Longitudinal tear early-warning method for conveyor belt based on infrared vision

Longitudinal tear of the conveyor belt is a serious threat to the safe operation of the belt conveyor. To address this problem, a novel approach based on infrared vision for early-warning of longitudinal tearing of the conveyor belt was proposed in the paper. Unlike most existing methods, the proposed approach captures images of the conveyor belt only by one infrared camera and judges whether the conveyor belt is at the risk of longitudinal tearing based on the connected components detection result. The method first performs image filtering, ROI selection and image binarization on the infrared image. Then, it is determined by the number of connected components detection whether the early-warning should be issued. Experimental results exhibit that the average detection accuracy of the longitudinal tear early-warning based on our method can reach 99.19%. The method processes an infrared image for less than 6 ms, which can meet the real-time system requirements. (C) 2019 Elsevier Ltd. All rights reserved.