Revision history [back]

Stabilizing landmark points

Read here and there that calcOpticalFlowPyrLK can be used to normalize the jitters. Was trying like something like this

lk_params = dict(winSize  = (600,600),
                 maxLevel = 3,
                 criteria = (cv2.TERM_CRITERIA_EPS | cv2.TERM_CRITERIA_COUNT, 30, 0.01))

# calculate optical flow
p1, st, err = cv2.calcOpticalFlowPyrLK(prevGray, image_gray, old_landmarks[0], landmarks[0], **lk_params)

old_landmarks = [p1]
prevGray = cv2.bitwise_and(image_gray,image_gray)

At starts it seems to work, but then goes bananas and gives very weird results. I wonder if there is somebody mastered stabilization and can suggest something. Thank you!

Stabilizing landmark points

Read here and there that calcOpticalFlowPyrLK can be used to normalize the jitters. Was trying ~~like~~ something like this

lk_params = dict(winSize  = (600,600),
                 maxLevel = 3,
                 criteria = (cv2.TERM_CRITERIA_EPS | cv2.TERM_CRITERIA_COUNT, 30, 0.01))

# calculate optical flow
p1, st, err = cv2.calcOpticalFlowPyrLK(prevGray, image_gray, old_landmarks[0], landmarks[0], **lk_params)

old_landmarks = [p1]
prevGray = cv2.bitwise_and(image_gray,image_gray)

At starts it seems to work, but then goes bananas and gives very weird results. I wonder if there is somebody mastered stabilization and can suggest something. Thank you!