👀 Look into

[X] (Local) Lucas-Kanade
[X] (Global) Horn-Schunck
[X] Visualizations
[ ] Source code

📃 Find the papers:

[x] Andry et al. (2013), Revisiting Lucas-Kanade and Horn-Schunck, Journal of Computer Engineering and Informatics, Apr. 2013, Vol. 1 Iss. 2, PP. 23-29.

Optical flow

This is defined as the velocity (in x and y components) and the intensity gradient in the same point

Lucas-Kanade

This approach is local because it assumes neighboring pixels move together

Horn-Schunck

the formulation of this method includes a "smoothing term" which helps propagate the neighboring value through flat texture-less areas
This help the algorithm deal with large optical flow values but degrades the boundary conditions between groups of pixels

Multi-channel

Just means all colors RGB or whatever the image means

Multi-resolution

Resizing the image helps the algorithm to detect large blobs because of the overall lack of resolution Creates iteratively smaller images to help clear up boundaries

Visualizations

There should be a python function to do the visualizations required but it also should be hard to make after we implement each algorithm

the direction of the gradient vector is the hue of the segmented pixels and the strength of this vector is the brightness associated with the pixel.

Implementations

The source code regarding this is scarce but there is some documentation in OpenCV regarding particulary Lucas-Kanade

martinhofigueiredo / VC

Research #4