A device comprises a processor coupled with an ultrasonic transducer coupled which is configured to emit an ultrasonic pulse and receive returned signals received after a ringdown period of the transducer and corresponding to the emitted ultrasonic pulse. The processor is configured to evaluate the returned signals to find a candidate echo, from an object located in a ringdown blind spot area, in a time window between one and two times the ringdown period; locate multiple echoes from the object of higher order than the candidate echo; validate the candidate echo as at least a secondary echo associated of the object; and determine, based on analysis of the returned signals, an estimated distance from the transducer to the object in the ringdown blind spot area, wherein the ringdown blind spot area is located between the transducer and a closest distance at which objects can be sensed by the transducer.

The present disclosure provides a system and method for removing noise from an ultrasonic signal using a generative adversarial network (GAN). The present disclosure provides three input formats for the neural network (NN) in order to feed one-dimensional (1D) input data to the network. The system is generalizable to multiple noise sources, as it learns from different motion functions and noise types. The end-to-end system of the present disclosure is trained on raw ultrasonic signals with very little pre-processing or feature extraction.

The present disclosure provides a system and method for removing noise from an ultrasonic signal using a generative adversarial network (GAN). The present disclosure provides three input formats for the neural network (NN) in order to feed one-dimensional (1D) input data to the network. The system is generalizable to multiple noise sources, as it learns from different motion functions and noise types. The end-to-end system of the present disclosure is trained on raw ultrasonic signals with very little pre-processing or feature extraction.

A method for providing an estimate of a time-of-flight between an ultrasonic signal emitted by a device and an ultrasonic echo signal returned by a target object hit by the ultrasonic signal and received at the device. The method includes acquiring the ultrasonic echo signal thereby obtaining an electric echo signal; determining a noise power of the electric echo signal; determining an envelope signal indicative of an envelope of the electric echo signal; determining a portion of the envelope signal based on at least one operative parameter, the at least one operative parameter being determined according to Particle Swarm Optimization; processing the portion of the envelope signal and the noise power of the echo ultrasonic signal according to an Unscented Kalman Filter to obtain an estimate of the envelope signal, wherein the estimate of the envelope signal is a regenerated version of the envelope signal being regenerated from the portion of the envelope signal, the processing being based on at least one Unscented Kalman Filter parameter determined according to the Particle Swarm Optimization, and providing the estimate of the time-of-flight according to the estimate of the envelope signal.

A device comprises a processor coupled with an ultrasonic transducer coupled which is configured to emit an ultrasonic pulse and receive returned signals received after a ringdown period of the transducer and corresponding to the emitted ultrasonic pulse. The processor is configured to evaluate the returned signals to find a candidate echo, from an object located in a ringdown blind spot area, in a time window between one and two times the ringdown period; locate multiple echoes from the object of higher order than the candidate echo; validate the candidate echo as at least a secondary echo associated of the object; and determine, based on analysis of the returned signals, an estimated distance from the transducer to the object in the ringdown blind spot area, wherein the ringdown blind spot area is located between the transducer and a closest distance at which objects can be sensed by the transducer.

A method of performing distance estimation between a first recording device at a first location and a second recording device at a second location includes: estimating acoustic relative transfer function (RTF) between the first recording device and the second recording device for a sound signal, e.g., by applying an improved proportionate normalized least mean square (IPNLMS) filter; and estimating the distance between the first recording device and the second recording device based on the RTF. The at least one acoustic feature extracted from the RTF estimated between the first recording device and the second recording device includes at least one of clarity index, direct-to-reverberant ratio (DRR), and reverberation time. A distributed-gradient-boosting algorithm with regression trees is used in combination with signal-to-reverberation ratio (SRR) and the at least one acoustic feature extracted from the RTF to estimate the distance between the first recording device and the second recording device.

An object detection apparatus is mounted to a moving body to which a plurality of distance measurement sensors are mounted, and detects an object that is present in a vicinity of the moving body. In response to direct waves and indirect waves being received, the object detection apparatus acquires a relative position of an object to a moving body based on principles of triangulation using distance measurement information based on the direct waves and distance measurement information based on the indirect waves. In response to the received waves being reflected waves from an object of which the relative position has been already acquired and only either of the direct waves and the indirect waves being received as received waves, the object detection apparatus estimates the relative position of the object to the moving body based on a reference position that is the relative position that has been already acquired.

Each of a plurality of tracking/proximity devices periodically transmits an acoustic message signal and an electronic/Bluetooth message signal and receives the same from the other devices. Each of the devices determines the proximity/separation/distance to/from/between the others by assuming that the receipt time of an electronic message signal equals its transmission time and that the receipt time of the corresponding acoustic message signal minus the receipt time of the electronic message signal equals the amount of time that the acoustic signal traveled from the transmission device to the receiving device. The receiving device converts the acoustic signal travel time into a distance by multiplying by the speed of sound. Thus, the receiving device determines the distance to the transmitting device and may alert a server, user, or wearer of the determined distance, or merely that the determined distance is less than a configurable predetermined amount.

A device comprises a processor coupled with an ultrasonic transducer coupled which is configured to emit an ultrasonic pulse and receive returned signals received after a ringdown period of the transducer and corresponding to the emitted ultrasonic pulse. The processor is configured to evaluate the returned signals to find a candidate echo, from an object located in a ringdown blind spot area, in a time window between one and two times the ringdown period; locate multiple echoes from the object of higher order than the candidate echo; validate the candidate echo as at least a secondary echo associated of the object; and determine, based on analysis of the returned signals, an estimated distance from the transducer to the object in the ringdown blind spot area, wherein the ringdown blind spot area is located between the transducer and a closest distance at which objects can be sensed by the transducer.

An object detection system includes an acoustic wave generator to generate an acoustic wave by generating heat upon energization and a processing circuit to perform object detection processing to detect an object in target space using an acoustic wave generated by the acoustic wave generator. The object detection processing includes setting processing, wave transmission processing, and determination processing. The setting processing sets a search range corresponding to a distance to the object in the target space. The wave transmission processing controls the acoustic wave generator to generate an acoustic wave at a target sound pressure associated with a search range set in the setting processing. The determination processing acquires, from a wave receiver to receive an acoustic wave from the target space, a received-wave signal representing an acoustic wave received by the wave receiver and determines whether the object is present based on the received-wave signal.