def generate_target(time, radar):
# Generate true state
state_transition_model = autocommon.DWNAModel(
target_process_noise_covariance)
initial_state = np.array([
initial_position[0], initial_velocity[0], initial_position[1],
initial_velocity[1]
])
true_state_list = []
for k, t in enumerate(time):
if k == 0:
true_state = autocommon.Estimate(t,
initial_state,
np.identity(4),
is_posterior=True)
else:
true_state = state_transition_model.draw_transition(
true_state_list[-1], t, is_posterior=True)
true_state_list.append(true_state)
# Generate measurements
target_originated_measurements = []
for k, t in enumerate(time):
true_pos = true_state_list[k].est_posterior.take((0, 2))
measurement = radar.generate_target_measurements([true_pos], t)
target_originated_measurements.append(measurement)
return target_originated_measurements, true_state_list
def setup_ipda_manager():
target_model = autocommon.DWNAModel(target_process_noise_covariance)
track_gate = autocommon.TrackGate(gate_probability, maximum_velocity)
clutter_model = autocommon.ConstantClutterModel(clutter_density)
measurement_model = autocommon.CartesianMeasurementModel(
measurement_mapping,
measurement_covariance,
PD,
clutter_model=clutter_model)
tracker = autotrack.IPDAFTracker(target_model, measurement_model,
track_gate, survival_probability)
track_initiation = autoinit.IPDAInitiator(tracker, init_prob,
conf_threshold, term_threshold)
track_termination = autotrack.IPDATerminator(term_threshold)
ipda_track_manager = automanagers.Manager(tracker, track_initiation,
track_termination)
return ipda_track_manager
def generate_target(time, radar):
# Generate true state
state_transition_model = autocommon.DWNAModel(
target_process_noise_covariance)
initial_state = np.array([
initial_position[0], initial_velocity[0], initial_position[1],
initial_velocity[1]
])
true_state_list = []
for k, t in enumerate(time):
if k == 0:
true_state_list.append(
autocommon.Estimate(t,
initial_state,
np.identity(4),
is_posterior=True))
elif t <= termination_time:
true_state = state_transition_model.draw_transition(
true_state_list[-1], t, is_posterior=True)
true_state_list.append(true_state)
# Generate measurements
true_detectability = []
true_existence = []
target_originated_measurements = []
for k, t in enumerate(time):
if t >= detectability_change_time:
radar.update_detection_probability(PD_low)
if k < len(true_state_list):
true_detectability.append(radar.detection_probability)
true_pos = true_state_list[k].est_posterior.take((0, 2))
measurement = radar.generate_target_measurements([true_pos], t)
[true_state_list[k].store_measurement(z) for z in measurement]
target_originated_measurements.append(measurement)
true_existence.append(1)
else:
true_detectability.append(None)
target_originated_measurements.append(set())
true_existence.append(0)
return target_originated_measurements, true_state_list, np.array(
true_detectability), np.array(true_existence)
def generate_scenario():
ais_data, measurements_all, measurement_timestamps = autobag.bag2raw_data(
selected_rosbag, return_timestamps=True)
ais_data = add_landmark(measurements_all, landmark_mmsi, ais_data)
ais_data = autobag.synchronize_track_file_to_timestamps(
ais_data, measurement_timestamps, target_process_noise_covariance)
true_targets = {
mmsi: ais_data[mmsi]
for mmsi in chosen_targets if mmsi in ais_data.keys()
}
ownship_state = ais_data[ownship_mmsi]
return true_targets, ownship_state, measurements_all, measurement_timestamps
target_model = autocommon.DWNAModel(target_process_noise_covariance)
track_gate = autocommon.TrackGate(gate_probability, maximum_velocity)
clutter_model = autocommon.NonparametricClutterModel()
def setup_trackers(titles):
current_managers = dict()
for title in titles:
if title == 'MC1-IPDA':
measurement_model = autocommon.ConvertedMeasurementModel(
measurement_mapping,
measurement_covariance_range,
measurement_covariance_bearing,
single_PD,
min_cartesian_cov,
clutter_model=clutter_model)