You can create multi-object trackers that fuse information from various
trackerGNN to maintain a single hypothesis about the tracked
trackerTOMHT to maintain multiple hypotheses about the tracked
assign multiple probable detections to the tracked objects. Use
trackerPHD to represent tracked objects using probability
hypothesis density (PHD) function.
|Assignment using auction global nearest neighbor|
|Jonker-Volgenant global nearest neighbor assignment algorithm|
|Assignment using k-best global nearest neighbor|
|K-best S-D solution that minimizes total cost of assignment|
|Munkres global nearest neighbor assignment algorithm|
|S-D assignment using Lagrangian relaxation|
|Track-oriented multi-hypotheses tracking assignment|
|Feasible joint events for trackerJPDA|
|Partition detections based on Mahalanobis distance|
|Represent sensor configuration for tracking|
|Multi-hypothesis, multi-sensor, multi-object tracker|
|Multi-sensor, multi-object tracker using GNN assignment|
|Joint probabilistic data association tracker|
|Multi-sensor, multi-object PHD tracker|
|Create object detection report|
|Returns updated track positions and position covariance matrix|
|Obtain updated track velocities and velocity covariance matrix|
|Cluster track-oriented multi-hypothesis history|
|Formulate global hypotheses from clusters|
|Prune track branches with low likelihood|
|Confirm and delete tracks based on recent track history|
|Confirm and delete tracks based on track score|
|Track-oriented MHT branching and branch history|
This example shows how to configure and use the global nearest neighbor (GNN) tracker.
Introduction to methods and examples of multiple extended object tracking in the toolbox.
This example shows how to define and use confirmation and deletion logic that are based on history or score.