Motion analysis apparatus, motion analysis method, and computer program product

Patent metadata

Field	Value
Publication number	US-11030564-B2
Application number	US-201715659948-A
Country	US
Kind code	B2
Filing date	Jul 26, 2017
Priority date	Jan 5, 2017
Publication date	Jun 8, 2021
Grant date	Jun 8, 2021

Abstract

According to an embodiment, a motion analysis apparatus includes a memory and processing circuitry. The processing circuitry detects a corresponding segment using first time-series data based on output of a first sensor configured to measure movement of a first object and second time-series data based on output of a second sensor configured to measure movement of a second object, the corresponding segment being a segment in which the first time-series data and the second time-series data are similar in their waveform patterns or co-occur. The processing circuitry associates information specifying the detected corresponding segment with at least one of information specifying the first object or information specifying the second object.

First claim

What is claimed is:

1. A motion analysis apparatus comprising:
a memory; and
processing circuitry configured to:
extract, as a motion segment in which there is presumably a movement,
a segment in which a statistical quantity is equal to or greater than a first threshold, the statistical quantity being obtained using an analysis window of a predetermined time length for a waveform of a high frequency band of a first waveform pattern representing first time-series data based on output of a first sensor configured to measure movement of a first object or a second waveform pattern representing second time-series data based on output of a second sensor configured to measure movement of a second object,
a segment in which a variation is equal to or greater than a second threshold, the variation being obtained using an analysis window of a predetermined time length for a waveform of a low frequency band of the first waveform or the second waveform, and
a segment in which the variation falls below the second threshold and subsequently becomes equal to or greater than the second threshold and that has a segment length equal to or smaller than a third threshold;

detect, by using the extracted motion segment, a corresponding segment being a segment in which the first time-series data based on output of a first sensor configured to measure movement of a first object and second time-series data based on output of a second sensor configured to measure movement of a second object, the corresponding segment being a segment in which the first time-series data and the second time-series data are similar in their waveform patterns or cooccur; and
associate information specifying the detected corresponding segment with at least one of information specifying the first object or information specifying the second object.

2. The apparatus according to claim 1 , wherein the processing circuitry detects, as the corresponding segment, a segment in which the first waveform pattern representing the first time-series data and the second waveform pattern representing the second time-series data matches, or a segment in which similarity between the first waveform pattern and the second waveform pattern is equal to or greater than a reference value, and
the processing circuitry further associates the information specifying the detected corresponding segment with the similarity between the first waveform pattern and the second waveform pattern in the corresponding segment.

3. The apparatus according to claim 1 , wherein the first sensor and the second sensor are at least one of an acceleration sensor configured to measure vibration, a gyro sensor configured to measure rotational movement, and a geomagnetic sensor configured to detect geomagnetism.

4. The apparatus according to claim 1 , wherein the first object is a person and the second object is an object used by the person.

5. The apparatus according to claim 1 , wherein
the processing circuitry detects, from the second time-series data, the corresponding segment that is similar to or cooccurs with any one of a plurality of pieces of the first time-series data corresponding to a plurality of first objects, and
the processing circuitry associates information specifying the detected corresponding segment with information specifying the first object corresponding to the first time-series data that is similar to or cooccurs with the second time-series data.

6. The apparatus according to claim 1 , wherein the processing circuitry is further configured to classify similarity between the first waveform pattern representing the first time-series data and the second waveform pattern representing the second time-series data in the corresponding segment, or a feature calculated from the first time-series data or the second time-series data in the corresponding segment, into a designated number of clusters, and associate the information specifying the detected corresponding segment with a result of classification.

Assignees

• Toshiba Kk

Inventors

• Fuke Sawa
• Imoto Kazunori

Classifications

• G06N20/00

  Machine learning · CPC title

• G06F3/011 Primary

  Arrangements for interaction with the human body, e.g. for user immersion in virtual reality (blind teaching G09B21/00) · CPC title

• G06Q10/0639 Primary

  Performance analysis of employees; Performance analysis of enterprise or organisation operations · CPC title

• G06F2203/011

  Emotion or mood input determined on the basis of sensed human body parameters such as pulse, heart rate or beat, temperature of skin, facial expressions, iris, voice pitch, brain activity patterns · CPC title