Gang Huang, Chaozhong Wu, Nengchao Lyu, Pingfan Li
{"title":"The vehicle speed measuring and precision analysis of video shot by moved camera based on 2D DLT algorithm","authors":"Gang Huang, Chaozhong Wu, Nengchao Lyu, Pingfan Li","doi":"10.1109/ICTIS.2015.7232203","DOIUrl":null,"url":null,"abstract":"To solve the problem that the Direct Linear Transformation (DLT) algorithm cannot be used in the background moving scene, a novel transforming method based on 2D DLT is proposed. The method transforms the feature points in different scenes to the same object space coordinate. Firstly the precision of 2D DLT algorithm has been verified in high-precision 3-D digital camera calibration field. Experiments have been carried out on the platform of miniature traffic scene to calculate errors of the algorithm caused by movements of the camera. The results of the experiments indicated that the errors are all less than 2.5%. Although the errors present a rising trend, the limitation of actual traffic scene makes the proposed method available. The researching results can be used as an aid for speed measuring of road accident identified, and it can provide a scientific basis for the error estimation of the speed identification based on surveillance video which the backgrounds are changing.","PeriodicalId":389628,"journal":{"name":"2015 International Conference on Transportation Information and Safety (ICTIS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 International Conference on Transportation Information and Safety (ICTIS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICTIS.2015.7232203","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
To solve the problem that the Direct Linear Transformation (DLT) algorithm cannot be used in the background moving scene, a novel transforming method based on 2D DLT is proposed. The method transforms the feature points in different scenes to the same object space coordinate. Firstly the precision of 2D DLT algorithm has been verified in high-precision 3-D digital camera calibration field. Experiments have been carried out on the platform of miniature traffic scene to calculate errors of the algorithm caused by movements of the camera. The results of the experiments indicated that the errors are all less than 2.5%. Although the errors present a rising trend, the limitation of actual traffic scene makes the proposed method available. The researching results can be used as an aid for speed measuring of road accident identified, and it can provide a scientific basis for the error estimation of the speed identification based on surveillance video which the backgrounds are changing.