Thank you for your sample, it's definitely helps with "the most difficult task in computer vision"!
I have a question about these lines in example here:
#Подаём в трекер и сразу имеем результат!
if len(detects)!=0:
trackers = mot_tracker.update(detects)
while the doctoring of the Sort.update method states:
Requires: this method must be called once for each frame even with empty detections (use np.empty((0, 5)) for frames without detections).
Have you added this check intentionally and how this affects the tracking quality?
Thank you for your sample, it's definitely helps with "the most difficult task in computer vision"!
I have a question about these lines in example here:
while the doctoring of the Sort.update method states:
Have you added this check intentionally and how this affects the tracking quality?