KalmanTracker 'history' is reset in update

[laclouis5]

self.history is reset in KalmanTracker().update() func:

https://github.com/abewley/sort/blob/54e63a7e432491619a48678bda6f05cc3bd12859/sort.py#L109

This removes history when a new measurement is available but save state when only doing prediction.

Also, here in predict():

https://github.com/abewley/sort/blob/54e63a7e432491619a48678bda6f05cc3bd12859/sort.py#L125

Property history is fed with x predicted. But when the tracker is updated with a new measurement, the state x is refined and should replace the old x predicted no?

As predict() is always followed by update() this should look like this:

  def update(self, bbox):
    """
    Updates the state vector with observed bbox.
    """
    self.time_since_update = 0
    self.hits += 1
    self.hit_streak += 1
    self.kf.update(convert_bbox_to_z(bbox))
    self.history[-1] = convert_bbox_to_z(self.kf.x) # history should be previously init with convert_bbox_to_z(bbox) to not be empty

  def predict(self):
    """
    Advances the state vector and returns the predicted bounding box estimate.
    """
    if((self.kf.x[6]+self.kf.x[2])<=0):
      self.kf.x[6] *= 0.0
    self.kf.predict()
    self.age += 1
    if(self.time_since_update>0):
      self.hit_streak = 0
    self.time_since_update += 1
    self.history.append(convert_x_to_bbox(self.kf.x))
    return history[-1]