Method, apparatus, and system for wireless human and non-human motion detection

A method for wireless human-nonhuman motion detection, comprising:

• transmitting a wireless signal through a wireless multipath channel of a venue;
• receiving the wireless signal through the wireless multipath channel of the venue, wherein the received wireless signal differs from the transmitted wireless signal due to the wireless multipath channel that is impacted by a motion of an object in the venue;
• obtaining a time series of channel information (TSCI) of the wireless multipath channel based on the received wireless signal;
• computing an autocorrelation function (ACF) of the channel information (CI) of the TSCI;
• computing multiple same-ACF features of the ACF or of a function of the ACF;
• computing an ACF statistics comprising an aggregate of a set of same-ACF features, the set of same-ACF features being at least one of:
• a first set of same-ACF features comprising a local maximum (Local-Max) value of the ACF and at least one additional Local-Max value of the ACF,
• a second set of same-ACF features comprising a local minimum (Local-Min) value of the ACF and at least one additional Local-Min value of the ACF,
• a third set of same-ACF features comprising an inter-Local-Max distance of the ACF and at least one additional inter-Local-Max distance of the ACF, each inter-Local-Max distance being a temporal interval between a pair of adjacent Local-Max values of the ACF, or
• a fourth set of same-ACF features comprising an inter-Local-Min distance of the ACF and at least one additional inter-Local-Min distance of the ACF, each inter-Local-Min distance being a temporal interval between a pair of adjacent Local-Min values of the ACF,
• wherein each aggregate comprises at least one of:
• weighted mean, weighted sum, weighted product, percentile, median, mode, maximum, minimum, variance, or standard deviation;
• computing a motion statistics based on the ACF evaluated at a particular time lag or a value of the function of the ACF evaluated at the particular time lag;
• computing a speed statistics associated with a speed of the motion of the object based on a speed quantity computed based on one of the following same-ACF features:
• a Local-Max value of the ACF, a Local-Max value of the function of the ACF, a Local-Min value of the ACF, or a Local-Min value of the function of the ACF;
• computing a gait statistics associated with a gait motion of the object based on a metric of a periodic behavior of the speed quantity;
• detecting the motion of the object based on the motion statistics;
• and
• in response to a determination that the motion is detected:
• determining multiple candidate object classes for the object, wherein the multiple candidate object classes include:
• a human, an adult, a child, a baby, a non-human, a pet, a robot, a machine, a fan, more than one human, and more than one non-human,
• determining a plurality of pairings of candidate object classes from the multiple candidate object classes,
• performing each of a plurality of pairwise detections for a respective pairing of the candidate object classes,
• computing a plurality of pairwise detection scores based on the ACF statistics, the motion statistics, the speed statistics, and the gait statistics, each pairwise detection score being computed for a respective pairwise detection between a respective first candidate object class and a respective second candidate object class, and
• classifying the object associated with the detected motion to be one of the multiple candidate object classes based on the plurality of pairwise detection scores.

An apparatus for wireless human-nonhuman motion detection, comprising:

• a receiver configured to receive a wireless signal transmitted by a transmitter through a wireless multipath channel in a venue, wherein the received wireless signal differs from the transmitted wireless signal due to the wireless multipath channel that is impacted by a motion of an object in the venue;
• a memory having a set of instructions stored therein;
• and
• a processor communicatively coupled to the memory and the receiver, and configured to:
• obtain a time series of channel information (TSCI) of the wireless multipath channel based on the received wireless signal,
• compute an autocorrelation function (ACF) of the channel information (CI) of the TSCI,
• compute multiple same-ACF features of the ACF or of a function of the ACF,
• compute an ACF statistics comprising an aggregate of a set of same-ACF features, the set of same-ACF features being at least one of:
• a first set of same-ACF features comprising a local maximum (Local-Max) value of the ACF and at least one additional Local-Max value of the ACF,
• a second set of same-ACF features comprising a local minimum (Local-Min) value of the ACF and at least one additional Local-Min value of the ACF,
• a third set of same-ACF features comprising an inter-Local-Max distance of the ACF and at least one additional inter-Local-Max distance of the ACF, each inter-Local-Max distance being a temporal interval between a pair of adjacent Local-Max values of the ACF, or
• a fourth set of same-ACF features comprising an inter-Local-Min distance of the ACF and at least one additional inter-Local-Min distance of the ACF, each inter-Local-Min distance being a temporal interval between a pair of adjacent Local-Min values of the ACF,
• wherein each aggregate comprises at least one of:
• weighted mean, weighted sum, weighted product, percentile, median, mode, maximum, minimum, variance, or standard deviation,
• compute a motion statistics based on the ACF evaluated at a particular time lag or a value of the function of the ACF evaluated at the particular time lag,
• compute a speed statistics associated with a speed of the motion of the object based on a speed quantity computed based on one of the following same-ACF features:
• a Local-Max value of the ACF, a Local-Max value of the function of the ACF, a Local-Min value of the ACF, or a Local-Min value of the function of the ACF,
• compute a gait statistics associated with a gait motion of the object based on a metric of a periodic behavior of the speed quantity,
• detect the motion of the object based on the motion statistics, and
• in response to a determination that the motion is detected:
• determine multiple candidate object classes for the object, wherein the multiple candidate object classes include:
• a human, an adult, a child, a baby, a non-human, a pet, a robot, a machine, a fan, more than one human, and more than one non-human,
• determine a plurality of pairings of candidate object classes from the multiple candidate object classes,
• perform each of a plurality of pairwise detections for a respective pairing of the candidate object classes,
• compute a plurality of pairwise detection scores based on the ACF statistics, the motion statistics, the speed statistics, and the gait statistics, each pairwise detection score being computed for a respective pairwise detection between a respective first candidate object class and a respective second candidate object class, and
• classify the object associated with the detected motion to be one of the multiple candidate object classes based on the plurality of pairwise detection scores.