System and Method for Motion Detection and Interpretation

Abstract

A motion detection and interpretation system comprising a camera plus an infrared transmitter/receiver paired with a single reflective surface that records image data from two vantage points. The camera is connected to a computer and a display screen. The system creates a virtual touch screen for interaction with the display screen. The components of the system can be protected behind a transparent barrier while the virtual touch screen is provided for user interaction thus preventing user interference with, deterring vandalism and theft of, and prolonging the usable life of the equipment. In addition to finite hand movements detected by the virtual touch screen, the system can also simultaneously perform facial recognition and body movement recognition. The system is capable of interpreting multi-touch inputs. All recognitions are defined in the computer to carry out preprogrammed responses.

1 . An interactive motion detection system, comprising:
 a camera;   a mirror for providing the camera a reflected a field of view;   a processor for utilizing data from the camera to carry out a computer implemented method having the steps of:
 defining an action area within the reflected field of view; 
 retrieving a set of reflected distance to target information in the action area in a first coordinate system; 
 retrieving a set of position information, from the camera, in the first coordinate system; 
 retrieving a set of image information, from the camera, in a second coordinate system; 
 translating the set of reflected distance to target information and the set of position information, from the first coordinate system into the second coordinate system; and 
 interpreting the set of reflected distance to target information and the first set of position information as a computer command of the set of computer commands, based on the set of image information. 
   
     
     
         2 . The system of  claim 1 , wherein the camera is positioned, adjacent to a display, so as to provide a partially obstructed field of view; and,
 wherein the step of defining further comprises:
 defining the action area adjacent the display. 
   
     
     
         3 . The system of  claim 1 , wherein the action area is comprised of a set of sub-action areas. 
     
     
         4 . The system of  claim 3 , wherein a sub-action area, of the set of sub-action areas, is defined by a unique closed space. 
     
     
         5 . The system of  claim 3  wherein a sub-action area, of the set of sub-action areas, is defined in part by a linear function. 
     
     
         6 . The system of  claim 1  further comprising a transparent barrier; and,
 wherein the display, the camera, and the mirror are coupled to a distance sensor and are positioned adjacent a first side of the transparent barrier; and, 
 the action area is positioned adjacent a second side of the transparent barrier. 
 
     
     
         7 . The system of  claim 6  further comprising a transparent barrier; and,
 wherein the display, the camera, and the distance sensor are positioned adjacent a first side of the transparent barrier; and, 
 the action area and the mirror are positioned adjacent the second side of the transparent barrier. 
 
     
     
         8 . The system of  claim 1  wherein the mirror is one from the group consisting of a concave mirror and a convex mirror. 
     
     
         9 . The system of  claim 1  wherein the implemented method comprises the further step of displaying a feedback response, related to the computer command, on the display. 
     
     
         10 . The system of  claim 1  wherein the computer implemented method comprises the step of:
 transforming the set of reflected distance to target information based on a mirror curvature. 
 
     
     
         11 . The system of  claim 1  wherein the step of translating further comprises the steps of:
 setting an initial location in the second coordinate system; 
 moving a pointer to the initial location; 
 querying the camera for a perceived location; 
 calculating the difference between the initial position and the perceived position; and, 
 deriving a translation function based on the initial location and the perceived location. 
 
     
     
         12 . The system of  claim 1  wherein the computer implemented method further comprises the steps of:
 setting a reflected location in the first coordinate system; 
 moving a pointer to the reflected location; 
 querying the camera for a perceived reflected location; and 
 deriving and storing a transform function based on the reflected location and the perceived reflected location. 
 
     
     
         13 . The system of  claim 1  wherein the camera is positioned adjacent the display so as to provide a partially obstructed view; and
 wherein the computer is programmed to carry out the additional steps of:
 recording in a set of image information from the camera from the partially unobstructed view; and, 
 interpreting the set of image information as a computer command. 
 
 
     
     
         14 . The system of  claim 1  wherein the computer is programmed to carry out the additional step of:
 interpreting the set of image information as a face. 
 
     
     
         15 . The system of  claim 14  wherein the step of interpreting the set of image information further comprises the steps of:
 identifying a set of facial features; 
 determining a map of the set of facial features; and, 
 retrieving a set of demographic information related to the map.