Multi-scene visual detection system for fuse box

Abstract

The invention discloses a multi-scene visual detection system for a fuse box, and the system comprises an industrial camera which is installed in a camera obscura and triggers photographing through aninfrared photoelectric switch, and a to-be-detected single board passes through the camera obscura. The infrared photoelectric switch triggers photographing respectively including photographing a front view and a rear view of the fuse box and a top view; during detection, the single board moves along with the conveying belt to block infrared rays emitted by the infrared photoelectric switch perpendicular to the movement direction of the single board, and the industrial camera is triggered to shoot pictures. The industrial camera sends collected pictures to the computer; visual detection software arranged in the computer is used for carrying out picture identification and comparison on the shot picture and a preset template picture serving as a standard; if the comparison result conforms to the preset error range, the visual inspection of the single board is considered to be qualified, and the inspection of the next fuse box single board is carried out; If he comparison result does notconform to the preset error range, alert is issued and the content beyond the error range is displayed on a computer display device. According to the invention, the fault part can be found in an assisting manner, and the product percent of pass is improved.

Description

technical field [0001] The invention relates to the field of computer vision recognition, in particular to a multi-scene fuse box vision detection system. Background technique [0002] Computer vision recognition is often regarded as a branch of artificial intelligence and computer science, and it is currently widely deployed and used in various industries. And these recognitions need to be in a specific environment with specified lighting, background and target pose requirements. Therefore, in practice, due to the limitations of the complexity of the detected object, external environment and cost, it is not too easy to achieve the expected detection goal. By increasing the performance of the camera, making the physical movement uniform, applying eye-catching colors or shapes to the detection target, and requiring ideal conditions in the surrounding environment, the difficulty of visual recognition can be reduced and the accuracy rate can be improved. In the process of mas...

AI Technical Summary

Problems solved by technology

In this method, only a framework is mentioned for the process of visual recognition, without more details, which is not conducive to popularization and use

Images