System and method for database driven action capture

摘要

There is provided a system and method for database driven action capture. By utilizing low cost, lightweight MEMS devices such as accelerometers, a user friendly, wearable, and cost effective system for motion capture is provided, which relies on a motion database of previously recorded motions to reconstruct the actions of a user. By relying on the motion database, calculation errors such as integration drift are avoided and the need for complex and expensive positional compensation hardware is avoided. The accelerometers may be implemented in an E-textile embodiment using inexpensive off-the-shelf components. In some embodiments, compression techniques may be used to accelerate linear best match searching against the motion database. Adjacent selected motions may also be blended together for improved reconstruction results and visual rendering quality. Various perceivable effects may be triggered in response to the reconstructed motion, such as animating a 3D avatar, playing sounds, or operating a motor.

主权项

1. A method for translating motions of a user into perceptible effects, the method comprising:
receiving a first motion data from a plurality of motion sensing devices based on detecting the motions of the user; converting the first motion data to a first processed motion data, wherein the converting includes generating a first set of sliding data windows containing a first acceleration data corresponding to the first motion data; selecting a first recorded motion from a database of recorded human motions by querying the database using the first processed motion data; causing a first perceptible effect in response to selecting the first recorded motion; receiving a second motion data from the plurality of motion sensing devices, wherein the second motion data contains a first subset of data from the first motion data and a second subset of data more recent in time than, the first motion data; converting the second motion data to a second processed motion data, wherein the converting includes generating a second set of sliding data windows containing a second acceleration data corresponding to the second motion data; selecting a second recorded motion from the database by querying the database using the second processed motion data, wherein the first subset of data is given less weight than the second subset of data when selecting a second recorded motion; and causing a second perceptible effect in response to selecting the first recorded motion and selecting the second recorded motion.