Method for recognizing motion gesture commands

Abstract

A computer capable of recognizing gesture commands is disclosed. Suppose that a user makes a gesture of swinging a hand from side to side in front of a camera associated with a computer. A camera module receives frames with shots of the gesture in order. The camera module calculates a gradation difference between corresponding pixels of each frame and a background image to generate a set of binarized differential images. The camera module then combines differential images to generate composite images. In response to a determination that any of the composite images matches a reference pattern, the camera module outputs a computer command. The computer command can be used to control the power state of the computer or start a specific application within the computer.

What is claimed is:  
     
         1 . A method comprising:
 defining a reference pattern;   receiving a frame from an image sensor that has captured a blurred image of an object;   identifying a shape of said blurred image included in said received frame;   comparing said identified shape of said blurred image with said reference pattern to determine whether or not said identified shape represents a gesture command; and   in response to a determination that said identified shape represents a gesture command, generating a corresponding command for controlling an operation of a computer.   
     
     
         2 . The method of  claim 1 , wherein said receiving further includes receiving a plurality of consecutive frames of said object taken at a predetermined frame rate. 
     
     
         3 . The method of  claim 2 , wherein said identifying further includes
 identifying shapes of blurred images in said plurality of consecutive frames;   combining said shapes of said blurred images respectively included in said plurality of consecutive frames to generate a composite image.   
     
     
         4 . The method of  claim 3 , wherein said identifying further includes comparing a background image with said images in said consecutive frames to determine a difference between gradation values of corresponding pixels in order to generate a binarized differential image. 
     
     
         5 . The method of  claim 3 , wherein said identifying further includes comparing said frames with each other to determine a difference between gradation values of corresponding pixels in order to generate a binarized differential image. 
     
     
         6 . The method of  claim 5 , wherein said comparing further includes determining a logical sum for said binarized differential image to generate said composite image. 
     
     
         7 . A method comprising:
 defining a reference pattern with which a computer command is associated;   setting an exposure time of an image sensor to capture a blurred image of a motion gesture;   receiving, from said image sensor, a frame with said motion gesture shot therein;   identifying a shape of said blurred image from said frame;   determining whether or not said shape of said blurred image matches said reference pattern; and   in response to a determination that said shape of said blurred image matches said reference pattern, sending a corresponding computer command to a computer.   
     
     
         8 . The method of  claim 7 , further comprising changing a power state of said computer in response to said computer command. 
     
     
         9 . The method of  claim 7 , further comprising causing said computer to start executing an application program in response to said computer command. 
     
     
         10 . The method of  claim 7 , wherein a shape of said reference pattern is a fan shape that forms a blurred image as a result of reciprocating motion of an arm using an elbow or a shoulder as a pivot point. 
     
     
         11 . A computer comprising:
 a camera system;   a reference image registering block for storing a reference pattern with which a command is associated;   a blurred image processing block for identifying a shape of a blurred image of a moving object from a frame with the object shot therein; and   a pattern recognition block for
 comparing said identified shape of said blurred image with said reference pattern; 
 determining whether or not said shape of said blurred image matches said reference pattern; and 
 generating, in response to a determination that said shape of said blurred image matches said reference pattern, a corresponding computer command. 
   
     
     
         12 . The computer of  claim 11 , wherein said blurred image processing block includes
 a differential image generating section for determining a gradation difference between corresponding pixels of frames to generate a binarized differential image; and   a composite image generating block for determining a logical sum for the differential image to generate a composite image.   
     
     
         13 . The computer of  claim 11 , further comprising:
 a background image generating section for generating a background image of said object;   a differential image generating section for calculating a gradation difference between corresponding pixels of said background image and each frame to generate a binarized differential image; and   a composite image generating section for calculating a logical sum for said differential image to generate a composite image.   
     
     
         14 . The computer of  claim 13 , wherein when said computer detects an acceleration greater than or equal to a predetermined value, said background image generating block updates the background image.