pysteps.tracking.lucaskanade.track_features¶

pysteps.tracking.lucaskanade.track_features(prvs_image, next_image, points, winsize=(50, 50), nr_levels=3, criteria=(3, 10, 0), flags=0, min_eig_thr=0.0001, verbose=False)¶

Interface to the OpenCV Lucas-Kanade feature tracking algorithm (cv.calcOpticalFlowPyrLK).

Parameters

prvs_image: ndarray_ or MaskedArray_: Array of shape (m, n) containing the first image. Invalid values (Nans or infs) are replaced with the min value.
next_image: ndarray_ or MaskedArray_: Array of shape (m, n) containing the successive image. Invalid values (Nans or infs) are replaced with the min value.
points: array_like: Array of shape (p, 2) indicating the pixel coordinates of the tracking points (corners).
winsize: tuple of int, optional: The winSize parameter in calcOpticalFlowPyrLK. It represents the size of the search window that it is used at each pyramid level. The default is (50, 50).
nr_levels: int, optional: The maxLevel parameter in calcOpticalFlowPyrLK. It represents the 0-based maximal pyramid level number. The default is 3.
criteria: tuple of int, optional: The TermCriteria parameter in calcOpticalFlowPyrLK , which specifies the termination criteria of the iterative search algorithm. The default is (3, 10, 0).
flags: int, optional: Operation flags, see documentation calcOpticalFlowPyrLK. The default is 0.
min_eig_thr: float, optional: The minEigThreshold parameter in calcOpticalFlowPyrLK. The default is 1e-4.
verbose: bool, optional: Print the number of vectors that have been found. The default is False.

Returns

xy: ndarray: Array of shape (d, 2) with the x- and y-coordinates of d <= p detected sparse motion vectors.
uv: ndarray: Array of shape (d, 2) with the u- and v-components of d <= p detected sparse motion vectors.