Get Started with Sensor Fusion and Tracking Toolbox

Design, simulate, and test multisensor tracking and positioning systems

Sensor Fusion and Tracking Toolbox™ includes algorithms and tools for designing, simulating, and testing systems that fuse data from multiple sensors to maintain situational awareness and localization. Reference examples provide a starting point for multi-object tracking and sensor fusion development for surveillance and autonomous systems, including airborne, spaceborne, ground-based, shipborne, and underwater systems.

You can fuse data from real-world sensors, including active and passive radar, sonar, lidar, EO/IR, IMU, and GPS. You can also generate synthetic data from virtual sensors to test your algorithms under different scenarios. The toolbox includes multi-object trackers and estimation filters for evaluating architectures that combine grid-level, detection-level, and object- or track-level fusion. It also provides metrics, including OSPA and GOSPA, for validating performance against ground truth scenes.

For simulation acceleration or rapid prototyping, the toolbox supports C and C++ code generation.

Tutorials

Toolbox Conventions

Orientation, Position, and Coordinate Convention
Learn about toolbox conventions for spatial representation and coordinate systems.

Tracking Scenario and Sensors

Tracking Simulation Overview
You can build a complete tracking simulation using the functions and objects supplied in this toolbox.
Simulate Radar Detections
Simulate target detections by radar sensors.

Inertial Sensor Fusion

Model IMU, GPS, and INS/GPS
Model combinations of inertial sensors and GPS.

Estimation Filters

Introduction to Estimation Filters
General review of estimation filters provided in the toolbox.

Multi-Object Tracking

Introduction to Multiple Target Tracking
Introduction to assignment-based multiple target trackers.

Metrics and Visualization

Introduction to Tracking Metrics
While designing a multi-object tracking system, it is essential to devise a method to evaluate its performance against the available ground truth.
Use theaterPlot to Visualize Tracking Scenario
This example shows how to use the theaterPlot object to visualize various aspects of a tracking scenario.

Featured Examples

Introduction to Tracking Scenario and Simulating Sensor Detections

Introduces how to generate synthetic radar detections in a tracking scenario that simulates target motion and sensor detections. Specifically, this example shows:

Open Live Script

Design and Simulate Tracking Scenario with Tracking Scenario Designer

Use trackingScenarioDesigner with an existing session file. Using the application, you can add, modify, or remove platforms, monostatic radar sensors, and trajectories of all objects in the scenario. You can also export the scenario as a MATLAB script for further analysis.

Open Live Script

Scanning Radar Mode Configuration

Model different radar scan modes using the fusionRadarSensor. This example shows how to configure the fusionRadarSensor for several commonly used radar scan modes. With this model, you can simulate radars which mechanically scan, electronically scan, and which use both mechanical and electronic scanning. The scan limits in azimuth and elevation are configurable for both mechanical and electronic scan modes.

Open Script

Estimate Orientation Through Inertial Sensor Fusion

Use 6-axis and 9-axis fusion algorithms to compute orientation. There are several algorithms to compute orientation from inertial measurement units (IMUs) and magnetic-angular rate-gravity (MARG) units. This example covers the basics of orientation and how to use these algorithms.

Open Live Script

Tracking Maneuvering Targets

Track maneuvering targets using various tracking filters. The example shows the difference between filters that use a single motion model and multiple motion models.

Open Script

Automatically Tune Tracking Filter for Multi-Object Tracker

Tune a tracking filter and improve the tracking performance of the tracker.

Since R2022b
Open Live Script

Analyze Truth Data and Define Truth Model

Analyze recorded truth data to model the motion of truth objects and configure a filter to track them.

Since R2024a
Open Live Script

Convert Detections to objectDetection Format

These examples show how to convert actual detections in the native format of the sensor into objectDetection objects. objectDetection is the standard input format for most tracking filters and trackers in the toolbox. The six examples progressively show how to set up objectDetection with varied tracking scenarios.

Open Live Script

Tuning a Multi-Object Tracker

Tune and run a tracker to track multiple objects in the scene. The example explains and demonstrates the importance of key properties of the trackers in the Sensor Fusion and Tracking Toolbox.

Open Live Script

Videos

Part 1: What is Sensor Fusion?
An overview of what sensor fusion is and how it helps in the design of autonomous systems.

Part 2: Fusing Mag, Accel, and Gyro to Estimate Orientation
Use magnetometer, accelerometer, and gyro to estimate an object’s orientation.

Part 3: Fusing GPS and IMU to Estimate Pose
Use GPS and an IMU to estimate an object’s orientation and position.

Part 4: Tracking a Single Object With an IMM Filter
Track a single object by estimating state with an interacting multiple model filter.

Part 5: How to Track Multiple Objects at Once?
Introduce two common problems in multi object tracking: Data association and track maintenance.

Part 6: What is Track-Level Fusion?
Introduce track-to-track fusion and tracking architecture.