Proposed is a noise avoiding method for a space monitoring apparatus using a sound signal and, more specifically, is a technology that allows the space monitoring apparatus, which uses a sound signal to monitor a spatial condition, to avoid noise in a space to be monitored to correctly determine the spatial condition.

Systems and methods for data and confidentiality preservation for feature identification by robotic devices are disclosed herein. According to at least one non-limiting exemplary embodiment, a method for determining if an image depicts a human is disclosed. The determination may be utilized to either (i) censor the face of the human, or (ii) identify features within the image. The determination enhances feature identification by ensuring only uncensored and unobscured images are provided to one or more models for the identification to preserve human confidentiality.

A system for monitoring animate presence, including one or more ultrasonic transducers configured to transmit an ultrasonic signal, one or more ultrasonic receivers configured to receive an echo signal in response to the transmitted ultrasonic signal, an electronic circuit for comparing the transmitted signal to the received echo signal and identify a phase shift between the signals; wherein the electronic circuit identifies animate presence based on the identified phase shift.

A living object detection system may detect the interaction between an observer and a target object. The system may include an object sensor device, an object classification data unit, and an object detection module. The object sensor device may be attachable to the observer and include an ultrasonic sensor for sensing distance and a passive infrared sensor for sensing temperature. The object classification data unit may store predetermined object classifiers that identifies an object as a living object or non-living object. The object detection module may determine the target object as a living object or a non-living object based on the object classifiers stored in the object classification data unit and on a physical feature set of the target object, where the physical feature set may include distance and temperature parameters.

Methods and devices for detecting movement of an object includes: receiving a plurality of output signal values from a sound wave receiver, each of the plurality of output signal values being representative of a distance between the object and the sound wave receiver; determining, based on the received plurality of output signal values, a difference value representative of a difference between a first output signal value and a second output signal value among the plurality of output signal values; determining whether the difference value is representative of motion of the object based on whether the difference value has a magnitude between a predetermined minimum threshold and a predetermined maximum threshold; and outputting a motion detection signal if the difference value is determined to have a magnitude between the predetermined minimum threshold and the predetermined maximum threshold.

A computer-implemented method for monitoring a condition of a person includes receiving, at a computerized device, at least one signal from a condition sensor and determining if a condition is an emergency condition of a user based on the at least one signal.

An electronic device includes a speaker configured to output an inaudible acoustic signal, one or more microphones configured to receive a first reflected wave signal, a memory storing one or more instructions, and one or more processors configured to execute the one or more instructions to obtain a signal change amount based on a correlation between a reference signal corresponding to the inaudible acoustic signal and the received first reflected wave signal, based on the signal change amount exceeding a first threshold value corresponding to a movement of an object, obtain object location information corresponding to a location of the object in a spatial structure based on the signal change amount, and based on the signal change amount exceeding a second threshold value corresponding to a change in the spatial structure, update a final parameter set corresponding to the inaudible acoustic signal by using a waveform optimization model.

Techniques enabling improved classification of touch or hover interactions of objects with a touch sensitive surface of a device are presented. A speaker of the device can emit an ultrasonic audio signal comprising a first frequency distribution. A microphone of the device can detect a reflected audio signal comprising a second frequency distribution. The audio signal can be reflected off of an object in proximity to the surface to produce the reflected audio signal. A classification component can determine movement status of the object, or classify the touch or hover interaction, in relation to the surface, based on analysis of the signals. The classification component also can classify the touch or hover interaction based on such ultrasound data and/or touch surface or other sensor data. The classification component can be trained, using machine learning, to perform classifications of touch or hover interactions of objects with the surface.

Various implementations include a personal sonar system sized to be worn on a body of a user. In some cases, the system includes: at least one acoustic transmitter for transmitting ultrasonic signals into an environment proximate the user; at least two acoustic receivers for receiving return ultrasonic signals from the environment proximate the user; a directional indication system for providing a directional output to the user; and a controller coupled with the at least one transmitter, the at least two acoustic receivers, and the directional indication system, the controller configured to: identify a physical object within the environment proximate the user based on the return ultrasonic signals; and initiate the directional output at the directional indication system based on the identified physical object within the environment.

Techniques enabling improved classification of touch or hover interactions of objects with a touch sensitive surface of a device are presented. A speaker of the device can emit an ultrasonic audio signal comprising a first frequency distribution. A microphone of the device can detect a reflected audio signal comprising a second frequency distribution. The audio signal can be reflected off of an object in proximity to the surface to produce the reflected audio signal. A classification component can determine movement status of the object, or classify the touch or hover interaction, in relation to the surface, based on analysis of the signals. The classification component also can classify the touch or hover interaction based on such ultrasound data and/or touch surface or other sensor data. The classification component can be trained, using machine learning, to perform classifications of touch or hover interactions of objects with the surface.