Data Import and Preparation

Import real-world and simulated tracking data; convert data units, formats, and coordinate systems

Use the Tracking Data Importer app to interactively import and convert real-world or simulated tracking truth data to a variety of standardized formats supported by Sensor Fusion and Tracking Toolbox™. Visualize the tracking data on a virtual globe. With the app, you can also create a TrackingTruthDataImporter object for batch conversion of tracking data belonging to the same format.

In addition to the app, you can import and convert data using the objectDetection object or the dataFormat function.

Functions

expand all

TrackingTruthDataImporterImport and convert tracking data from file or table (Since R2025a)
trackingScenarioRecordingCreate trackingScenarioRecording object from truth data (Since R2025a)
tuningDataCreate truth table for tuning from truth data (Since R2025a)
truthlogCreate truth log for metric evaluation from truth data (Since R2025a)
convertedTableCreate converted table from truth data (Since R2025a)
dataFormatStructure for data format required by task-oriented tracker (Since R2024b)
objectDetectionReport for single object detection

Apps

Tracking Data ImporterImport, convert, and visualize tracking data (Since R2025a)

Featured Examples

New
Import Flight Log Data Using Tracking Data Importer App

Import Flight Log Data Using Tracking Data Importer App

The Tracking Data Importer app enables you to process the truth data by identifying the data information, visualizing the data on a map, and ultimately exporting the data in formats compatible with Sensor Fusion and Tracking Toolbox™ functionalities.

New
Import Driving Data in Tracking Data Importer App

Import Driving Data in Tracking Data Importer App

Import estimated ground truth data in the Tracking Data Importer App to visualize track data information and export it for tracking purposes.

Convert Detections to objectDetection Format

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.

Highway Vehicle Tracking Using Multi-Sensor Data Fusion

Highway Vehicle Tracking Using Multi-Sensor Data Fusion

Track vehicles on a highway with commonly used sensors such as radar, camera, and lidar. In this example, you configure and run a Joint Integrated Probabilistic Data Association (JIPDA) tracker to track vehicles using recorded data from a suburban highway driving scenario.

Track Vehicles Using Lidar: From Point Cloud to Track List

Track Vehicles Using Lidar: From Point Cloud to Track List

Track vehicles using measurements from a lidar sensor mounted on top of an ego vehicle.

Import Camera-Based Datasets in MOT Challenge Format for Object Tracking

Import Camera-Based Datasets in MOT Challenge Format for Object Tracking

Read camera image sequences and import ground truth and detections in MOT Challenge format.

People Tracking Using TI mmWave Radar

People Tracking Using TI mmWave Radar

Use data captured using the Texas Instruments (TI) mmWave radar for tracking people in an indoor environment. You learn how to use a processing chain to process radar point clouds and estimate the number of people in the scene as well as their states such as position and velocity.

Estimate Phone Orientation Using Sensor Fusion

Estimate Phone Orientation Using Sensor Fusion

MATLAB® Mobile™ reports sensor data from the accelerometer, gyroscope, and magnetometer on Apple or Android® mobile devices. Raw data from each sensor or fused orientation data can be obtained. This example shows how to compare the fused orientation data from the phone with the orientation estimate from the ahrsfilter object.