can be used normally. Directly upgrading the equipment will cause a great waste of resources, and the construction and transformation on site will also affect the production progress

Images