Abstract: A method for quality control monitoring of additive manufacturing processes comprising forming at least one channel in an additive manufacturing build platform, wherein the channel is formed in the upper surface of the build platform to a predetermined depth, and wherein the channel is formed in a predetermined pattern across the upper surface of the build platform; placing a sensor in the channel formed in the upper surface of the build platform, wherein the sensor gathers information relevant to an additive manufacturing process occurring on or in close proximity to the build platform; enclosing the sensor within the channel formed in the upper surface of the build platform with an additive manufacturing substrate, wherein components or parts are built directly on the substrate using an additive manufacturing process, and using the sensor to gather information about the components or parts and the additive manufacturing process itself.

Abstract: A noise data artificial intelligence learning method for identifying the source of problematic noise may include a noise data pre-conditioning method for identifying the source of problematic noise including: selecting a unit frame for the problematic noise among noises sampled with time; dividing the unit frame into N segments; analyzing frequency characteristic for each segment of the N segments and extracting a frequency component of each segment by applying Log Mel Filter; and outputting a feature parameter as one representative frame by averaging information on the N segments, wherein an artificial intelligence learning by the feature parameter extracted according to a change in time by the noise data pre-conditioning method applies Bidirectional RNN.

Abstract: A method includes extracting, from a frame of the audio sample, spectral features indicative of cochlear impulse response of an auditory system; obtaining an estimate of a speech signal in the frame from a neural network that is trained, during a training phase, to accept the spectral features as input and output the estimate of the speech signal, where the estimate of the speech signal includes reverberation and excludes noise present in the frame; mapping the estimate of the speech signal to a frequency domain of the frame using mapping parameters obtained during the training phase to obtain an estimate of a reverberant speech spectrum in the frame; and obtaining, from a time-distributed neural network, a dereverberant frame of the frame, where the estimate of the reverberant speech spectrum in the frame is used as an input to the time-distributed neural network.

Abstract: A method includes receiving audio signal features generated by neural network feature extraction, identifying a vehicle type by neural network feature recognition, and determining a risk level of a vehicle driver based on the vehicle type. A computing system includes a processor and a memory storing instructions that when executed cause the computing system to receive audio signal features generated by neural network feature extraction, identify a vehicle type by neural network feature recognition, and determine a risk level of a vehicle driver based on the vehicle type. A non-transitory computer readable medium contains instructions that when executed cause a computer to receive audio signal features generated by neural network feature extraction, identify a vehicle type by neural network feature recognition layer and determine a risk level of a vehicle driver based on the vehicle type.

Abstract: A method for protecting a person left in a vehicle includes determining whether the person present on a rear seat is an infant, by using a waveform of a reflected wave generated by a radar sensor after an ignition of the vehicle is turned off, determining a risk level when the person on the rear seat is determined to be the infant, and taking a first step measure that corresponds to a risk factor, when the risk level indicates a possibility of danger to the person.

Abstract: Systems and methods for superimposing the human elements of video generated by computing devices, wherein a first user device and second user device capture and transmit video to a central server which analyzes the video to identify and extract human elements, superimpose these human elements upon one another, adds in at least one augmented reality element, and then transmits the newly created superimposed video back to at least one of the user devices.

Abstract: A computer-implemented method includes providing a first application to a mobile computing device that obtains a set of audio signals, transforms the set of audio signals into a set of signal features, wherein no audio signal in the set of audio signals can be derived from the set of signal features, and transmits the set of signal features to a remote computing system, without transmitting any portion of the set of audio signals. The method also includes receiving, at the remote computing system, the set of signal features, identifying a type of the vehicle at least in part by applying the set of signal features to a trained neural network, and one or both of (i) causing the identified type of the vehicle to be displayed, and (ii) causing the identified type of the vehicle to be provided to a second application.

Abstract: A computer-implemented method for acoustics-based light source control of a lighting system is provided. The method may include detecting sounds emitted by a sound source from positions located along the path. A velocity of the sound source is determined with respect to a point on the path based on the detected sound emissions. A spatio-temporal trajectory of the sound source is based on the determined velocity and a topography of the path at the positions of the sound source. One or more light sources positioned adjacent to the determined trajectory are identified. Responsive to determining that a distance between the sound source and the identified light sources does not exceed a predetermined threshold, the identified light sources are energized to illuminate the length of the path ahead of the sound source.

Abstract: The invention relates to a method for determining a detection range (12) of a traffic route (2) in which traffic participants can be detected by a transmitting and receiving device (4), wherein the transmitting and receiving device (4) is arranged at a device position in a device orientation and is designed to emit a transmitted radiation and to receive reflected transmitted radiation, wherein the method comprises the following steps: a) calculating a spatial detecting range of the transmitting and receiving device (4) at least also from the device position and the device orientation by means of a 3D model, b) determining an aerial detecting range in a measurement plane (10) from the spatial detecting range, and c) determining the detecting range (12) from the areal detecting range.

Abstract: An environmentally-friendly vehicle sound generator apparatus. The apparatus includes a vehicle state sensing unit, a sound source storage unit, a sound source playback unit, a sound source amplification unit, a sound output unit, and a control unit. The control unit receives a sensing signal from the vehicle state sensing unit and controlling the operation of the sound source playback unit so as to play back the operating sound in different playback methods to control and change the operating sound according to the received sensing signal. The vehicle state sensing unit senses a vehicle speed, and if it is determined according to a vehicle speed signal that the vehicle speed reaches a preset speed range, the control unit fades out the output of the sound output unit at a preset ratio of the vehicle speed to a time elapsed after the vehicle speed reaches the preset speed range.

Abstract: An exterior alerting system for a vehicle. The system may include a sensor, a controller, and an alerting device. The sensors maybe configured to detect an object exterior to the vehicle. Additionally, the controller may be configured to receive a position of the object from the sensor, calculate a danger zone based on a trajectory of the vehicle and the position of the object, and generate at least one exterior alerting signal when the vehicle cannot avoid the danger zone.

Abstract: Assessing and removing jitter from tachometer signals enhances the performance of condition monitoring systems where accurate tachometer signals are needed. A system as disclosed herein can be designed and configured to have a low order of operations, so as to allow for implementation on low cost microcontrollers, which can be important for bused, distributed monitoring systems in which the tachometer zero crossing data is collected at a tachometer sensor and then broadcast to other remote sensors needing that information for vibration or other advanced analysis. Moreover, for monolithic architecture systems (e.g., a centralized processing and control architecture), the low order of operation and small software code base allows the system to be a simple/low cost addition to existing monitoring systems.

Abstract: Systems and methods for real-time traffic detection are described. In one embodiment, the method comprises capturing ambient sounds as an audio sample in a user device, and segmenting the audio sample into a plurality of audio frames. Further, the method comprises identifying periodic frames amongst the plurality of audio frames. Spectral features of the identified periodic frames are extracted, and horn sounds are identified based on the spectral features. The identified horn sounds are then used for real-time traffic detection.

Abstract: A wading indicator system for a vehicle comprising: at least one sound wave pulse emitter device; at least one sound wave pulse receiver device; and a control unit. The control unit configured to measure one or more of the following variables: (i) the time of flight of a sound pulse between the at least one sound wave pulse emitter device and the at least one sound wave pulse receiver device; (ii) the amplitude of a sound pulse emitted by the at least one sound wave pulse emitter device when received by the at least one sound wave pulse receiver device; and (iii) the wavelength of a sound pulse emitted by the at least one sound wave pulse emitter device when received by the at least one sound wave pulse receiver device. Thereby the control unit is configured to determine whether at least a portion of the vehicle is immersed in water.

Abstract: A navigation system helps users navigate through an environment by a plurality of sensors. The sensors include one or both of short and long range sensors that detect objects within the user's environment. Information obtained from the sensors' detection of objects within the user's environment can be used to help the user avoid colliding with objects within the environment and help navigate the user to a destination. The navigation system may provide the user with audible feedback regarding the objects with the user's environment and/or instructions regarding how to avoid colliding with an object and how to navigate to a destination.

Abstract: A parking sensor device has a casing, a front cover, a sensor module and an assembling clamp. The casing has two first hooking elements. The front cover is mounted on the casing. The sensor module is mounted in the casing and the front cover. The assembling clamp detachably engages the casing and has two second hooking elements. The second hooking elements selectively hook the first hooking elements of the casing respectively. The casing and the assembling clamp are engaged quickly with each other, thereby facilitating the easy fabrication of the parking sensor device and improving the convenience of maintenance of the parking sensor device.

Abstract: A parking sensor device has a casing, a front cover, a sensor module and an assembling clamp. The casing has two first hooking elements. The front cover is mounted on the casing. The sensor module is mounted in the casing and the front cover. The assembling clamp detachably engages the casing and has two second hooking elements. The second hooking elements selectively hook the first hooking elements of the casing respectively. The casing and the assembling clamp are engaged quickly with each other, thereby facilitating the easy fabrication of the parking sensor device and improving the convenience of maintenance of the parking sensor device.

Abstract: An adaptive sensing system is configured to acquire sensor data pertaining to objects in the vicinity of a land vehicle. The adaptive sensing system may be configured to identify objects that are at least partially obscured by other objects and, in response, the adaptive sensing system may be configured to modify the configuration of one or more sensors to obtain additional information pertaining to the obscured objects. The adaptive sensing system may comprise and/or be communicatively coupled to a collision detection module, which may use the sensor data acquired by the adaptive sensing system to detect potential collisions.

Abstract: Provided is an object detection apparatus capable of accurately estimating the movement amount of the position, which moves within an oncoming vehicle, of a reflection point of an electromagnetic wave radiated from a radar apparatus, and using the movement amount for collision possibility determination. The object detection apparatus provided in a vehicle includes: a relative position detection section radiating the electromagnetic wave to an object in front of the vehicle, and receiving a reflection wave from the object, thereby detecting the relative position, to the vehicle, of an electromagnetic wave reflection point on the object reflecting the electromagnetic wave; and a movement amount estimation section capable of, based on the relative position to the vehicle of the electromagnetic wave reflection point, estimating, as continuous values, a movement amount of the electromagnetic wave reflection point on the object from a predetermined timing until the object approaches the vicinity of the vehicle.

Abstract: A method includes transmitting a measurement command from a controller to an occupancy sensor with an address that corresponds to an occupancy sensor identifier. The measurement command causes the occupancy sensor to transmit an ultrasonic signal into a parking space, receive echo signals reflected back to the occupancy sensor, and determine, based on the echo signals, whether the associated parking space is occupied or empty. The method includes subsequently sending a status check to the occupancy sensor and receiving a response that includes the occupancy sensor's determination as to whether the associated parking space is occupied or empty. The method also includes calibrating the occupancy sensors from the controller.

Abstract: The invention relates to a method for supporting a driver of a vehicle (2) in maneuvering the vehicle (2) on a driving route (4), in particular when parking a vehicle (2) into or out of a parking space (3), with the aid of a portable communication device (13). At least one vehicle external sensor device (11, 17) is provided which is arranged stationarily relative to the driving route (4). The sensor device (11, 17) captures data relating to the vehicle (2) located on the driving route (4) and wirelessly emits signals (15, 15?) comprising the captured data in such a way that same signals (15, 15?) reach the interior of the vehicle (2). The signals (15, 15?) are received through the portable communication device (13), and the data are output through the portable communication device (13). The invention also relates to a system (10) as well as a portable communication device (13).

Abstract: A method and apparatus of recognizing the presence of a passenger in front of a door of a transit vehicle comprises directing an ultrasound transmitter/receiver at a volume of space adjacent the door, emitting an ultrasound pulse into the empty volume, recording and integrating intensity of the echoes and storing the integrated value as a standard value, repeatedly emitting an ultrasound pulse into the volume, and comparing the integrated values to the standard value.

Abstract: A fail-safe circuitry for a vehicle barrier security system prevents accidental raising of the barrier due to inadvertent closing of an activation relay causing power to be provided to an activation mechanism raising the barrier. A latching relay, having a latched state and reset state, is placed in series between the activation relay and the activation mechanism. The latching relay is reset whenever the OPEN switch is pressed for lowering the barrier or an automatic reset relay is energized by a controller whenever passage of a vehicle is sensed. Prior to raising the barrier, the latching relay must be reset, which can occur by pressing the OPEN switch or by the controller detecting passage of a prior vehicle and activating a automatic reset relay. Accidental raising of the barrier due to malfunctions of the activation relay due to vibrations is prevented by latching and resetting the latching relay.

Abstract: Methods and arrangements for employing roadside acoustics sensing in ascertaining traffic density states. Traffic monitoring input is received from a road segment, the traffic monitoring input including traffic audio input. The traffic monitoring input is processed and the processed traffic monitoring input is classified with a predetermined traffic density state. The classified traffic monitoring input is combined with other classified traffic monitoring input.

Abstract: A vehicle detector and method for detecting the presence of a vehicle. The vehicle detector includes an array of ultrasonic transducers to direct and receive ultrasonic beams to and from a target. Further, the vehicle detector includes a control system for turning on and off the ultrasonic transducers and for generating data corresponding to the distance between the vehicle detector and the target, the speed of the target, and the direction of motion of the target; and for comparing the generated data to stored data to determine whether or not a vehicle is present. Finally, the vehicle detector includes output circuitry that directs a signal to an external device whether or not a vehicle is present.

Abstract: A parking space detection device and method thereof, wherein, firstly, store a plurality of border data relating to moved distance of a vehicle, and distance between vehicle and an obstacle for reverse transmission of ultrasonic waves; then determine if said border data satisfy evaluation conditions, such that it is in a first detecting parking space then obstacle state, or in a first detecting obstacle then parking space state. Wherein, in case that any of evaluation conditions is satisfied, start to calculate a first difference between each of said border data and their average, to determine if it is grater than a standard deviation; in case that answer is positive, fetch at least two data points, a first data point and a second data point, corresponding to border data, then calculate their difference to adjust weights of first data point and second data point, in obtaining a highly accurate parking space.

Abstract: An ultrasonic sensor includes a transmitting device, a receiving device, and a circuit device. The circuit device determines that the receiving device receives an ultrasonic wave reflected from an object, when an output voltage of the receiving device is equal to or greater than a first threshold. The circuit device includes a humidity detection section configured to detect an ambient humidity of the transmitting and receiving devices and a threshold adjustment section configured to calculate, based on the detected ambient humidity, a sound pressure of the ultrasonic wave that is received by the receiving device after propagating over a round-trip distance between the ultrasonic sensor and the object. The threshold adjustment section reduces the first threshold, when the output voltage corresponding to the calculated sound pressure is less than a second threshold that is greater the first threshold.

Abstract: There is provided an approaching vehicle detection device that detects an approaching vehicle on the basis of sounds collected by a plurality of sound collectors 13A, 14A, 15A, and 16A, in which a sound source (in particular, traveling sound of the vehicle) is detected using pairs of the sound collectors 11A (13A, 14A) and 12A (15A, 16A) with narrow spacings, and approach of the sound source is detected using a pair of the sound collectors 13A and 16A which are disposed to be more widely spaced than the pairs of the sound collectors 11A and 12A.

Abstract: The invention relates to a vehicle treatment installation with a drive-in area for a vehicle to be treated, a treatment gantry that can move along a drive-in direction, and at least one camera for creating an image of the drive-in area and vehicle. Such known vehicle treatment installations often fail and/or are maintenance-intensive. The task of providing an installation and also a method for its operation that simplifies, with simple means, the drive-in process into the correct treatment position for the driver of a vehicle to be treated is achieved by a display device that is visible to the driver of the vehicle during the drive-in process, and at least one mark. The subject matter of the invention is also a method for the operation of the vehicle treatment installation.

Abstract: A moving object detection system is provided with an existence detection part, an integrating part and an existence judgment part. Based on first and second detection signals, the existence detection part calculates a rotation angle of each transition factor that is obtained from the first and second detection signals and rotates around the origin in a two-dimensional coordinate system. The existence detection part is configured so that the rotation angle becomes less than 90 degrees. The integrating part integrates each rotation angle to obtain an integrated angle. The existence judgment part judges whether or not a moving object approaching or leaving a receiver of the device exists in a detection area based on the integrated angle and a threshold angle.

Abstract: A system is provided for establishing a compliance zone and monitoring interactions therewith. The system includes a compliance zone designator and a wearable device. The compliance zone designator transmits an ultrasound signal to establish the compliance zone. The ultrasound signal may be encoded with information on the compliance zone. The compliance zone designator is configured for placement at a location in which the compliance zone is desired. The wearable device is separate from the compliance zone designator. The wearable device includes a compliance zone recognition component configured to recognize the compliance zone and identify one or more pre-defined interaction criteria for the compliance zone. When the wearable device is within the compliance zone, the compliance zone recognition component recognizes the compliance zone and identifies the interaction criteria of the compliance zone.

Abstract: A method is used for detecting the environment of a vehicle and utilizes a number of sensors, the sensors having different detection ranges, and a transition of an object between two detection ranges is bridged by prediction by using a handover algorithm.

Abstract: When an own vehicle waits to turn left or right, a vehicle data processing unit processes information of an oncoming vehicle based on data analyzed by data analyzing units. A support processing unit sets a blind angle rank according to a difficulty degree of recognizing a following vehicle due to the blind angle of a lead vehicle from the relationship in the vehicle body size between the lead and following vehicles based on the oncoming vehicle information, and sets the highest blind angle rank value as an oncoming straight-ahead vehicle rank flag. It also sets an evaluation rank according to a risk degree when the own vehicle turns left or right, based on the oncoming straight-ahead vehicle rank flag and an oncoming vehicle rank flag set according to the size of an oncoming vehicle waiting to turn left or right, and informs the driver of driving support information according to the evaluation rank.

Abstract: Disclosed are a system and method for recognizing an obstacle at the time of parking.

Abstract: A system is provided for detecting the passage of vehicles and the classification thereof by weight using geophone outputs and a unique density measurement in which the number of peaks of the geophone signal above a predetermined threshold over a number of time frames indicates the presence of a vehicle, with the number of time frames in which the density exceeds the threshold indicating whether the vehicle is a heavy vehicle such as a tank, or a light vehicle such as a car, with the threshold eliminating both manmade and natural noise, as well as distinguishing seismic vibrations due to personnel and animals. In one embodiment, various thresholds are utilized to detect the onset of vehicle presence and the end of the event.

Abstract: A method and an apparatus for recognizing a parking area are disclosed. The parking area recognizing apparatus includes: a signal transmitter transmitting a signal using a sensor; an echo signal receiver receiving an echo signal for the signal; a multiple signal generator generating a multiple echo signal using the echo signal based on first and second preset thresholds; and a parking area recognizer recognizing a parking area by calculating a round trip time and a duration time for the multiple echo signal and selecting an available echo signal based on at least one of the round trip time and the duration time. Accordingly, a precision in recognition of a parking area is enhanced by reducing a measurement error by processing an echo signal received after it is reflected on an object with a multiple echo signal in recognition of the parking area using a sensor such as an ultrasonic sensor or a radar sensor.

Abstract: A vehicle presence alert apparatus for alerting a target object to a presence of the vehicle via an alert sound with a frequency in an audible range is disclosed. The vehicle presence alert apparatus includes: a sound emitter configured to (i) cause a carrier wave with a frequency in an ultrasonic range to carry the alert sound, and (ii) emit the carrier wave carrying the alert sound as a radiation wave toward the target object; a sound receiver configured to receive a reflected wave, the reflected wave being generated due to reflection of the radiation wave by the target object; and relative velocity calculation means for calculating a relative velocity of the target object with respect to the vehicle based on a frequency of the radiation wave and a frequency of the reflected wave.

Abstract: A collision avoidance system for use with vehicles includes a sensor mounted on a moving vehicle, wherein the sensor is operative to measure the distance between an overhead obstacle ahead of the vehicle and the sensor itself; a processor connected to the sensor; means for determining a reference height which is the height above ground level at which the sensor is mounted on the vehicle, and wherein the reference height is entered into the processor; means for determining the height of the tallest portion of the vehicle above ground level, wherein the height of the tallest portion of the vehicle is also entered into the processor; and wherein the processor adds the reference height to the distance between the obstacle and the sensor to determine a measured height of the obstacle, and wherein the processor produces an alarm if the measured height of the obstacle is less than the height of the tallest portion of the vehicle.

Abstract: A vehicular collision avoidance system includes a sensor mounted on a vehicle, wherein the sensor is operative to measure the distance between an overhead obstacle ahead of the vehicle and the sensor; a processor connected to the sensor; means for determining a reference height which is the height above ground level at which the sensor is mounted on the vehicle, and wherein the reference height is entered into the processor; means for determining the height of the tallest portion of the vehicle above ground level, wherein the height of the tallest portion of the vehicle is also entered into the processor; and wherein the processor adds the reference height to the distance between the obstacle and the sensor to determine a measured height of the obstacle. The processor produces an alarm if the measured height of the obstacle is less than the height of the tallest portion of the vehicle.

Abstract: A system is provided for establishing a compliance zone and monitoring interactions therewith. The system includes a compliance zone designator and a wearable device. The compliance zone designator transmits an ultrasound signal to establish the compliance zone. The ultrasound signal may be encoded with information on the compliance zone. The compliance zone designator is configured for placement at a location in which the compliance zone is desired. The wearable device is separate from the compliance zone designator. The wearable device includes a compliance zone recognition component configured to recognize the compliance zone and identify one or more pre-defined interaction criteria for the compliance zone. When the wearable device is within the compliance zone, the compliance zone recognition component recognizes the compliance zone and identifies the interaction criteria of the compliance zone.

Abstract: A method and apparatus for identifying running vehicles in an area to be monitored using acoustic signature recognition. The apparatus includes an input sensor for capturing an acoustic waveform produced by a vehicle source, and a processing system. The waveform is digitized and divided into frames. Each frame is filtered into a plurality of gammatone filtered signals. At least one spectral feature vector is computed for each frame. The vectors are integrated across a plurality of frames to create a spectro-temporal representation of the vehicle waveform. In a training mode, values from the spectro-temporal representation are used as inputs to a Nonlinear Hebbian learning function to extract acoustic signatures and synaptic weights. In an active mode, the synaptic weights and acoustic signatures are used as patterns in a supervised associative network to identify whether a vehicle is present in the area to be monitored. In response to a vehicle being present, the class of vehicle is identified.

Abstract: The fields of the invention are vehicle on-board security and vehicle piloting safety. The invention relates to a method and device for aiding the restoral of command of a vehicle by an operator of the vehicle. The command of the vehicle by the operator is ensured through vehicle piloting controls, when the operator has lost command of the vehicle in favor of a device for disabling piloting controls. The device disables the action of the piloting controls on the piloting means during the loss of command. According to the invention, the method includes emitting a restoral of command request; a vehicle motion phase is determined; a reference state of the piloting control is determined as a function of the motion phase; a current state of the piloting control is determined; the current state with the reference state is compared so as to identify a deviation ? between the current state and the reference state. When no deviation ? is identified, the command of the vehicle by the operator is restored.

Abstract: An obstacle detecting device includes a wall member and an ultrasonic sensor. The wall member has a base member having an inner surface, and the base member extends in parallel with an imaginary plane. The ultrasonic sensor is attached to the inner surface of the base member for transmitting and receiving an ultrasonic wave via the base member. The ultrasonic sensor includes an ultrasonic transducer, and is in contact with the base member via a contact portion of the inner surface of the base member. The wall member includes a plurality of rigidity changing portions that are arranged on an other part of the inner surface other than the contact portion in an arrangement direction away from the contact portion.

Abstract: A method and apparatus for identifying running vehicles in an area to be monitored using acoustic signature recognition. The apparatus includes an input sensor for capturing an acoustic waveform produced by a vehicle source, and a processing system. The waveform is digitized and divided into frames. Each frame is filtered into a plurality of gammatone filtered signals. At least one spectral feature vector is computed for each frame. The vectors are integrated across a plurality of frames to create a spectro-temporal representation of the vehicle waveform. In a training mode, values from the spectro-temporal representation are used as inputs to a Nonlinear Hebbian learning function to extract acoustic signatures and synaptic weights. In an active mode, the synaptic weights and acoustic signatures are used as patterns in a supervised associative network to identify whether a vehicle is present in the area to be monitored. In response to a vehicle being present, the class of vehicle is identified.

Abstract: A system for detecting and classifying a security breach may include at least one sensor configured to detect seismic vibration from a source, and to generate an output signal that represents the detected seismic vibration. The system may further include a controller that is configured to extract a feature vector from the output signal of the sensor and to measure one or more likelihoods of the extracted feature vector relative to set {bi} (i=1, . . . , imax) of breach classes bi. The controller may be further configured to classify the detected seismic vibration as a security breach belonging to one of the breach classes bi, by choosing a breach class within the set {bi} that has a maximum likelihood.

Abstract: A method and apparatus for identifying running vehicles in an area to be monitored using acoustic signature recognition. The apparatus includes an input sensor for capturing an acoustic waveform produced by a vehicle source, and a processing system. The waveform is digitized and divided into frames. Each frame is filtered into a plurality of gammatone filtered signals. At least one spectral feature vector is computed for each frame. The vectors are integrated across a plurality of frames to create a spectro-temporal representation of the vehicle waveform. In a training mode, values from the spectro-temporal representation are used as inputs to a Nonlinear Hebbian learning function to extract acoustic signatures and synaptic weights. In an active mode, the synaptic weights and acoustic signatures are used as patterns in a supervised associative network to identify whether a vehicle is present in the area to be monitored. In response to a vehicle being present, the class of vehicle is identified.

Abstract: An occupant detection system emits an ultrasonic signal for detecting the presence of an occupant by reflecting the signal off the occupant and then determines that an occupant is present by detecting motion of the occupant. One type of motion that is detected is the small rhythmic motion associated with respiration. The motion detection system improves detection of motion smaller than a wavelength of the ultrasonic signal by shifting the wavelength of the ultrasonic signal to increase the detected motion signal. The system may also determine the presence of an occupant by comparing the motion signal to a motion pattern that corresponds to respiration.

Abstract: A target position setting device includes a distance meter, an imager, first and second calculating portions, a determination portion, and a setting portion. The distance meter measures a distance to an object around a vehicle. The imager takes an image of an environment around the vehicle. The first calculating portion calculates a first candidate of a target position of the vehicle according to a measuring result of the distance meter. The second calculating portion calculates a second candidate of the target position of the vehicle according to an imaging result of the imager. The determination portion determines whether a relationship between the first candidate and the second candidate meets a given condition. The setting portion sets the target position according to the second candidate of the target position when the determination portion determines that the relationship between the first candidate and the second candidate meets the given condition.

Abstract: A vehicle presence alert apparatus for alerting a target object to a presence of the vehicle via an alert sound with a frequency in an audible range is disclosed. The vehicle presence alert apparatus includes: a sound emitter configured to (i) cause a carrier wave with a frequency in an ultrasonic range to carry the alert sound, and (ii) emit the carrier wave carrying the alert sound as a radiation wave toward the target object; a sound receiver configured to receive a reflected wave, the reflected wave being generated due to reflection of the radiation wave by the target object; and relative velocity calculation means for calculating a relative velocity of the target object with respect to the vehicle based on a frequency of the radiation wave and a frequency of the reflected wave.

Abstract: A sensor transmitter device for transmitting the payload data of a sensor to a bus control device is described, the sensor transmitter device being connectable to a data bus of a vehicle, which is configured for simultaneous transmission of bus data packets between a plurality of sensor transmitter devices and a bus control device. The bus data packets should include at least one signaling field and one payload data field having a plurality of payload data blocks. The sensor transmitter device includes a sensor interface for receiving payload data which represent a physical variable and a memory which is configured for storing position information which identifies at least one payload data block from the payload data field, which is reserved exclusively for the transmission of payload data from the sensor transmitter device to the bus control device.