Skip to content

Latest commit

 

History

History
24 lines (19 loc) · 1.1 KB

File metadata and controls

24 lines (19 loc) · 1.1 KB

Optical flow: Horn–Schunck method

Description

Python implementation of Horn–Schunck method for estimating optical flow.

Use computeHS to compute u,v optical flow vectors and draw quiver.
computeHS(name1, name2, alpha, delta)
Input: images name, smoothing parameter, tolerance
Output: images variations
The paramter 'alpha' is the regularization constant. It determines the smoothness of the output: The bigger this parameter is, the smoother the solutions we obtain (more locally consistent vectors of motion flow).

Example

From project directory type in console: MyHornSchunck.py car1.jpg car2.jpg
Output:

Anothr test options:
MyHornSchunck.py sphere1.bmp sphere2.bmp
MyHornSchunck.py table1.jpg table2.jpg
See results.