Abstract: The present invention relates to a device containing an automatic zoom lens, and more particularly to a zoom lens that is controlled by a processor that is linked to a gaze tracking system. As a user looks onto an object through the device, the gaze tracking system collects data relating to the position of each eye of the user. This eye position data is input into the processor where the focal point of the user is determined. The processor then adjusts the zoom lens to zoom in or out onto the object based on either a predetermined or user input zoom factor.

Abstract: An appliance controller is disclosed that monitors the operation of an appliance and automatically adjusts the appliance in response to predefined audio activity. The disclosed appliance controller includes one or more microphones to capture audio information associated with an appliance. A number of exemplary appliance adjustment rules define various audio features that suggest when an appliance setting should be adjusted. Each rule contains one or more audio features and a corresponding appliance adjustment that should be performed when the rule is satisfied. The appliance adjustment rules can be predefined or dynamically determined from observed user behavior.

Abstract: System and method for displaying a driving scene to a driver of an automobile. The system comprises at least one camera having a field of view and facing in the forward direction of the automobile. The camera captures images of the driving scene, the images comprised of pixels of the field of view in front of the automobile. A control unit receives the images from the camera and applies a salt and pepper noise filtering to the pixels comprising the received images. The filtering improves the quality of the image of the driving scene received from the camera when degraded by a weather condition. A display receives the images from the control unit after application of the filtering operation and displays the images of the driving scene to the driver.

Abstract: Cameras and image processing techniques are applied to the control of HVAC systems. Occupancy is detected using head-counting or motion detection. Activities are recognized in images and image sequences by machine-recognition techniques. The nature of activities, the intensity of activities, the number of occupants and their activities, etc. are all inferred from images and image sequences and used to predict current loads and/or required control signals for regulating an HVAC system.

Abstract: Generally, an Eigen network and system using same are disclosed that use Principal Component Analysis (PCA) in a middle (or “hidden”) layer of a neural network. The PCA essentially takes the place of a Radial Basis Function hidden layer. A classifier comprises inputs that are routed to a PCA device. The PCA device performs PCA on the inputs and produces outputs (entitled “PCA outputs” for clarity). The PCA outputs are connected to output nodes. Generally, each output is connected to each output node. Each connection is multiplied by a weight, and each output node uses weighted PCA outputs to produce an output (entitled a “node output” for clarity). These node outputs are then generally compared in order to assign a class to the input. A system uses the PCA classifier to classify input patterns. In a third aspect of the invention, a PCA classifier is trained in order to determine weights for each of the connections that are connected to the output nodes.

Abstract: A method and apparatus are disclosed for monitoring a location using vision-based technologies and to automatically trigger the activation of a child safety feature or an alarm when a child is detected. One or more image capture devices are focused on a given location. The captured images are processed to identify the presence of a child and to initiate an appropriate response, such as sending assistance, activating a child safety feature or triggering an alarm. A number of rules can be utilized to define various child safety events. Each rule contains one or more conditions that must be satisfied in order for the rule to be triggered, and, optionally, a corresponding action-item that should be performed when the rule is satisfied, such as sending assistance, activating a child safety feature or triggering an alarm.

Abstract: Point matches between images within an image sequence are identified by sparse optical flow computation and employed to compute a fundamental matrix for the epipolar geometry, which in turn is employed to derive an epipolar geometry constraint for computing dense optical flow for the image sequence. The epipolar geometry constraint may further be combined with local, heuristic constraints or robust statistical methods. Improvements in both accuracy and performance in computing optical flow are achieved utilizing the epipolar geometry constraint.

Abstract: An infinity homography for an image pair within an image sequence is transferred to other image pairs within the image sequence utilizing point matches for the subject image pairs. An image set including the image pair for which the infinity homography is known and a third image are selected. Then intermediate parameters for homography transfer for one image pair overlapping the known infinity homography image pair is computed from the known infinity homography and epipoles and fundamental matrices of the overlapping image pairs, to derive the infinity homography for the selected overlapping image pair. The process may then be repeated until infinity homographies for all image pairs of interest within the image sequence have been derived.

Abstract: This invention provides an alarm system and method for adjusting the wake-up signals. The system includes a means for tracking the behavior of a person in a predetermined area under surveillance after the activation of an alarm clock, and a means for determining whether the person is motionless for a predetermined time period. Upon recognition that the observed behavior indicates the person is still sleeping, the wake-up signals are gradually increased. At the same time, the electrical power supplied to a plurality of electronic devices may be increased to assist the person to wake up.

Abstract: The present invention relates to a control system and method for automatically adjusting the viewing condition to enhance the experiences associated with watching a television program. The system includes a unit for deriving a classification of each video signal received therein, a unit for observing a viewer's facial expression, and a unit for processing the output of the observed facial expression to determine whether the observed facial expression is associated with predefined facial expressions stored in a recognition module. Based on the classification and/or if there is a match between the observed facial expression with the at least one of the predefined facial expressions, the electrical power supplied to any one of electrical devices provided in the room is varied according to predetermined criteria.

Abstract: A camera-based system implements a calibration procedure for determining, for a given system user, calibration information that characterizes the manner in which the user points within the system. The system directs the user to point separately at each point in a set of two or more points at different positions on a display. The system then detects, for each of the points pointed to by the user, a location of a pointing finger of the user in an image generated by each camera in a set of cameras of the system, such that for each of the points the location of the pointing finger and the corresponding point on the display specify a line. The lines associated with the points are then used to compute a reference point or other pointing direction calibration information for the user. The calibration information for the user may be stored with user-identifying information in a database of the system, and is utilized in subsequent pointing direction determinations for that user.

Abstract: A system and method for classifying facial images from a partial view of a facial image, the method comprising the steps of: training a classifier device for recognizing facial images, the classifier device being trained with input data associated with a facial image of a subject; detecting a partial view of a subject's facial image; warping the partial view of the subject's facial image onto a frontal image to obtain a warped image of the subject; and, classifying the warped image according to a classification method performed by the trained classifier device.

Abstract: A system and method for classifying facial image data, the method comprising the steps of: training a classifier device for recognizing one or more facial images and obtaining corresponding learned models the facial images used for training; inputting a vector including data representing a portion of an unknown facial image to be recognized into the classifier; classifying the portion of the unknown facial image according to a classification method; repeating inputting and classifying steps using a different portion of the unknown facial image at each iteration; and, identifying a single class result from the different portions input to the classifier.

Abstract: Linear method for performing head motion estimation from facial feature data, the method comprising the steps of: obtaining first facial image and detecting a head in the first image; detecting position of four points P of said first facial image where P={p1, p2, p3, p4}, and pk=(xk, yk); obtaining second facial image and detecting a head in the second image; detecting position of four points P′ of the second facial image where P′={p1′, p2′, p3′, p4′} and pk′=(xk′, yk′); and, determining the motion of the head represented by a rotation matrix R and translation vector T using the points P and P′.

Abstract: A system and method for classifying facial images from a temporal sequence of images, comprises the steps of: training a classifier device for recognizing facial images, the classifier device being trained with input data associated with a full facial image; obtaining a plurality of probe images of the temporal sequence of images; aligning each of the probe images with respect to each other; combining the images to form a higher resolution image; and, classifying said higher resolution image according to a classification method performed by the trained classifier device.

Abstract: A system and method for classifying facial image data, the method comprising the steps of: training a classifier device for recognizing facial images and obtaining learned models of the facial images used for training; inputting a vector of a facial image to be recognized into the classifier, the vector comprising data content associated with one-half of a full facial image; and, classifying the one-half face image according to a classification method. Preferably, the classifier device is trained with data corresponding to one-half facial images, the classifying step including matching the input vector of one-half image data against corresponding data associated with each resulting learned model.

Abstract: A ball-throwing machine includes a camera connected to a computer vision unit and a microphone connected to a speech-processing unit. The computer vision unit processes images from the camera to determine a user's position, and to detect user gestures from a predetermined repertoire of gestures. The speech-processing unit recognizes user vocal commands from a predetermined repertoire of commands. A computer receives information from a control panel, from the computer vision unit, from the speech-processing unit, and from a file describing the ballistic properties of the ball to be thrown. The computer accordingly determines a ball trajectory according to the user's position and parameters indicated by a combination of control-panel settings, user gestures, and user vocal commands. The computer then adjusts the direction, elevation, ball speed, and ball spin to conform to the determined trajectory, and initiates throwing of a ball accordingly.

Abstract: A system and apparatus are disclosed for modeling patterns of behavior of humans or other animate objects and detecting a violation of a repetitive pattern of behavior. The behavior of one or more persons is observed over time and features of the behavior are recorded in a multi-dimensional space. Over time, the multi-dimensional data provides an indication of patterns of human behavior. Activities that are repetitive in terms of time, location and activity, such as sleeping and eating, would appear as a Gaussian distribution or cluster in the multi-dimensional data. Probability distribution functions can be analyzed using known Gaussian or clustering techniques to identify repetitive patterns of behavior and characteristics thereof, such as a mean and variance. Deviations from repetitive patterns of behavior can be detected and an alarm can be triggered, if appropriate.

Abstract: A measure of effectiveness of a camera's deployment includes the camera's effectiveness in providing image information to computer-vision applications. In addition to, or in lieu of, measures based on the visual coverage provided by the deployment of multiple cameras, the effectiveness of the deployment includes measures based on the ability of one or more computer-vision applications to perform their intended functions using the image information provided by the deployed cameras. Of particular note, the deployment of the cameras includes consideration of the perspective information that is provided by the deployment.

Abstract: A method for monitoring a person of interest in a scene, the method comprising: capturing image data of the scene; detecting and tracking the person of interest in the image data; analyzing features of the person of interest; and detecting at least one of an event and behavior associated with the detected person of interest based on the features; and informing a third party of the at least one detected events and behavior.