{"title":"Research on positioning algorithm of binocular camera based on multi-media","authors":"Qianghua Xiong, Lei Yang, Qingqiang Chen","doi":"10.1145/3448734.3450476","DOIUrl":null,"url":null,"abstract":"With the development of computer technology, image processing technology has become an increasing number of mature. However, the accuracy of target positioning has not reached the expectation in the case of multi-medium. Based on the binocular positioning algorithm, Aiming at the binocular positioning algorithm, this paper proposes a multi-medium binocular positioning algorithm. First, from the calibration of the camera, the internal parameters of the camera is obtained and the distortion caused by the camera is removed, and the picture is corrected. Secondly, the position of the target is detected by the YOLOv4 algorithm and the pixels of the target in the picture is obtained. Finally, through the binocular vision algorithm, camera imaging principle and the propagation characteristics of light on the interface of different medium, the spatial position of the target in the world coordinate system is obtained.","PeriodicalId":105999,"journal":{"name":"The 2nd International Conference on Computing and Data Science","volume":"66 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"The 2nd International Conference on Computing and Data Science","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3448734.3450476","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
With the development of computer technology, image processing technology has become an increasing number of mature. However, the accuracy of target positioning has not reached the expectation in the case of multi-medium. Based on the binocular positioning algorithm, Aiming at the binocular positioning algorithm, this paper proposes a multi-medium binocular positioning algorithm. First, from the calibration of the camera, the internal parameters of the camera is obtained and the distortion caused by the camera is removed, and the picture is corrected. Secondly, the position of the target is detected by the YOLOv4 algorithm and the pixels of the target in the picture is obtained. Finally, through the binocular vision algorithm, camera imaging principle and the propagation characteristics of light on the interface of different medium, the spatial position of the target in the world coordinate system is obtained.