Abstract: Cameras installed at a facility capture images over periods of time and detect features such as locations of hands, heads or other body parts within the images. Time series of data regarding such features are provided to machine learning systems to determine whether an event such as a taking or a return of the item is depicted within the images, or whether no such event is detected. The time series are provided to the machine learning system in an iterative manner, with time series associated with a set of baseline features provided to the machine learning system first. If an event is not detected and associated with an actor based on the baseline features, time series associated with supplemental features are successively provided to the machine learning system, along with the time series associated with the baseline features, until the event is detected and associated with an actor.

Abstract: Techniques for compensating signal data from first order high pass filters for exponential decay to extract and underlying step function associated with the signal data. The techniques include adjusting a time scale of the signal data using a charge amplifier. The techniques also include determining a dynamic neutral point for the signal data using an exponential decay function. The techniques further apply an inverse transfer function to remove decay from the signal data and generate a step function associated with the signal data.

Abstract: An apparatus comprising an array of electrical conductors connected to circuitry that determines data indicative of objects at particular locations based on capacitance at junctions of conductors in the array. The apparatus comprises a first set of conductors arranged on a first substrate and a second set of conductors arranged on a second substrate to form an array. The first and second substrates are separated by an air gap within which the electrical conductors are positioned. Each conductor may be independently addressable, having a proximal end connected to readout electronics and a distal end that is not. The apparatus may be cut, at the ends distal to where the conductors connect to the circuitry, to fit a desired location, such as on a store shelf, while remaining operational.

Abstract: When two or more devices are near each other, they are likely to hear the same ambient sounds. To detect such proximity, each device captures a short digital audio signal from its microphone and uploads it to a proximity-detecting service along with a timestamp that indicates when the clip was captured. The proximity-detecting service maintains a history of sound clips for its clients and analyzes recently received sound clips that have similar time stamps. The devices can then be grouped according to the similarities of their sound clips. Devices that are grouped together in this way are deemed to be near each other.

Abstract: A portable heads-up display device for deployment on the dashboard of a vehicle. The device includes a housing suitable for mounting to or placing on a surface, and containing system electronics and a projector. A curved high-gain reflective screen disposed on the housing rearward of the projector receives an image produced by the projector, and reflects that image to a semi-transparent curved combiner disposed near the front of the housing. A virtual image appears at the combiner that has a focal point in the distance beyond the combiner. One or more rear-facing sensors and the control electronics detect hand gestures by the driver, which controls the operation of the device in displaying images. The device mounts to a dashboard via a conformable and foot that adapts to the shape of the dashboard. Magnetic coupling between the housing and a puck element held in the foot facilitates removal and replacement of the device.

Abstract: An embodiment of the present invention provides a radio frequency identification (RFID) tag, comprising at least one light emitting diode (LED) that is controlled by the RFID's logic and powered by the RFID's power harvesting circuit, wherein the RFID tag is capable of being interrogated by an RFID reader and reporting its unique identification number by RF backscatter and/or controlling the illumination state of the at least one LED.

Abstract: When two or more devices are near each other, they are likely to hear the same ambient sounds. To detect such proximity, each device captures a short digital audio signal from its microphone and uploads it to a proximity-detecting service along with a timestamp that indicates when the clip was captured. The proximity-detecting service maintains a history of sound clips for its clients and analyzes recently received sound clips that have similar time stamps. The devices can then be grouped according to the similarities of their sound clips. Devices that are grouped together in this way are deemed to be near each other.

Abstract: An embodiment of the present invention provides a radio frequency identification (RFID) tag, comprising at least one light emitting diode (LED) that is controlled by the RFID's logic and powered by the RFID's power harvesting circuit, wherein the RFID tag is capable of being interrogated by an RFID reader and reporting its unique identification number by RF backscatter and/or controlling the illumination state of the at least one LED.

Abstract: An embodiment of the present invention provides a radio frequency identification (RFID) tag, comprising at least one light emitting diode (LED) that is controlled by the RFID's logic and powered by the RFID's power harvesting circuit, wherein the RFID tag is capable of being interrogated by an RFID reader and reporting its unique identification number by RF backscatter and/or controlling the illumination state of the at least one LED.

Abstract: A cryptographic method and systems using a keyed one-way function. A sending device uses the keyed one-way function to authenticate one or more receiving devices prerequisite to communication. A multidimensional hypercube is generated, from which is formed a multidimensional vector by randomly selecting one corner of the multidimensional hypercube. The keyed one-way function is computed using the multidimensional vector.

Abstract: A method and system of creating an approximate kernel matrix to train a kernel machine. In one embodiment of the invention, a set of kernel machine training data is partitioned into a set of partitioned training data based on a set of partition parameters. The set of partition parameters includes one or more of, an axis-aligned grid location, or an axis-aligned grid resolution in one embodiment of the invention. A partition matrix that approximates a kernel machine kernel matrix is created from the set of partitioned training data and the partition matrix is used to train a kernel machine in one embodiment of the invention.

Abstract: In some embodiments, object recognition using global similarity-based classifier is presented. In this regard, an apparatus is introduced comprising: a camera, a display, and a processor, the processor to: receive an image from the camera, convert the image to a numerical representation, compute a similarity function between the converted image and a plurality of prototype image representations, and classify the output of the similarity function to identify the image. Other embodiments are also disclosed and claimed.

Abstract: An embodiment of the present invention provides a radio frequency identification (RFID) tag, comprising at least one light emitting diode (LED) that is controlled by the RFID's logic and powered by the RFID's power harvesting circuit, wherein the RFID tag is capable of being interrogated by an RFID reader and reporting its unique identification number by RF backscatter and/or controlling the illumination state of the at least one LED.

Abstract: Systems and methods associated with approximating a kernel matrix are described. One method embodiment includes accessing a set of kernel machine training data and then partitioning that data into a set of partitioned data based on a set of partition parameters. The method embodiment may also include creating a partition matrix from the partitioned data, where the partition matrix is to approximate a kernel matrix that may have been created using radial basis functions from the training data.

Abstract: An MPEG compressed bit stream representing video information is associated with supplemental information such as motion, audio, scene cut, and editorial information. The motion information is identified and processed to determine characteristics of the video information. Motion information is processed to determine magnitude, coherence, and correlation with known motion information templates. MPEG motion vectors are used to determine motion information. Audio, scene cut, and editorial information is similarly identified and processed. The motion information along with other types of information is provided to a client by using color bars or other techniques to allow a client to interact with the video information using supplemental information.

Abstract: Dense range data obtained at real-time rates is employed to estimate the pose of an articulated figure. In one approach, the range data is used in combination with a model of connected patches. Each patch is the planar convex hull of two circles, and a recursive procedure is carried out to determine an estimate of pose which most closely correlates to the range data. In another aspect of the invention, the dense range data is used in conjunction with image intensity information to improve pose tracking performance. The range information is used to determine the shape of an object, rather than assume a generic model or estimate structure from motion. In this aspect of the invention, a depth constraint equation, which is a counterpart to the classic brightness change constraint equation, is employed. Both constraints are used to jointly solve for motion estimates.

Abstract: A cryptographic method and systems using a keyed one-way function. A sending device uses the keyed one-way function to authenticate one or more receiving devices prerequisite to communication.

Abstract: Dense range data obtained at real-time rates is employed to estimate the pose of an articulated figure. In one approach, the range data is used in combination with a model of connected patches. Each patch is the planar convex hull of two circles, and a recursive procedure is carried out to determine an estimate of pose which most closely correlates to the range data. In another aspect of the invention, the dense range data is used in conjunction with image intensity information to improve pose tracking performance. The range information is used to determine the shape of an object, rather than assume a generic model or estimate structure from motion. In this aspect of the invention, a depth constraint equation, which is a counterpart to the classic brightness change constraint equation, is employed. Both constraints are used to jointly solve for motion estimates.

Abstract: Dense range data obtained at real-time rates is employed to estimate the pose of an articulated figure. In one approach, the range data is used in combination with a model of connected patches. Each patch is the planar convex hull of two circles, and a recursive procedure is carried out to determine an estimate of pose which most closely correlates to the range data. In another aspect of the invention, the dense range data is used in conjunction with image intensity information to improve pose tracking performance. The range information is used to determine the shape of an object, rather than assume a generic model or estimate structure from motion. In this aspect of the invention, a depth constraint equation, which is a counterpart to the classic brightness change constraint equation, is employed. Both constraints are used to jointly solve for motion estimates.