Method, apparatus, and system for object tracking and navigation

Patent metadata

Field	Value
Publication number	US-2018183650-A1
Application number	US-201815873806-A
Country	US
Kind code	A1
Filing date	Jan 17, 2018
Priority date	Dec 5, 2012
Publication date	Jun 28, 2018
Grant date	—

Abstract

Method, apparatus and systems for object tracking are disclosed. In one example, a disclosed method includes obtaining at least one time series of channel information (CI) of a wireless multipath channel using: a processor, a memory communicatively coupled with the processor and a set of instructions stored in the memory. The at least one time series of channel information is extracted from a wireless signal transmitted between a Type 1 heterogeneous wireless device at a first position in a venue and a Type 2 heterogeneous wireless device at a second position in the venue through the wireless multipath channel. The wireless multipath channel is impacted by a current movement of an object in the venue. The method also includes determining a spatial-temporal information of the object based on at least one of: the at least one time series of channel information, a time parameter associated with the current movement, and a past spatial-temporal information of the object. The at least one time series of channel information is preprocessed. Associated computation may be shared among the processor, the Type 1 heterogeneous wireless device and the Type 2 heterogeneous wireless device.

First claim

We claim:

1 . A method performed by a system, comprising:
obtaining at least one time series of channel information (CI) of a wireless multipath channel using: a processor, a memory communicatively coupled with the processor and a set of instructions stored in the memory,
wherein the at least one time series of channel information is extracted from a wireless signal transmitted between a Type 1 heterogeneous wireless device at a first position in a venue and a Type 2 heterogeneous wireless device at a second position in the venue through the wireless multipath channel,
wherein the wireless multipath channel is impacted by a current movement of an object in the venue; and
determining a spatial-temporal information of the object based on at least one of: the at least one time series of channel information, a time parameter associated with the current movement, and a past spatial-temporal information of the object,
wherein the at least one time series of channel information is preprocessed,
wherein the spatial-temporal information is related to the current movement of the object and comprises at least one of: a location, a horizontal location, a vertical location, a length, an area, a volume, a capacity, a distance, a direction, a displacement, a speed, a velocity, an acceleration, a rotational speed, a rotational acceleration, a gait cycle, a motion type, a motion classification, a motion characteristics, a sudden motion, a transient motion, a periodic motion, a period of the periodic motion, a frequency of the periodic motion, a transient motion, a time trend, a time stamp, a time period, a time window, a sliding time window, a history, a frequency trend, a spatial-temporal trend, a spatial-temporal change, and an event,
wherein computational workload associated with the method is shared among the processor, the Type 1 heterogeneous wireless device and the Type 2 heterogeneous wireless device, and
performing a task based on the spatial-temporal information,
wherein the task comprises at least one of: locationing of the object, tracking the object, navigation for the object, obstacle avoidance for the object, tracking activity of the object, tracking behavior of the object, object identification, user identification, detecting motion of the object, detecting a vital sign of the object, detecting a periodic motion associated with the object, detecting breathing of the object, detecting an event associated with the current movement of the object, detecting a fall-down of the object, presenting the spatial-temporal information, and graphical display of the spatial-temporal information.

2 . The method of claim 1 , further comprising:
determining a distance of the current movement of the object based on the at least one time series of channel information; and obtaining an estimated direction of the current movement of the object, wherein the spatial-temporal information of the object is determined based on at least one of: the distance and the estimated direction of the current movement of the object.

3 . The method of claim 1 , further comprising:
computing at least one similarity score each based on a pair of temporally adjacent CI of the time series of CI associated with the current movement of the object; computing a characteristic similarity score based on the at least one similarity score; and determining a distance of the current movement of the object based on comparing the characteristic similar score to a reference decay curve, wherein the spatial-temporal information of the object is determined based on the distance of the current movement of the object.

4 . The method of claim 1 , further comprising:
determining at least one most recent CI each being most recent in one of the at least one time series of CI; computing at least one time series of similarity scores, each similarity score being computed based on two CI of a particular time series associated with the similarity score: the most recent CI, and a temporally adjacent CI within a time window associated with the current movement of the object; determining at least one curve, each based on a time series of similar scores; and identifying at least one feature point each associated with a curve, wherein the spatial-temporal information of the object is determined based on the at least one feature point,
wherein the at least one feature point comprises at least one of: a local maximum, a local minimum, a first maximum, a second maximum, another maximum, a first minimum, a second minimum, another minimum, a zero-crossing, a first zero-crossing, a second zero-crossing, another zero-crossing, a point having a pre-determined relationship with a second feature point, and another feature point.

5 . The method of claim 1 , further comprising:
computing at least one second similarity score each based on an initial CI and a current CI,
wherein the initial CI is temporally close to a beginning of the current movement,
wherein the current CI is temporally close to an end of the current movement;
determining a characteristic second similarity score based on the at least one second similar score; and determining the object to be stationary and the current movement to be a null movement if the characteristic second similarity score is greater than a threshold.

6 . The method of claim 1 , further comprising:
preprocessing the at least one time series of channel information, which comprises at least one of: doing nothing, de-noising, smoothing, conditioning, enhancement, restoration, feature extraction, weighted averaging, low-pass filtering, bandpass filtering, high-pass filtering, median filtering, ranked filtering, quartile filtering, percentile filtering, mode filtering, linear filtering, nonlinear filtering, finite impulse response (FIR) filtering, infinite impulse response (IIR) filtering, moving average (MA) filtering, auto-regressive (AR) filtering, auto-regressive moving average (ARMA) filtering, thresholding, soft thresholding, hard thresholding, soft clipping, local maximization, local minimization, optimization of a cost function, neural network, machine learning, supervised learning, unsupervised learning, semi-supervised learning, transform, Fourier transform, Laplace, Hadamard transform, transformation, decomposition, selective filtering, adaptive filtering, derivative, first order derivative, second order derivative, higher order derivative, integration, zero crossing, indicator function, absolute conversion, convolution, multiplication, division, another transform, another processing, another filter, a third function, and another preprocessing; and computing a similarity score based on a pair of temporally adjacent CI of a particular time series of CI,
wherein the similarity score is at least one of: a time reversal resonating strength (TRRS), a correlation, a cross-correlation, an auto-correlation, a covariance, a cross-covariance, an auto-covariance, an inner product of two vectors, a distance score, a discriminating score, a metric, a neural network output, a deep learning network output, and another score, and
wherein the channel information is associated with at least one of:
signal strength, signal amplitude, signal phase,
attenuation of the wireless signal through the wireless multipath channel,
received signal strength indicator (RSSI),
channel state information (CSI),
an equalizer information,
a channel impulse response,
a frequency domain transfer function,
information associated with at least one of: a frequency band, a frequency signature, a frequency phase, a frequency amplitude, a frequency trend, a frequency characteristics, a frequency-like characteristics, an orthogonal decomposition characteristics, and a non-orthogonal decomposition characteristics,
informat

Assignees

• Origin Wireless Inc

Inventors

• Zhang Feng
• Lai Hung-Quoc Duc
• Chen Chun-I
• Wong Chau-Wai
• Wang Beibei
• Chen Chen
• Au Oscar Chi-Lim
• Han Yi
• Liu K J Ray

Classifications

• H04W72/21

  in the uplink direction of a wireless link, i.e. towards the network · CPC title

• G01S13/00

  Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified · CPC title

• G01S2013/462

  using multipath signals · CPC title

• G01S13/46

  Indirect determination of position data · CPC title

• H04L27/362 Primary

  Modulation using more than one carrier, e.g. with quadrature carriers, separately amplitude modulated (H04L27/366 takes precedence) · CPC title