{"title":"改进的SoftPOSIT三维视觉跟踪算法","authors":"J. Diaz, M. Abderrahim","doi":"10.1109/WISP.2007.4447523","DOIUrl":null,"url":null,"abstract":"This paper presents a new formulation of SoftPOSIT, a model based camera algorithm for determining the pose (position and orientation) of a 3D object from a single 2D image when correspondences between object points and image points are not known. This algorithm integrates the Softassign technique for computing correspondences and the POSIT technique for computing object pose. The method finds the rotation and translation parameters of the camera with respect to an object. The major contribution of this work is in contriving a pragmatic approach for 3D pose estimation and tracking, which yielded faster computation than the original algorithm and good target tracking performance. A new calculation of the Distance Matrix which represents the relationship between the features model projected and the image points has been introduced This new approach has been successfully applied in synthetic and real images demonstrate the effectiveness of the proposal modification.","PeriodicalId":164902,"journal":{"name":"2007 IEEE International Symposium on Intelligent Signal Processing","volume":"240 1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2007-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":"{\"title\":\"Modified SoftPOSIT algorithm for 3D visual tracking\",\"authors\":\"J. Diaz, M. Abderrahim\",\"doi\":\"10.1109/WISP.2007.4447523\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper presents a new formulation of SoftPOSIT, a model based camera algorithm for determining the pose (position and orientation) of a 3D object from a single 2D image when correspondences between object points and image points are not known. This algorithm integrates the Softassign technique for computing correspondences and the POSIT technique for computing object pose. The method finds the rotation and translation parameters of the camera with respect to an object. The major contribution of this work is in contriving a pragmatic approach for 3D pose estimation and tracking, which yielded faster computation than the original algorithm and good target tracking performance. A new calculation of the Distance Matrix which represents the relationship between the features model projected and the image points has been introduced This new approach has been successfully applied in synthetic and real images demonstrate the effectiveness of the proposal modification.\",\"PeriodicalId\":164902,\"journal\":{\"name\":\"2007 IEEE International Symposium on Intelligent Signal Processing\",\"volume\":\"240 1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2007-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"7\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2007 IEEE International Symposium on Intelligent Signal Processing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/WISP.2007.4447523\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2007 IEEE International Symposium on Intelligent Signal Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/WISP.2007.4447523","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Modified SoftPOSIT algorithm for 3D visual tracking
This paper presents a new formulation of SoftPOSIT, a model based camera algorithm for determining the pose (position and orientation) of a 3D object from a single 2D image when correspondences between object points and image points are not known. This algorithm integrates the Softassign technique for computing correspondences and the POSIT technique for computing object pose. The method finds the rotation and translation parameters of the camera with respect to an object. The major contribution of this work is in contriving a pragmatic approach for 3D pose estimation and tracking, which yielded faster computation than the original algorithm and good target tracking performance. A new calculation of the Distance Matrix which represents the relationship between the features model projected and the image points has been introduced This new approach has been successfully applied in synthetic and real images demonstrate the effectiveness of the proposal modification.