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 method and apparatus are disclosed for automatically learning and identifying events in image data using hierarchical HMMs to define and detect one or more events. The hierarchical HMMs include multiple paths that encompass variations of the same event. Hierarchical HMMs provide a framework for defining events that may be exhibited in various ways. Each event is modeled in the hierarchical HMM with a set of sequential states that describe the paths in a high-dimensional feature space. These models can then be used to analyze video sequences to segment and recognize each individual event to be recognized. The hierarchical HMM is generated during a training phase, by processing a number of images of the event of interest in various ways, typically observed from multiple viewpoints.

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.

Abstract: A sound imaging system and method for generating multi-channel audio data from an audio/video signal having an audio component and a video component. The system comprises: a system for associating sound sources within the audio component to video objects within the video component of the audio/video signal; a system for determining position information of each sound source based on a position of the associated video object in the video component; and a system for assigning sound sources to audio channels based on the position information of each sound source.

Abstract: A system and method provides for the automatic generation of a list of channels, stations, selections, etc., that are selected most often on a media presentation device by a user during a particular period of time.

Abstract: A system and method for generating an animation video signal of sign language gestures corresponding to words in an audio/video signal for display on a monitor screen. A speech component is isolated from the audio/video signal and the spoken words in the speech signal are recognized. The spoken words are then used to identify sign language gestures which are mapped onto an animation model for generating an animation signal. The animation signal is used to animate a character icon stored in the monitor to display sign language gestures corresponding to the words of the speech signal.

Abstract: The present invention is a method and apparatus for enhancing a perceived video quality (e.g. higher resolution) on a display in a region surrounding an intersection point of a user's gaze onto a screen of the display.

Abstract: An adaptive face recognition system and method. The system includes a database configured to store a plurality of face classes; an image capturing system for capturing images; a detection system, wherein the detection system detects face images by comparing captured images with a generic face image; a search engine for determining if a detected face image belongs to one of a plurality of known face class; and a system for generating a new face class for the detected face image if the search engine determines that the detected face image does not belong to one of the known face classes. In the event that the search engine determines that the detected face image belongs to one of the known face classes, an adaptive training system adds the detected face to the associated face class.

Abstract: A technique is provided for calculating the time offsets between different video cameras and re-synchronizing the captured frames in a post-processing manner, thus eliminating the necessity of an explicit common clock for synchronization. This approach allows effective synchronization of frames from different cameras so that a multi-camera system can be used to more accurately analyze a subject under observation.

Abstract: A computer-implemented method and apparatus for tracking an image object within successive first and second image frames. The first frame has a first contour model which defines the image object within the first frame. The first contour model has a global motion parameter which defines global motion of the image object between the first frame and at least one frame preceding the first frame. A second contour model is defined in the second frame based upon the global motion parameter. Image blocks that are associated with points on the first contour model are matched with image blocks associated with points on the second frame to produce motion probabilities associated with each contour point. The motion probabilities are based upon the amount of displacement between respective matched image blocks of the first and second contour models. The shape of the second contour model is locally adjusted based upon the motion probabilities to produce a locally adjusted second contour model.