Lucas kanade optic flow Winsize parameter [closed]

asked 2020-05-18 13:50:13 -0500

xaru8145 gravatar image

updated 2022-05-23 09:57:29 -0500

lucasw gravatar image


I am trying to calculate optic flow from an image using the opencv cpp implementation of the pyramidal Lucas-Kanade algorithm: cv.calcOpticalFlowPyrLK()

I am confused as for what the winSize parameter stands for. It is defined as: size of the search window at each pyramid level. Does that mean it refers to the neighborhood

The opencv documentation says:

We have seen an assumption before, that all the neighbouring pixels will have similar motion. Lucas-Kanade method takes a 3x3 patch around the point. So all the 9 points have the same motion.

Is this 3x3 the winSize parameter? If so, why is there an option to choose the parameter If it is fixed to 3?


edit retag flag offensive reopen merge delete

Closed for the following reason OpenCV Question: THe OpenCV community prefers to answer questions at: by gvdhoorn
close date 2020-05-18 13:50:51.564965



I'm sorry, but this reads like an OpenCV question.

While we do use OpenCV with ROS, ROS Answers is not a support channel for OpenCV. That would be OpenCV Answers.

Please post your question there.

gvdhoorn gravatar image gvdhoorn  ( 2020-05-18 13:51:54 -0500 )edit

Post over at OpenCV Answers: Lucas kanade optic flow Winsize parameter.

gvdhoorn gravatar image gvdhoorn  ( 2020-05-19 02:23:22 -0500 )edit