{"title":"Detection Method of Ore Particle Size Distribution Based on YOLOv5","authors":"Niu Niu, Yongming Wang, Libin Tan","doi":"10.1109/WCMEIM56910.2022.10021430","DOIUrl":null,"url":null,"abstract":"Traditional ore size detection algorithms are mainly machine vision-based ore image segmentation algorithms, which cannot meet the requirements of the industry in terms of accuracy and real-time. Therefore, this paper proposed a deep learning network model based on YOLOv5 for real-time detection of ore particle size. The location of the ore bounding box and its width and height information were output from the YOLOv5 network model, and then the FERET particle size of the ore was extracted. The cumulative error rate between the final particle size distribution detection results and the actual distribution was less than 3%, and the performance was good.","PeriodicalId":202270,"journal":{"name":"2022 5th World Conference on Mechanical Engineering and Intelligent Manufacturing (WCMEIM)","volume":"154 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 5th World Conference on Mechanical Engineering and Intelligent Manufacturing (WCMEIM)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/WCMEIM56910.2022.10021430","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Traditional ore size detection algorithms are mainly machine vision-based ore image segmentation algorithms, which cannot meet the requirements of the industry in terms of accuracy and real-time. Therefore, this paper proposed a deep learning network model based on YOLOv5 for real-time detection of ore particle size. The location of the ore bounding box and its width and height information were output from the YOLOv5 network model, and then the FERET particle size of the ore was extracted. The cumulative error rate between the final particle size distribution detection results and the actual distribution was less than 3%, and the performance was good.