Giter Site home page Giter Site logo

bregmanstudio / action-video-toolkit Goto Github PK

View Code? Open in Web Editor NEW
11.0 6.0 7.0 52.11 MB

ACTION: Audio-visual Cinematic Toolkit for Interaction, Organization, and Navigation

Home Page: http://bregman.dartmouth.edu/action

Python 75.16% Shell 2.89% C++ 15.16% Makefile 4.12% HTML 1.00% Batchfile 1.68%

action-video-toolkit's Introduction

ACTION

Public repo for the ACTION project at Dartmouth

Check out http://bregman.dartmouth.edu/action for more information!

Welcome to the ACTION toolbox from the Bregman Music and Audio Research Studio at Dartmouth College. These pages document the toolbox and show examples of its use.

What is ACTION?

Audio-visual Cinematic Toolkit for Interaction, Organization, and Navigation (of video datasets)

ACTION provides a work bench to study such features in combination with machine learning methods to yield latent stylistic patterns distributed among films and directors. As such, ACTION is a platform for researching new methodologies in the study of film and media history.

The platform allows such features as access to and analysis of low-level frame-by-frame data, automated segmentation and clustering of this data, audio analysis for soundtracks, and other content analysis tools. ACTION provides Python tools to support research and development, and depends on the Bregman Python Toolkit. OpenCV 2.4 compiled with Python bindings is required for analysis.

Co-principle investigators: Michael Casey (Bregman) and Mark Williams (Film and Media Studies). Postdoctoral researcher: Tom Stoll (Bregman). Sponsored by the National Endowment for the Humanities (NEH), Office of Digital Humanities (ODH) Grant #HD-51394-11

Who Is ACTION for?

ACTION provides Python tools to support research and development including, but not limited to:

  • Multimedia IR - explore methods for video information retrieval (requires OpenCV package)
  • See Bregman’s documentation index for a similar list of aims.

How is ACTION Used?

Using ACTION is as easy as:

from action.suite import *
cfl = ColorFeaturesLAB('North_by_Northwest')
cfl.analyze_movie()

...then access the analysis data:

myseg = Segment(0, cfl.determine_movie_length())
data = cfl.full_color_features_for_segment(myseg)

You can also view the data alongside the imagery of the film:

cfl.playback_movie()

ACTION also has functionality for analyzing and accessing optical flow (movement) information and audio analysis metadata.

More Information

Check out http://bregman.dartmouth.edu/action for more information!

action-video-toolkit's People

Contributors

soundspotter avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar

action-video-toolkit's Issues

.info files

Copy text metadata to a .info file per film.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.