Research on conveyor belt deviation detection method based on machine vision

Abstract

Abstract This study aims to identify the conveyor belt deviation. It presents a machine vision-based detection approach that uses the coordinates of the crossing point between the conveyor belt centerline and the laser line to determine whether the deviation fault occurs. In order to avoid the influence of the defects of the traditional Canny operator, an improved Canny edge detection algorithm combining hybrid filter and maximum inter-class variance method (OTSU) is used. Then the Hough transform is used to detect the straight line of the edge detected image and extract the laser centerline with the centerline extraction algorithm; finally, the Shi-Tomasi operator is used to detect the corners to get the intersection of the edge line and the laser line. The slope and center coordinates of the conveyor belt edges are calculated to determine whether the conveyor belt has run-off faults and calculate the offset amount. The results show that the proposed method can accurately determine the conveyor belt deviation and calculate the deviation amount.