Extracting information from tracks

[bkev13]

Hi, How can I get the content of the tracks set (for instance how many tracks got initiated, and deleted in total, what/how many measurements belong to each selected track)? My tracker plot is the same as Tutorial #10 from the documentation. This is my tracker and it works great.

from stonesoup.tracker.simple import MultiTargetMixtureTracker

tracker = MultiTargetMixtureTracker(
initiator=initiator,
deleter=deleter,
detector=detector,
data_associator=data_associator,
updater=updater,
)

detections = set()
tracks = set()
for time, ctracks in tqdm.tqdm(tracker, desc="Tracking...", unit="step", total=total):
detections.update(detector.detections)
tracks.update(ctracks)

print(f"Number of detections: {len(detections)}")
print(f"Number of tracks: {len(tracks)}")
print(f'tracks: {tracks}')

If I try to print tracks, I get this error message:

Fatal Python error: Cannot recover from stack overflow.
Python runtime state: initialized

[apiszcz]

You can iterate through tracker output objects. Another approach is to create a YAML file with the writer. https://stonesoup.readthedocs.io/en/v1.4/stonesoup.writer.html#module-stonesoup.writer.yaml

…

On Sun, Aug 25, 2024 at 4:20 PM bkev13 ***@***.***> wrote: Hi, How can I get the content of the tracks set (for instance how many tracks got initiated, and deleted in total, what/how many measurements belong to each selected track)? My tracker plot is the same as Tutorial #10 <#10> from the documentation. This is my tracker and it works great. from stonesoup.tracker.simple import MultiTargetMixtureTracker tracker = MultiTargetMixtureTracker( initiator=initiator, deleter=deleter, detector=detector, data_associator=data_associator, updater=updater, ) detections = set() tracks = set() for time, ctracks in tqdm.tqdm(tracker, desc="Tracking...", unit="step", total=total): detections.update(detector.detections) tracks.update(ctracks) print(f"Number of detections: {len(detections)}") print(f"Number of tracks: {len(tracks)}") print(f'tracks: {tracks}') If I try to print tracks, I get this error message: Fatal Python error: Cannot recover from stack overflow. Python runtime state: initialized — Reply to this email directly, view it on GitHub <#1076>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AAK5KTM4R7WYWNWT75CYEZTZTI4BNAVCNFSM6AAAAABNC2N6KGVHI2DSMVQWIX3LMV43ERDJONRXK43TNFXW4OZXGA4TINBRGI> . You are receiving this because you are subscribed to this thread.Message ID: ***@***.***>

[bkev13]

@apiszcz , thank you for your suggestion. I am attempting the iteration approach and this is what I have so far:

Variables to store track information

detections = set()
tracks = set()
track_details = {}
track_initiation_times = {}
track_deletion_times = {}

for time, ctracks in tqdm.tqdm(tracker, desc="Tracking...", unit="step", total=total):
detections.update(detector.detections)
tracks.update(ctracks)

for track in ctracks:
    track_id = track.id

    # Record the track details including associated measurements
    if track_id not in track_details:
        track_details[track_id] = {
            'measurements': [],
            'initiated_at': time,
            'deleted_at': None
        }
        track_initiation_times[track_id] = time

    # Directly access the measurement from the hypothesis
    if track.hypothesis and track.hypothesis.measurement:
        track_details[track_id]['measurements'].append(track.hypothesis.measurement)

# Check for deleted tracks
for track in list(tracks):  # Convert to list to allow safe removal during iteration
    if track not in ctracks:
        if track_details[track.id]['deleted_at'] is None:
            track_details[track.id]['deleted_at'] = time
            track_deletion_times[track.id] = time
            tracks.remove(track)

Calculate the lifespan and final status of each track

for track_id, details in track_details.items():
initiated_at = details['initiated_at']
deleted_at = details['deleted_at'] or time # Use final time if still active
lifespan = deleted_at - initiated_at

# Add lifespan and final status to details
track_details[track_id]['lifespan'] = lifespan
track_details[track_id]['final_status'] = 'deleted' if details['deleted_at'] else 'active'

[apiszcz]

Hi, you can control track length with deleters, the composite deleter can combine length, duration and interval. https://stonesoup.readthedocs.io/en/v0.1b5/stonesoup.deleter.html

…

On Mon, Aug 26, 2024 at 7:51 AM bkev13 ***@***.***> wrote: @apiszcz <https://github.com/apiszcz> , thank you for your suggestion. I am attempting the iteration approach and this is what I have so far: Variables to store track information detections = set() tracks = set() track_details = {} track_initiation_times = {} track_deletion_times = {} for time, ctracks in tqdm.tqdm(tracker, desc="Tracking...", unit="step", total=total): detections.update(detector.detections) tracks.update(ctracks) for track in ctracks: track_id = track.id # Record the track details including associated measurements if track_id not in track_details: track_details[track_id] = { 'measurements': [], 'initiated_at': time, 'deleted_at': None } track_initiation_times[track_id] = time # Directly access the measurement from the hypothesis if track.hypothesis and track.hypothesis.measurement: track_details[track_id]['measurements'].append(track.hypothesis.measurement) # Check for deleted tracks for track in list(tracks): # Convert to list to allow safe removal during iteration if track not in ctracks: if track_details[track.id]['deleted_at'] is None: track_details[track.id]['deleted_at'] = time track_deletion_times[track.id] = time tracks.remove(track) Calculate the lifespan and final status of each track for track_id, details in track_details.items(): initiated_at = details['initiated_at'] deleted_at = details['deleted_at'] or time # Use final time if still active lifespan = deleted_at - initiated_at # Add lifespan and final status to details track_details[track_id]['lifespan'] = lifespan track_details[track_id]['final_status'] = 'deleted' if details['deleted_at'] else 'active' — Reply to this email directly, view it on GitHub <#1076 (reply in thread)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AAK5KTKHI4A53ZNFCDVJWADZTMJETAVCNFSM6AAAAABNC2N6KGVHI2DSMVQWIX3LMV43URDJONRXK43TNFXW4Q3PNVWWK3TUHMYTANBVGA4DSNQ> . You are receiving this because you were mentioned.Message ID: ***@***.***>