Lucent Technologies Inc.

At+t Corp.

At&t Bell Laboratories

At&t Ipm Corp.

Jakub Segen

Senthil Kumar

David Crawford Gibbon

Behzad Shahraray

Arun N Netravali

Russell L Andersson

Sarma Vgk Pingali

Sentihil Kumar

An input interface system provides gesture-based user control of an application running on a computer by classification of user gestures in image signals. A given one of the image signals is processed to determine if it contains one of a number of designated user gestures, e.g., a point gesture, a reach gesture and a click gesture, each of the gestures being translatable to a particular control signal for controlling the application. If the image signal is determined to contain a point gesture, further processing is performed to determine position and orientation information for a pointing finger of a hand of the user and its corresponding shadow. The position and orientation information for the pointing finger and its shadow are then utilized to generate a three-dimensional pose estimate for the pointing figure in the point gesture. For example, the three-dimensional pose estimate may be in the form of a set of five parameters (X, Y, Z, &agr;, &egr;), where (X, Y, Z) denotes the position of a tip of the pointing finger in three-dimensional space, and (&agr;, &egr;) denotes the respective azimuth and elevation angles of an axis of the pointing finger. The point gesture can thus be used to provide user control in virtual flight simulators, graphical editors, video games and other applications.

Gesture-based input interface system with shadow detection

An interface method and apparatus using video images of hand gestures. A video signal having a frame image containing regions is input to a processor. A plurality of regions in the frame are defined and screened to locate an image of a hand in one of the regions. The hand image is processed to locate extreme curvature values, such as peaks and valleys, corresponding to predetermined hand positions and gestures. The number of peaks and valleys are then used to identify and correlate a predetermined hand gesture to the hand image for effectuating a particular computer operation or function.

Video hand image computer interface

A system and method for manipulating virtual objects in a virtual environment, for drawing curves and ribbons in the virtual environment, and for selecting and executing commands for creating, deleting, moving, changing, and resizing virtual objects in the virtual environment using intuitive hand gestures and motions. The system is provided with a display for displaying the virtual environment and with a video gesture recognition subsystem for identifying motions and gestures of a user's hand. The system enables the user to manipulate virtual objects, to draw free-form curves and ribbons and to invoke various command sets and commands in the virtual environment by presenting particular predefined hand gestures and/or hand movements to the video gesture recognition subsystem.

Gesture-based computer interface

A video gesture-based three-dimensional computer interface system that uses images of hand gestures to control a computer and that tracks motion of the user's hand or an elongated object or a portion thereof in a three-dimensional coordinate system with five degrees of freedom. The system includes a computer with image processing capabilities and at least two cameras connected to the computer. During operation of the system, hand images from the cameras are continually converted to a digital format and input to the computer for processing. The results of the processing and attempted recognition of each image are then sent to an application or the like executed by the computer for performing various functions or operations. However, when the computer recognizes a hand gesture as a &ldquo;point&rdquo; gesture with one finger extended, the computer uses information derived from the images to track three-dimensional coordinates of the extended finger of the user's hand with five degrees of freedom. The computer utilizes two-dimensional images obtained by each camera to derive three-dimensional position (in an x, y, z coordinate system) and orientation (azimuth and elevation angles) coordinates of the extended finger.

Video hand image three-dimensional computer interface

A video gesture-based three-dimensional computer interface system that uses images of hand gestures to control a computer and that tracks motion of the user's hand or a portion thereof in a three-dimensional coordinate system with ten degrees of freedom. The system includes a computer with image processing capabilities and at least two cameras connected to the computer. During operation of the system, hand images from the cameras are continually converted to a digital format and input to the computer for processing. The results of the processing and attempted recognition of each image are then sent to an application or the like executed by the computer for performing various functions or operations. When the computer recognizes a hand gesture as a 'point' gesture with one or two extended fingers, the computer uses information derived from the images to track three-dimensional coordinates of each extended finger of the user's hand with five degrees of freedom. The computer utilizes two-dimensional images obtained by each camera to derive three-dimensional position (in an x, y, z coordinate system) and orientation (azimuth and elevation angles) coordinates of each extended finger.

Video hand image-three-dimensional computer interface with multiple

The specification relates to a method and apparatus for tracking object position during active segments of motion monitored from a plurality of video cameras, repetitively sampling object position, representing various object trajectories during active segments as equations, and synthesizing an animated version of the motion of the object from the representative equations. The present description is described in the context of synthesis of an animated version of a tennis game, although a representation of object motion of any sort is equally applicable, if the object motion is capable of being reduced to the form of an equation or series of equations. In a further enhancement, player position, player extremities, and player controlled objects (such as a racquet) are also tracked and sampled and utilized to provide an animation more faithfully reproducing player position, player motion and other game parameters.

Method and apparatus for tracking, storing, and synthesizing an animated

The head in a series of video images is identified by digitizing sequential images, subtracting a previous image from an input image to determine moving objects, calculating boundary curvature extremes of regions in the subtracted image, comparing the extremes with a stored model of a human head to find regions shaped like a human head, and identifying the head with a surrounding shape.

Method and means for detecting people in image sequences

A method and apparatus for tracking moving objects, such as people, in real time by grouping existing feature paths from a current video frame with preexisting clusters from current video frames. Grouping is accomplished by selecting, as a candidate cluster to a specified feature path, the cluster having the closest relative distance to the specified feature path. The relative distance is calculated according to a function having a first component and a second component. The first component is representative of a maximum displacement between the select feature path and the candidate cluster, and the second component is representative of the difference between velocity vectors defining the select feature path motion and velocity vectors defining the candidate cluster motion. The method and apparatus also provide for updating the candidate cluster with parameters obtained from the select feature path and for merging overlapping clusters.

Method and apparatus for tracking moving objects in real time using

An apparatus and method for determining the location of an object in an active area of a first plane. The apparatus includes a first reflecting device, disposed substantially perpendicular to the first plane at a periphery of the active area. The first reflecting device receives a first image of the object from the active area and reflects the first image back toward the active area substantially parallel to the first plane. A second reflecting device, disposed substantially perpendicular to the first plane at a periphery of the active area, receives a second image of the object from the active area and reflects the second image back toward the active area substantially parallel to the first plane. The second reflecting device is disposed at a first angle which is less than one-hundred eighty degrees to the first reflecting device. The angle opens toward the active area and toward a detecting device. The detecting device is disposed in the first plane at a periphery of the active area opposite the first and second reflecting devices. The detecting device receives the first image and the second image and produces a signal indicating the position of the first and second images.

Sensing stylus position using single 1-D image sensor

An inexpensive, yet robust color matcher is achieved by an apparatus which includes a compare device coupled to receive, as a first input, an input signal representing a combination of a luminance component Y and a chrominance component, and further coupled to receive as a second input, a threshold T, for comparing the input signal to the threshold T and outputting a color match signal if the input signal falls within a range defined by T and -T; and a threshold supply device coupled to the second input for supplying the threshold T, wherein the threshold T is a function of Y and at least two adjustable parameters.

Apparatus for matching colors in image signals

An image recognition system uses feature or attribute matching for fast coarse selection of a group of reference images which closely resemble an unknown image and thereafter selects the best reference image match from that group using 2-dimensional intensity correlation or template matching. The system provides highly accurate image recognition without resorting to time consuming exhaustive search by template matching.

Growing community of inventors

Fair Haven, NJ, United States of America

Jakub Segen