Conveyor belt longitudinal tearing detection method and device based on machine vision

The invention provides a conveyor belt longitudinal tear detection method and device based on machine vision, and the method comprises the steps: obtaining a conveyor belt image which comprises 2D information and 3D information of a conveyor belt; extracting and separating the conveyor belt image to obtain a conveyor belt 2D information image and a conveyor belt 3D information image; according to the conveying belt 2D information image and the conveying belt 3D information image, judging whether the conveying belt has defects or not ; if the conveyor belt has the defect, judging whether the defect is longitudinal tearing or not according to the conveyor belt 2D information image and the conveyor belt 3D information image; and if the defect is longitudinal tearing, calculating and outputting information data corresponding to the longitudinal tearing. According to the method, the 3D information image and the 2D information image of the conveying belt are combined, whether the longitudinal tearing defect occurs