Giter Site home page Giter Site logo

cv-ip / click_carving Goto Github PK

View Code? Open in Web Editor NEW

This project forked from suyogduttjain/click_carving

0.0 2.0 0.0 80.88 MB

Interactive Foreground Segmentation using Point Clicks

Home Page: http://vision.cs.utexas.edu/projects/clickcarving

License: Other

MATLAB 56.28% C++ 43.72%

click_carving's Introduction

Click Carving: Segmenting Objects in Videos with Point Clicks v1.0
================================================================================

Suyog Jain and Kristen Grauman
[email protected]

Please go through run_driver.m to see how to run this code.

Only parameter that you need to adjust is num_proposals, which defines the number of proposals to generate for each frame.

This is a image only version of the algorithm, hence we only use the appearance information to generate the propoasls.

The MCG code is included in the external_libs folder, it was compiled on a 64-bit linux machine, you might need to recompile it for your purpose. 

==========
Interface
==========
Please check the video demo on the wesbite for a quick overview of the interface:
http://vision.cs.utexas.edu/projects/clickcarving/

1) Please use left mouse click on the ***boundaries*** of the object of interest. This will put positive clicks.

2) This version also supports negative clicks. Please use right click to place negative clicks. Negative clicks can be placed anywhere, including the ***interiors***.

The positive clicks are shown in green, the negative ones are shown in red.

After each click, you should see an updated reranking. 

Please note that the GUI is developed using Matlab, which doesn't work well with different screen sizes. However it should be work well for reasonable screen sizes (>15 inch screens).

[1] Suyog Jain, Kristen Grauman, “Click Carving: Segmenting Objects in Video with Point Clicks”, Fourth AAAI Conference on Human Computation and Crowdsourcing (HCOMP), 2016. 


click_carving's People

Contributors

suyogjain avatar

Watchers

 avatar  avatar

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.