Main Content


Predict track state

Since R2020a


predictedtracks = predictTracksToTime(tracker,trackID,time) returns the predicted tracks, predictedtracks, of the tracker, at the specified time, time. The tracker or fuser must be updated at least once before calling this object function. Use isLocked(tracker) to test whether the tracker or fuser has been updated.


This function only outputs the predicted tracks and does not update the internal track states of the tracker.


predictedtracks = predictTracksToTime(tracker,category,time) returns all predicted tracks for a specified category, category, of tracked objects.

predictedtracks = predictTracksToTime(tracker,category,time,'WithCovariance',tf) also allows you to specify whether to predict the state covariance of each track or not by setting the tf flag to true or false. Predicting the covariance slows down the prediction process and increases the computation cost, but it provides the predicted track state covariance in addition to the predicted state. The default is false.


collapse all

Create a track from a detection at time t=0 second and predict it to t=1second.

tracker = multiObjectTracker;
detection = objectDetection(0,[0;0;0]);
predictedtracks = predictTracksToTime(tracker,'all',1)
predictedtracks = 
  objectTrack with properties:

                     TrackID: 1
                    BranchID: 0
                 SourceIndex: 0
                  UpdateTime: 1
                         Age: 1
                       State: [6x1 double]
             StateCovariance: [6x6 double]
             StateParameters: [1x1 struct]
               ObjectClassID: 0
    ObjectClassProbabilities: 1
                  TrackLogic: 'History'
             TrackLogicState: [1 0 0 0 0]
                 IsConfirmed: 0
                   IsCoasted: 0
              IsSelfReported: 1
            ObjectAttributes: [1x1 struct]

Input Arguments

collapse all

Multi-object tracker, specified as a multiObjectTracker System object.

Track identifier, specified as a positive integer. Only the track specified by the trackID is predicted in the tracker.

Example: 15

Data Types: single | double

Prediction time, specified as a scalar. The states of tracks are predicted to this time. The time must be greater than the time input to the tracker in the previous track update. Units are in seconds.

Example: 1.0

Data Types: single | double

Track categories, specified as 'all', 'confirmed', or 'tentative'. You can choose to predict all tracks, only confirmed tracks, or only tentative tracks.

Data Types: char

Output Arguments

collapse all

List of tracks or branches, returned as:

  • An array of objectTrack objects in the MATLAB interpreted mode.

  • An array of structures in the code generation mode. The field names of the structures are the same as the names of properties in objectTrack.

Data Types: struct | object

Version History

Introduced in R2020a