Main Content

Multi-Object Trackers

Multi-sensor multi-object trackers, data association, and track fusion

You can create multi-object trackers that fuse information from various sensors. Use trackerGNN to maintain a single hypothesis about the tracked objects. Use trackerTOMHT to maintain multiple hypotheses about the tracked objects. Use trackerJPDA to assign multiple probable detections to the tracked objects. Use trackerPHD to represent tracked objects using probability hypothesis density (PHD) function. Use trackerGridRFS to track objects using a grid-based occupancy evidence approach. Use trackFuser to fuse tracks generated by tracking sensors or trackers and architect decentralized tracking systems.


expand all

assignauctionAssignment using auction global nearest neighbor
assignjvJonker-Volgenant global nearest neighbor assignment algorithm
assignkbestAssignment using k-best global nearest neighbor
assignkbestsdK-best S-D solution that minimizes total cost of assignment
assignmunkresMunkres global nearest neighbor assignment algorithm
assignsdS-D assignment using Lagrangian relaxation
assignTOMHTTrack-oriented multi-hypotheses tracking assignment
jpdaEventsFeasible joint events for trackerJPDA
partitionDetectionsPartition detections based on distance
mergeDetectionsMerge detections into clustered detections (Since R2021b)
trackerGNNMulti-sensor, multi-object tracker using GNN assignment
trackerJPDAJoint probabilistic data association tracker
trackerTOMHTMulti-hypothesis, multi-sensor, multi-object tracker
trackerPHDMulti-sensor, multi-object PHD tracker
trackerGridRFSGrid-based multi-object tracker (Since R2020b)
smootherJIPDAJoint probabilistic data association smoother (Since R2023a)
dynamicEvidentialGridMapDynamic grid map output from trackerGridRFS (Since R2021a)
objectDetectionReport for single object detection
objectDetectionDelaySimulate out-of-sequence object detections (Since R2022a)
getTrackPositionsReturns updated track positions and position covariance matrix
getTrackVelocitiesObtain updated track velocities and velocity covariance matrix
clusterTrackBranchesCluster track-oriented multi-hypothesis history
compatibleTrackBranchesFormulate global hypotheses from clusters
pruneTrackBranchesPrune track branches with low likelihood
trackHistoryLogicConfirm and delete tracks based on recent track history
trackScoreLogicConfirm and delete tracks based on track score
trackBranchHistoryTrack-oriented MHT branching and branch history
trackingSensorConfiguration Represent sensor configuration for tracking
trackFuserSingle-hypothesis track-to-track fuser (Since R2019b)
trackingArchitectureTracking system-of-system architecture (Since R2021a)
staticDetectionFuserStatic fusion of synchronous sensor detections
objectTrackSingle object track report (Since R2019b)
fusecovintCovariance fusion using covariance intersection
fusecovunionCovariance fusion using covariance union
fusexcovCovariance fusion using cross-covariance
fuserSourceConfiguration Configuration of source used with track fuser (Since R2019b)
triangulateLOSTriangulate multiple line-of-sight detections


expand all

Global Nearest Neighbor Multi Object TrackerMulti-sensor, multi-object tracker using GNN assignment (Since R2019b)
Joint Probabilistic Data Association Multi Object TrackerJoint probabilistic data association tracker (Since R2019b)
Track-Oriented Multi-Hypothesis TrackerTrack-Oriented Multi-Hypothesis Tracker (Since R2020a)
Probability Hypothesis Density (PHD) TrackerMulti-sensor, multi-object PHD tracker (Since R2021a)
Grid-Based Multi Object TrackerGrid-based multi-object tracker using random finite set approach (Since R2021b)
Track-To-Track FuserTrack-to-Track Fusion (Since R2021a)
Detection ConcatenationCombine detection reports from different sensors (Since R2021a)
Track ConcatenationConcatenate tracks (Since R2021a)