objectTrack

Single object track report

Since R2020a

Description

objectTrack captures the track information of a single object. objectTrack is the standard output format for trackers.

Creation

Syntax

track = objectTrack

track = objectTrack(Name,Value)

Description

track = objectTrack creates an objectTrack object with default property values. An objectTrack object contains information like the age and state of a single track.

Tip

To create an empty objectTrack object, use objectTrack.empty().

track = objectTrack(Name,Value) allows you to set properties using one or more name-value pairs. Enclose each property name in single quotes.

Properties

TrackID — Unique track identifier

1 (default) | nonnegative integer

Unique track identifier, specified as a nonnegative integer. This property distinguishes different tracks.

Example: 2

BranchID — Unique track branch identifier

0 (default) | nonnegative integer

Unique track branch identifier, specified as a nonnegative integer. In multi-hypothesis tracking, a track may have multiple hypotheses, each represented by a different branch. This property distinguishes different track branches. For more information, see trackerTOMHT (Sensor Fusion and Tracking Toolbox).

Example: 1

SourceIndex — Index of source track reporting system

1 (default) | nonnegative integer

Index of source track reporting system, specified as a nonnegative integer. This property identifies the source that reports the track.

Example: 3

UpdateTime — Update time of track

0 (default) | nonnegative real scalar

Time at which the track was updated by a tracker, specified as a nonnegative real scalar.

Example: 1.2

Data Types: single | double

Age — Number of times track was updated

1 (default) | positive integer

Number of times the track was updated, specified as a positive integer. When a track is initialized, its Age is equal to 1. Any subsequent update with a hit or miss increases the track Age by 1.

Example: 2

State — Current state of track

zeros(6,1) (default) | real-valued N-element vector

The current state of the track at the UpdateTime, specified as a real-valued N-element vector, where N is the dimension of the state. The format of track state depends on the model used to track the object. For example, for 3-D constant velocity model used with constvel, the state vector is [x; v_x; y; v_y; z; v_z].

Example: [1 0.2 3 0.2]

Data Types: single | double

StateCovariance — Current state uncertainty covariance of track

eye(6,6) (default) | real positive semidefinite symmetric N-by-N matrix

The current state uncertainty covariance of the track, specified as a real positive semidefinite symmetric N-by-N matrix, where N is the dimension of state specified in the State property.

Data Types: single | double

StateParameters — Parameters of the track state reference frame

struct() (default) | structure | structure array

Parameters of the track state reference frame, specified as a structure or a structure array. Use this property to define the track state reference frame and how to transform the track from the source coordinate system to the fuser coordinate system.

ObjectClassID — Object class identifier

0 (default) | nonnegative integer

Object class identifier, specified as a nonnegative integer. This property distinguishes between different user-defined object types. For example, you can use 1 for objects of type "car", and 2 for objects of type "pedestrian". 0 is reserved for unknown classification.

If you specify this property as a nonzero integer, you can use the ObjectClassProbablities property to specify the classification probabilities.

Example: 3

ObjectClassProbablities — Object classification probabilities

1 (default) | N-element vector of nonnegative scalars

Object classification probabilities of the track, specified as an N-element vector of nonnegative scalars. N is the total number of possible classes of the track. Each element must be a scalar in the range [0 1], and the sum of all elements must be equal to 1.The i-th element of the vector corresponds to the probability that the track belongs to the class i.

Example: [0.7 0.3]

TrackLogic — Track confirmation and deletion logic type

'History' (default) | 'Integrated' | 'Score'

Confirmation and deletion logic type, specified as:

• 'History' – Track confirmation and deletion is based on the number of times the track has been assigned to a detection in the latest tracker updates.

• 'Score' – Track confirmation and deletion is based on a log-likelihood track score. A high score means that the track is more likely to be valid. A low score means that the track is more likely to be a false alarm.

• 'Integrated' – Track confirmation and deletion is based on the integrated probability of track existence.

TrackLogicState — State of track logic

1-by-M logical vector | 1-by-2 real-valued vector | nonnegative scalar

The current state of the track logic type. Based on the logic type specified in the TrackLogic property, the logic state is specified as:

• 'History' – A 1-by-M logical vector, where M is the number of latest track logical states recorded. true (1) values indicate hits, and false (0) values indicate misses. For example, [1 0 1 1 1] represents four hits and one miss in the last five updates. The default value for logic state is 1.

• 'Score' – A 1-by-2 real-valued vector, [cs, ms]. cs is the current score, and ms is the maximum score. The default value is [0, 0].

• 'Integrated' – A nonnegative scalar. The scalar represents the integrated probability of existence of the track. The default value is 0.5.

IsConfirmed — Indicate if track is confirmed

true (default) | false

Indicate if the track is confirmed, specified as true or false.

Data Types: logical

IsCoasted — Indicate if track is coasted

false (default) | true

Indicate if the track is coasted, specified as true or false. A track is coasted if its latest update is based on prediction instead of correction using detections.

Data Types: logical

IsSelfReported — Indicate if track is self reported

true (default) | false

Indicate if the track is self reported, specified as true or false. A track is self reported if it is reported from internal sources (senors, trackers, or fusers). To limit the propagation of rumors in a tracking system, use the value false if the track was updated by an external source.

Example: false

Data Types: logical

ObjectAttributes — Object attributes

struct() (default) | structure

Object attributes passed by the tracker, specified as a structure.

Object Functions

toStruct

Convert objectTrack object to struct

Examples

Create Track Report using objectTrack

Create a report of a track using objectTrack.

x = (1:6)';
P = diag(1:6);
track = objectTrack('State',x,'StateCovariance',P);
disp(track)

  objectTrack with properties:

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

Extended Capabilities

C/C++ Code Generation

Generate C and C++ code using MATLAB® Coder™.

• The TrackLogic property can only be set during construction.

Version History

Introduced in R2020a

R2022b: Represent track class probability

The objectTrack object has a new property, ObjectClassProbabilities, which represents the probabilities that the tracked target belongs to specific classes.