G. Stępień, Artur Kujawski, A. Tomczak, R. Hałaburda, K. Borczyk
{"title":"基于工业相机影像的内河航运不完全时空数据改进方法——以西奥得河为例","authors":"G. Stępień, Artur Kujawski, A. Tomczak, R. Hałaburda, K. Borczyk","doi":"10.2478/ttj-2022-0005","DOIUrl":null,"url":null,"abstract":"Abstract Main aim of the paper is to use a single non-metric camera to support the determination of the position of. Authors propose to use the existing infrastructure of CCTV cameras mounted on bridges and wharves to determine the position of inland waterway vessels. Image from cameras giving the pixel coordinates of moving object is transformed to the geodetic data domain using a modified projective transformation method. Novel approach is to use of Sequential Projection Transformation (SPT) which additionally uses virtual reference points. The transformation coefficients calculated using the virtual points are used to determine the position of the vessels and are also simultaneously used to calibrate the industrial camera. The method has been verified under real conditions, and the results obtained are average 30% more accurate compared to the traditionally used projective transformation using a small number of real points.","PeriodicalId":44110,"journal":{"name":"Transport and Telecommunication Journal","volume":"65 1","pages":"48 - 61"},"PeriodicalIF":1.1000,"publicationDate":"2022-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Method of Improving Incomplete Spatial-Temporal Data in Inland Navigation, on the Basis of Industrial Camera Images – West Oder River Case Study\",\"authors\":\"G. Stępień, Artur Kujawski, A. Tomczak, R. Hałaburda, K. Borczyk\",\"doi\":\"10.2478/ttj-2022-0005\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract Main aim of the paper is to use a single non-metric camera to support the determination of the position of. Authors propose to use the existing infrastructure of CCTV cameras mounted on bridges and wharves to determine the position of inland waterway vessels. Image from cameras giving the pixel coordinates of moving object is transformed to the geodetic data domain using a modified projective transformation method. Novel approach is to use of Sequential Projection Transformation (SPT) which additionally uses virtual reference points. The transformation coefficients calculated using the virtual points are used to determine the position of the vessels and are also simultaneously used to calibrate the industrial camera. The method has been verified under real conditions, and the results obtained are average 30% more accurate compared to the traditionally used projective transformation using a small number of real points.\",\"PeriodicalId\":44110,\"journal\":{\"name\":\"Transport and Telecommunication Journal\",\"volume\":\"65 1\",\"pages\":\"48 - 61\"},\"PeriodicalIF\":1.1000,\"publicationDate\":\"2022-02-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Transport and Telecommunication Journal\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.2478/ttj-2022-0005\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"TRANSPORTATION SCIENCE & TECHNOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Transport and Telecommunication Journal","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2478/ttj-2022-0005","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"TRANSPORTATION SCIENCE & TECHNOLOGY","Score":null,"Total":0}
Method of Improving Incomplete Spatial-Temporal Data in Inland Navigation, on the Basis of Industrial Camera Images – West Oder River Case Study
Abstract Main aim of the paper is to use a single non-metric camera to support the determination of the position of. Authors propose to use the existing infrastructure of CCTV cameras mounted on bridges and wharves to determine the position of inland waterway vessels. Image from cameras giving the pixel coordinates of moving object is transformed to the geodetic data domain using a modified projective transformation method. Novel approach is to use of Sequential Projection Transformation (SPT) which additionally uses virtual reference points. The transformation coefficients calculated using the virtual points are used to determine the position of the vessels and are also simultaneously used to calibrate the industrial camera. The method has been verified under real conditions, and the results obtained are average 30% more accurate compared to the traditionally used projective transformation using a small number of real points.