Jump to content


Check out our Community Blogs

Register and join over 40,000 other developers!


Recent Status Updates

View All Updates

Photo
- - - - -

Face Tracking : Kinect, Intel RealSense, or VisageSDK?

kinect realsense intel microsoft hci visagesdk

This topic has been archived. This means that you cannot reply to this topic.
3 replies to this topic

#1 ArthurTur

ArthurTur

    CC Lurker

  • Just Joined
  • Pip
  • 2 posts

Posted 03 July 2015 - 05:42 AM

Hi,

 

I am working on a research project that aims at helping people improve their intercultural communication skills through video conference. For this I want to augment the video conference experience and display information about the difference of facial/gestual behavior. Thus I was looking for a tool that was JavaScript-ready (for video chat augmenting), that can do face-tracking (including facial features and Action Units),some emotion-detection, gesture-tracking if possible, etc.  Best would be if there would be minimal work to do in order to collect the data, my project is about using this data, not collecting it.

I found different possibilities like FaceReader (Noldus), VisageSDK (Visage Technologies), EMOTIENT (iMotions), RealSense (Intel), and Kinect. But most of these tools are aimed at enterprises who look into market research and advertising, so they are quite expensive and not handy for what I would like to do. That is why I reduced to the following list: Kinect, RealSense and VisageSDK.

I would like to know if anybody did have experience with these tools, and how they compare and differ in terms of accuracy, work needed to get results, etc.

Thanks a lot,

Arthur


Edited by ArthurTur, 03 July 2015 - 05:45 AM.


#2 WingedPanther73

WingedPanther73

    A spammer's worst nightmare

  • Moderator
  • 17757 posts

Posted 03 July 2015 - 12:13 PM

Okay, the first thing that popped into my mind: If I'm skyping, for example, then Skype has already grabbed the video input, and I likely don't have a relevant web page open for JavaScript.

 

My first thought is: what programs do you want this to work with, or are you writing your own?


Programming is a branch of mathematics.
My CodeCall Blog | My Personal Blog

My MineCraft server site: http://banishedwings.enjin.com/


#3 ArthurTur

ArthurTur

    CC Lurker

  • Just Joined
  • Pip
  • 2 posts

Posted 06 July 2015 - 04:14 AM

The idea for now is to write our own html5-based video chat. The whole thing is just to test if the idea of augmenting video chat makes sense in order to help people learn culture-general capabilities.



#4 WingedPanther73

WingedPanther73

    A spammer's worst nightmare

  • Moderator
  • 17757 posts

Posted 06 July 2015 - 06:37 AM

So it sounds like you'll have to capture images periodically and process them with the other tools on the server. Unfortunately, I'm not familiar with using any of them, but that seems to be the direction you'd need to investigate.


Programming is a branch of mathematics.
My CodeCall Blog | My Personal Blog

My MineCraft server site: http://banishedwings.enjin.com/





Recommended from our users: Dynamic Network Monitoring from WhatsUp Gold from IPSwitch. Free Download