State recognizing device, state recognizing method, and recording medium

• US 10,001,557 B2
• Filed: 10/22/2013
• Issued: 06/19/2018
• Est. Priority Date: 03/13/2013
• Status: Active Grant

• Current Assignee: OKI Electric Industry Company Limited
• Original Assignee: OKI Electric Industry Company Limited
• Inventors: Okuya, Daisuku, Maeno, Kurato, Matsui, Michiyo
• Primary Examiner(s): Bythrow, Peter M
• Application Number:
  US14/773,709
• Publication Number:
  US 20160025847A1
• Time in Patent Office: 1,701 Days
• Field of Search: 342 28
• CPC Class Codes: A61B 5/0205 Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
• CPC Class Codes: A61B 8/00 Diagnosis using ultrasonic, sonic or infrasonic waves imaging of objects using sonar G01S15/00
• CPC Class Codes: G01S 13/50 Systems of measurement based on relative movement of target
• CPC Class Codes: G01S 13/52 Discriminating between fixed and moving objects or between objects moving at different speeds
• CPC Class Codes: G01S 13/5244 Adaptive clutter cancellation specially adapted for airborne MTI, G01S13/5242
• CPC Class Codes: G01S 13/526 performing filtering on the whole spectrum without loss of range information, e.g. using delay line cancellers or comb filters G01S13/5244 takes precedence
• CPC Class Codes: G01S 13/53 performing filtering on a single spectral line and associated with one or more range gates with a phase detector or a frequency mixer to extract the Doppler information, e.g. pulse Doppler radar G01S13/5244 takes precedence
• CPC Class Codes: G01S 13/58 Velocity or trajectory determination systems; Sense-of-movement determination systems
• CPC Class Codes: G01S 7/292 Extracting wanted echo-signals
• CPC Class Codes: G01S 7/415 Identification of targets based on measurements of movement associated with the target
• CPC Class Codes: G01V 3/12 operating with electromagnetic waves operating with millimetre waves G01V8/005

Abstract

Provided is a state recognizing device including: a first filter unit performing a filtering process on a time-series signal obtained by performing remote measuring on a space, in accordance with a first cutoff frequency to allow a signal component deriving from movement of a biological organism to pass through; a second filter unit performing a filtering process on the time-series signal in accordance with a second cutoff frequency to allow a signal component based on biological information to pass through; an amplitude-component extracting unit extracting a first feature quantity related to an amplitude component from a signal passed through the first and/or second filter units; a frequency-component extracting unit extracting a second feature quantity related to a frequency component from a signal passed through the first and/or second filter units; and a recognizing unit recognizing a state of the space by using the first and second feature quantities.

Claims

1. A state recognizing device for recognizing a plurality of states of a space, comprising:

a first filter unit that performs a filtering process on a time-series signal, which is obtained as a result of performing remote measuring on the space, in accordance with a first cutoff frequency so as to allow a signal component deriving from movement of a biological organism to pass through;

a second filter unit that performs a filtering process on the time-series signal in accordance with a second cutoff frequency, which is lower than the first cutoff frequency, so as to allow a signal component based on biological information of the biological organism to pass through;

an amplitude-component extracting unit that extracts a first feature quantity related to an amplitude component from a signal passed through the first filter unit and the second filter unit;

a frequency-component extracting unit that extracts a second feature quantity related to a frequency component from a signal passed through the first filter unit and the second filter unit;

a model storage unit that collects an aggregate of feature quantity-state data, each piece of the feature quantity-state data including amplitude information corresponding to an output of the amplitude-component extracting unit, frequency information corresponding to an output of the frequency-component extracting unit, and one of the plurality of the sates for the amplitude information and the frequency information; and

a recognizing unit that recognizes a state of the space by using the first feature quantity, the second feature quantity, and the aggregate of feature quantity-state data.

2. The state recognizing device according to claim 1,

wherein the frequency-component extracting unit performs frequency conversion on the signal passed through the first filter unit and the second filter unit and sets a sum of spectrum intensity after the frequency conversion as the second feature quantity.

3. The state recognizing device according to claim 1,

wherein the frequency-component extracting unit applies a band-pass filter to the signal passed through the first filter unit and the second filter unit and sets a signal value after applying the band-pass filter as the second feature quantity.

4. The state recognizing device according to claim 1,

wherein the frequency-component extracting unit sets the total number of times the signal passed through the first filter unit and the second filter unit crosses over a zero point as the second feature quantity.

5. The state recognizing device according to claim 1,

wherein the amplitude-component extracting unit calculates an instantaneous amplitude of the signal passed through the first filter unit and the second filter unit and sets a representative value equivalent to a time window of the instantaneous amplitude as the first feature quantity.

6. The state recognizing device according to claim 5,

wherein the representative value is at least one of an average value, a median value, a mode value, variance, standard deviation, a maximum value, a minimum value, and spectrum intensity after performing frequency conversion on the signal passed through the first filter unit and the second filter unit.

7. The state recognizing device according to claim 1,

wherein the plurality of states include at least one of an absent state, a present state, a resting state, and an active state.

8. The state recognizing device according to claim 1, further comprising:

a detecting unit that performs remote measuring of the space and outputs the time-series signal.

9. The state recognizing device according to claim 8, further comprising:

a preprocessing unit that performs predetermined signal processing before the time-series signal output from the detecting unit is passed through the first filter unit and the second filter unit.

10. The state recognizing device according to claim 9,

wherein the preprocessing unit performs offset adjustment on the time-series signal.

11. A state recognizing method for recognizing a plurality of states of a space, comprising:

a first filtering step for performing a filtering process on a time-series signal, which is obtained as a result of performing remote measuring on the space, in accordance with a first cutoff frequency so as to allow a signal component deriving from movement of a biological organism to pass through;

a second filtering step for performing a filtering process on the time-series signal in accordance with a second cutoff frequency, which is lower than the first cutoff frequency, based on biological information of the biological organism;

an amplitude-component extracting step for extracting a first feature quantity related to an amplitude component from a signal passed in the first filtering step and the second filtering step;

a frequency-component extracting step for extracting a second feature quantity related to a frequency component from a signal passed in the first filtering step and the second filtering step;

a model storing step for collecting an aggregate of feature quantity-state data, each piece of the feature quantity-state data including amplitude information corresponding to an output of the amplitude-component extracting unit, frequency information corresponding to an output of the frequency-component extracting unit, and one of the plurality of the sates for the amplitude information and the frequency information; and

a state recognizing step for recognizing a state of the space by using the first feature quantity, the second feature quantity, and the aggregate of feature quantity-state data.

12. A non-transitory recording medium having a computer program stored therein for recognizing a plurality of states of a space, the computer program causing a computer to execute:

a first filtering step for performing a filtering process on a time-series signal, which is obtained as a result of performing remote measuring on the space, in accordance with a first cutoff frequency so as to allow a signal component deriving from movement of a biological organism to pass through;

a second filtering step for performing a filtering process on the time-series signal in accordance with a second cutoff frequency, which is lower than the first cutoff frequency, based on biological information of the biological organism;

an amplitude-component extracting step for extracting a first feature quantity related to an amplitude component from a signal passed in the first filtering step and the second filtering step;

a frequency-component extracting step for extracting a second feature quantity related to a frequency component from a signal passed in the first filtering step and the second filtering step;

a model storing step for collecting an aggregate of feature quantity-state data, each piece of the feature quantity-state data including amplitude information corresponding to an output of the amplitude-component extracting unit, frequency information corresponding to an output of the frequency-component extracting unit, and one of the plurality of the sates for the amplitude information and the frequency information; and

a state recognizing step for recognizing a state of the space by using the first feature quantity, the second feature quantity, and the aggregate of feature quantity-state data.