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.

Reference Applications

Simulate and track inertial navigation, autonomous, and surveillance systems.

Simulation of a space debris tracking system with a radar surveillance area, and space debris tracks represented by lines passing through the surveillance area and orbiting around the globe.

Surveillance Systems

Autonomous Systems

Pose plot showing an object on a 3-dimensional axis with individual lines representing the X, Y, and Z axis of the object.

Inertial Navigation Systems

Product Highlights

Scenario and Sensor Simulation

Define multiplatform scenarios, then assign motion profiles and attach sensor models to each platform. Simulate these scenarios and dynamically visualize the platform trajectories, sensor coverages, and object detections.

Tracking Scenario Designer Video (4:19)

Documentation | Examples

2D plot of the position of a moving target that initially travels at a constant velocity, then a constant turn, and finally a constant acceleration.

Estimation Filters

Use various estimation filters, like Kalman filters, multimodel filters, and particle filters, to estimate object states. These filters have been optimized for specific scenarios, such as linear or nonlinear motion models, or incomplete observability.

Automatically Tune Tracking Filter for Multi-Object Tracker

Documentation | Examples

Mountainous terrain showing the trajectories and tracks of a ground target and drone using colored lines.

Multi-Object Tracking

Use multi-object multi-sensor trackers that integrate filters, data association, and track management. Choose from a variety of trackers that include single-hypothesis, multiple-hypothesis, joint probabilistic data association, random finite sets, or grid-based tracking.

Bharat Electronics Develops Multi-Target Tracker for Surveillance Radar

Documentation | Examples

Multi-Sensor Fusion

Explore centralized or decentralized multi-object tracking architectures and evaluate design trade-offs between track-to-track fusion, central-level tracking, or hybrid tracking architectures for various tracking applications.

Introduction to Track-to-Track Fusion

Examples

Flight trajectory of an aircraft shown as a white line traversing the Earth’s surface, with its altitude, heading, ground speed, and climb rate specified, alongside radar coverage from 3 radars shown as blue ellipses.

Visualization, Evaluation, and Tuning

Analyze and evaluate the performance of tracking systems against ground truth using various tracking metrics. Visualize ground truth, sensor coverages, detections, and tracks on a map or in a MATLAB figure.

Tuning a Multi-Object Tracker

Documentation | Examples

An arrow pointing from MATLAB code to the chip of an STM32 Nucleo board, indicating the deployment of algorithms to hardware.

Deployment and Hardware Connectivity

Deploy algorithms to hardware targets by automatically generating C/C++ code from fusion and tracking algorithms. Deploy generated code to low-cost hardware with limited memory allocation and strictly single precision processing.

Processor-in-the-Loop Verification of JPDA Tracker for Automotive Applications

Examples