In deep_sort_app.py line 195, result contains confirmed track with time_since_update <= 1
# Store results.
for track in tracker.tracks:
if not track.is_confirmed() or track.time_since_update > 1:
continue
bbox = track.to_tlwh()
results.append([
frame_idx, track.track_id, bbox[0], bbox[1], bbox[2], bbox[3]])
When predict() is called, 1 is added to track.time_since_update, and when update() is called and matched with detection, track.time_since_update is initialized to 0.
So, If a track was updated and lost in next frame, track.time_since_update is 1. The result file will contain this track.
I compared this part with ByteTrack, but ByteTrack only contains confirmed matched tracks. Is this an error?
In deep_sort_app.py line 195, result contains confirmed track with time_since_update <= 1
When predict() is called, 1 is added to track.time_since_update, and when update() is called and matched with detection, track.time_since_update is initialized to 0. So, If a track was updated and lost in next frame, track.time_since_update is 1. The result file will contain this track.
I compared this part with ByteTrack, but ByteTrack only contains confirmed matched tracks. Is this an error?