DataHub v1 is the original DataHub catalog of 11,000+ open datasets, now migrated to PortalJS Arc.
Dataset

Moving Object Tracking Based on EKF and Mean Shift

Kalman filter is a traditional method of optimal estimation which is appropriate for linear and Gaussian model. But in practical application, there are many nonlinear and non-Gaussian models, and Extend Kalman filter is mainly used for nonlinear model. In this paper, Extend Kalman filter and Mean shift are combined to…

About

Kalman filter is a traditional method of optimal estimation which is appropriate for linear and Gaussian model. But in practical application, there are many nonlinear and non-Gaussian models, and Extend Kalman filter is mainly used for nonlinear model. In this paper, Extend Kalman filter and Mean shift are combined to track the moving object. Firstly Extend Kalman filter is used to predict the next possible position of the object at target center. Secondly, mean shift is adapted to search moving target later. Experiment results show that this method reduces the time for searching object, thus it improves the speed of tracking target. http://www.sjie.org/paperInfo.aspx?ID=284

Download & API
Moving Object Tracking Based on EKF and Mean Shiftaspx26 KB
Kalman filter is a traditional method of optimal estimation which is appropriate for linear and Gaussian model. But in practical application, there are many nonlinear and non-Gaussian models, and Extend Kalman filter is mainly used for nonlinear model. In this paper, Extend Kalman filter and Mean shift are combined to track the moving object. Firstly Extend Kalman filter is used to predict the next possible position of the object at target center. Secondly, mean shift is adapted to search moving target later. Experiment results show that this method reduces the time for searching object, thus it improves the speed of tracking target.
Download
Sources & license
License
  • Other (Open)