Method, apparatus, and system for wireless gait recognition

Patent metadata

Field	Value
Publication number	US-11928894-B2
Application number	US-202016790610-A
Country	US
Kind code	B2
Filing date	Feb 13, 2020
Priority date	Sep 18, 2012
Publication date	Mar 12, 2024
Grant date	Mar 12, 2024

Abstract

Methods, apparatus and systems for wireless gait recognition and rhythmic motion monitoring are described. In one example, a described system comprises: a transmitter, a receiver, and a processor. The transmitter is configured for transmitting a first wireless signal towards an object in a venue through a wireless multipath channel of the venue. The receiver is configured for: receiving a second wireless signal through the wireless multipath channel between the transmitter and the receiver. The second wireless signal differs from the first wireless signal due to the wireless multipath channel which is impacted by a rhythmic motion of the object. The processor is configured for: obtaining a time series of channel information (CI) of the wireless multipath channel based on the second wireless signal, monitoring the rhythmic motion of the object based on the time series of CI (TSCI), and triggering a response action based on a result of the monitoring.

First claim

We claim:

1. A system for rhythmic motion monitoring, comprising:
a transmitter configured for transmitting a first wireless signal in a venue through a wireless multipath channel of the venue;
a receiver configured for receiving a second wireless signal through the wireless multipath channel, wherein
the second wireless signal differs from the first wireless signal due to the wireless multipath channel which is impacted by a rhythmic motion of an object in the venue,
the rhythmic motion comprises a gait of the object,
the object is not in line-of-sight of the transmitter,
the object is not in line-of-sight of the receiver,
the first wireless signal and the second wireless signal are WiFi signals compliant to a data communication standard comprising one of: IEEE 802.11, IEEE802.11n/ac/ax/be, or WiFi; and

a processor configured for:
obtaining a time series of channel information (CI) of the wireless multipath channel based on the second wireless signal, wherein each CI is one of: channel state information (CSI), channel frequency response (CFR), or channel impulse response (CIR),
computing a characteristic of the time series of CI (TSCI),
computing a time series of intermediate quantity (IQ) based on the characteristic of the TSCI, wherein the IQ comprises a moving speed of the object, wherein the moving speed is a gait speed of the object and is computed based on a similarity score of a respective pair of temporally adjacent CI of the TSCI,
determining a time window and a plurality of sliding sub-windows in the time window,
computing a plurality of autocorrelation functions (ACF's) of the moving speed, wherein each ACF is computed for a respective sliding sub-window in the time window,
performing peak detection on each ACF of the moving speed,
detecting the time window as a stable period based on detected peaks of the plurality of ACF's in the time window,
monitoring the rhythmic motion of the object based on analyzing the time series of IQ in the stable period to obtain gait related features, and
identifying the object based on the gait related features.

2. The system of claim 1 , wherein the rhythmic motion further comprises at least one of:
a walking motion, a marching motion, a pacing motion, a running motion, a galloping action, a trotting action, a body motion, a leg motion, a hand motion, a finger motion, a trunk motion, a torso motion, a head motion,
a repeated motion, a complex repeated motion, a robotic motion, a mechanic motion, a wind-induced motion, a curtain motion, a current-induced motion, a fluid motion, a vibration, an earthquake, a tremor, a shaking motion, a quivering motion, a trembling motion,
a musical motion, a dancing motion, an oscillation, a regular motion, a periodic motion, a breathing motion, a heart beat, a palpitating motion, a relaxation oscillation, an increasing motion, a decreasing motion, an expanding motion, a contracting motion, a pulsating motion, a pumping motion, a pounding motion, a thudding motion, a throbbing motion, a hammering motion,
an alternating motion, a coordinated motion, a combination of multiple repeated motion, a modulated motion, a mixed motion, a composite motion with at least one underlying rhythm, a motion coupled to another rhythmic motion of another object, or a motion coupled to a rhythm.

3. The system of claim 1 , wherein the IQ comprises at least one of:
a time stamp, a starting time, an ending time, a time code, a timing, a time period, a time duration, a frequency, a period, a cycle, a rhythm, a pace, a count, an indicator, an occurrence, a state, a set,
a distance, a displacement, a direction, an acceleration, an angular distance, an angular speed, an angular acceleration, a change of location, a change of direction, a change of speed, a change of acceleration, a proximity, a presence, an absence, an appearance, a disappearance, a location, a statistics, a motion statistics, a breathing statistics, a distance statistics, a speed statistics, an acceleration statistics, a metric, an l_k distance metric, an l_0 distance metric, an l_1 distance metric, an absolute distance metric, an l_2 distance metric, a Euclidean distance metric, an l_infinity distance metric, a path, a volume, a mass, a surface area, a shape, a posture, an energy,
a trend, a time sequence, a label, a tag, a class, a category, a time profile, a time quantity, a frequency quantity, a transient quantity, an incremental quantity, an instantaneous quantity, an averaged quantity, a locally averaged quantity, a filtered quantity, a quantity change, a repeating quantity,
an event, a recognized event, a recognized motion sequence, a gesture, a hand gesture, a finger gesture, a wrist gesture, an elbow gesture, an arm gesture, a shoulder gesture, a head gesture, a facial gesture, a neck gesture, a waist gesture, a leg gesture, a foot gesture,
a maximum, a minimum, a constrained maximum, a constrained minimum, a local maximum, a local minimum, a first local maximum, a first local minimum, a k-th local maximum, a k-th local minimum, an average, a weighted average, a percentile, a mean, a median, a mode, a trimmed mean, a conditional mean, a conditional statistics, an ordered statistics, a variance, a skewness, a kurtosis, a moment, a high order moment, a cumulant, a correlation, a covariance, a co-skewness, a co-kurtosis, a first order statistics, a second order statistics, a third order statistics, a high order statistics, a robust quantity, an argument associated with another quantity,
a feature of a CI, a complex component of a CI, a magnitude of the complex component, a phase of the complex component, a function of the complex component of the CI, a polynomial of the magnitude of the complex component, a square of the magnitude of the complex component, a time series of the feature of CI, an autocorrelation function of the feature of CI, and a function of another quantity.

4. The system of claim 1 , wherein the processor is further configured for:
identifying the time window as the stable period when the object has a stable rhythmic motion, wherein there are at least two stable cycles of TSCI in the time window;
determining a time stamp associated with the stable rhythmic motion; and
adding the time stamp to the time window when at least one of the following is satisfied:
a weighted average of the moving speed in a sliding window associated with the time stamp is greater than a first threshold,
a feature of an autocorrelation function of the moving speed around the time stamp is greater than a second threshold, and
another criterion associated with the time stamp.

5. The system of claim 4 , wherein the processor is further configured for:
computing at least one local characteristic of the IQ in the time window of the stable rhythmic motion, wherein the at least one local characteristic comprises at least one of: a local maximum, local minimum, zero crossing, local maximum of a derivation of the IQ, local minimum of the derivative, and zero crossing of the derivative;
segmenting the time window into at least one step segment based on time stamps associated with the at least one local characteristic of the IQ, each step segment spanning from a time associated with a local characteristic to another time associated with a next local characteristic; and
identifying at least one motion cycle, each motion cycle comprising N consecutive step segments, wherein N is a positive integer.

6. The system of claim 5 , wherein the processor is further configured for:
computing at least one motion feature based on at least one of: the IQ in the time window of the stable rhythmic motion, the at least one local characteristic of the IQ, the at least one step segment, and the at least one motion cycle.

7. The system of claim

Assignees

• Wu Chenshu
• Zhang Feng
• Wang Beibei
• Hu Yuqian
• Liu K J Ray
• Au Oscar Chi Lim
• Origin Wireless Inc

Inventors

• Wu Chenshu
• Zhang Feng
• Wang Beibei
• Hu Yuqian
• Liu K J Ray
• Au Oscar Chi-Lim

Classifications

• G06V40/25 Primary

  Recognition of walking or running movements, e.g. gait recognition · CPC title

• G06F21/32

  using biometric data, e.g. fingerprints, iris scans or voiceprints · CPC title

• G06V40/103

  Static body considered as a whole, e.g. static pedestrian or occupant recognition · CPC title

• H04W4/029 Primary

  Location-based management or tracking services · CPC title

• H04W4/027

  using movement velocity, acceleration information · CPC title