Abstract: A control system uses visual odometry (VO) data to identify a position of the vehicle while moving along a path next to the row and to detect the vehicle reaching an end of the row. The control system can also use the VO image to turn the vehicle around from a first position at the end of the row to a second position at a start of another row. The control system may detect an end of row based on 3-D image data, VO data, and GNSS data. The control system also may adjust the VO data so the end of row detected from the VO data corresponds with the end of row location identified with the GNSS data.

Abstract: Provided is a directional acoustic sensor including a support member, and a plurality of resonators extending in a longitudinal direction with respect to the support member, wherein each of the plurality of resonators includes a driver configured to move based on an input sound signal, and a sensor configured to sense a capacitance change based on an air gap that changes based on a movement of the driver.

Abstract: Validation of an activation event of a device based on analyzing audio data is disclosed. The device detects an activation event, e.g., an input to a soft-touch button or a wake word detected by a microphone array. Responsive to detecting the activation event, the device captures, via a microphone array on the device, sound from a local area of the device. The device stores the captured sound as audio data in an audio buffer. The device performs a validation of the activation event by analyzing the captured sound. The device performs an action based on a result of the validation.

Abstract: A conference terminal and a feedback suppression method are provided. In the method, a transmitting sound signal is divided into sub sound signals of multiple frequency bands. Different sub sound signals correspond to different frequency bands. An interfered frequency band corresponding to the howling interference is detected according to the sub sound signals of those frequency bands. The power of the sub sound signal of the interfered frequency band increases along with time. The interfered frequency band is affected by the howling interference. An interference direction is determined according to multiple input sound signals received by the microphone array and merely pass through the interfered frequency band. A sound from the interference direction leads to the howling interference. A beam pattern of the microphone array is determined according to the interference direction. The gain of the beam pattern in the interference direction is reduced.

Abstract: After determining that a gunshot has been fired, particularly indoors, the method of the invention is employed to determining the number of gunshots fired by analyzing consecutive windows of time over a certain time period. That is, after it is determined that a gun has been fired, the method is employed to identify that the gun is an automatic or rapid fire weapon by quickly counting the number of rounds shot over short periods of time. This information can be used to provide shooting details, both in connection with notifying emergency personnel and enabling the personnel to assess details of the shooting incident.

Abstract: A type I phase locked loop (PLL) includes an oscillator and a feedback path to a phase detector. The PLL is configured to lock a first frequency and first relative phase of a first output signal to a frequency and a phase of a first input signal, and lock a second frequency and second relative phase of a second output signal to a frequency and a phase of a second input signal. A steady state phase lag of the PLL resulting from the difference between the first frequency and the second frequency is estimated, and the estimated steady state phase lag is used to determine a total phase shift (??LO,steady) between the second input signal and the second output signal. The PLL for the phase shift can be compensated. The determined total phase shift can be used in a distance estimation.

Abstract: An air traffic control system includes one or more servers each including a network interface, a processor, and memory; and a database communicatively coupled to the one or more servers, wherein the network interface in each of the one or more servers is communicatively coupled to one or more passenger drones via a plurality of wireless networks at least one of which comprises a cellular network; wherein the one or more servers are configured to obtain operational data from a passenger drone, obtain conditions from one or more of the operational data and the database, determine a future flight plan based on the operational data and a flying lane assignment for the passenger drone, determine potential collisions in the future flight plan based on static obstructions and dynamic obstructions, obtained from the database based on the future flight plan, and provide evasive maneuver instructions to the passenger drone.

Abstract: A method includes recording a first timestamp of a detection of an event with a first array of an array of light sensors or an array of acoustic sensors. The array of light sensors and the array of acoustic sensors are mounted on a same chassis. The method further includes determining a direction of the event, based on the detection with the first array; recording a second timestamp of a detection of the event by a second array of the array of light sensors or the array of audio sensors; determining a distance of the event from the arrays of light and audio sensors, based on the first timestamp and the second timestamp; and controlling a vehicle, based on the event, the vehicle including the chassis.

Abstract: Disclosed is an electronic apparatus configured to identify a location of an object. The electronic apparatus includes: a sound output unit comprising sound output circuitry; and a processor configured to: obtain first sound information from an external apparatus that receives a first sound output from the sound output unit, obtain second sound information from the external apparatus that receives a second sound output from an object, and identify locations of the electronic apparatus and the object with respect to the external apparatus based on a first signal characteristic and a second signal characteristic respectively detected using the obtained first sound information and second sound information.

Abstract: Techniques are described herein for enabling the use of “dynamic” or “context-specific” hot words for an automated assistant. In various implementations, an automated assistant may be operated at least in part on a computing device. Audio data captured by a microphone may be monitored for default hot word(s). Detection of one or more of the default hot words may trigger transition of the automated assistant from a limited hot word listening state into a speech recognition state. Transition of the computing device into a given state may be detected, and in response, the audio data captured by the microphone may be monitored for context-specific hot word(s), in addition to or instead of the default hot word(s). Detection of the context-specific hot word(s) may trigger the automated assistant to perform a responsive action associated with the given state, without requiring detection of default hot word(s).

Abstract: Techniques for acoustic vehicle location tracking are presented. In one embodiment, a processor receives, from a radio-frequency positioning system, measurements of a candidate location for a plurality of vehicles and receives, from a plurality of acoustic sensors, acoustic signals associated with a detected vehicle. The acoustic signals are compared to an acoustic vehicle signature library that includes acoustic information associated with the vehicles. Upon determining that the acoustic signals match acoustic information associated with a vehicle in the acoustic vehicle signature library, the measurements of the candidate location of the detected vehicle based on the radio-frequency signals are compared with a location of the vehicle based on the acoustic signals. Upon determining that the measurements of the candidate location are within a predetermined area of the location of the detected vehicle, the measurements are provided to a vehicle location database.

Abstract: The location of lost or entangled fishing gear, known as derelict gear, is detected. The motion or change of position of a buoy attached to fishing gear is determined via sensors mounted on the buoy and compared to typical buoy motion. If the buoy has moved beyond a threshold value from its original location, an alert is sent to the fisherman. The available sensor data will be used to determine the likelihood of loss or entanglement. This alert facilitates recovery of lost or entangled gear by identifying where immediate retrieval efforts should be focused. The number of traps lost to the ocean that otherwise would continue to trap or entangle marine life may be reduced.

Abstract: Techniques are described herein for enabling the use of “dynamic” or “context-specific” hot words for an automated assistant. In various implementations, an automated assistant may be operated at least in part on a computing device. Audio data captured by a microphone may be monitored for default hot word(s). Detection of one or more of the default hot words may trigger transition of the automated assistant from a limited hot word listening state into a speech recognition state. Transition of the computing device into a given state may be detected, and in response, the audio data captured by the microphone may be monitored for context-specific hot word(s), in addition to or instead of the default hot word(s). Detection of the context-specific hot word(s) may trigger the automated assistant to perform a responsive action associated with the given state, without requiring detection of default hot word(s).

Abstract: A gunshot detection system continually monitors ambient noise throughout a building, learns the building's auditory patterns, and alerts users when sounds are found to be unusual or generally indicative of a dangerous situation. For example, gunshot sensor units positioned throughout the building include microphones. During a learning period (e.g. during normal conditions), these microphones capture ambient noise. The gunshot detection system generates ambient noise models representing the ambient noise during the normal conditions. The gunshot detection system then continually processes currently captured audio data depicting ambient noise (and potential acoustic anomalies) against the ambient noise models to detect and/or identify the acoustic anomalies and to determine whether to generate an alert.

Abstract: According to one aspect of the invention, there is provided a method for providing a voice recognition trigger, comprising the steps of: estimating a first distance, which is a distance between a device and a user, on the basis of proximity information detected by the device, and estimating a second distance, which is a distance between the device and a location where a voice detected by the device is uttered, with reference to information on the voice detected by the device; and determining whether the voice detected by the device is an object of voice recognition, with reference to similarity between the first distance and the second distance.

Abstract: A method includes recording a first timestamp of a detection with a first sensor array of a first physical property of an event; determining a direction of the event, based on the detection with the first sensor array; recording a second timestamp of a detection with a second sensor array of a second physical property of the event; determining a distance of the event from the first and second sensor arrays, based on the first timestamp and the second timestamp; determining the event, based on the first physical property and the second physical property; and taking an action based on the event.

Abstract: A distance detection apparatus includes a wave transmitter configured to transmit a transmission wave, a wave receiver configured to receive the transmission wave which is reflected by an object, a storage portion configured to store a transmission signal, a correlation processing portion configured to obtain a correlation value between the transmission signal and a reception signal corresponding to a reception wave, and a detection portion configured to detect a distance to the obstacle in a case where the correlation value indicates that the transmission signal and the reception signal are similar to each other at a level which is equal to or greater than a predetermined level.

Abstract: A touch sensor is provided with different operational modes. One mode may be the operation of the touch sensor with a reduced set of transmitting rows than another mode. Transmitting on a reduced set of rows from the normal set of transmitting rows provides an operational mode that is able to detect touch events at greater distances from the touch surface than when a full set of transmitting rows is being driven.

Abstract: A gunshot detection system includes gunshot sensor units with microphones for detecting gunshots and capturing audio data depicting the detected gunshots and other ambient sounds, an environmental board with various environmental sensors for generating environmental data indicating environmental conditions. The audio data, environmental data, and position information can be stored locally on local nonvolatile storage of the gunshot sensor unit for later retrieval by law enforcement entities. In one embodiment, the gunshot sensor units include a wired and/or wireless data transfer interface for transferring the audio data, environmental data and/or position information to handheld units of law enforcement entities. The gunshot sensor unit can also stream live captured audio data for live monitoring by a control pane, and might also include speakers for providing audio playback of audio data from the control panel.

Abstract: The technology relates to detecting and responding to emergency vehicles. This may include using a plurality of microphones to detect a siren noise corresponding to an emergency vehicle and to estimate a bearing of the emergency vehicle. This estimated bearing is compared to map information to identify a portion of roadway on which the emergency vehicle is traveling. In addition, information identifying a set of objects in the vehicle's environment as well as characteristics of those objects is received from a perception system is used to determine whether one of the set of objects corresponds to the emergency vehicle. How to respond to the emergency vehicle is determined based on the estimated bearing and identified road segments and the determination of whether one of the set of objects corresponds to the emergency vehicle. This determined response is then used to control the vehicle in an autonomous driving mode.

Abstract: A method of operating a hearing aid system in order to provide improved performance for a multitude of hearing aid system processing stages and a hearing aid system (400) for carrying out the method.

Abstract: An electronic device includes a first microphone, a second microphone, a digital signal processor, and a detector. The first microphone samples a sound from a sound source at a first location to generate a first signal. The second microphone samples the sound from the sound source at a second location spaced from the first location to generate a second signal. The digital signal processor compares the first signal and the second signal to obtain external environment information associated with a location of the sound source. The detector determines a call mode, based on the external environment information.

Abstract: Active shooters are becoming a common threat in public areas. Detection and analysis of a gunshot in a public area can aid administrative and first responder personnel in determining that a gun has been fired and in stopping the threat quickly. Embodiments of the present disclosure are directed to solutions for detecting and analyzing gunshots and other threats, and transmitting that information to administrative personnel and first responders.

Abstract: There is provided an information processing apparatus and an information processing method, the information processing apparatus including: an acquiring unit configured to acquire position information of a microphone which has accepted a speech; and a response control unit configured to control a response to the speech on a basis of the speech and the position information.

Abstract: Disclosed are methods and systems for detection of a discharge of a projectile from a firearm. An example method for detection of a discharge of a projectile from a firearm may commence with recording environmental audio by at least one microphone associated with at least one electronic device. The method may continue with triggering, by a processing unit associated with the at least one electronic device, based on predetermined triggering criteria, a frequency analysis of the environmental audio. The analysis may be performed to determine a likelihood of the projectile being discharged from the firearm. The method may further include transferring, by a data transfer unit associated with the at least one electronic device, results of the frequency analysis from the at least one electronic device to a data storage unit for post-processing.

Abstract: In one embodiment, a sensor network is attached to a structure and employed to detect and analyze load changes such as impacts from projectiles. An analyzer coupled to the sensors can determine where on the structure the projectile impacted. Coupled with information on the origin point of the projectile, i.e. where it was fired from, the analyzer can then estimate the trajectory of the projectile. The analyzer can also determine whether the projectile passed through the structure and, if so, can extrapolate the estimated trajectory to determine an estimation of whether the projectile has also impacted an object behind the structure.

Abstract: There is described a fire detection/notification system for detecting a weapons discharge comprising a network and a control panel. The network includes multiple wireless devices, and each device includes a fire-related sensor and a first weapons discharge sensor, and a second weapons sensor. The control panel is configured to identify the weapons discharge based on data generated by the first and second weapons discharge sensors and produce an alert signal in response to identifying the weapons discharge. The control panel is connected to the network and includes an output circuit configured to communicate with an emergency responder device external to the fire detection/notification system in response to receiving the alert signal.

Abstract: Active shooters are becoming a common threat in public areas. Detection and analysis of a gunshot in a public area can aid administrative and first responder personnel in determining that a gun has been fired and in stopping the threat quickly. Embodiments of the present disclosure are directed to solutions for detecting and analyzing gunshots and fires, and transmitting that information to administrative personnel and first responders.

Abstract: Detecting sound sources in a physical space-of-interest is challenging due to strong ego-noise from micro aerial vehicles (MAVs)' propeller units, which is both wideband and non-stationary. The present subject matter discloses a system and method for acoustic source localization with aerial drones. In an embodiment, a wideband acoustic signal is received from an aerial drone. Further, the wideband acoustic signal is splitted into multiple narrow sub-bands having cells. Moreover, from a measurement position corresponding to each of the multiple narrow sub-bands, power in each of the cells is measured by forming a beam to each of the cells. In addition, intra-band and inter measurement fusion of the measured power at each of the cells is performed. Also, geo-location of an acoustic source corresponding to the wideband acoustic signal is identified upon performing intra-band and inter measurement fusion of the measured power.

Abstract: The location of lost or entangled fishing gear, known as derelict gear, is detected. The motion or change of position of a buoy attached to fishing gear is determined via sensors mounted on the buoy and compared to typical buoy motion. If the buoy has moved beyond a threshold value from its original location, an alert is sent to the fisherman. The available sensor data will be used to determine the likelihood of loss or entanglement. This alert facilitates recovery of lost or entangled gear by identifying where immediate retrieval efforts should be focused. The number of traps lost to the ocean that otherwise would continue to trap or entangle marine life may be reduced.

Abstract: An electronic communications terminal records in a memory a sampled audio segment of sound sensed by a micro-phone. A time stamp associated with timing of the recording of the sampled audio segment is determined and stored in the memory associated with the sampled audio segment. The sampled audio segment and the time stamp are transmitted through a network interface toward a location service client of a network node that determines location of the electronic communications terminal based on correlating the sampled audio segment and other sampled audio segments of the sound received from other electronic communications terminals. A related network node and corresponding methods by terminals and network nodes are disclosed.

Abstract: Aspects of the present disclosure provide systems and methods for determining an estimated orientation and/or position of a user's head using worn ear pieces and leveraging the estimated head orientation and/or position to provide information to the user. In one exemplary method, first and second spatial positions of respective first and second ear pieces worn by a user may each be determined. Based at least in part on the first and second spatial positions of the respective first and second ear pieces, an estimated orientation of the user's head may be determined. The method may further include requesting information to be provided to the user based at least in part on the estimated orientation of the user's head and providing contextual information to the user responsive to the request.

Abstract: Methods, systems, and devices are disclosed for operating a drone consistent with an access level of the drone and/or an operator of the drone. Various embodiments may include determining, by a processor of the drone, whether the drone is registered with an agency or the operator of the drone is registered to operate the drone. In response to determining that the drone and/or the operator is registered, the drone processor may operate the drone consistent with an access level of the drone and/or operator. In response to determining that the drone and/or the operator is registered, the drone processor may restrict operations of the drone.

Abstract: A method is provided. The method comprises: initializing a point mass filter; initializing the one or more Bayesian filters; obtaining measurement data associated with a horizontal position on a surface; obtaining measurement data of a horizontal position and a velocity; obtaining geo-mapping data; estimating, with the point mass filter, the horizontal position on the surface based upon the geo-mapping data and the measurement data; estimating, with the one or more Bayesian filters, remaining state parameters based upon an output of the point mass filter and the measurement data; predicting, with the point mass filter, an a priori horizontal position, on a surface for a future time when the next measurement data will be obtained; and predicting, with the one or more Bayesian filters, an a priori remaining state parameters for a future time when the next measurement data will be obtained.

Abstract: Examples are disclosed that relate to a head-mounted device configured to perform virtual echolocation. The head-mounted device is configured to cast an array of rays at specified angles from a position derived from a pose of the head-mounted device in a physical environment, identify a plurality of intersection points of the rays with a virtual model of the physical environment, for each identified intersection point, modify an audio signal based on a head-related transfer function corresponding to the intersection point to produce a plurality of spatialized audio signals, for each spatialized audio signal, determine a time-of-flight adjustment based upon a distance between the corresponding intersection point and the position from which the rays were cast, and output each spatialized audio signal to one or more speakers with a delay based on the time-of-flight adjustment.

Abstract: An audio processor receives ambient audio input and performs time frequency analysis. A controller receives a first description of a first step of a project, generates a first sound signature according to the time frequency analysis of the ambient audio input during a timeframe corresponding to performance of the first step, adds the first step to a project script including the first description and the first signature for matching to future audio input to determine whether the first step is being performed, receives a second description of a second step of the project, generates a second sound signature based on the time frequency analysis of the ambient audio input during a timeframe corresponding to performance of the second step, and adds the second step to the project script including the second description and the second signature for matching to future audio input to determine whether the second step is performed.

Abstract: A system and method for providing surveillance data are provided. The system includes: a pattern learner configured to learn a time-based data pattern by analyzing at least one of image data of one or more images and sound data of sound obtained from a surveillance zone at a predetermined time or time period, and to generate an event model based on the time-based data pattern; and an event detector configured to detect at least one event by comparing the event model with a time-based data pattern of at least one of first image data of one or more first images and first sound data of first sound obtained from the surveillance zone.

Abstract: Methods, systems, and devices are disclosed for providing conditional access for a drone for accessing a restricted area. Conditional access information associated with conditional access restrictions for the restricted area may be received by the drone. The drone may compare the received conditional access information to one or more access parameters for the drone. The drone may access the restricted area based on the comparison of the received conditional access information and the access parameter. A drone may take corrective action when the received conditional access information does not permit access to the restricted area based on the access parameter for the drone.

Abstract: A system, method, and computer program product are provided for estimating a distance. The system includes a Radio Frequency Identifier (RFID) reader. The system further includes an RFID tag. The system also includes measurement equipment for measuring a plurality of phase differences at different frequencies between transmitted Radio Frequency (RF) signals from the RFID reader and corresponding received RF signals at the RFID tag. The system additionally includes a processor. The processor is configured to calculate normalized phases from the plurality of phase differences. The processor is further configured to calculate corrected phases by resolving one or more ambiguities from the normalized phases. The processor is also configured to obtain a characteristic curve using the corrected phases. The processor is additionally configured to provide an estimate of the distance based on the characteristic curve and the corrected phases.

Abstract: A method for controlling a hearing device via touch gestures carried out by a wearer of the hearing device. As part of the gesture a finger is swiped across first and second sound inlets of the hearing device. A gesture is detected by determining if a first output signal from a first microphone at the first sound inlet contains a component caused by the finger touching the hearing device at the first sound inlet and if a second output signal from a second microphone at the second sound inlet contains a component caused by the finger touching the hearing device at the second sound inlet. Based on the detected gesture a control signal changes a processing parameter or setting of a signal processing unit of the hearing device. Additionally, a hearing device capable of performing the proposed method and a method of fitting such a hearing device are provided.

Abstract: Disclosed are methods and systems for determining distance between two or more mobile devices utilizing a sound emitted from each device such as a chirp. Each device may determine or receive an indication of a time reference for each instance the device emits or detects a chirp. Utilizing the time reference data, the distance between the two or more devices may be determined assuming the sound travels at a constant speed of 340.29 m/s. Techniques for disambiguating orientation of the devices relative to one another rare also disclosed.

Abstract: A sound processing apparatus includes a sound collection position calculating unit configured to calculate sound collection positions of sound signals of multiple channels on the basis of the sound signals, a sound source direction calculating unit configured to calculate a sound source direction on the basis of the sound signals of multiple channels, a first transfer function calculating unit configured to calculate a first transfer function corresponding to the sound source direction on the basis of the sound signals of multiple channels, and a second transfer function calculating unit configured to calculate a second transfer function by interpolating the first transfer function corresponding to each of a plurality of sound source directions.

Abstract: A method for focusing on an object to capture an image of that object is provided. The method includes obtaining the travel time between the point in time that an ultrasonic signal is sent and the point in time at which the reflected signal is received. The method also includes obtaining environment information of the electronic device based on location/position information. The method further includes determining local sound speed according to environment information and determining the distance to an object using the local sound speed and the travel time. In addition, the method can include focusing on the object according to the object distance.

Abstract: The invention relates to a monitoring system for monitoring a watercraft or several watercrafts, having an identification device and a first hydrophone, which is configured such that acoustic signals that are emitted by watercrafts are determined as underwater sound information therein, whereby the identification device has a first memory for storing the underwater sound information and a second memory for storing watercraft information, whereby the first and second memories are interconnected, characterized in that the first hydrophone is arranged in a stationary and fixed manner.

Abstract: Omnidirectional high resolution tracking and recording apparatus and method are disclosed. The high resolution tracking and recording apparatus comprises a pan/tilt/zoom camera executable rotation and zoom-in; assistant cameras configured to have fisheye lens; microphones performable beam steering; and a processor configured to control to search a location of an important object in a recorded image by analyzing an image taken by the pan/tilt/zoom camera and the assistant cameras and a sound source recorded by the microphones, rotate the pan/tilt/zoom camera to the searched location, perform zoom-in of the pan/tilt/zoom camera, and amplify a sound occurred in a direction of a sound source by searching the direction of the sound source through preset algorithm.

Abstract: An audio surveillance system includes a plurality of nodes and each node includes a microphone, a speaker, and a control unit. The microphone is configured to detect sound and the speaker is configured to provide sound. The control unit is configured to receive a plurality of inputs from the plurality of nodes and the plurality of inputs are based on a detected sound; determine a location of the source of the detected sound based on the plurality of inputs; classify the detected sound according to predefined alert conditions and based on the location of the source of the detected sound; provide an alert to a monitoring device regarding the detected sound based on the classification of the detected sound; and control at least one node from the plurality of nodes to provide an audio response to the detected sound.

Abstract: A sheet feeder includes a controller configured to control an emitter to emit an ultrasonic wave toward a target sheet being fed along a sheet guide, control a measurer to measure a first reception intensity of a first component of the ultrasonic wave received by a receiver during a first period of time, control the measurer to measure a second reception intensity of a second component of the ultrasonic wave received by the receiver during a second period of time, and determine a feeding state of the target sheet in a detectable area between the emitter and the receiver within the sheet guide, based on the first reception intensity and the second reception intensity.

Abstract: A first computer is configured to receive, from at least one second computer in a first vehicle, data relating to a gunshot. The computer is configured to then determine a location of the gunshot from the data, and to transmit a message, including the gunshot location, to at least one third computer in a second vehicle.

Abstract: A method for merging measurements of a flight parameter of an aircraft, from measurements (y1, y2, y3, y4) of this parameter supplied respectively by a plurality of sensors (C1, C2, C3, C4), comprising: for each sensor (C1; C2; C3; C4), computing a deviation (T1; T2; T3; T4), proportional to the absolute value of a difference between a measurement (y1, y2, y3; y4) supplied by this sensor, and an estimation of the parameter computed from the measurements supplied by the other sensors; comparing each deviation to a corresponding threshold (Td1; Td2; Td3; Td4); based on the comparisons, determining the presence or not of an anomaly on one of the sensors with a determined total probability of false alarm; and merging measurements to provide a final estimation of the parameter ({circumflex over (x)}).

Abstract: A tracking computer system may track a target using a single linear array. The system may receive first sensor measurements and one or more additional sensor measurements from the linear array. The system may determine whether a location of the target can be identified based on a cone intersection algorithm. When the target location can be identified based on the cone intersection algorithm, the first and the one or more additional sensor measurements may be applied to the cone intersection algorithm to identify the target location. When target location cannot be identified based on the cone intersection algorithm, the first and the one or more additional sensor measurements may be applied to an angular motion model to determine a best fit arc path corresponding to the target. A true target angle estimate and a target angular velocity may be determined based on the determined best fit arc path.