Does DLC (Deeplabcut) work using forward prediction?


Does anyone know whether Deeplacut makes forward prediction for tracking? I mean, is the position in one frame and next frame correlated so as to avoid abrupt jumps in tracking position?
I know this is done for extracting outliers, but does it also use this for training and analyzing videos?


For training no, for new video analysis, you can use dynamic cropping, which is not a true full forward frame prediction, but it predicts where the points should be given the location in the last frame. Read more in the DOCSTRING on how to use this:

dynamic: triple containing (state,detectiontreshold,margin)
       If the state is true, then dynamic cropping will be performed. That means that if an object is detected (i.e. any body part > detectiontreshold),
       then object boundaries are computed according to the smallest/largest x position and smallest/largest y position of all body parts. This  window is
       expanded by the margin and from then on only the posture within this crop is analyzed (until the object is lost, i.e. <detectiontreshold). The
       current position is utilized for updating the crop window for the next frame (this is why the margin is important and should be set large
       enough given the movement of the animal).
1 Like