Multi-Object Tracker

Create and manage tracks of multiple objects

• Library:

• Automated Driving Toolbox

Description

The Multi-Object Tracker block initializes, confirms, predicts, corrects, and deletes the tracks of moving objects. Inputs to the multi-object tracker are detection reports generated by Radar Detection Generator and Vision Detection Generator blocks. The multi-object tracker accepts detections from multiple sensors and assigns them to tracks using a global nearest neighbor (GNN) criterion. Each detection is assigned to a separate track. If the detection cannot be assigned to any track, the multi-object tracker creates a new track.

A new track starts in a tentative state. If enough detections are assigned to a tentative track, its status changes to confirmed. When a track is confirmed, the multi-object tracker considers that track to represent a physical object. If detections are not added to the track within a specifiable number of updates, the track is deleted.

The multi-object tracker also estimates the state vector and state vector covariance matrix for each track using a Kalman filter. These state vectors are used to predict a track's location in each frame and determine the likelihood of each detection being assigned to each track.

Ports

Input

Detections — Detection list

Simulink^® bus containing MATLAB^® structure

Detection list, specified as a Simulink bus containing a MATLAB structure. See Getting Started with Buses (Simulink). The structure has the form:

Field	Description	Type
NumDetections	Number of detections	integer
IsValidTime	False when updates are requested at times that are between block invocation intervals	Boolean
Detections	Object detections	Array of object detection structures. The first NumDetections of these detections are actual detections.

The definitions of the object detection structures are found in the Detections output port descriptions of the Radar Detection Generator and Vision Detection Generator blocks.

Note

The object detection structure contains a Time field. The time tag of each object detection must be less than or equal to the time of the current invocation of the block. The time tag must also be greater than the update time specified in the previous invocation of the block.

Prediction Time — Track update time

real scalar

Track update time, specified as a real scalar. The multi-object tracker updates all tracks to this time. Update time must always increase with each invocation of the block. Units are in seconds.

Note

The object detection structure contains a Time field. The time tag of each object detection must be less than or equal to the time of the current invocation of the block. The time tag must also be greater than the update time in the previous invocation of the block.

Dependencies

To enable this port, set Prediction time source to Input port.

Cost Matrix — Cost matrix

real-valued N_t-by-N_d matrix

Cost matrix, specified as a real-valued N_t-by-N_d matrix, where N_t is the number of existing tracks and N_d is the number of current detections.

The rows of the cost matrix correspond to the existing tracks. The columns correspond to the detections. Tracks are ordered as they appear in the list of tracks in the All Tracks output port of the previous invocation of the block.

In the first update to the multi-object tracker, or if the track has no previous tracks, assign the cost matrix a size of [0, N_d]. The cost must be calculated so that lower costs indicate a higher likelihood that the multi-object tracker assigns a detection to a track. To prevent certain detections from being assigned to certain tracks, use Inf.

Dependencies

To enable this port, select Enable cost matrix input.

Output

Confirmed Tracks — Confirmed tracks

Simulink bus containing MATLAB structure

Confirmed tracks, returned as a Simulink bus containing a MATLAB structure. See Getting Started with Buses (Simulink).

This table shows the structure fields.

Field	Description
NumTracks	Number of tracks
Tracks	Array of track structures of a length set by the Maximum number of tracks parameter. Only the first NumTracks of these are actual tracks.

This table shows the fields of each track structure.

Field	Definition
TrackID	Unique track identifier.
Time	Time at which the track is updated. Units are in seconds.
Age	Number of updates since track initialization.
State	Updated state vector. The state vector is specific to each type of Kalman filter.
StateCovariance	Updated state covariance matrix. The covariance matrix is specific to each type of Kalman filter.
IsConfirmed	Confirmation status. This field is true if the track is confirmed to be a real target.
IsCoasted	Coasting status. This field is true if the track is updated without a new detection.
ObjectClassID	Integer value representing the object classification. The value 0 represents an unknown classification. Nonzero classifications apply only to confirmed tracks.
ObjectAttributes	Cell array of object attributes reported by the sensor making the detection.

A track is confirmed if:

• At least M detections are assigned to the track during the first N updates after track initialization. To specify the values M and N, use the M and N for the M-out-of-N confirmation parameter.

• The detection initiating the track has an ObjectClassID greater than zero.

Tentative Tracks — Tentative tracks

Simulink bus containing MATLAB structure

Tentative tracks, returned as a Simulink bus containing a MATLAB structure. See Getting Started with Buses (Simulink). A track is tentative before it is confirmed.

This table shows the structure fields.

Field	Description
NumTracks	Number of tracks
Tracks	Array of track structures of a length set by the Maximum number of tracks parameter. Only the first NumTracks of these are actual tracks.

This table shows the fields of each track structure.

Field	Definition
TrackID	Unique track identifier.
Time	Time at which the track is updated. Units are in seconds.
Age	Number of updates since track initialization.
State	Updated state vector. The state vector is specific to each type of Kalman filter.
StateCovariance	Updated state covariance matrix. The covariance matrix is specific to each type of Kalman filter.
IsConfirmed	Confirmation status. This field is true if the track is confirmed to be a real target.
IsCoasted	Coasting status. This field is true if the track is updated without a new detection.
ObjectClassID	Integer value representing the object classification. The value 0 represents an unknown classification. Nonzero classifications apply only to confirmed tracks.
ObjectAttributes	Cell array of object attributes reported by the sensor making the detection.

Dependencies

To enable this port, select Enable tentative tracks output.

All Tracks — All tracks

Simulink bus containing MATLAB structure

Combined list of confirmed and tentative tracks, returned as a Simulink bus containing a MATLAB structure. See Getting Started with Buses (Simulink).

This table shows the structure fields.

Field	Description
NumTracks	Number of tracks
Tracks	Array of track structures of a length set by the Maximum number of tracks parameter. Only the first NumTracks of these are actual tracks.

This table shows the fields of each track structure.

Field	Definition
TrackID	Unique track identifier.
Time	Time at which the track is updated. Units are in seconds.
Age	Number of updates since track initialization.
State	Updated state vector. The state vector is specific to each type of Kalman filter.
StateCovariance	Updated state covariance matrix. The covariance matrix is specific to each type of Kalman filter.
IsConfirmed	Confirmation status. This field is true if the track is confirmed to be a real target.
IsCoasted	Coasting status. This field is true if the track is updated without a new detection.
ObjectClassID	Integer value representing the object classification. The value 0 represents an unknown classification. Nonzero classifications apply only to confirmed tracks.
ObjectAttributes	Cell array of object attributes reported by the sensor making the detection.

Dependencies

To enable this port, select Enable all tracks output.

Parameters

Tracker Management

Filter initialization function name — Kalman filter initialization function

initcvkf (default) | function name

Kalman filter initialization function, specified as a function name. The toolbox provides several initialization functions. For an example of an initialization function, see initcvekf.

Threshold for assigning detections to tracks — Detection assignment threshold

30.0 (default) | positive real scalar

Detection assignment threshold, specified as a positive real scalar. To assign a detection to a track, the detection's normalized distance from the track must be less than the assignment threshold. If some detections remain unassigned to tracks that you want them assigned to, then increase the threshold. If some detections are assigned to incorrect tracks, decrease the threshold.

M and N for the M-out-of-N confirmation — Confirmation parameters for track creation

[2,3] (default) | two-element vector of positive integers

Confirmation parameters for track creation, specified as a two-element vector of positive integers, [M,N]. A track is confirmed when at least M detections are assigned to the track during the first N updates after track initialization. M must be less than or equal to N.

• When setting N, consider the number of times you want the tracker to update before it confirms a track. For example, if a tracker updates every 0.05 seconds, and you allow 0.5 seconds to make a confirmation decision, set N = 10.

• When setting M, take into account the probability of object detection for the sensors. The probability of detection depends on factors such as occlusion or clutter. You can reduce M when tracks fail to be confirmed or increase M when too many false detections are assigned to tracks.

Example: [3,5]

Number of times a confirmed track is coasted — Coasting threshold for track deletion

5 (default) | positive integer

Coasting threshold for track deletion, specified as a positive integer. A track coasts when no detections are assigned to the track after one or more prediction steps. If the number of coasting steps exceeds this threshold, the block deletes the track.

Maximum number of tracks — Maximum number of tracks

200 (default) | positive integer

Maximum number of tracks that the block can process, specified as a positive integer.

Maximum number of sensors — Maximum number of sensors

20 (default) | positive integer

Maximum number of sensors that the block can process, specified as a positive integer. This value should be greater than or equal to the highest SensorIndex value used in the Detections input port.

Inputs and Outputs

Prediction time source — Source for prediction time

Input port (default) | Auto

Source for prediction time, specified as Input port or Auto. Select Input port to input an update time by using the Prediction Time input port. Otherwise, the simulation clock managed by Simulink determines the update time.

Example: Auto

Source of output bus name — Source of output bus name

Auto (default) | Property

Source of output bus name, specified as Auto or Property.

• If you select Auto, the block automatically creates a bus name.

• If you select Property, specify the bus name using the Specify an output bus name parameter.

Specify an output bus name — Name of output bus

no default

Dependencies

To enable this parameter, set the Source of output bus name parameter to Property.

Enable cost matrix input — Enable input port for cost matrix

off (default) | on

Select this check box to enable the input of a cost matrix by using the Cost Matrix input port.

Enable tentative tracks output — Enable output port for tentative tracks

off (default) | on

Select this check box to enable the output of tentative tracks by using the Tentative Tracks output port.

Enable all tracks output — Enable output port for all tracks

off (default) | on

Select this check box to enable the output of all the tracks by using the All Tracks output port.

Simulate using — Type of simulation to run

Interpreted execution (default) | Code generation

• Interpreted execution — Simulate the model using the MATLAB interpreter. This option shortens startup time. In Interpreted execution mode, you can debug the source code of the block.

• Code generation — Simulate the model using generated C/C++ code. The first time you run a simulation, Simulink generates C/C++ code for the block. The C code is reused for subsequent simulations as long as the model does not change. This option requires additional startup time.

Model Examples

Sensor Fusion Using Synthetic Radar and Vision Data in Simulink

Implement a synthetic data simulation for tracking and sensor fusion in Simulink with Automated Driving Toolbox™.

Open Model

Adaptive Cruise Control with Sensor Fusion

Implement an automotive adaptive cruise controller using sensor fusion.

Open Model

Extended Capabilities

C/C++ Code Generation
Generate C and C++ code using Simulink® Coder™.