Abstract: For generating a breathing alert is disclosed, a method receives a video stream of a subject. The method further estimates a breathing signal from the video stream. The method determines one of a large-scale motion and/or a breathing event of the subject based on the breathing signal. The method generates an alert if both no breathing event is identified and no large-scale motion of the subject is identified within an event time interval.

Abstract: For generating a breathing alert is disclosed, a method receives a video stream of a subject. The method further estimates a breathing signal from the video stream. The method determines one of a large-scale motion and/or a breathing event of the subject based on the breathing signal. The method generates an alert if both no breathing event is identified and no large-scale motion of the subject is identified within an event time interval.

Abstract: For generating a breathing alert is disclosed, a method receives a video stream of a subject. The method further estimates a breathing signal from the video stream. The method determines one of a large-scale motion and/or a breathing event of the subject based on the breathing signal. The method generates an alert if both no breathing event is identified and no large-scale motion of the subject is identified within an event time interval.

Abstract: For generating a breathing alert, a method captures a video stream of a subject. The method further generates a vector time series that includes a vector for each image frame of the video stream. The method estimates of breathing signal from the vector time series. The method further determines one of large-scale motion and a breathing event of the subject based on the breathing signal. The method generates an alert if no breathing event is identified and no large-scale motion of the subject is identified within an event time interval.

Abstract: For generating a breathing alert, a method captures a video stream of a subject. The method further generates a vector time series that includes a vector for each image frame of the video stream. The method estimates of breathing signal from the vector time series. The method further determines one of large-scale motion and a breathing event of the subject based on the breathing signal. The method generates an alert if no breathing event is identified and no large-scale motion of the subject is identified within an event time interval.

Abstract: For remote heart rate estimation, a method detects an object of interest (OOI) in each image of a video data and tracks the OOI in each image of the video data. The method identifies a region of interest (ROI) within the OOI and generates a plurality of super pixels from a plurality of pixels in each ROI. The method further generates a super-pixel time series from the plurality of super pixels in each image and removes interfering signals from the super-pixel time series. The method further models the super-pixel time series as a super-pixel model and calculates a heart beat signal from the super-pixel model. The method calculates heart characteristics from the heart beat signal. The heart characteristics include one or more of a heart rate, an inter-beat interval, and a heart rate variability.

Abstract: For remote heart rate estimation, a method detects an object of interest (OOI) in each image of a video data and tracks the OOI in each image of the video data. The method identifies a region of interest (ROI) within the OOI and generates a plurality of super pixels from a plurality of pixels in each ROI. The method further generates a super-pixel time series from the plurality of super pixels in each image and removes interfering signals from the super-pixel time series. The method further models the super-pixel time series as a super-pixel model and calculates a heart beat signal from the super-pixel model. The method calculates heart characteristics from the heart beat signal. The heart characteristics include one or more of a heart rate, an inter-beat interval, and a heart rate variability.

Abstract: Environmental recognition systems may improve recognition accuracy by leveraging local and nonlocal features in a recognition target. A local decoder may be used to analyze local features, and a nonlocal decoder may be used to analyze nonlocal features. Local and nonlocal estimates may then be exchanged to improve the accuracy of the local and nonlocal decoders. Additional iterations of analysis and exchange may be performed until a predetermined threshold is reached. In some embodiments, the system may comprise extrinsic information extractors to prevent positive feedback loops from causing the system to adhere to erroneous previous decisions.

Abstract: Environmental recognition systems may improve recognition accuracy by leveraging local and nonlocal features in a recognition target. A local decoder may be used to analyze local features, and a nonlocal decoder may be used to analyze nonlocal features. Local and nonlocal estimates may then be exchanged to improve the accuracy of the local and nonlocal decoders. Additional iterations of analysis and exchange may be performed until a predetermined threshold is reached. In some embodiments, the system may comprise extrinsic information extractors to prevent positive feedback loops from causing the system to adhere to erroneous previous decisions.

Abstract: Adaptive learning of a multichannel prefilter response processes multiple audio signals prior to emitting them from a set of loudspeakers. The signals are filtered and mixed in such a way that the emitted signals will be reconstructed at pre-specified points in a room. This is done in a user selective way so that, at each location, only one of the source signals is reconstructed and the other signals vanish. A gradient descent adaptive filtering method is applied.

Abstract: A system and method that utilizes direct sequence spread spectrum signal (DSSS) encoding to enable testing of a live wire, wherein an original data signal is modified and then transmitted along the wire, and a reflected signal is collected and analyzed using correlation techniques to determine characteristics of the live wire, including the location of a fault.

Abstract: Disclosed is a highly integrated and flexible system for vending products and services to consumers. The system receives information in advance of the vend by having the consumer insert an identification (ID) card, preferably a driver's license, into a point-of-purchase terminal (referred to as an OSU device). The OSU device preferably contains an Optical Scanning Unit (OSU), capable of scanning the textual information on the ID card. In one embodiment, the scanned information is compared against optical templates present in the system to discern or verify the information on the ID card, and is then used by the system to enable or disable the vending transaction, and/or to allow access to several preregistered system accounts.

Abstract: An echo canceler includes an recursive least squares lattice to whiten a far-end signal s1(t) and provide whitened time delays. The echo canceler further decorrelates a microphone signal based on the whitened time delays to reduce echoes of the far-end signal s1(t) that are contained in the microphone signal x2(t). The echo canceler does not use a double-talk detector and avoids all problems inherent with their use. Thus, speaker phones, and other communication devices, can continuously operate in full-duplex mode of operation thereby providing natural conversational hands-free communication.

Abstract: An echo canceler includes an adaptable filter that is updated during double-talk and far-end talk. The echo canceler receives a microphone signal that includes a near-end signal and echoes resulting from a far-end signal. The echo canceler whitens the far-end signal and decorrelates the microphone signal. The whitening and decorrelating is done as a preprocessing step for the one-unit blind source separation algorithm. A criterion of measure is used to emphasize the statistical independence of the echo canceled signal and the far-end signal. The echo cancellation problem is cast as a one-unit blind source separation problem. A one-unit blind source separation algorithm such as negentropy maximization can be used to extract the echo canceled signal.

Abstract: A system and method that utilizes direct sequence spread spectrum signal (DSSS) encoding to enable testing of a live wire, wherein an original data signal is modified and then transmitted along the wire, and a reflected signal is collected and analyzed using correlation techniques to determine characteristics of the live wire, including the location of a fault.