Abstract: A video tracking system and method are provided for tracking a target object with a video camera.

Abstract: A video tracking system and method are provided for tracking a target object with a video camera.

Abstract: A method for reacquiring a target in an automated video tracking system is provided. The method includes the steps of: selecting a desired target to be tracked; switching the automated video tracking system to an automatic mode to initiate a tracking sequence to automatically track the selected desired target; switching the automated video tracking system from an automatic mode to a manual mode if the automated video tracking system encounters a period of difficulty in tracking the desired target; reacquiring the desired target in manual mode; and switching the automated video tracking system to the automatic mode for automatic tracking of the reacquired desired target without initiating a new tracking sequence. An apparatus and automated video tracking system for carrying out the methods of the present invention are also provided.

Abstract: A method and apparatus are disclosed for tuning the content of information presented to an audience, for example, on a large display screen or an information kiosk. A disclosed content selection and driving system (i) extracts relevant characteristics about the audience, (ii) analyzes the characteristics, (iii) modifies the presented content based on the analysis, and (iv) records relevant statistics for reporting. An audio/visual analyzer derives audience characteristics and other information on the public reaction to the presented advertising or information by analyzing audio or video information, or both. The derived characteristics are utilized to tune the content of the presented advertising or information to the characteristics of the current audience. A reporting module receives real-time audience statistics and an indication of the selected content.

Abstract: A method for selecting a target in an automated video tracking system. The method including the steps of: displaying video image data of a scene having a target to be tracked; freezing the video image data to display a frame thereof; and selecting a desired target in the frame of the video image data. Also provided is an apparatus for selecting a target in an automated video tracking system and an automated video tracking system employing such methods and apparatus.

Abstract: A security monitoring system including; an exit and entrance camera located at the exit and entrance of a structure; a detector for detecting the exit or entry of an individual; an image recording system for stroring images from the exit and entrance cameras; and a computer vision system for analyzing the stored images using a predetermined criteria to determine if the exiting and entering individuals are the same. In a preferred implementation, the system also includes a database for storing face image data for each authorized individual of the structure; and a face recognition system for comparing the stored images from the entry and entrance camera with the stored image data in the database and for determining if the exiting and entering individual is one of the authorized individuals.

Abstract: A video tracking system and method which includes a video camera having a selectively adjustable panning orientation, tilting orientation and focal length. A processor receives video images acquired by the camera. The processor is programmed to detect target objects in the images and selectively adjust the camera to track the target object. The camera is adjusted at variable rates which are selected as a function of a property, such as the velocity, of the target object. The focal length of the camera is selectively adjusted as a function of the distance of the target object from the camera. The images acquired by the camera are geometrically transformed to align images having different fields of view to facilitate the analysis of the images and thereby allowing the camera to be continuously adjustable for the production of video images having relatively smooth transitional movements.

Abstract: A tracking system that provides high resolution images and a low tracking dropout rate is disclosed. The system uses a camera equipped with a dual-angle lens (or another dual-angle focusing system) to obtain both a wide-angle image and a narrow-angle image of a scene. The narrow-angle image provides a high resolution view of the scene. If the object being tracked moves out of the field of view of the narrow-angle image, the wide-angle image is used to find the object. The aim of the camera is then adjusted so that the object will once again appear in the narrow-angle image.

Abstract: A system and method that detects and identifies an event from a sequence of images received. The system comprises a control unit that receives and processes the sequence of images from the camera. The control unit identifies at least one stationary image prior to the event and one stationary image subsequent to the event. The control unit compares one or more representations corresponding to one or more edges in the first stationary image with one or more representations corresponding to one or more edges in the second stationary image to determine whether an object has been deposited or removed during the event.

Abstract: A security monitoring system including: an alarm system having detectors for detection of an alarm in a structure; at least one camera for capturing image data inside and/or outside the structure; a processor for selecting a subset of the image data upon the occurrence of the alarm based on a predetermined criteria; and a modem for transmitting the subset of image data to a remote location. The processor ranks each video frame from the image data according to how well each video frame meets the predetermined criteria and the modem transmits a predetermined number of video frames having the best rank to the remote location.

Abstract: A security monitoring system including: an alarm system having detectors for detecting an unauthorized individual in a structure; at least one camera for capturing first image data of the unauthorized individual; a memory for storing second image data of at least one individual authorized to be in the structure; and a data link for transmitting third image data to a remote location upon the detection of the unauthorized individual. The third image data including at least portions of the first and second image data for comparison at the remote location. In a preferred implementation, the first image data includes image data of more than the face of the unauthorized individual and the system further includes a computer vision system for detecting the face of the unauthorized individual from the first image data.

Abstract: A security monitoring system including: an alarm system having detectors for detection of an alarm in a structure; at least one camera for capturing image data inside and/or outside the structure; a processor for selecting a subset of the image data upon the occurrence of the alarm based on a predetermined criteria; and a modem for transmitting the subset of image data to a remote location. The processor ranks each video frame from the image data according to how well each video frame meets the predetermined criteria and the modem transmits a predetermined number of video frames having the best rank to the remote location.

Abstract: A method and apparatus are disclosed for monitoring a location using vision-based technologies to recognize predefined assistance-invoking events. One or more image capture devices are focused on a given location. The captured images are processed to identify one or more predefined events and to initiate an appropriate response, such as sending assistance or recording the event for evidentiary purposes. A number of rules define various assistance-invoking events. Each rule contains one or more conditions that must be satisfied and a corresponding action-item that should be performed when the rule is satisfied. At least one of the conditions for each rule identifies a feature that must be detected in an image using vision-based techniques. An event monitoring process is also disclosed that analyzes the captured images to detect one or more assistance-invoking events defined by the event rules.

Abstract: To facilitate the framing of an image in a camera's field of view, a mirror system is provided that has a field of reflection that corresponds substantially to the field of view of the camera. If a target person can see his or her reflection in the mirror, the target person is assured that a substantially similar image is being seen by the camera. This invention also includes an integration of the mirror-camera framing system with computer vision applications, such as a teleconferencing system, a recognition system, a broadcast system, and a messaging system with attached images for personalization and authentication. The use of a mirror for image feedback allows the invention to be embodied in a small low powered device, such as a watch, pendant, or portable telephone.

Abstract: A method for reacquiring a target in an automated video tracking system is provided. The method includes the steps of: selecting a desired target to be tracked; switching the automated video tracking system to an automatic mode to initiate a tracking sequence to automatically track the selected desired target; switching the automated video tracking system from an automatic mode to a manual mode if the automated video tracking system encounters a period of difficulty in tracking the desired target; reacquiring the desired target in manual mode; and switching the automated video tracking system to the automatic mode for automatic tracking of the reacquired desired target without initiating a new tracking sequence. An apparatus and automated video tracking system for carrying out the methods of the present invention are also provided.

Abstract: A system and method that detects and identifies an event from a sequence of images received. The system comprises a control unit that receives and processes the sequence of images from the camera. The control unit identifies at least one stationary image prior to the event and one stationary image subsequent to the event. The control unit compares one or more representations corresponding to one or more edges in the first stationary image with one or more representations corresponding to one or more edges in the second stationary image to determine whether an object has been deposited or removed during the event.

Abstract: A method for selecting a target in an automated video tracking system. The method including the steps of: displaying video image data of a scene having a target to be tracked; freezing the video image data to display a frame thereof; and selecting a desired target in the frame of the video image data. Also provided is an apparatus for selecting a target in an automated video tracking system and an automated video tracking system employing such methods and apparatus.

Abstract: A security monitoring system including: an alarm system having detectors for detection of an alarm in a structure; at least one camera for capturing image data inside and/or outside the structure; a processor for selecting a subset of the image data upon the occurrence of the alarm based on a predetermined criteria; and a modem for transmitting the subset of image data to a remote location. Preferably, the processor ranks each video frame from the image data according to how well each video frame meets the predetermined criteria and the modem transmits a predetermined number of video frames having the best rank to the remote location.

Abstract: A security monitoring system including; an exit and entrance camera located at the exit and entrance of a structure; a detector for detecting the exit or entry of an individual; an image recording system for storing images from the exit and entrance cameras; and a computer vision system for analyzing the stored images using a predetermined criteria to determine if the exiting and entering individuals are the same. Preferably, the cameras are video cameras and the detector is either a door contact sensor or an infra-red. The system preferably transmits an alarm signal and/or at least a portion of the stored images to a remote site if the exiting and entering individual is determined not to be the same.

Abstract: A security monitoring system including: an alarm system having detectors for detecting an unauthorized individual in a structure; at least one camera for capturing first image data of the unauthorized individual; a memory for storing second image data of at least one individual authorized to be in the structure; and a data link for transmitting third image data to a remote location upon the detection of the unauthorized individual. The third image data including at least portions of the first and second image data for comparison at the remote location. In a preferred implementation, the first image data includes image data of more than the face of the unauthorized individual and the system further includes a computer vision system for detecting the face of the unauthorized individual from the first image data.