{"title":"Time-recursive motion estimation using dynamical models for motion prediction","authors":"K. Karmann","doi":"10.1109/ICPR.1990.118109","DOIUrl":null,"url":null,"abstract":"The author describes a time-recursive method for motion estimation that utilizes dynamical models for object motion to predict the positions and motion parameters of all objects at future times. The predicted positions and motion vectors are used to reduce the search space of a segment matching step, which serves to measure the object displacements by comparing object positions in consecutive frames. The predicted positions and motion vectors are corrected by the use of the measured displacements during a measurement update step, in which corrected positions and motion vectors are computed. The method has been applied to several tracking problems (traffic monitoring and intrusion protection) and yielded excellent results during simulations on a general-purpose computer.<<ETX>>","PeriodicalId":135937,"journal":{"name":"[1990] Proceedings. 10th International Conference on Pattern Recognition","volume":"37 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1990-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"[1990] Proceedings. 10th International Conference on Pattern Recognition","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICPR.1990.118109","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3
Abstract
The author describes a time-recursive method for motion estimation that utilizes dynamical models for object motion to predict the positions and motion parameters of all objects at future times. The predicted positions and motion vectors are used to reduce the search space of a segment matching step, which serves to measure the object displacements by comparing object positions in consecutive frames. The predicted positions and motion vectors are corrected by the use of the measured displacements during a measurement update step, in which corrected positions and motion vectors are computed. The method has been applied to several tracking problems (traffic monitoring and intrusion protection) and yielded excellent results during simulations on a general-purpose computer.<>