pyoptflow 1.3.0

Pure Python optical flow: Horn-Schunck

Optical Flow: Horn-Schunck

Python implementation of optical flow estimation using only the Scipy stack for:

• Horn Schunck

Lucas-Kanade is also possible in the future, let me know if you’re interested in Lucas Kanade.

Contents

• Optical Flow: Horn-Schunck

  • Install

  • Examples

    • Box

    • Office

    • Rubic

    • Sphere

  • Comparision with Matlab Computer Vision toolbox

  • Reference

Install

Requires Python >= 3.6:

pip install -e .

optionally, to run self-tests:

pip install -e .[tests]

pytest -v

Examples

The program scripts expect <directory> <glob pattern> It uses [imageio](https://imageio.github.io/) to load a very wide varity of images and video.

Box

python HornSchunck.py data/box box*.bmp

Office

all time steps:

python HornSchunck.py data/office office*.bmp

or just the first 2 time steps:

python HornSchunck.py data/office office.[0-2].bmp

Rubic

python HornSchunck.py data/rubic rubic*.bmp

Sphere

python HornSchunck.py data/sphere sphere*.bmp

Comparision with Matlab Computer Vision toolbox

In Matlab directory, similar method in Octave and a comparison plot using Matlab Computer Vision toolbox.

Reference

Inspiration