An Intelligent Detection Method for Conveyor Belt Deviation State Based on Machine Vision

Abstract

To address the shortcomings of existing conveyor belt deviation detection methods, such as poor fault location accuracy, a low automation level and low reliability, a method that utilizes machine vision technology to detect belt deviations in belt conveyors is proposed. This method involves preprocessing operations on captured video images, including Region of Interest (ROI) extraction, grayscale processing, and noise reduction, thereby eliminating image noise and interference. To address the edge blurring due to Gaussian filtering and threshold setting issues in Canny detection, an enhanced edge detection technique using a guided filter and the Otsu method modifies the traditional Canny operator is introduced. Subsequent application of Hough Transform and least squares fitting processes delineate the edges of the conveyor belt and its rollers during operation. Utilizing the detected edges of the conveyor belt and rollers as references, a dual-baseline positioning method is for the first time proposed to quantify the deviation degree, facilitating the identification of deviation faults. After detection with the improved Canny algorithm, clearer contour binary images with fewer noise and impurities were obtained. Experiments conducted on images from various deviation scenarios yielded an average detection accuracy of 95.4% and a detection speed of 26 frames per second (FPS). This approach not only enhances the detection speed and accuracy but also reduces the frequency of conveyor belt failures and improves the operational efficiency of belt conveyors.