Defect detection system for mining conveyor belt surface based on reliable region fusion
Aiming at the difficulties in identifying and locating surface defects on mining conveyor belt,a mining conveyor belt surface defect detection system was designed based on reliable region fusion.Firstly,the YOLOv4 and SSD models were trained using public datasets with the transfer learning,and the decision-level fusion method was proposed for defect detection results based on its predicted score and overlapping situation.At the decision level,the two models of YOLOv4 and SSD are fused to maximize reliable regions,which can achieve defect identification and localization of conveyor belt.The effectiveness and reliability of the proposed method were validated and analyzed through public datasets and mining conveyor belt defect datasets.The results illustrated that the proposed method can fully utilize the detection results of YOLOv4 and SSD models to achieve high accuracy,recall,and overlap rates.It can achieve the accuracy rate and overlap rate of over 85%and 0.6,respectively.The defect detection system is beneficial for defect detection and maintenance of mining conveyor belt,and it is significant for safe and reliable operation of the mining belt conveyor.
mining belt conveyordefect detectiondecision-level fusionregion integrationimage detection
NETL
NSTL
万方数据
