Map-MatchingΒΆ

[1]:

# Import libraries
import numpy as np
import pandas as pd

from pytrack.graph import graph, distance
from pytrack.analytics import visualization
from pytrack.matching import candidate, mpmatching_utils, mpmatching

[2]:

df = pd.read_excel("dataset.xlsx")

latitude = df["latitude"].to_list()
longitude = df["longitude"].to_list()

points = [(lat, lon) for lat, lon in zip(latitude[:30], longitude[:30])]

[3]:

# Create BBOX
north, east = np.max(np.array([*points]), 0)
south, west = np.min(np.array([*points]), 0)

# Extract road graph
G = graph.graph_from_bbox(*distance.enlarge_bbox(north, south, west, east, 500), simplify=True, network_type='drive')

Downloaded 448.27kB

[4]:

# Initialize maps
loc = (np.mean(latitude[:30]), np.mean(longitude[:30]))
maps = visualization.Map(location=loc, zoom_start=15)
#maps

[5]:

# Show extracted graph
maps.add_graph(G, plot_nodes=True)
maps

[5]:
Make this Notebook Trusted to load map: File -> Trust Notebook
[6]:

# Extract candidates
G_interp, candidates = candidate.get_candidates(G, points, interp_dist=5, closest=True, radius=30)

# Plot results
maps.draw_candidates(candidates, 30)
maps

[6]:
Make this Notebook Trusted to load map: File -> Trust Notebook
[7]:

# Extract trellis DAG graph
trellis = mpmatching_utils.create_trellis(candidates)

# Plot trellis graph
trellis_draw = visualization.draw_trellis(trellis, figsize=(15, 100), dpi=200)
trellis_draw
../_images/notebooks_map-matching_7_0.png 
[8]:

# Perform the map-matching process
path_prob, predecessor = mpmatching.viterbi_search(G_interp, trellis, "start", "target")

[9]:

# Plot map-matching results
maps.draw_path(G_interp, trellis, predecessor)
maps

[9]:
Make this Notebook Trusted to load map: File -> Trust Notebook