Visual Gesture Builder (VGB)

This post has been republished via RSS; it originally appeared at: Channel 9.

It's been a long time since we've highlighted the Visual Gesture Builder (VGB), Custom Gestures, Kinect for Windows v2 and the Visual Gesture Builder and Saluting the Visual Gesture Builder - Details and example code.

It's a great tool and one that can really help streamline your Kinect development, so it's time to look at it again...

Visual Gesture Builder: Overview

Visual Gesture Builder (VGB) generates data that applications use to perform gesture detection at run time. Even for simple cases, gesture detection is a challenging task that may require many lines of code to obtain reliable results, considering all of the different users and spaces that an application might encounter. By using a data-driven model, VGB shifts the emphasis from writing code to building gesture detection that is testable, repeatable, configurable, and database-driven. This method provides better gesture recognition and reduces development time.

VGB uses a number of detection technologies. The user selects the detection technologies to use—namely AdaBoostTrigger or RFRProgress—and tags frames in a clip related to a meaningful gesture, such as a punch or a kick. At the end of the tagging process, VGB builds a gesture database; with this database, an application can process body input from a user to, for example, detect a hit or swing progress.


The following are some of the results of using VGB:

  • Mitigating the current code-intensive approach.
  • Reusing gesture definitions in different versions of the same application.
  • Sharing gesture definitions among applications.
  • Creating a library of gesture definitions.
  • Improving the predictability and reliability of gesture definitions.
  • Testing framework for gesture detection.
  • Analyzing and visualizing gesture-detection results.
  • Managing a large quantity of data in a user friendly IDE.

Using Visual Gesture Builder



Project Information URL:

REMEMBER: these articles are REPUBLISHED. Your best bet to get a reply is to follow the link at the top of the post to the ORIGINAL post! BUT you're more than welcome to start discussions here:

This site uses Akismet to reduce spam. Learn how your comment data is processed.