Conveyor belt edge defect detection method and device, computer equipment, and storage medium

Abstract

The embodiment of the invention discloses a conveyor belt edge defect detection method and device, computer equipment, and a storage medium. The method comprises the steps of: obtaining a picture of a conveyor belt to obtain a to-be-detected picture; performing binarization semantic segmentation on the to-be-detected picture to obtain a semantic segmentation picture containing a conveyor belt region and a background; performing edge straight line detection on the semantic segmentation picture to obtain a parameter equation of a straight line so as to determine a conveyor belt edge reference surface; performing roller detection on the to-be-detected picture to obtain an upper edge roller and a lower edge roller; determining a roller reference surface; determining the conveyor belt edge wear degree according to the roller reference surface, the conveyor belt edge reference surface and the conveyor belt region; warning according to the conveyor belt edge wear degree. By means of the method provided by the embodiment of the invention, the problem that a parameter equation of an edge straight line is not accurate due to edge wear of a conveyor belt can be avoided, edge wear detection is recognized, and the wear degree can be given, so that cost is greatly saved, and deployment steps are simplified.

Description

technical field [0001] The present invention relates to a conveyor belt, more specifically to a conveyor belt edge defect detection method, device, computer equipment and storage medium. Background technique [0002] The edge wear detection of the cargo conveyor belt is a very important part in the inspection of port cargo transportation. However, most of the current detection relies too much on hardware devices such as sensors. These devices are often too expensive and the deployment process is relatively complicated. [0003] The existing detection method uses a photoelectric sensor module, a dedicated sensor module, an RFID module, and a host computer. The damage is detected by the photoelectric sensor, and then the information is transmitted to the host computer. The advantage of this method is that the accuracy and timeliness are relatively high, but due to the addition of hardware, the cost is greatly increased, and once a certain piece of hardware has a problem, the ...

AI Technical Summary

Problems solved by technology

The existing conveyor belt edge reference line uses Hough transform for straight line detection, but this kind of method often causes unevenness due to the wear of the conveyor belt edge, resulting in multiple edges being detected or some The case where the edge cannot be detected

[0004] Therefore, it is necessary to design a new method to avoid the inaccurate parameter equation of the edge line caused by the edge wear of the conveyor belt. It can identify the edge wear detection, and at the same time give the wear degree, which greatly saves Cost and Simplified Deployment Steps

Images