This project is aiming at detecting gestures(like wave,swipe) and training user-defined gesture templates. Since people do the the same gesture in different ways, before you try a gesture template trained by others, you may need to "play" the skeleton file first to see how the gesture was recorded. Or you may train your own gesture templates directly. See the usage for details.

The function is provided in a package for Unity3D. It reads skeleton data from MS Kinect or similar motion capture devices. To acquire skeleton data, we uses OpenNI 1.5.4 because it is an open source library. The scripts in the project are written in c#.

The algorithm we use is template matching. The structure of the code is clear and not very complicated. If you want to use it on other platforms, you may pick part of the scripts in the "GestureScripts" folder and try to edit them to fit other SDKs or platforms.

The usage and algorithm introduction are also provided. Try it and have fun!

Features

  • Open source
  • Support all kinds of gestures and postures
  • Allow user to train their own gesture templates
  • The algorithm is not complicated, therefore fast
  • Document provided

Project Samples

Project Activity

See All Activity >

Follow GestureDetect

GestureDetect Web Site

Other Useful Business Software
PRTG Catches Network Issues Before They Cause Downtime Icon
PRTG Catches Network Issues Before They Cause Downtime

Threshold-based alerts flag problems early, so your team can act before users notice, not after.

Reactive troubleshooting usually means hearing about a problem from frustrated users, not your monitoring tool. PRTG sets threshold-based alerts across devices, servers and applications, notifying your team by email, SMS or push the moment a metric crosses a set limit. That means catching a failing disk or overloaded server before it becomes an outage and getting time back from firefighting. Start a free trial and set your first alerts today.
Download 30-Day Trial
Rate This Project
Login To Rate This Project

User Reviews

Be the first to post a review of GestureDetect!

Additional Project Details

Registered

2013-08-28