{"title":"基于图像识别方法的超高性能混凝土板纤维空间数量分布研究","authors":"Xueming Fan, Kun Zhao, Honglin Wu, Xiangdong Sun, Yuquan Ma, Jiabo Xu, Chunhua Chen, Yueqiang Tian","doi":"10.1177/13694332241263867","DOIUrl":null,"url":null,"abstract":"In this paper, the detection of fiber distribution in six UHPC slabs with fiber content of 1%, 2%, 3%, and horizontal pouring and vertical pouring is studied by image recognition method. The results show that: firstly, the fiber distribution can be identified by a series of processing steps, such as grayscale and binarization of fiber source image, extraction of initial detection area, extraction of fiber contour and segmentation of fiber adhesion area. Furthermore, it is proposed that the scaling curve of n-e detection area per pixel of fiber number can anchor the effective recognition area range of fiber. Secondly, the statistical analysis of the identification results can visually draw the fiber distribution maps of different types of UHPC slabs in different directions, and quantitatively characterize the fiber distribution uniformity of UHPC slabs by quoting the evaluation index of fiber distribution coefficient. Finally, the cross-sectional fiber Scatter Density Plot can perceptually show the degree of fiber dispersion and its position distribution. The more uniform the color, the more uniform the fiber distribution in the cross-section of the specimen.","PeriodicalId":50849,"journal":{"name":"Advances in Structural Engineering","volume":"44 1","pages":""},"PeriodicalIF":2.1000,"publicationDate":"2024-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Research on the spatial quantity distribution of fibers in ultra high performance concrete slabs based on image recognition method\",\"authors\":\"Xueming Fan, Kun Zhao, Honglin Wu, Xiangdong Sun, Yuquan Ma, Jiabo Xu, Chunhua Chen, Yueqiang Tian\",\"doi\":\"10.1177/13694332241263867\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper, the detection of fiber distribution in six UHPC slabs with fiber content of 1%, 2%, 3%, and horizontal pouring and vertical pouring is studied by image recognition method. The results show that: firstly, the fiber distribution can be identified by a series of processing steps, such as grayscale and binarization of fiber source image, extraction of initial detection area, extraction of fiber contour and segmentation of fiber adhesion area. Furthermore, it is proposed that the scaling curve of n-e detection area per pixel of fiber number can anchor the effective recognition area range of fiber. Secondly, the statistical analysis of the identification results can visually draw the fiber distribution maps of different types of UHPC slabs in different directions, and quantitatively characterize the fiber distribution uniformity of UHPC slabs by quoting the evaluation index of fiber distribution coefficient. Finally, the cross-sectional fiber Scatter Density Plot can perceptually show the degree of fiber dispersion and its position distribution. The more uniform the color, the more uniform the fiber distribution in the cross-section of the specimen.\",\"PeriodicalId\":50849,\"journal\":{\"name\":\"Advances in Structural Engineering\",\"volume\":\"44 1\",\"pages\":\"\"},\"PeriodicalIF\":2.1000,\"publicationDate\":\"2024-07-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Advances in Structural Engineering\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1177/13694332241263867\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"CONSTRUCTION & BUILDING TECHNOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Advances in Structural Engineering","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1177/13694332241263867","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CONSTRUCTION & BUILDING TECHNOLOGY","Score":null,"Total":0}
Research on the spatial quantity distribution of fibers in ultra high performance concrete slabs based on image recognition method
In this paper, the detection of fiber distribution in six UHPC slabs with fiber content of 1%, 2%, 3%, and horizontal pouring and vertical pouring is studied by image recognition method. The results show that: firstly, the fiber distribution can be identified by a series of processing steps, such as grayscale and binarization of fiber source image, extraction of initial detection area, extraction of fiber contour and segmentation of fiber adhesion area. Furthermore, it is proposed that the scaling curve of n-e detection area per pixel of fiber number can anchor the effective recognition area range of fiber. Secondly, the statistical analysis of the identification results can visually draw the fiber distribution maps of different types of UHPC slabs in different directions, and quantitatively characterize the fiber distribution uniformity of UHPC slabs by quoting the evaluation index of fiber distribution coefficient. Finally, the cross-sectional fiber Scatter Density Plot can perceptually show the degree of fiber dispersion and its position distribution. The more uniform the color, the more uniform the fiber distribution in the cross-section of the specimen.
期刊介绍:
Advances in Structural Engineering was established in 1997 and has become one of the major peer-reviewed journals in the field of structural engineering. To better fulfil the mission of the journal, we have recently decided to launch two new features for the journal: (a) invited review papers providing an in-depth exposition of a topic of significant current interest; (b) short papers reporting truly new technologies in structural engineering.