{"title":"A method for measuring kinematic parameters of experimental vehicle based on machine vision","authors":"Li-Ping Zi, W. Tao","doi":"10.1109/CIAPP.2017.8167243","DOIUrl":null,"url":null,"abstract":"The vehicle kinematic parameter is important evaluation index of vehicle performance. But The measurement technique of vehicle kinematics parameters is still immature. Practical and efficient measuring system is now in badly demand. With the develop of machine vision technique, more and more measurement problems can be solved better by combining the measuring task with optical system. And on this basis the accuracy and efficiency of kinematic parameter measurement can be improved. A measuring plan is presented in this paper. In order to simplify the measuring algorithm, a simple and practical marker is designed as the substitute of vehicle. The complex measurement system is simplified and transformed to the detection and trajectory tracking of the marker. The marker has clear distinction from the background, it has clear boundary, obvious characteristics and easy to be recognition and detected, at the same time, it meets the precision requirement of position and direction measurement. Meanwhile, in order to reduce the amount of computation and improve the speed of detection, two efficient local detection strategies using neighborhood and movement prediction theories are presented. Several experiments through MATLAB are conducted to verify the feasibility and accuracy of measuring method proposed above.","PeriodicalId":187056,"journal":{"name":"2017 2nd IEEE International Conference on Computational Intelligence and Applications (ICCIA)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 2nd IEEE International Conference on Computational Intelligence and Applications (ICCIA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CIAPP.2017.8167243","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
The vehicle kinematic parameter is important evaluation index of vehicle performance. But The measurement technique of vehicle kinematics parameters is still immature. Practical and efficient measuring system is now in badly demand. With the develop of machine vision technique, more and more measurement problems can be solved better by combining the measuring task with optical system. And on this basis the accuracy and efficiency of kinematic parameter measurement can be improved. A measuring plan is presented in this paper. In order to simplify the measuring algorithm, a simple and practical marker is designed as the substitute of vehicle. The complex measurement system is simplified and transformed to the detection and trajectory tracking of the marker. The marker has clear distinction from the background, it has clear boundary, obvious characteristics and easy to be recognition and detected, at the same time, it meets the precision requirement of position and direction measurement. Meanwhile, in order to reduce the amount of computation and improve the speed of detection, two efficient local detection strategies using neighborhood and movement prediction theories are presented. Several experiments through MATLAB are conducted to verify the feasibility and accuracy of measuring method proposed above.