Skip to content
forked from pathak22/pyflow

Fast, accurate and easy to run dense optical flow with python wrapper

License

Notifications You must be signed in to change notification settings

mpwillia/pyflow

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

19 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Python Dense Optical Flow

Python wrapper for Ce Liu's C++ implementation of Coarse2Fine Optical Flow. This is super fast and accurate optical flow method based on Coarse2Fine warping method from Thomas Brox. This python wrapper has minimal dependencies, and it also eliminates the need for C++ OpenCV library. For real time performance, one can additionally resize the images to a smaller size.

Run the following steps to download, install and demo the library:

git clone https://github.com/pathak22/pyflow.git
cd pyflow/
python setup.py build_ext -i
python demo.py    # -viz option to visualize output

This wrapper code was developed as part of our CVPR 2017 paper on Unsupervised Learning using unlabeled videos. Github repository for our CVPR 17 paper is here.

Fork Modification - Verbose Argument

Added a verbose argument to the coarse2fine_flow function that allows the user to enable/disable most console output from the function. The verbose argument defaults to False, suppressing output messages.

The output affected by this flag includes all non-error related messages as well as any error messages associated with recoverable errors. Messages relating to non-recoverable errors are never suppressed.

Setup and usage of the library is identical to the original wrapper.

The demo.py file has been updated make use of the new verbose argument set to True for the sake of example. Besides the inclusion of the new extra argument the behavior is identical to the original demo.py file.

About

Fast, accurate and easy to run dense optical flow with python wrapper

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • C++ 97.1%
  • Python 2.5%
  • C 0.4%