Ultrasonic Action Estimation via Inaudible Sound Segmentation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing action estimation techniques that rely on audible sounds are susceptible to noise from various everyday sounds, making it difficult to accurately estimate user actions.

Innovation Solution

An action estimation device that collects and processes inaudible sound information in the ultrasonic band, using a trained model to estimate user actions based on the sound information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If audible sounds are used for action estimation, then the technique can detect a wide range of everyday sounds, but the estimation accuracy deteriorates due to noise from various sounds

Engineering Contradiction:

Improvedetection range of soundsVSAvoidaction estimation accuracy

Core Design Contradiction:

Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The patent segments the sound spectrum into different frequency bands, specifically utilizing ultrasonic bands (above 20kHz) that are inaudible to humans. By focusing on this specific segment of the sound spectrum, the system achieves both wide detection capability and high estimation accuracy, as ultrasonic sounds produce less interference from common environmental noises.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent transitions from using audible sound frequencies to ultrasonic frequencies, effectively moving to another dimension of the sound spectrum. This dimensional change allows the system to detect actions through a different physical parameter (frequency range) that is less susceptible to noise from everyday sounds while maintaining comprehensive detection capability.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

2Device complexity

If only audible sounds are collected, then the system is simpler to implement, but actions that only produce inaudible sounds cannot be detected

Engineering Contradiction:

Improvesystem implementation complexityVSAvoidvariety of detectable actions

Core Design Contradiction:

Device complexityVSAdaptability or versatility

Solution Approach 1:

The patent implements a universal sound collection system that captures both audible and inaudible (ultrasonic) sounds using the same ultrasonic microphone array. This multi-functional approach allows the system to detect a broader variety of actions including those that only produce inaudible sounds, while maintaining relatively simple implementation through a unified detection mechanism.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS20250029630A1Action estimation device, action estimation method, and recording medium

Publication Date: 2025.01.23 PANASONIC INTELLECTUAL PROPERTY CORP OF AMERICA

AI summary

An action estimation device includes: an obtainer that obtains sound information pertaining to an inaudible sound, the inaudible sound being a sound in an ultrasonic band collected by a sound collector; and an estimator that estimates an output result, obtained by inputting the sound information obtained by the obtainer into a trained model indicating a relationship between the sound information and action information pertaining to an action of a person, as the action information of the person.