topic Re: Use R200 Camera to convert body language to speech in Items with no label

Use R200 Camera to convert body language to speech

NMinh1 — Sun, 23 Jul 2017 07:40:04 GMT

Hello

I would like to use Camera Realsense R200 convert body language (belly-to-head) into speech.

I think it should use Machine Learning and OpenCV library.

Anybody can help me clarify my ideal, and how to do it?

Thank you.

P.s: I have to use the R200 camera in this project. And I have an Up Board, I will create a portable device can carry everywhere I want.

Re: Use R200 Camera to convert body language to speech

MartyG — Sun, 23 Jul 2017 07:59:59 GMT

Information about the position of areas of the body can be captured using the R200's 'Person Tracking' system.

https://software.intel.com/sites/landingpage/realsense/camera-sdk/v1.1/documentation/html/index.html?doc_pt_person_tracking.html Intel® RealSense™ SDK 2016 R2 Documentation

My own approach is to animate a full-body avatar based on camera inputs and make logic decisions based on what the joints of that avatar are doing. This is done using a custom system I built called CamAnims. My blog post below explains the basic principles of CamAnms.

Re: Use R200 Camera to convert body language to speech

NMinh1 — Sun, 23 Jul 2017 14:20:26 GMT

Body language include position of fingers, can R200's 'Person Tracking' capture it?

Re: Use R200 Camera to convert body language to speech

MartyG — Sun, 23 Jul 2017 14:29:34 GMT

The R200 unfortunately does not have support for finger joint tracking like the SR300 camera model does. It can only follow the palms through a method such as Blob Tracking.