from trackers.kalman_filter_view_AIS_as_measurement import kalman_filter_ais_as_measurement from utils.scenario_generator import generate_scenario_2 from utils import open_object, calc_metrics from utils.save_figures import save_figure # run dependent fusion and plot sigma_process = 0.5 sigma_meas_radar = 20 sigma_meas_ais = 10 seed = 1996 num_steps = 30 generate_scenario_2(seed=seed, permanent_save=False, sigma_process=sigma_process, sigma_meas_radar=sigma_meas_radar, sigma_meas_ais=sigma_meas_ais, timesteps=num_steps) folder = "temp" # temp instead of seed, as it is not a permanent save save_fig = True # load ground truth and the measurements data_folder = "../scenarios/scenario2/" + folder + "/" ground_truth = open_object.open_object(data_folder + "ground_truth.pk1") measurements_radar = open_object.open_object(data_folder + "measurements_radar.pk1") measurements_ais = open_object.open_object(data_folder + "measurements_ais.pk1") # load start_time start_time = open_object.open_object(data_folder + "start_time.pk1") # prior
from stonesoup.types.state import GaussianState from matplotlib import pyplot as plt from matplotlib.patches import Ellipse from trackers.kalman_filter_view_AIS_as_measurement import kalman_filter_ais_as_measurement from utils.scenario_generator import generate_scenario_2 from utils import open_object from utils.save_figures import save_figure # run dependent fusion and plot seed = 1996 generate_scenario_2(seed=seed, permanent_save=False, sigma_process=0.01, sigma_meas_radar=3, sigma_meas_ais=1) folder = "temp" # temp instead of seed, as it is not a permanent save # load ground truth and the measurements data_folder = "../scenarios/scenario2/" + folder + "/" ground_truth = open_object.open_object(data_folder + "ground_truth.pk1") measurements_radar = open_object.open_object(data_folder + "measurements_radar.pk1") measurements_ais = open_object.open_object(data_folder + "measurements_ais.pk1") # load start_time start_time = open_object.open_object(data_folder + "start_time.pk1") # prior prior = GaussianState([0, 1, 0, 1], np.diag([1.5, 0.5, 1.5, 0.5]) ** 2, timestamp=start_time)