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?={p?1, p?2, p?3, p?4} and p?k=(x?k, y?k); and, determining the motion of the head represented by a rotation matrix R and translation vector T using the points P and P?. The head motion estimation is governed according to an equation: P?i=RPi+T, where R = [ r 1 T r 2 T r 3 T ] = [ r ij ] 3 × 3 and T=[T1 T2 T3]T represents camera rotation and translation respectively.

Abstract: Using known methods of face recognition, appliances can be automatically initiated and/or adjusted as a user enters an environment, such as a home or a room. The environment is networked such that there is a communication link between a camera monitoring the entrance to the environment, a face recognition system, and the appliances. The method of automatically controlling a networked environment includes capturing a face image of an individual, storing the face image (i.e., in a memory), and associating at least one appliance setup to the face image. The method also includes comparing the face image to stored face images, retrieving the at least one appliance setup for a matched face image, and initiating the at least one appliance setup. An appliance setup controls turning on or off an appliance, such as an illumination source, a television, or a stereo.

Abstract: A method for generating a recommendation for video content to a viewer where the viewer has a user profile corresponding to a viewing history of the viewer. The method including: accessing at least one other user profile corresponding to a viewing history of another user (202); combining a portion of the at least one other user profile with the user profile of the viewer to create a combined user profile (208); and determining a recommendation for video content based on the combined user profile (210).

Abstract: Aspects of the present invention can be configured to demultiplex an asynchronously multiplexed video signal, which comprises images from a number of different cameras. Image matching techniques are used to assign input images with states. After a period, the number of states will generally equal the number of input cameras. The states may be modeled through any number of techniques, such as histogram analysis, clustering, and hidden Markov model analysis. Input images are assigned to states, and the input images are output as being associated with the states. Zone surveillance may be performed on a series of images from one or more of the states. Any events that occur can be distinguished and reported.

Abstract: Objects are classified using a normalized cross correlation (NCC) measure to compare two images acquired under non-uniform illumination conditions. An input pattern is classified to assign a tentative classification label and value. The input pattern is assigned to an output node in the radial basis function network having the largest classification value. If the input pattern and an image associated with the node, referred to as a node image, both have uniform illumination, then the node image is accepted and the probability is set above a user specified threshold. If the test image or the node image are not uniform, then the node image is not accepted and the classification value is kept as the value assigned by the classifier. If both the test image and the node image are not uniform, then an NCC measure is used and the classification value is set as the NCC value.

Abstract: A video content analysis system extends content analysis capability of one system to multiple channels by providing for the spatial multiplexing of the multiple channels and appropriately analyzing the spatially multiplexed video signal. The resulting system may be lower in cost that present systems and permit the system to work with ancillary equipment such as video recorders. The system also preserves the real-time information inherent in the multiple source signals.

Abstract: An image processing system processes a sequence of images to generate a statistical model for each of a number of different persons to be tagged so as to be identifiable in subsequent images. The statistical model for a given tagged person incorporates at least one appearance feature, such as color, texture, etc., and at least one geometric feature, such as shape or position of a designated region of similar appearance within one or more images. The models are applied to subsequent images in order to perform a person detection, person location and/or person tracking operation. An action of the image processing system is controlled based on a result of the operation.

Abstract: An image processing system processes a sequence of images to generate a statistical model for each of a number of different persons to be tagged so as to be identifiable in subsequent images. The statistical model for a given tagged person incorporates at least one appearance feature, such as color, texture, etc., and at least one geometric feature, such as shape or position of a designated region of similar appearance within one or more images. The models are applied to subsequent images in order to perform a person detection, person location and/or person tracking operation. An action of the image processing system is controlled based on a result of the operation.

Abstract: A method for classifying objects in a scene, is provided. The method including: capturing video data of the scene; locating at least one object in a sequence of video frames of the video data; inputting the at least one located object in the sequence of video frames into a time-delay neural network; and classifying the at least one object based on the results of the time-delay neural network.

Abstract: A monitoring system for an infant, child, invalid, or other person requiring care uses computer vision and hearing, and inputs of other modalities, to analyze the status of a caretaker and/or cared-for person and its environment. The conditions are classified as normal or alarm conditions and an informative alarm signal is generated which may include records of the vision audio and other inputs. The system also has the ability to solicit responses from the occupants to stimulate a classifiable input to reduce ambiguity in its state signal.

Abstract: A camera system comprising a camera, a monitor, an image detector, a touch screen, and a remote control. The monitor displays a field of view of a lens of the camera. The image detector provides a viewer image to the remote control whereby the remote control can determine a desired image within the field of view that the viewer is gazing upon. The touch screen enables a viewer of the monitor to point to the desired image of the field of view and provides signal(s) indicative of the pointing. The remote control is operable to activate various drives to pan and/or tilt the camera, or to zoom and/or focus the lens to the desired image and to follow any movement of the image within the field of view.

Abstract: The learning rate used for updating the weights of a self-ordering feature map is determined by a process that injects some type of perturbation into the value so that it is not simply monotonically decreased with each training epoch. For example, the learning rate may be generated according to a pseudorandom process. The result is faster convergence of the synaptic weights.

Abstract: An image processing system is disclosed that provides automatic face or skin blurring for images. All faces or skin can be blurred, or specific faces can be blurred. In one aspect of the invention, a particular face is blurred on an image or on a series of images in a video. Faces are determined in an image, and face matching is performed to match a particular face to faces in the image. If a match is found, the face or a portion of the face is blurred in the image. The blurring is performed on a portion of the image containing the particular face. Blurring may be performed through a variety of techniques. In another aspect of the invention, voice processing is used as an adjunct to or in place of face analysis to determine if a face in an image or series of images should be blurred. In another aspect of the invention, all faces or human skin in an image or series of images is blurred.

Abstract: A lighting controller is disclosed that automatically adjusts a lighting device based on user activity. The disclosed lighting controller processes at least one of audio and video information to identify predefined user events that suggest that a lighting device should be activated or adjusted. In one implementation, a number of behavior rules define various user activities or events that suggest that the user would like to activate or adjust a lighting device. Each rule contains one or more conditions, and, optionally, a corresponding action-item that should be performed when the rule is satisfied to activate or adjust the lighting device. Upon detection of a predefined event, the corresponding action, if any, is performed by the lighting controller.

Abstract: A system having a video display screen that provides video to a user. The position of the display screen is adjustable based upon the location of the user with respect to the display screen. The system includes at least one image capturing device trainable on a viewing region of the display screen and coupled to a control unit having image recognition software. The image recognition software identifies the user in an image generated by the image capturing device. The software of the control unit also generates at least one measurement of the position of the user based upon the detection of the user in the image.

Abstract: An animated virtual creature is generated on a display such as a television set, in order to simulate a pet or to facilitate user interface functions. In one embodiment, one or more signals corresponding to the program being watched are monitored. When certain events are detected based on this monitoring, the animated character is controlled in a manner that corresponds to the detected event. In another embodiment, the animated virtual creature responds to program selections made by a user in a program recommendation system.

Abstract: A method and system for providing a mood based virtual photo album which provides photos based upon a sensed mood the viewer. The method may include the steps of capturing a first image of a facial expression of a viewer by a camera, providing the image to a pattern recognition module of a processor, determine a mood of the viewer by comparing the facial expression with a plurality of previously stored images of facial expressions having an associated emotional identifier that indicates a mood of each of the plurality of previously stored images, retrieving a set of photos from storage for transmission to the viewer based on the emotional identifier associated with the determined mood, and transmitting the set of photos in the form of an electronic photo album.

Abstract: A system and method is disclosed for taking the results of a search (i.e., electronic documents) using the TFIDF of terms contained in those search result documents to quantify how related the search result documents are to one another, and organizing the search results based on those qualified relations. Using such a system and method, the search result documents can be displayed in such a manner that the relationships between the search result documents is evident to the viewer.

Abstract: Methods and apparatus are disclosed for predicting events using acoustic and visual cues. The present invention processes audio and video information to identify one or more (i) acoustic cues, such as intonation patterns, pitch and loudness, (ii) visual cues, such as gaze, facial pose, body postures, hand gestures and facial expressions, or (iii) a combination of the foregoing, that are typically associated with an event, such as behavior exhibited by a video conference participant before he or she speaks. In this manner, the present invention allows the video processing system to predict events, such as the identity of the next speaker. The predictive speaker identifier operates in a learning mode to learn the characteristic profile of each participant in terms of the concept that the participant “will speak” or “will not speak” under the presence or absence of one or more predefined visual or acoustic cues.

Abstract: A method and apparatus are disclosed for displaying available television programs with an indication of the strength of the contribution of one or more program attributes or features to the overall recommendation score assigned by a program recommender. The program and corresponding indication of the strength of the contribution of one or more program attributes can be presented to the user, for example, using grids listing the available television programs by time and date, channel and title. The overall recommendation scores or component scores associated with each program are also displayed to the user. The overall recommendation scores or component scores can be displayed with each program directly or can be mapped onto a color spectrum or another visual cue, such as a variable size-of-text, rate of blinking or bar height. The visual cues are then applied to each program in the program grid in accordance with the present invention.