Tracking and Sensor Fusion

Object tracking and multisensor fusion, bird’s-eye plot of detections and object tracks

You can create a multi-object tracker to fuse information from radar and video camera sensors. The tracker uses Kalman filters that let you estimate the state of motion of a detected object. Use the sensor measurements made on a detected object to continuously solve for the position and velocity of that object. To track moving objects, you can use constant-velocity or constant-acceleration motion models, or you can define your own models.

Functions

expand all

multiObjectTrackerTrack objects using GNN assignment
objectDetectionReport for single object detection
getTrackPositionsReturns updated track positions and position covariance matrix
getTrackVelocitiesObtain updated track velocities and velocity covariance matrix

Linear Kalman Filter

trackingKFLinear Kalman filter for object tracking
initcakfCreate constant-acceleration linear Kalman filter from detection report
initcvkfCreate constant-velocity linear Kalman filter from detection report

Extended Kalman Filter

trackingEKFExtended Kalman filter for object tracking
initcaekfCreate constant-acceleration extended Kalman filter from detection report
initctekfCreate constant turn-rate extended Kalman filter from detection report
initcvekfCreate constant-velocity extended Kalman filter from detection report

Unscented Kalman Filter

trackingUKFUnscented Kalman filter for object tracking
initcaukfCreate constant-acceleration unscented Kalman filter from detection report
initctukfCreate constant turn-rate unscented Kalman filter from detection report
initcvukfCreate constant-velocity unscented Kalman filter from detection report

Constant Velocity

constvelConstant velocity state update
constveljacJacobian for constant-velocity motion
cvmeasMeasurement function for constant velocity motion
cvmeasjacJacobian of measurement function for constant velocity motion

Constant Acceleration

constaccConstant-acceleration motion model
constaccjacJacobian for constant-acceleration motion
cameasMeasurement function for constant-acceleration motion
cameasjacJacobian of measurement function for constant-acceleration motion

Constant Turn-Rate

constturnConstant turn-rate motion model
constturnjacJacobian for constant turn-rate motion
ctmeasMeasurement function for constant turn-rate motion
ctmeasjacJacobian of measurement function for constant turn-rate motion

Bird's-Eye Plot

birdsEyePlotPlot detections, tracks, and sensor coverages around vehicle
coverageAreaPlotterCoverage area plotter for bird's-eye plot
detectionPlotterDetection plotter for bird's-eye plot
trackPlotterTrack plotter for bird's-eye plot
laneBoundaryPlotterLane boundary plotter for bird's-eye plot
laneMarkingPlotterLane marking plotter for bird's-eye plot
pathPlotterPath plotter for bird's-eye plot
outlinePlotterOutline plotter for bird's-eye plot
findPlotterFind plotters associated with bird’s-eye plot
clearDataClear data from specific plotter of bird’s-eye plot
clearPlotterDataClear data from bird’s-eye plot
plotCoverageAreaDisplay sensor coverage area on bird's-eye plot
plotDetectionDisplay object detections on bird's-eye plot
plotLaneBoundaryDisplay lane boundaries on bird’s-eye plot
plotLaneMarkingDisplay lane markings on bird’s-eye plot
plotOutlineDisplay object outlines on bird's-eye plot
plotPathDisplay actor paths on bird’s-eye plot
plotTrackDisplay object tracks on bird's-eye plot

Video Annotation

insertObjectAnnotationAnnotate truecolor or grayscale image or video stream

Video Viewers

vision.VideoPlayerPlay video or display image
vision.DeployableVideoPlayerDisplay video

Blocks

expand all

Multi-Object TrackerCreate and manage tracks of multiple objects
Detection ConcatenationCombine detection reports from different sensors

Simulink Visualization Tool

Bird's-Eye ScopeVisualize sensor coverages, detections, and tracks

Topics

Multi-Object Tracking

Track Multiple Vehicles Using a Camera

Detect and track multiple vehicles with a monocular camera mounted in a vehicle.

Track Pedestrians from a Moving Car

Track pedestrians using a camera mounted in a moving car.

Multiple Object Tracking Tutorial

Perform automatic detection and motion-based tracking of moving objects in a video by using a multi-object tracker.

Linear Kalman Filters

Estimate and predict object motion using a Linear Kalman filter.

Extended Kalman Filters

Estimate and predict object motion using an extended Kalman filter.

Sensor Fusion with Synthetic Data

Sensor Fusion Using Synthetic Radar and Vision Data

Generate a scenario, simulate sensor detections, and use sensor fusion to track simulated vehicles.

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™.

Visualization

Visualize Sensor Data and Tracks in Bird's-Eye Scope

Visualize sensor coverages, detections, and tracks in a Simulink model.

Visualize Sensor Coverage, Detections, and Tracks

Configure and use a bird's-eye plot to display sensor coverage, detections, and tracking results around the ego vehicle.

Deployment

Code Generation for Tracking and Sensor Fusion

Generate C code for a MATLAB® function that processes data recorded from a test vehicle and tracks the objects around it.

Featured Examples