{"title":"Probabilistic learning and modelling of object dynamics for tracking","authors":"T. Tay, K. Sung","doi":"10.1109/ICCV.2001.937580","DOIUrl":null,"url":null,"abstract":"The problem of tracking can be decomposed and independently addressed in two steps, namely the prediction step and the verification step. In this paper we present a new approach of addressing the prediction step that is based on modelling joint probability densities of successive states of tracked objects. This approach has the advantage that it is conceptually general such that given sufficient training data, it is capable of modelling a wide range of complex dynamics. Furthermore, we show that this conceptual prediction framework can be implemented in a tractable manner using a Gaussian mixture representation which allows predictions to be generated efficiently. We then descibe experiments that demonstrate these benefits.","PeriodicalId":429441,"journal":{"name":"Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001","volume":"50 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2001-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCV.2001.937580","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 4
Abstract
The problem of tracking can be decomposed and independently addressed in two steps, namely the prediction step and the verification step. In this paper we present a new approach of addressing the prediction step that is based on modelling joint probability densities of successive states of tracked objects. This approach has the advantage that it is conceptually general such that given sufficient training data, it is capable of modelling a wide range of complex dynamics. Furthermore, we show that this conceptual prediction framework can be implemented in a tractable manner using a Gaussian mixture representation which allows predictions to be generated efficiently. We then descibe experiments that demonstrate these benefits.