Abstract: System and method for detection of pre-drowning and drowning events based on underwater and exterior images in and around a swimming area.

Abstract: A switching system is connected to the power amplifier of an RF system. The switching system can switch the DC supply voltage to the power amplifier while handling the high DC current and the nanosecond switching speed requirements that are mandatory for most RF systems. The embodiments can rapidly control DC voltages but not interfere with the optimized operation of the RF transistor. The embodiments provide a desired sharp turn-on leading edge for an RF pulse while eliminating the extremely long and undesirable ramp down that typically occurs beyond the desired RF pulse period.

Abstract: The present disclosure provides a detection system for detecting matter and distinguishing specific matter from other matter. The detection system comprises at least one light source arranged to emit one or more light beams having a known wavelength or wavelength range. Further, the detection system comprises at least one optical element configured to direct the one or more light beams onto a plurality of locations within an area of interest including the matter. The detection system also comprises a detector for detecting intensities of the one or more light beams reflected at the plurality of locations within the area of interest including the matter. In addition, the detection system comprises an outcome determination system. The system is arranged to obtain information indicative of at least a portion of a shape of at least some of the matter based on detected light intensities of the one or more light beams reflected at the plurality of locations.

Abstract: Techniques for low power gunshot detection are disclosed. Infrared information is collected using a gunshot sensor device. The infrared information is collected using mid-infrared band sensing to provide motion detection. Additional infrared information is buffered using the gunshot sensor device. The additional infrared information is collected using near-infrared band sensing. The buffering is enabled by the motion detection. Acoustic information is collected using the gunshot sensor device. The collecting acoustic information is enabled by the motion detection. A gunshot is detected using the gunshot sensor device. The detecting is based on the additional infrared information and the acoustic information. The detecting includes monitoring the acoustic information to identify a high-intensity gunshot sound and correlating the high-intensity gunshot sound to the infrared information that was buffered.

Abstract: A switching system is connected to the power amplifier of an RF system. The switching system can switch the DC supply voltage to the power amplifier while handling the high DC current and the nanosecond switching speed requirements that are mandatory for most RF systems. The embodiments can rapidly control DC voltages but not interfere with the optimized operation of the RF transistor. The embodiments provide a desired sharp turn-on leading edge for an RF pulse while eliminating the extremely long and undesirable ramp down that typically occurs beyond the desired RF pulse period.

Abstract: System and method for detection of pre-drowning and drowning events based on underwater and exterior images in and around a swimming area.

Abstract: Techniques for low power gunshot sensor testing are disclosed. An acoustic generator and an infrared generator are disposed in a housing. The housing encompasses the acoustic generator and the infrared generator. The housing covers the gunshot sensor. The acoustic generator and the infrared generator are used for testing a gunshot sensor. The infrared generator and the acoustic generator are coupled to an activation circuit. A switch is coupled to the acoustic generator and the infrared generator. The switch provides activation control of the acoustic generator and the infrared generator. The infrared generator includes a light source operating in the near-infrared (NIR) band. The light source operating in the NIR band provides testing for a gunshot muzzle flash sensor. The infrared generator includes a light source operating in the mid-infrared (MIR) band. The light source operating in the MIR band provides testing for a passive infrared (PIR) sensor.

Abstract: System and method for detection of pre-drowning and drowning events based on underwater images are disclosed.

Abstract: System and method for detection of pre-drowning and drowning events based on underwater images are disclosed.

Abstract: Techniques for cable-free indoor gunshot detection are disclosed. Acoustic information is collected within an indoor environment using a gunshot sensor device which uses cable-free communication to a network. The gunshot sensor device is powered by a battery. Infrared information from the muzzle flash of a firearm is collected using the gunshot sensor device. The infrared information is buffered within the gunshot sensor device. The gunshot sensor device is used to monitor the acoustic information and identify a high-intensity gunshot sound. The gunshot sensor device is used to match the high-intensity gunshot sound to the buffered infrared information. The matching includes making a correspondence between the gunshot sound and an infrared event that occurred in time before the gunshot sound. The gunshot sensor device is used to notify the network of a possible gunshot occurrence, based on an analysis of the high-intensity gunshot sound and the infrared event that was matched.

Abstract: Techniques for gunshot analysis in an indoor environment are disclosed. A gunshot sensor is placed in the indoor environment. The gunshot sensor includes multiple individual sensors, including, but not limited to, an infrared sensor and an acoustic sensor. A firearm typically emits energy within the infrared spectrum, which is detected by the infrared sensor. A firearm typically further emits an acoustic pressure wave, which is detected by acoustic sensor. The gunshot detector can differentiate between a gunshot and a strobe from a fire alarm, based on information from the infrared sensor and acoustic sensors. The infrared sensor information and the acoustic sensor information are analyzed to determine that a gunshot has occurred in a timeframe between strobe events. The gunshot determination takes place independently of the location of the gunshot sensor. Reverberations and reflections add cumulatively to the collected acoustic and infrared information.

Abstract: Gunshot detection within an indoor environment is performed with video analytics. One or more position-independent gunshot sensors are deployed. Infrared and acoustic information is collected within an indoor environment for indoor gunshot detection with video analytics. The infrared information and the acoustic information are analyzed to determine a gunshot occurrence. Video analytics for tracking a suspected shooter of the gunshot is performed, based on the gunshot occurrence, using video that is collected. A person of interest is tagged, as a portion of the video analytics, for the purpose of tracking the person of interest. Video collection from one or more video streams is engaged, based on the detection of the gunshot. The video analytics uses image classifiers. The image classifiers are used to identify a gun type. The suspected shooter is identified based on the video analytics. An audio microphone is activated based on the detecting of the gunshot.

Abstract: It is provided a method of detecting human drowning, comprising: attempting to detect humans in a sequence of underwater images taken by a single camera, for identifying humans-in-water candidates in the images, said detection using at least a machine learning algorithm, tracking humans-in-water candidates throughout this sequence, and detecting human drowning risk. It is also provided a system for detecting human drowning, comprising at least one underwater camera configured to take at least a sequence of underwater images, the system being configured to attempt to detect humans in the sequence of underwater images, for identifying humans-in-water candidates in the images, said detection using at least a machine learning algorithm, track humans-in-water candidates throughout this sequence, and detect human drowning risk.

Abstract: Techniques for gunshot sensor testing are disclosed. An acoustic generator and infrared generator are disposed in a housing. Soundproofing insulation is distributed around and/or within the housing to provide sound deadening which minimizes disturbance to building occupants during testing. The housing is placed in proximity to a gunshot sensor. A trigger device enables multiple modes of triggering both the acoustic generator and infrared generator. The generators stimulate corresponding components of a gunshot sensor. Input from the gunshot sensor components is evaluated to determine an operating condition of the gunshot sensor. The gunshot sensor verifies its operation by communicating with a server. The server further tests mass communication channels by issuing a test message. The test results indicative of the condition of the gunshot sensor are sent to a mobile device for an operator to review.

Abstract: A computing-device implemented system and method for identifying an item in an x-ray image is described. The method includes training a machine learning algorithm with at least one training data set of x-ray images to generate at least one machine-learned model. The method further includes receiving at least one rendered x-ray image that includes an item, identifying the item using the at least one model, and generating an automated detection indication associated with the item.

Abstract: A switching system is connected to the power amplifier of an RF system. The switching system can switch the DC supply voltage to the power amplifier while handling the high DC current and the nanosecond switching speed requirements that are mandatory for most RF systems. The embodiments can rapidly control DC voltages but not interfere with the optimized operation of the RF transistor. The embodiments provide a desired sharp turn-on leading edge for an RF pulse while eliminating the extremely long and undesirable ramp down that typically occurs beyond the desired RF pulse period.

Abstract: Techniques for gunshot detection in an indoor environment are disclosed. A gunshot sensor is placed in the indoor environment. The gunshot sensor includes multiple individual sensors, including, but not limited to, an acoustic sensor and an infrared sensor. A firearm typically emits energy within the infrared spectrum when fired. This energy is detected by the infrared sensor. A firearm also typically emits an acoustic pressure wave when fired. The acoustic sensor detects the acoustic pressure wave. A strobe from a fire alarm occurring near in time to the gunshot can cause false gunshot detection. The infrared sensor information and the acoustic sensor information are analyzed to determine that a gunshot has occurred. The gunshot determination takes place independently of the location of the gunshot sensor. The strobe occurrence is evaluated to provide gunshot false alert detection. Reverberations are not used in the determination of a gunshot false alert.

Abstract: Indoor gunshot detection analysis is performed in the presence of a fire alarm. A gunshot sensor, which includes infrared and acoustic sensors, is used to detect an infrared pulse, whether the pulse originates from a muzzle flash or a fire alarm strobe. The infrared pulse is determined to correspond to a strobe occurrence. An evaluation determines that a gunshot did or did not occur based on the strobe occurrence. In another embodiment, a gunshot is detected while the fire alarm is occurring, where the gunshot occurs at a different time from the strobe occurrence and can be sensed by the acoustic sensor. A fire alarm strobe frequency and duration are determined, and further strobe occurrences are edited. Editing detection edits out a sensing time window by the infrared sensor. When the strobe stops, editing is eliminated, but if the strobe restarts, then editing is resumed.

Abstract: Indoor gunshot detection is performed using video analytics. Infrared and acoustic information are collected within an indoor environment using a gunshot sensor. A gunshot is detected, in the indoor environment, based on the infrared and the acoustic information. Video collection is engaged based on the detecting of the gunshot. The video collection is from a video stream. In embodiments, the video stream is a buffered stream. Video analytics are performed for tracking a suspected shooter of the gunshot using the video that is collected. The suspected shooter is identified based on the video analytics. In embodiments, an audio microphone is activated based on the detecting of the gunshot. The suspected shooter is tracked based on the audio microphone. A person of interest is tagged and tracked by an operator of the gunshot detection system. Direction of the gunshot can be determined relative to the gunshot sensor unit.

Abstract: Systems, methods, and non-transitory computer-readable media taught herein process a subset of a three-dimensional array of voxels to form an image of a region of interest in an object. Images thus formed are clear, comprehensible, and contextual. The systems, methods, and non-transitory computer-readable media taught herein select the subset of voxels that represent the region of interest along a direction perpendicular to a view direction defined by the region of interest. The subset of voxels represents one or more portions of a plurality of image slices of the object.