Gesture detection based on joint skipping

Abstract

A system is disclosed for detecting or confirming gestures performed by a user by identifying a vector formed by non-adjacent joints and identifying the angle the vector forms with a reference point. Thus, the system skips one or more intermediate joints between an end joint and a proximal joint closer to the body core of a user. Skipping one or more intermediate joints results in a more reliable indication of the position or movement performed by the user, and consequently a more reliable indication of a given gesture.

Description

Technical field [0001] The present invention relates to a motion capture system, in particular to posture detection in a motion capture system. Background technique [0002] In the past, computing applications such as computer games and multimedia applications used control commands to allow users to manipulate game characters or other aspects of the application. Generally, such control commands are input using, for example, a controller, remote control, keyboard, mouse, etc. Recently, computer games and multimedia applications have begun to use cameras and software gesture recognition engines to provide human-machine interfaces ("HCI"). Use HCI to detect and interpret user gestures and use them to control game characters or other aspects of the application. [0003] In conventional games and multimedia applications, the user's body position is usually used to measure whether the user performs a given gesture. Specifically, the HCI system can measure the angle formed by a vector ...

AI Technical Summary

Problems solved by technology

[0004] The problem with this traditional approach to pose detection is that the angle formed between two adjacent end joints suffers from a lot of jitter and noise

Thus, using adjacent joints can sometimes be unreliable for pose detection

Images