WO2018018757A1

WO2018018757A1 - Human body activity detection method and apparatus, and sensor

Info

Publication number: WO2018018757A1
Application number: PCT/CN2016/102146
Authority: WO
Inventors: 郝祁; 兰功金; 梁锦豪
Original assignee: 南方科技大学
Priority date: 2016-07-25
Filing date: 2016-10-14
Publication date: 2018-02-01
Also published as: CN106226821B; CN106226821A

Abstract

A human body activity detection method, comprising: encoding a ground space according to a preset matrix (S110), wherein a ground sensing device is laid in the ground space, the ground sensing device consists of at least two layers of ground sensors, each layer of sensor is provided with holes according to the codes, and the ground sensors at the holes send conduction signals when the holes are pressed; detecting output signals of the ground sensing device, and determining pressing positions in the ground space according to the output signals and the preset matrix (S120), wherein the output signals consist of conduction or non-conduction signals sent by each layer of ground sensor; and determining the activity of a human body according to the pressing positions (S130). A human body activity detection apparatus and a sensor.

Description

Human activity detection method, device and sensor

Technical field

Embodiments of the present disclosure relate to smart detection techniques, for example, to a human activity detection method, apparatus, and sensor.

Background technique

With the development of science and technology, the technology for detecting human activities is becoming more and more mature.

In the related art, the most commonly used method is to shoot a human body through a camera, and transmit the image after shooting to a computer for image processing to obtain an activity behavior of the human body.

However, the camera-based human body simple behavior activity detection method has the disadvantages of large data throughput, large computational complexity, high energy consumption, complicated equipment, and high price. Because the camera-based target recognition method involves a large amount of image information that needs to be transmitted to a computer in real time, a large network bandwidth is usually required. And this method involves the processing of real-time image processing, requires complex hardware support, and brings a huge amount of computation and huge energy consumption. At the same time, the method is complicated, the hardware is large, and needs to occupy a dedicated volume. It is not suitable for embedding into an existing device without changing the usage space.

Summary of the invention

The present disclosure provides a human body activity detecting method, device and sensor, which has low energy consumption for detecting human activity, small calculation amount, simple detection method, low detection equipment cost, and does not need to occupy a dedicated volume space.

In a first aspect, an embodiment of the present disclosure provides a human activity detecting method, including:

The ground space is encoded according to a preset matrix, wherein the ground space is provided with a ground sensing device, and the ground sensing device is composed of at least two layers of ground sensors, and each layer of the sensor has a hole according to the code. When the hole position is pressed, the ground sensor where the hole is located emits a conduction signal;

Detecting an output signal of the ground sensing device, and determining a pressing position in the ground space according to the output signal and the preset matrix, wherein the output signal is a conduction signal sent by each floor sensor or Non-conducting signal composition;

The activity of the human body is determined according to the pressed position.

Optionally, encoding the ground space according to the preset matrix includes:

Binding the ground space according to a preset LDPC sparse matrix;

Each of the layers of the sensor having holes according to the code includes:

The sensor of each layer performs puncturing according to the ground space corresponding to the code of 1 in the binary code.

Optionally, determining, according to the output signal and the preset matrix, the pressing position in the floor space includes:

Obtaining a vector y according to the output signal;

According to the formula

Obtaining a value of x, where H represents the preset matrix, x represents a pressed position in the ground space, a symbol

Is a binary XOR operator.

Optionally, determining the activity of the human body according to the pressing position comprises:

Determining a trajectory of human activity according to the pressed position; or

At least one of a fall, a standing, and a sitting posture of the human body is determined according to the pressed position.

Optionally, encoding the ground space according to the preset matrix includes:

The ground space is coded in four layers according to the preset matrix. Correspondingly, the ground sensing device is formed by stacking four layers of ground sensors, which are composed of conductive tin foil paper, wires and sponges.

In a second aspect, an embodiment of the present disclosure further provides a human activity detecting apparatus, including:

The coding module is configured to encode the ground space according to the preset matrix, wherein the ground space is provided with a ground sensing device, wherein the ground sensing device is composed of at least two layers of ground sensors, and each layer sensor is according to the The coded hole has a hole, and when the hole is pressed, the ground sensor where the hole is located emits a conduction signal;

a detecting module configured to detect an output signal of the ground sensing device;

Pressing a position determining module, configured to determine a pressing position in the floor space according to the output signal and the preset matrix, wherein the output signal is composed of a conduction signal or a non-conduction signal sent by each floor sensor ;as well as

The human activity determining module is configured to determine an activity of the human body according to the pressing position.

In a third aspect, the embodiment of the present disclosure further provides a human activity detecting sensor, which is used in the foregoing human activity detecting method, and may include:

a first conductive layer, a second conductive layer, and an insulating layer interposed between the first conductive layer and the second conductive layer, the first conductive layer, the second conductive layer and the insulating layer are bonded, the insulation A hole is formed in the layer, and the first conductive layer and the second conductive layer are adhered with a wire, wherein a position of the hole is determined according to the code.

In a fourth aspect, an embodiment of the present disclosure further provides a non-transitory computer storage medium, where The computer executable instructions are arranged to perform a human activity detection method.

The present disclosure encodes a ground space according to a preset matrix, wherein the ground space is provided with a ground sensing device, and the ground sensing device is composed of at least two layers of ground sensors, and each layer of the sensor is labeled according to the code. a hole, when the hole is pressed, the ground sensor on which the hole is located emits an on signal, detects an output signal of the ground sensing device, and determines the image according to the output signal and the preset matrix a pressing position in the ground space, wherein the output signal is composed of a conduction signal or a non-conduction signal emitted by each floor sensor, and determining the activity of the human body according to the pressing position, and solving the simple behavior of the camera based on the camera in the related art The activity detection method has the disadvantages of large data flux, large amount of calculation, high energy consumption, complicated equipment, and high price, which makes the detection of human activity low in energy consumption and small in calculation amount, and the detection method is simple and the detection equipment cost is low. There is no need to occupy a dedicated volume.

BRIEF abstract

1 is a flowchart of a human body activity detecting method according to Embodiment 1 of the present disclosure;

2 is a schematic diagram of spatial coding and corresponding ground sensor punching positions according to Embodiment 1 of the present disclosure;

3 is a flowchart of a human body activity detecting method according to Embodiment 2 of the present disclosure;

4 is a schematic diagram of spatial coding and corresponding ground sensor punching positions according to Embodiment 2 of the present disclosure;

FIG. 5 is a schematic diagram of a human activity track determined by a human activity detecting method according to Embodiment 2 of the present disclosure.

6 is a structural diagram of a human body activity detecting apparatus according to Embodiment 3 of the present disclosure;

7 is a structural diagram of a ground sensor according to Embodiment 4 of the present disclosure;

FIG. 8 is a schematic diagram of a hardware structure of an apparatus for performing a human body activity detecting method according to Embodiment 5 of the present disclosure.

detailed description

The present disclosure will be described in detail below with reference to the accompanying drawings and embodiments. It is understood that the specific embodiments described herein are merely illustrative of the disclosure and are not intended to be limiting. It is also to be noted that, for the convenience of description, only some but not all of the structures related to the present disclosure are shown in the drawings, and the features of the following embodiments and the embodiments may be arbitrarily combined without conflict.

Embodiment 1

1 is a flowchart of a human activity detecting method according to Embodiment 1 of the present disclosure. The present embodiment is applicable to a situation in which human activity is detected. The method may be performed by a computing device such as a smart terminal or a server, and the computing device and The ground sensing device is connected through a wired or wireless network. It can be known to those skilled in the art that the present embodiment is not limited to detecting human activity, and may also be detecting any object moving on the ground, and may include the following steps:

Step 110: Encode the ground space according to the preset matrix.

Wherein the ground space is provided with a ground sensing device, the ground sensing device is composed of at least two layers of ground sensors, and each layer of the sensor has a hole according to the code, when the hole position is pressed, The ground sensor on which the hole is located emits an on signal.

The floor space may be an indoor space for people's daily activities, such as a family home, an office building or a shopping mall, or an open-air outdoor space such as a stadium stand, a concert stand or a large open-air event. The ground space is provided with a ground sensing device, and the ground sensing device is composed of at least two layers of ground sensors, and the ground sensor functions to determine whether the layer is turned on, and if the layer is turned on, an on signal is issued. Illustratively, the ground sensor is composed of two conductive layers and an insulating layer. The insulating layer is sandwiched between the two conductive layers. Optionally, the two conductive layers are conductive tin foil, and the insulating layer is a sponge. . Wherein, the insulating layer of the ground sensor is perforated, and when the area near the hole is pressed, the two conductive layers are in contact with each other, and the conductive layer in the ground sensor is also pasted or embedded with a wire, when the two conductive layers are in contact with each other Due to the conductive characteristics of the conductive layer, the wires respectively pasted or embedded in the conductive layer are connected (short-circuited) to emit an on signal.

The punching position of the ground sensor insulating layer is determined by a preset matrix. Exemplarily, the ground space is divided into n rows and m columns according to the preset matrix to obtain n*m ground space units, and the number of codes of the preset matrix in each unit represents a ground sensor included in the ground sensing device. The number of layers, where the first code of each cell represents whether the first layer of ground sensor is punctured at that location, the second code represents whether the second layer of ground sensor is punctured at that location, and so on.

For ease of understanding, a relationship between a layer of spatial coding and the location of the hole of the ground sensor corresponding to the spatial encoding is given below. As shown in FIG. 2, FIG. 2 is a schematic diagram of spatial coding and corresponding ground sensor punching positions according to Embodiment 1 of the present disclosure. Assuming that the spatial code is [1000010110111100], the corresponding ground space is divided into 4 rows and 4 columns and a total of 16 ground space units, wherein the value of each bit in the spatial coding sequentially represents whether the ground space unit is punched. Exemplarily, the ground space unit corresponding to the code 1 needs to be punched, that is, the corresponding position in the ground sensor of the layer is punched, and the code is 0. The corresponding ground space unit is not processed. In this way, each layer of ground sensor is punched accordingly.

It can be seen from the structure of the ground sensor that if the punched area is pressed, the ground level sensor sends an on signal, that is, for the layer sensor, it means that the position corresponding to the area coded 1 can be recognized whether it is pressed. And the position corresponding to the area coded 0 is not recognized whether it is pressed. Correspondingly, if the pressing position is to be determined, multiple layers of ground sensors are required to be superimposed, and a reasonable perforation distribution is performed according to the respective spatial codes to respectively detect whether or not each is turned on to finally determine the pressing position. The more the number of spatial coding bits, the more the number of ground sensor layers is, the finer the identifiable ground space unit is, and the number of coded bits is determined according to actual needs. For example, the area of the ground space unit detected by the ground sensor can be 3 cm. *3 cm, 5 cm * 5 cm or 1 m * 1 m.

In this scheme, after extensive experimentation and comprehensive consideration of hardware layout, the LDPC sparse matrix can be used to binary code the ground space. That is, the preset matrix is optionally an LDPC sparse matrix. Among them, the LDPC sparse matrix is a packet error correction code with a sparse check matrix proposed by Robert Institute of Technology in 1962. It is applicable to all channels. The performance of LDPC sparse matrix is close to Shannon limit, and the decoding is simple. And parallel operation is possible, suitable for hardware implementation.

Step 120: Detect an output signal of the ground sensing device, and determine a pressing position in the ground space according to the output signal and the preset matrix.

Wherein, the output signal is composed of a conduction signal or a non-conduction signal sent by each floor sensor.

It can be seen from step 110 that when a person moves in the ground space, if a position is stepped on the foot, the ground sensor where the hole is located is turned on, and an on signal is sent, and the exemplary conduction signal is 1, the ground sensor that is not turned on emits a continuous non-conduction signal, and the exemplary non-conduction signal is zero. Exemplarily, if the ground sensing device is composed of 8 layers of ground sensors, the signal received by the ground sensing device is composed of 8 bits, and the exemplary output signal may be [01001100], according to which the output may be The signal and preset matrix get the position to be pressed. Exemplarily, let the output signal be a vector y, the vector y is composed of 8 bits, that is, an 8-dimensional vector, according to the formula

Calculate the value of x, where H represents the preset matrix and x represents the pressed position in the ground space, symbol

Is a binary XOR operator. In the process of solving the x value, for example, a Bayesian inference method or an MP algorithm may be used.

Step 130: Determine an activity of the human body according to the pressed position.

Among them, the activity of the human body can be dynamic walking, running, or static standing, falling or sitting posture.

In this step, when the activity of the human body is recognized, the movement trajectory of the human body can be obtained according to the pressing position determined at different time intervals. Optionally, the time may be 1 s, 3 s, or 5 s, that is, each 1 s, 3 s, or 5 s determines a pressed position in the ground space, and the obtained continuous pressing position determines the trajectory of the person.

In this step, when the standing, falling or sitting posture of the human body is recognized, the posture corresponding to the data corresponding to the comparison may be determined by comparing the pressing position with the data in the pre-established a priori database. The posture of the human body. Exemplarily, the pre-established a priori database stores judgment data of standing, falling or sitting postures. Alternatively, the standing posture is that there are two simultaneous pressed positions at the same time, and the falling posture exists at the same time. In a plurality of consecutive pressed positions, there are 3 to 5 pressed positions at the same time, and the human body is obtained by comparing the pressed position determined in step 120 with the recorded data in the prior database. Static posture.

The technical solution of the embodiment encodes the ground space according to the preset matrix, wherein the ground space is provided with a ground sensing device, and the ground sensing device is composed of at least two layers of ground sensors, and each layer of the sensor is The code is apertured, and when the hole is pressed, the ground sensor on which the hole is located emits an on signal, detecting an output signal of the ground sensing device, and according to the output signal and the pre And determining, by the matrix, a pressing position in the ground space, wherein the output signal is composed of a conduction signal or a non-conduction signal sent by each floor ground sensor, and determining an activity of the human body according to the pressing position, The camera's simple behavioral activity detection method has the disadvantages of large data throughput, large computational complexity, high energy consumption, complicated equipment, and high price, which makes the detection of human activities low in energy consumption and small in computation, and the detection method is simple and convenient. The equipment costs are low and does not require a dedicated volume.

Embodiment 2

3 is a flowchart of a human body activity detecting method according to Embodiment 2 of the present disclosure. This embodiment provides a process for detecting human activity through a ground sensing device including a 4-layer ground sensor on the basis of Embodiment 1. Those skilled in the art may know that detecting a presence or absence of a pressing position in 16 ground space units by a 4-layer ground sensor may cause a certain error. However, the present solution is only for describing the determining manner, and the error is eliminated as the number of ground sensor layers increases. If the recognition accuracy is higher, the ground space is divided into 32 or 64 spatial units, which requires more ground sensors.

As shown in Figure 3, it can be:

Step 201: Perform 4 layers of coding on the ground space according to the preset matrix.

The ground sensing device is formed by stacking four layers of ground sensors, which are composed of conductive tin foil paper, wires and sponges.

4 is a schematic diagram of a spatial encoding and a corresponding ground sensor punching position according to Embodiment 2 of the present disclosure. As shown in FIG. 4, the ground sensing device is composed of four layers of ground sensors superimposed and identified as a first layer, respectively. The second layer, the third layer, and the fourth layer, wherein the perforation position of each layer is determined by terrestrial space coding, and the terrestrial space coding is determined by an LDPC sparse matrix.

Optionally, the ground space is divided into 16 ground space units by ground space coding, and each corresponding ground sensor is also divided into 16 ground space units. The code of each ground space unit is composed of 4 bits, for example, the ground space unit of the first row and the first column is coded as "1001", and the ground space code of the first row and the second column is coded as "0001", wherein each floor space The code values in the unit correspond to whether the four-layer ground sensor needs to be punched in the same floor space unit. For example, the code corresponding to the first column of the fourth row in the terrestrial space coding is “1110”, wherein the value of the first bit of the code represents whether the hole is punched in the first layer ground sensing device, in the code. The first bit of 1 means that the same ground space unit of the first floor ground sensor needs to be punched. Similarly, the second bit in "1110" is also 1, and the corresponding ground sensor is required in the second floor. Punching the same floor space unit, the fourth bit value in "1110" is 0, which means that the same floor space unit of the fourth floor ground sensor does not need to be punched.

Step 202: Detect an output signal of the ground sensing device, and determine a pressing position in the ground space according to the output signal and the preset matrix.

Step 203: Determine an activity of the human body according to the pressed position.

FIG. 5 is a schematic diagram of a human activity track determined by the human activity detecting method according to the second embodiment of the present disclosure. For example, when the pressing position determined in the ground space determined in step 202 is “1110” ground space unit, “1100” When the ground space unit, "0111" ground space unit, "1101" ground space unit, "0100" ground space unit, "1111" ground space unit, "1010" ground space unit and "1011" unit, the obtained simulated trajectory As shown in Fig. 5, the left side in Fig. 5 is a hypothetical human body in which the path of the arrow is the active path of the human body.

The technical solution of the embodiment is to perform 4-layer coding on the ground space according to the matrix, determine the punching position in the ground sensor according to each layer code, and detect whether the ground sensing device has a signal output, and if so, according to the The signal output by the ground sensing device and the matrix determine the pressing position in the ground space, and the activity of the human body is determined according to the pressing position. Under the premise of satisfying the measurement accuracy, the calculation amount is minimum, which is in accordance with actual application requirements.

Embodiment 3

FIG. 6 is a structural diagram of a human activity detecting apparatus according to Embodiment 3 of the present disclosure, which may include:

The coding module 1 is configured to encode the ground space according to the preset matrix, wherein the ground space is provided with a ground sensing device, and the ground sensing device is composed of at least two layers of ground sensors, and each layer of the sensor is The coded hole has a hole, and when the hole is pressed, the ground sensor on which the hole is located emits a conduction signal;

The detecting module 2 is configured to detect an output signal of the ground sensing device;

Pressing the position determining module 3, configured to determine a pressing position in the floor space according to the output signal and the preset matrix, wherein the output signal is a conduction signal or a non-conduction signal sent by each floor sensor composition;

The human activity determining module 4 is configured to determine the activity of the human body based on the pressed position.

On the basis of the foregoing technical solution, the coding module 1 is configured to perform binary coding on the ground space according to a preset LDPC sparse matrix; the per-layer sensor according to the coding has holes: the each layer of the sensor The puncturing is performed according to the ground space corresponding to the code of 1 in the binary code.

On the basis of the above technical solution, the pressing position determining module 3 is configured to: obtain a vector y according to the output signal; according to the formula

Is a binary XOR operator.

Based on the above technical solution, the human activity determining module 4 is configured to: determine a trajectory of the human body activity according to the pressing position; and/or determine a falling, standing, and sitting posture of the human body according to the pressing position. At least one.

On the basis of the foregoing technical solution, the coding module 1 is configured to: perform 4-layer coding on the ground space according to the preset matrix, and correspondingly, the ground sensing device is superposed by four layers of ground sensors, and the ground sensor is composed of Conductive foil paper, wire and sponge.

The above product can perform the method provided by any embodiment of the present disclosure, and has the corresponding functional modules and beneficial effects of the execution method.

Embodiment 4

FIG. 7 is a structural diagram of a ground sensor according to Embodiment 4 of the present disclosure. This embodiment provides an optional ground sensor structure based on the above embodiment. As shown in FIG. 6, the ground sensor includes:

a first conductive layer 01, a second conductive layer 02, and an insulating layer 03 interposed between the first conductive layer 01 and the second conductive layer 02, the first conductive layer 01, the second conductive layer 02, and the insulating layer The layer 03 is bonded, the insulating layer 03 is filled with holes, and the first conductive layer 01 and the second conductive layer 02 are adhered with a wire 04, wherein the position of the hole is determined according to the code. Exemplarily, the position coded 1 corresponds to the punch, and the position coded 0 is not processed.

The position of the wire 04 is not fixed as long as it is connected to the conductive layer. Optionally, the ground sensor and the computing device are connected by wire.

Optionally, the ground sensing device may further include a wireless module, and the wireless module and the computing device perform signal interaction.

Optionally, the first conductive layer 01 and the second conductive layer 02 are made of tin foil paper, and the insulating layer 03 is made of a sponge.

The ground sensor provided by the embodiment is low in price, can be put into operation in a large area and is laid in the ground space, and solves the problem that the existing sensing device for acquiring human activities is expensive and cannot be used in a large area, and at the same time, accurate detection of human activities is realized. .

The embodiment of the invention further provides a non-transitory computer storage medium storing computer executable instructions, the computer executable instructions being configured to perform the human activity detection method of the above embodiment.

Embodiments of the present invention also provide an apparatus for performing a human body activity detecting method. Referring to Figure 8, the device includes:

One or more processors 80, one processor 80 is taken as an example;

Memory 81.

The apparatus may also include an input device 82 and an output device 83. The processor 80, the memory 81, the input device 82, and the output device 83 in the device may be connected by a bus or other means, and the bus connection is taken as an example in FIG.

The memory 81 is used as a computer readable storage medium, and can be used to store a software program, a computer executable program, such as a program instruction/module corresponding to the human activity detecting method in the embodiment of the present invention. The processor 80 executes the function application and the data processing of the server by executing the software program, the instruction and the module stored in the memory 81, that is, the human activity detecting method in the above method embodiment.

The memory 81 may include a storage program area and an storage data area, wherein the storage program area may store an operating system, an application required for at least one function; the storage data area may store data created according to use of the terminal device, and the like. Further, the memory 81 may include a high speed random access memory, and may also include a nonvolatile memory such as at least one magnetic disk storage device, flash memory device, or other nonvolatile solid state storage device. In some examples, memory 81 can include memory remotely located relative to processor 80, which can be connected to the terminal device over a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

Input device 82 can be arranged to receive input numeric or character information and to generate key signal inputs related to user settings and function control of the terminal. The output device 83 may include a display device such as a display screen.

The one or more modules are stored in the memory 81 and, when executed by the one or more processors 80, perform the steps of the method embodiments described above.

Industrial applicability

The embodiment of the present disclosure solves the shortcomings of the human body simple behavior activity detection method based on the camera in the related art, which has the disadvantages of large data flux, large calculation amount, high energy consumption, complicated equipment, and high price, so that the detection energy consumption of human activities is low, and the operation is low. The amount is small, the detection method is simple, the detection equipment cost is low, and it is not necessary to occupy a dedicated volume space.

Claims

A method for detecting human activity includes:

The ground space is encoded according to a preset matrix, wherein the ground space is provided with a ground sensing device, and the ground sensing device is composed of at least two layers of ground sensors, and each layer of the sensor has a hole according to the code. When the hole position is pressed, the ground sensor where the hole is located emits a conduction signal;

Detecting an output signal of the ground sensing device, and determining a pressing position in the ground space according to the output signal and the preset matrix, wherein the output signal is a conduction signal sent by each floor sensor or Non-conducting signal composition;

The activity of the human body is determined according to the pressed position.
The method of claim 1 wherein encoding the floor space in accordance with the preset matrix comprises:

Binding the ground space according to a preset LDPC sparse matrix;

Each of the layers of the sensor having holes according to the code includes:

The sensor of each layer performs puncturing according to the ground space corresponding to the code of 1 in the binary code.
The method according to claim 1, wherein determining the pressing position in the floor space according to the output signal and the preset matrix comprises:

Obtaining a vector y according to the output signal;

According to the formula
Obtaining a value of x, where H represents the preset matrix, x represents a pressed position in the ground space, a symbol
Is a binary XOR operator.
The method of claim 1, wherein determining the activity of the human body based on the pressing position comprises:

Determining a trajectory of human activity according to the pressed position; or

At least one of a fall, a standing, and a sitting posture of the human body is determined according to the pressed position.
The method according to any one of claims 1 to 4, wherein encoding the floor space according to the preset matrix comprises:

The ground space is coded in four layers according to the preset matrix. Correspondingly, the ground sensing device is formed by stacking four layers of ground sensors, which are composed of conductive tin foil paper, wires and sponges.
A human activity detecting device includes:

The coding module is configured to encode the ground space according to the preset matrix, wherein the ground space is provided with a ground sensing device, and the ground sensing device is composed of at least two layers of ground sensors, Each layer sensor has a hole according to the code, and when the hole position is pressed, the ground sensor where the hole is located emits an on signal;

a detecting module configured to detect an output signal of the ground sensing device;

Pressing a position determining module, configured to determine a pressing position in the floor space according to the output signal and the preset matrix, wherein the output signal is composed of a conduction signal or a non-conduction signal sent by each floor sensor ;as well as

The human activity determining module is configured to determine an activity of the human body according to the pressing position.
The apparatus of claim 6 wherein said encoding module is configured to:

Binding the ground space according to a preset LDPC sparse matrix;

Each of the layers of the sensor having holes according to the code includes:

The sensor of each layer performs puncturing according to the ground space corresponding to the code of 1 in the binary code.
The apparatus according to claim 6, wherein said pressing position determining module is configured to:

Obtaining a vector y according to the output signal;

According to the formula
Obtaining a value of x, where H represents the preset matrix, x represents a pressed position in the ground space, a symbol
Is a binary XOR operator.
The apparatus according to claim 6, wherein said human activity determining module is configured to:

Determining a trajectory of human activity according to the pressed position; or

At least one of a fall, a standing, and a sitting posture of the human body is determined according to the pressed position.
A floor sensor for use in any of claims 1-5, comprising:

a first conductive layer, a second conductive layer, and an insulating layer interposed between the first conductive layer and the second conductive layer, the first conductive layer, the second conductive layer and the insulating layer are bonded, the insulation A hole is formed in the layer, and the first conductive layer and the second conductive layer are adhered with a wire, wherein a position of the hole is determined according to the code.
A non-transitory computer storage medium storing computer executable instructions arranged to perform the method of any of claims 1-5.