10 - Tracking in simulation: bringing all components together¶
The previous tutorials have introduced various aspects of Stone Soup covering inference and data association for multiple-target trackers, using simulated data. This tutorial consolidates those aspects in a notebook which can be modified to individual need. It contains all aspects introduced in previous tutorials, and nothing new.
This notebook, as with the previous, proceeds according to the following steps:
Create the simulation
Initialise the ‘playing field’
Choose number of targets and initial states
Create some transition models
Create some sensor models
Initialise the tracker components
Initialise data associations, hypothesisers
Initiators and deleters
Create the tracker
Run the tracker
Plot the output
Create the simulation¶
Separate out the imports
import numpy as np import datetime
Initialise ground truth¶
Here are some configurable parameters associated with the ground truth, e.g. defining where tracks are born and at what rate, death probability. This follows similar logic to the code in previous tutorial section Simulating multiple targets.
from stonesoup.types.array import StateVector, CovarianceMatrix from stonesoup.types.state import GaussianState initial_state_mean = StateVector([, , , ]) initial_state_covariance = CovarianceMatrix(np.diag([4, 0.5, 4, 0.5])) timestep_size = datetime.timedelta(seconds=5) number_of_steps = 20 birth_rate = 0.3 death_probability = 0.05 initial_state = GaussianState(initial_state_mean, initial_state_covariance)
Create the transition model - default set to 2d nearly-constant velocity with small (0.05) variance.
Put this all together in a multi-target simulator.
from stonesoup.simulator.simple import MultiTargetGroundTruthSimulator groundtruth_sim = MultiTargetGroundTruthSimulator( transition_model=transition_model, initial_state=initial_state, timestep=timestep_size, number_steps=number_of_steps, birth_rate=birth_rate, death_probability=death_probability )
Initialise the measurement models¶
The simulated ground truth will then be passed to a simple detection simulator. This again has a number of configurable parameters, e.g. where clutter is generated and at what rate, and detection probability. This implements similar logic to the code in the previous tutorial section Generate Detections and Clutter.
from stonesoup.simulator.simple import SimpleDetectionSimulator from stonesoup.models.measurement.linear import LinearGaussian # initialise the measurement model measurement_model_covariance = np.diag([0.25, 0.25]) measurement_model = LinearGaussian(4, [0, 2], measurement_model_covariance) # probability of detection probability_detection = 0.9 # clutter will be generated uniformly in this are around the target clutter_area = np.array([[-1, 1], [-1, 1]])*30 clutter_rate = 1
The detection simulator
Create the tracker components¶
In this example a Kalman filter is used with global nearest neighbour (GNN) associator. Other options are, of course, available.
Initialise the predictor using the same transition model as generated the ground truth. Note you don’t have to use the same model.
Initialise the updater using the same measurement model as generated the simulated detections. Note, again, you don’t have to use the same model (noise covariance).
Initialise a hypothesiser which will rank predicted measurement - measurement pairs according to some measure. Initialise a Mahalanobis distance measure to facilitate this ranking.
Initialise the GNN with the hypothesiser.
Initiator and Deleter¶
Create deleter - get rid of anything with a covariance trace greater than 2
Set a standard prior state and the minimum number of detections required to qualify for initiation
Initialise the initiator - use the ‘full tracker’ components specified above in the initiator. But note that other ones could be used if needed.
Run the Tracker¶
With the components created, the multi-target tracker component is created, constructed from the components specified above. This is logically the same as tracking code in the previous tutorial section Running the Tracker
Plot the outputs¶
We plot the output using a Stone Soup
MetricGenerator which does plots (in this instance
TwoDPlotter. This will produce plots equivalent to that seen in previous tutorials.
groundtruth = set() detections = set() tracks = set() for time, ctracks in tracker: groundtruth.update(groundtruth_sim.groundtruth_paths) detections.update(detection_sim.detections) tracks.update(ctracks) from stonesoup.metricgenerator.plotter import TwoDPlotter plotter = TwoDPlotter(track_indices=[0, 2], gtruth_indices=[0, 2], detection_indices=[0, 2]) fig = plotter.plot_tracks_truth_detections(tracks, groundtruth, detections).value ax = fig.axes ax.set_xlim([-30, 30]) _ = ax.set_ylim([-30, 30])
Total running time of the script: ( 0 minutes 1.080 seconds)