Method, apparatus, and system for fall-down detection based on a wireless signal

A wireless device of a wireless target motion detection system, comprising:

• a processor;
• a memory communicatively coupled to the processor;
• and
• a receiver communicatively coupled to the processor, wherein:
• an additional wireless device of the wireless target motion detection system is configured for transmitting a first wireless signal through a wireless multipath channel of a venue to the receiver,
• the receiver is configured for receiving a second wireless signal through the wireless multipath channel,
• the second wireless signal differs from the first wireless signal due to the wireless multipath channel that is impacted by a target motion of an object in the venue, and
• the processor is configured for:
• obtaining a time series of channel information (TSCI) of the wireless multipath channel based on the second wireless signal,
• computing a time series of spatial-temporal information (TSSTI) of the object based on the TSCI,
• computing, in an offline stage of the wireless target motion detection system, at least one representative STI template based on a set of training TSSTI, wherein:
• each training TSSTI is computed based on a respective training TSCI obtained based on a respective training wireless signal from a respective training wireless device received by a respective training wireless device in a respective training venue when a respective training object in the respective training venue undergoes a respective training target motion,
• the at least one representative STI template is computed based on cleaning each training TSSTI by segmenting the training TSSTI into:
• a respective initial non-target segment of spatial-temporal information (STI), a respective target segment of STI, and a respective trailing non-target segment of STI,
• computing the at least one representative STI template comprises computing an optimal TSSTI based on an optimization of a combined score with respect to the set of cleaned training TSSTI,
• the optimization comprises at least one of:
• maximization, minimization, constrained maximization, or constrained minimization,
• the combined score comprises an aggregation of at least one of:
• a plurality of first scores each being a first pairwise score between the TSSTI and a cleaned training TSSTI based on a pairwise mapping between the TSSTI and the cleaned training TSSTI,
• a plurality of second scores each being a second pairwise score between a time derivative of the TSSTI and a time derivative of a cleaned training TSSTI based on the pairwise mapping, or
• a plurality of third scores each being a third pairwise score between a signal processed TSSTI and a signal processed cleaned training TSSTI based on the pairwise mapping, and
• the aggregation comprises at least one of:
• sum, mean, or discriminative cost,
• the discriminative cost comprises a weighted difference between (a) a first normalized aggregation of a first pairwise mapping score between the TSSTI and each of a first subset of the cleaned training TSSTI, and (b) a second normalized aggregation of a second pairwise mapping score between the TSSTI and each of a second subset of the cleaned training TSSTI,
• any normalized aggregation comprises at least one of:
• mean or weighted mean, and
• detecting, in an online stage of the wireless target motion detection system, the target motion of the object based on at least one of:
• the TSSTI and the at least one representative STI template.

A method of a target motion detection system, comprising:

• transmitting, by a transmitter, a first wireless signal through a wireless multipath channel of a venue to a receiver;
• receiving, by the receiver in an online stage of the target motion detection system, 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 that is impacted by a target motion of an object in the venue;
• obtaining a time series of channel information (TSCI) of the wireless multipath channel based on the second wireless signal, using a processor, a memory communicatively coupled with the processor and a set of instructions stored in the memory;
• computing a time series of spatial-temporal information (TSSTI) of the object based on the TSCI;
• in an offline stage before the online stage, computing at least one representative STI template based on a set of training TSSTI, wherein:
• each training TSSTI is computed based on a respective training TSCI obtained based on a respective training wireless signal from a respective training transmitter received by a respective training receiver in a respective training venue when a respective training object in the respective training venue undergoes a respective training target motion,
• the at least one representative STI template is computed based on cleaning each training TSSTI by segmenting the training TSSTI into:
• a respective initial non-target segment of STI, a respective target segment of STI corresponding to the respective training target motion of the respective training object, and a respective trailing non-target segment of STI,
• computing the at least one representative STI template comprises computing an TSSTI based on an optimization of a combined score with respect to the set of cleaned training TSSTI,
• the optimization comprises at least one of:
• maximization, minimization, constrained maximization, or constrained minimization,
• the combined score comprises an aggregation of at least one of:
• a plurality of first scores each being a first pairwise score between the TSSTI and a cleaned training TSSTI based on a pairwise mapping between the TSSTI and the cleaned training TSSTI,
• a plurality of second scores each being a second pairwise score between a time derivative of the TSSTI and a time derivative of a cleaned training TSSTI based on the pairwise mapping, or
• a plurality of third scores each being a third pairwise score between a signal processed TSSTI and a signal processed cleaned training TSSTI based on the pairwise mapping,
• the aggregation comprises at least one of:
• sum, mean, or discriminative cost,
• the discriminative cost comprises a weighted difference between (a) a first normalized aggregation of a first pairwise mapping score between the TSSTI and each of a first subset of the cleaned training TSSTI, and (b) a second normalized aggregation of a second pairwise mapping score between the TSSTI and each of a second subset of the cleaned training TSSTI,
• any normalized aggregation comprises at least one of:
• mean or weighted mean;
• and
• detecting the target motion of the object based on the TSSTI and the at least one representative STI template.