Abstract: According to an example aspect of the present disclosure, there is provided an apparatus configured for applying a stationary motion noise high-pass filter to at least one chronological frame-rate stream of motion vectors, to generate a high-pass filtered stream of motion vectors, to apply a short-term low-pass filter to the high-pass filtered stream of motion vectors to generate a low-pass and high-pass filtered stream of motion vectors, and, for applying a band-pass filter to the low-pass and high-pass filtered stream of motion vectors, to generate a band-pass filtered stream of motion vectors, wherein the band-pass filter is configured to distinguish short-term moving activity and means for detecting whether at least one event is present based on the low-pass and high-pass filtered stream of motion vectors and the band-pass filtered stream of motion vectors.

Abstract: Micro-structures are formed within multilayer laminate security documents by embossing and/or debossing one or more thermoplastic layers prior to lamination of the layers. The embossed and/or debossed structures are arranged and/or formed in a way that creates a number of different security features, including a watermark formed by a relief micro-structure pattern on an opaque film (layer), a multi-color optically variable device, a 3-dimensional feature over kinegram/metallic ink and/or embossment/debossment over printed surfaces.

Abstract: A driver behavior monitoring system includes: a video camera; an image processing system; and a driver alert system. The video camera records the driver's behavior, and the image processing system analyzes the recorded video content to recognize and classify the driver's behavior as at least one of: (i) distracted behavior; and (ii) accident behavior. Based on the recognition and classification, the driver alert system may perform various operations such as alerting the driver, alerting the authorities, etc.

Abstract: Micro-structures are formed within multilayer laminate security documents by embossing and/or debossing one or more thermoplastic layers prior to lamination of the layers. The embossed and/or debossed structures are arranged and/or formed in a way that creates a number of different security features, including a watermark formed by a relief micro-structure pattern on an opaque film (layer), a multi-color optically variable device, a 3-dimensional feature over kinegram/metallic ink and/or embossment/debossment over printed surfaces.

Abstract: In at least some example embodiments, a data processing apparatus is configured to recover a network connection within an application framework that hides sockets by separating acquisition and processing into different threads of the same process, and, thus, when the processing thread is unable to retrieve a frame from the acquisition thread, the data processing device may terminate the acquisition thread with impunity since all important application state may safely remain within the processing thread.

Abstract: Methods and apparatus are disclosed for authenticating a user based on the geo-location history of a geo-location-enabled wireless device (e.g., a GPS-enabled wireless telecommunications terminal, a smart card, an RFID tag, etc.). In a first illustrative embodiment, a user of a geo-location-enabled wireless telecommunications terminal (e.g., a GPS-enabled cell phone, a GPS-enabled notebook computer, etc.) who attempts to access a restricted resource is challenged with one or more questions that are generated from the terminal's geo-location history. In a second illustrative embodiment, a user of a data-processing system who attempts to access a restricted resource is asked to provide a username Z. The user is then challenged with one or more questions that are generated from the geo-location history of a wireless device that is associated with username Z (e.g., a cell phone that belongs to the user whose username is Z, etc.).

Abstract: In at least some example embodiments, a learning apparatus may include a processor configured to capture one or more parallel samples of a feature at a regular interval, selectively perform accelerated learning of a trend based on a number of the one or more parallel samples, and analyze a latest parallel sample of the one or more parallel samples based on the trend, where the accelerated learning may include capturing augmented samples.

Abstract: In at least some example embodiments, a data processing apparatus is configured to recover a network connection within an application framework that hides sockets by separating acquisition and processing into different threads of the same process, and, thus, when the processing thread is unable to retrieve a frame from the acquisition thread, the data processing device may terminate the acquisition thread with impunity since all important application state may safely remain within the processing thread.

Abstract: A server receives signals indicating an alert condition for a location that is defined by a set of location attributes and identifies one or more base stations that serve one or more cells that overlap with the location, which encompasses less than all of the cells. The server transmits a message to the one or more base stations identifying the alert condition and including the set of location attributes. A user equipment receives the message identifying the alert condition and including the set of location attributes that define the location of the alert condition. The user equipment compares a location of the user equipment to the set of location attributes and generates an alert in response to the location of the user equipment being within the location of the alert condition.

Abstract: An illustrative example surveillance system designed according to an embodiment of this invention includes a plurality of cells that respectively include a surveillance network including at least one detector that is configured to detect at least one type of subject. The cells have respective detection areas within which a subject may be detected by the at least one detector of that cell. A controller of the cell determines information regarding tracking of a detected subject that is in that cell. The controller hands off tracking of the subject to a second one of the cells based upon an indication that the tracked subject is moving toward the detection area of the second one of the cells.

Abstract: An apparatus for monitoring movement of objects of interest in an area includes an activity map generation circuit and a unified activity map generation circuit. The activity map generation circuit is configured to: generate a plurality of activity maps based on video content from a plurality of cameras, each of the plurality of activity maps being indicative of relative activity of the objects of interest over time within a field of view of a camera among the plurality of cameras, and each of the plurality of cameras having a different corresponding field of view in the area; and standardize the plurality of activity maps with regard to a single common point of view. The unified spatial activity map generation circuit is configured to combine the plurality of standardized activity maps into a unified activity map.

Abstract: An apparatus and method are disclosed for determining authentication frequency (i.e., the length of time between authenticating and re-authenticating a user) and challenge type (e.g., username/password, fingerprint recognition, voice recognition, etc.) based on what software applications a user is running on a data-processing system, and how those applications are being used (e.g., what functions are used, what data is input to or output by the application, how often and for how long applications are used, what input devices and output devices are used, etc.) Advantageously, the illustrative embodiment enables authentication frequency and challenge type to be adjusted based on the likelihood of malicious activity and/or the potential cost of malicious activity, as inferred from current and past application usage. In addition, the illustrative embodiment enables selection of an authentication challenge type that is less intrusive to a user based on current application usage.

Abstract: An apparatus and method are disclosed for determining authentication frequency (i.e., the length of time between authenticating and re-authenticating a user) and challenge type (e.g., username/password, fingerprint recognition, voice recognition, etc.) based on one or more environmental properties (e.g., ambient noise level, ambient luminosity, temperature, etc.), or one or more physiological properties of a user (e.g., heart rate, blood pressure, etc.), or both. Advantageously, the illustrative embodiment enables authentication frequency and challenge type to be adjusted based on the likelihood of malicious activity, as inferred from these properties. In addition, the illustrative embodiment enables the authentication challenge type to be tailored to particular environmental conditions (e.g., noisy environments, dark environments, etc.).

Abstract: A system and method processes visual information including at least one object in motion. The visual information is processed by locating at least one spatial edge of the object, generating a plurality of spatio-temporal gradients for the at least one spatial edge over N frames, and then generating motion blur images from the spatio-temporal gradients. A regression analysis is performed on the motion blur images to determine direction of motion information of the object, and scene activity vectors are then generated for the N frames based on the direction of motion information. An event is detected in the visual information based on the scene activity vectors.

Abstract: An illustrative example surveillance system designed according to an embodiment of this invention includes a plurality of cells that respectively include a surveillance network including at least one detector that is configured to detect at least one type of subject. The cells have respective detection areas within which a subject may be detected by the at least one detector of that cell. A controller of the cell determines information regarding tracking of a detected subject that is in that cell. The controller hands off tracking of the subject to a second one of the cells based upon an indication that the tracked subject is moving toward the detection area of the second one of the cells.

Abstract: An apparatus for monitoring movement of objects of interest in an area includes an activity map generation circuit and a unified activity map generation circuit. The activity map generation circuit is configured to: generate a plurality of activity maps based on video content from a plurality of cameras, each of the plurality of activity maps being indicative of relative activity of the objects of interest over time within a field of view of a camera among the plurality of cameras, and each of the plurality of cameras having a different corresponding field of view in the area; and standardize the plurality of activity maps with regard to a single common point of view. The unified spatial activity map generation circuit is configured to combine the plurality of standardized activity maps into a unified activity map.

Abstract: A system and method processes visual information including at least one object in motion. The visual information is processed by locating at least one spatial edge of the object, generating a plurality of spatio-temporal gradients for the at least one spatial edge over N frames, and then generating motion blur images from the spatio-temporal gradients. A regression analysis is performed on the motion blur images to determine direction of motion information of the object, and scene activity vectors are then generated for the N frames based on the direction of motion information. An event is detected in the visual information based on the scene activity vectors.

Abstract: An apparatus and method are disclosed for determining authentication frequency (i.e., the length of time between authenticating and re-authenticating a user) and challenge type (e.g., username/password, fingerprint recognition, voice recognition, etc.) based on what software applications a user is running on a data-processing system, and how those applications are being used (e.g., what functions are used, what data is input to or output by the application, how often and for how long applications are used, what input devices and output devices are used, etc.) Advantageously, the illustrative embodiment enables authentication frequency and challenge type to be adjusted based on the likelihood of malicious activity and/or the potential cost of malicious activity, as inferred from current and past application usage. In addition, the illustrative embodiment enables selection of an authentication challenge type that is less intrusive to a user based on current application usage.

Abstract: Methods and apparatus are disclosed for authenticating a user based on the geo-location history of a geo-location-enabled wireless device (e.g., a GPS-enabled wireless telecommunications terminal, a smart card, an RFID tag, etc.). In a first illustrative embodiment, a user of a geo-location-enabled wireless telecommunications terminal (e.g., a GPS-enabled cell phone, a GPS-enabled notebook computer, etc.) who attempts to access a restricted resource is challenged with one or more questions that are generated from the terminal's geo-location history. In a second illustrative embodiment, a user of a data-processing system who attempts to access a restricted resource is asked to provide a username Z. The user is then challenged with one or more questions that are generated from the geo-location history of a wireless device that is associated with username Z (e.g., a cell phone that belongs to the user whose username is Z, etc.).

Abstract: A driver behavior monitoring system includes: a video camera; an image processing system; and a driver alert system. The video camera records the driver's behavior, and the image processing system analyzes the recorded video content to recognize and classify the driver's behavior as at least one of: (i) distracted behavior; and (ii) accident behavior. Based on the recognition and classification, the driver alert system may perform various operations such as alerting the driver, alerting the authorities, etc.