A method, system, device and storage medium for detecting human traffic

Abstract

The present invention provides a method, system, device and storage medium for detecting human flow, the method comprising: obtaining node data of a sensor matrix within a preset time period through a gateway; selecting nodes whose level is greater than or equal to a pressure threshold from the node data, adding weights to the nodes and nodes in the matrix around the nodes to form a contour matrix; identifying a score peak cluster in the contour matrix, selecting a calibration point and demarcating a small data window and a large data window with the calibration point as the center; calculating the sole area and geometric centroid of a person based on the small data window; within the validity period of the large data window, identifying the foot shape data of the small data window symmetrical to the current foot shape feature, determining the walking data of the same person, and judging the movement direction of the person through the change of the geometric centroid coordinates; counting the people in the in-and-out directions based on the movement direction, and accumulating to obtain human flow information. The present invention can improve the accuracy and reliability of human flow detection.

Description

Technical Field

[0001] The present application relates to the technical field of human flow detection, and in particular to a human flow detection method, system, device and storage medium. Background Art

[0002] There are currently three main technologies used to detect the number of people entering and exiting shopping malls or large-scale events: camera detection technology, infrared detection technology, and pressure-sensitive sensor technology based on PET film printing.

[0003] Among them, although camera detection technology is widely used, its high initial investment cost, complex image processing algorithm requirements and potential threats to privacy protection make this solution not only economically burdensome, but also likely to cause discomfort and disgust to participants. In addition, the camera system also faces data security issues. Once illegally invaded, sensitive information may be stolen and abused.

[0004] Infrared detection technology counts the number of people passing through by setting up detection columns at the entrance and exit. This method not only limits the space for pedestrians to pass through, but is also prone to missing detection when multiple people pass through at the same time. More importantly, infrared detection can only identify the passage of objects, but cannot distinguish whether the person passing through is a valid entrant, nor can it determine whether he or she is an adult or a child, which greatly reduces the accuracy and practicality of the data.

[0005] The existing hardware solutions for pressure-sensitive sensor technology based on PET film printing, that is, using PET film to print various conductive materials with different resistance values ​​to form pressure-sensitive sensors or sensor groups, are also unsatisfactory. Switch-type products only have two states: on and off, and lack pressure detection capabilities; and the flexible pressure film switch used for force analysis is more comprehensive in function, but due to its large number of rows and columns and small sensing point size, it consumes a lot of ink and is costly. At the same time, this type of switch also needs to be equipped with a chip with a large number of ADC detection pins for data collection and processing. The main control solution is complex and the amount of data is large, which brings great challenges to data analysis and processing. In addition, most of these hardware products on the market are designed for trampling statistics in static scenes, and cannot meet the needs of dynamic traffic statistics and monitoring.

[0006] In view of this, the present invention proposes a method, system, device and storage medium for detecting human flow, which can accurately count people entering and exiting, and obtain human flow information by accumulating people entering and exiting in different directions. Summary of the invention

[0007] In order to solve the problems of privacy exposure, detection limitations, high costs and complex data processing in existing pedestrian flow detection technologies, the present application provides a pedestrian flow detection method, system, device and storage medium to solve the above-mentioned technical defects.

[0008] According to the first aspect of the present application, a method for detecting human flow is proposed, the method comprising the following steps: S1, electrically connecting multiple floor mat units to form a sensor matrix, and obtaining node data of the sensor matrix within a preset time period through a gateway; S2, selecting nodes whose levels are greater than or equal to the pressure threshold from the node data, and adding weights to the nodes and the nodes in the surrounding matrix to form a contour matrix; S3, identifying the score peak cluster in the profile matrix, selecting the point in the score peak cluster closest to the origin as the calibration point, and delineating the small data window and the large data window with the calibration point as the center; S4, calculating the area of ​​the sole of the person's foot and the geometric center of mass based on the small data window, and determining the left and right feet of the person according to the coordinate position of the geometric center of mass; During the validity period of the big data window, the foot shape data of the small data window that is symmetrical to the current foot shape feature is identified to determine the walking data of the same person. The movement direction of the person is determined by analyzing the relationship between the geometric centroid coordinates of the data in the small data window and the geometric centroid coordinates of the corresponding data in the big data window. S5. Count the people in and out of the room based on the direction of movement, and accumulate the information to obtain the flow of people.

[0009] Preferably, in step S1, electrically connecting a plurality of floor mat units to form a sensor matrix specifically comprises the following sub-steps: S11, electrically connecting multiple floor mat units to each other, and sending a configuration data packet to the first floor mat unit by the gateway; S12, after receiving the configuration data packet, the first floor mat unit transmits the configuration data packet and the sorting data packet with the sending identification bit to the next floor mat unit through the connection interface; S13, after each floor mat unit receives the sorting data packet transmitted by the previous floor mat unit, it updates its own ID according to the sequence information in the sorting data packet, and continues to pass the updated sorting data packet to the subsequent floor mat units until all floor mat units complete the ID allocation, and the terminal floor mat unit feeds back the updated sorting data packet to the gateway; S14. The gateway parses the IDs of all floor mat units and the number of current floor mat units according to the updated sorted data packet to form a sensor matrix.

[0010] Further preferably, step S13 specifically includes the following sub-steps: S131, each floor mat unit takes the next sequence number as its own ID and records it according to the non-blank bit sequence in the received sorting data packet; S132, if there is a newly connected floor mat unit after the current floor mat unit, continue to transmit the updated configuration data packet and sorting data packet backward; S133: If the current ground pad unit has no subsequent ground pad unit, the indication bit of the sorting data packet is changed to an upload flag, and the sorting data packet is forwarded to the gateway.

[0011] Further preferably, in step S14, the gateway parses the IDs of all floor mat units and the number of current floor mat units according to the updated sorted data packet to form a sensor matrix, further comprising: The gateway receives the uploaded updated sorted data packet, identifies the IDs of all floor mat units, and determines the number of currently connected floor mat units by counting all non-blank bit sequences; If the floor mat unit is replaced, the MCU of the replaced floor mat unit resets the gateway ID, current ID and sequence length. When the replaced floor mat unit receives the sorted data packet transmitted by the previous floor mat unit, it compares the ID information, queue information and local MCUID information. If there is no match, the current position and ID information are redetermined.

[0012] Further preferably, the configuration data packet in step S11 includes: gateway ID, current sequence length key, upload information time interval, ID length and system synchronization clock information.

[0013] Preferably, in step S4, the area of ​​the sole of the person's foot and the geometric center of mass are calculated based on the small data window, and the left and right feet of the person are determined according to the coordinate position of the geometric center of mass, which specifically includes the following steps: The number of nodes whose levels in the small data window are greater than or equal to the preset threshold is multiplied by the area coefficient to obtain the area of ​​the person's foot; The coordinates of the geometric centroid are obtained by taking the weighted average of the level degrees and coordinates of all nodes in the small data window; The left foot or right foot of the person is determined based on the relative position of the coordinates of the geometric centroid and the left and right horizontal coordinates of the small data window.

[0014] Preferably, the human flow detection method proposed by the present invention further includes: The different pressure-sensitivity level data of each floor mat unit in the sensor matrix are stored and recorded, and statistical analysis is performed on them to obtain the personnel's preference for the entrances to different blocks, and to count the entry and exit of personnel of different weights at the entrances to each block.

[0015] In a second aspect, the present invention provides a human flow detection system, the system comprising: A node data acquisition module is configured to electrically connect a plurality of floor mat units to form a sensor matrix, and acquire node data of the sensor matrix within a preset time period through a gateway; The contour matrix forming module is configured to select nodes whose levels are greater than or equal to the pressure threshold from the node data, and add weights to the nodes and nodes in the surrounding matrix to form a contour matrix; A window delineation module is configured to identify a score peak cluster in the profile matrix, select a point in the score peak cluster that is closest to the origin as a calibration point, and delineate a small data window and a large data window with the calibration point as the center; The movement direction judgment module calculates the area of ​​the person's sole and the geometric center of mass based on a small data window, and judges the person's left and right feet based on the coordinate position of the geometric center of mass; During the validity period of the big data window, the foot shape data of the small data window that is symmetrical to the current foot shape feature is identified to determine the walking data of the same person. The movement direction of the person is determined by analyzing the relationship between the geometric centroid coordinates of the data in the small data window and the geometric centroid coordinates of the corresponding data in the big data window. The crowd flow information acquisition module counts the people entering and leaving the room based on the direction of movement, and accumulates the crowd flow information.

[0016] In a third aspect, the present invention proposes a terminal device, comprising a processor, a memory, and a computer program stored in the memory, wherein the computer program is executed by the processor to implement a human flow detection method as described in any one of the above items.

[0017] In a fourth aspect, the present invention proposes a computer-readable storage medium, wherein the medium stores a computer program, and when the computer program is executed by a processor, the human flow detection method as described in any one of the above is implemented.

[0018] Compared with the prior art, the beneficial results of the present invention are: (1) Enhanced privacy protection: By using a sensor matrix composed of floor mat units to detect pedestrian flow, the use of visual monitoring equipment such as cameras is avoided, thereby reducing the risk of personal privacy exposure.

[0019] (2) Improved detection range and accuracy: The sensor matrix can cover a larger detection area. At the same time, through the fine processing of node data, it can accurately identify the area of ​​a person's foot, geometric center of mass, and direction of movement, thereby improving the accuracy and reliability of detection.

[0020] (3) Cost reduction: Compared with traditional visual monitoring equipment, floor mat units are cheaper and easier to install and maintain, thereby reducing the cost of the overall system.

[0021] (4) Simplified data processing: By converting complex image processing problems into simple processing of sensor data, the data processing process is simplified and the operating efficiency of the system is improved.

[0022] (5) Adaptability and flexibility: The system can adaptively update the ID and sequence information according to the connection status of the floor mat unit to ensure the stability and accuracy of the sensor matrix. At the same time, the system can also adjust parameters such as pressure threshold and area coefficient according to actual needs, which improves the flexibility and adaptability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings: Figure 1 is a flow chart of a method for detecting human flow according to the present application; Figure 2 is a schematic diagram of a self-organizing network algorithm of a sequence sensor matrix according to the present application; Figure 3 is a schematic diagram of an algorithm for identifying the presence of a person according to a sensor matrix sequence of the present application; Figure 4 is a schematic diagram of a method for obtaining weights of sensor matrix nodes according to the present application; Figure 5 is a structural diagram of a human flow detection system according to the present application; Figure 6 It is a structural diagram of a computer system suitable for implementing an electronic device of an embodiment of the present application. DETAILED DESCRIPTION

[0024] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It is also necessary to explain that, for ease of description, only the parts related to the relevant invention are shown in the accompanying drawings.

[0025] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0026] Figure 1 The flow chart of the human flow detection method of the present application is shown as follows: Figure 1 As shown, the method comprises the following steps: S1. Electrically connect multiple floor mat units to form a sensor matrix, and obtain node data of the sensor matrix within a preset time period through a gateway.

[0027] Figure 2 The schematic diagram of the self-organizing network algorithm of the sequence sensor matrix of the present application is shown as follows: Figure 2 As shown, electrically connecting a plurality of floor mat units to form a sensor matrix specifically includes the following sub-steps: S11, electrically connect multiple floor mat units to each other, and the gateway sends a configuration data packet to the first floor mat unit; wherein the configuration data packet includes: gateway ID, current sequence length key, upload information time interval, ID length and system synchronization clock information.

[0028] S12: After receiving the configuration data packet, the first floor mat unit transmits the configuration data packet and the sorting data packet with a sending identification bit to the next floor mat unit through the connection interface.

[0029] S13. After each floor mat unit receives the sorting data packet transmitted by the previous floor mat unit, it updates its own ID (for example, from AZ) according to the sequence information in the sorting data packet, and continues to pass the updated sorting data packet to the subsequent floor mat units until all floor mat units complete the ID allocation. The terminal floor mat unit then feeds back the updated sorting data packet to the gateway.

[0030] S14. The gateway parses the IDs of all floor mat units and the number of current floor mat units according to the updated sorted data packet to form a sensor matrix.

[0031] Wherein, step S13 specifically includes the following sub-steps: S131, each floor mat unit takes the next sequence number as its own ID and records it according to the non-blank bit sequence in the received sorting data packet; S132, if there is a newly connected floor mat unit after the current floor mat unit, continue to transmit the updated configuration data packet and sorting data packet backward; S133: If the current ground pad unit has no subsequent ground pad unit, the indication bit of the sorting data packet is changed to an upload flag, and the sorting data packet is forwarded to the gateway.

[0032] In step S14, the gateway parses the IDs of all floor mat units and the number of current floor mat units according to the updated sorted data packet to form a sensor matrix, which also includes: The gateway receives the uploaded updated sorted data packet, identifies the IDs of all floor mat units, and determines the number of currently connected floor mat units by counting all non-blank bit sequences; If a floor mat unit is replaced, the MCU of the replaced floor mat unit resets the gateway ID, current ID and sequence length, and the replaced floor mat unit compares the ID information, queue information and local MCUID information when receiving the sorted data packet transmitted by the previous floor mat unit. If there is no match, the current position and ID information are re-determined. For example, if there are 5 floor mat units connected in series in the original product, the system will assign unique IDs to these 5 floor mat units respectively, and the ID data contains the relative position information of the floor mat unit. Specifically, the ID of the first floor mat unit is No. 1, the second is No. 2, and so on. Every time the MCU resets the gateway, the gateway will send an ID (including the position number) for identifying each floor mat unit. If the floor mat unit is not reassembled in series, its sequence number will remain unchanged before power failure or reset. However, if the floor mat unit is reassembled in series, the order of its position number may change. At this time, the system will reset the existing floor mat order to ensure that the ID of each floor mat unit matches its actual position.

[0033] Based on the ID information, the gateway can sort and number the sensor group information of all the serially connected locations to form a splicing matrix. For example, if the sensors are connected in series horizontally, X blocks of A*B points of the matrix sensors are connected to form a matrix of (A*X)*B, where the number of the (a, b)th sensor of the xth floor mat unit in the overall matrix is ​​(A*x, b). Specifically, in a 60*20 matrix formed by connecting five 12*20-point floor mat units, the number of the (5,11)th point of the third floor mat unit is (41,11).

[0034] Figure 3 The schematic diagram of the algorithm for identifying the presence of people by the sensor matrix sequence of the present application is shown, combined with the reference Figure 1 and Figure 3 The human flow detection method provided in this application also includes the following steps: S2. Filter out nodes whose levels are greater than or equal to the pressure threshold from the node data, and add weights to the nodes and the nodes in the surrounding matrix to form a contour matrix.

[0035] S3. Identify the score peak cluster in the contour matrix, select the point in the score peak cluster closest to the origin as the calibration point, and delineate the small data window and the large data window with the calibration point as the center.

[0036] S4. Calculate the area of ​​the sole of the person's foot and the geometric center of mass based on the small data window, and determine the left and right feet of the person according to the coordinate position of the geometric center of mass.

[0037] During the validity period of the big data window (for example, valid within 5 seconds after the current score peak cluster disappears), identify the foot shape data of the small data window symmetrical to the current foot shape feature, determine the walking data of the same person, and judge the movement direction of the person by analyzing the relationship between the geometric centroid coordinates of the data in the small data window and the geometric centroid coordinates of the corresponding data in the big data window. It should be understood that the foot shape feature is mainly reflected in the two aspects of the sole area and the geometric centroid. The distribution characteristics of the sole area are characterized by a larger forefoot area and a relatively smaller heel area. There is an arch structure on the inner side of the center of the sole, and this area is smaller than the forefoot and heel parts when subjected to force. When standing on both feet, the soles of both feet are facing up and the heels are relatively close. At this time, the pressure distribution shows that the center area of ​​the arch is less stressed and the color is lighter, while the outside of the foot is relatively stressed. During the walking process, the order of force on the foot is as follows: the heel starts to be stressed first, then gradually transitions to the sole, and finally the sole and heel are stressed at the same time. The change pattern of the geometric center of mass is: in the initial stage, it is located at the center of the heel force area, then gradually transitions to the center of the arch and heel, and finally concentrates on the center of the joint action area of ​​the sole, arch and heel. Through this dynamic change, the walking direction can be inferred.

[0038] S5. Count the people in and out of the room based on the direction of movement, and accumulate the information to obtain the flow of people.

[0039] It should be understood that the mat should be able to identify short consecutive tracks of the same person to prevent the same person from being counted multiple times.

[0040] The complete matrix formed by the gateway is from the coordinate system at one end, taking the first floor mat unit (12, 1) as the origin. After completely collecting the sensor dot matrix data within a time slot and calculating the current footprint area With geometric centroid .

[0041] Figure 4 A schematic diagram of a method for obtaining weights of sensor matrix nodes of the present application is shown. Figure 4 As shown, the footprint area is calculated The present invention adds weight to each node with pressure sensitivity (level ≥ threshold 1). , the other nodes in the surrounding 3x3 matrix are weighted , other nodes are 0 points, then in this global lattice score, the weight score of a point a is 0 to . Then, a contour matrix based on the pressure level can be obtained. The point (a, b) closest to the origin in a certain score peak cluster (continuous 3*5 grids or more, level ≥ threshold 2) is used as the calibration, and a small data window of 10cmx35cm is defined at the point (a-awi, b-bawi) for calibrating a single footprint. A large data window with an area of ​​A2 is defined, with a typical value of 35cm-100cm, for tracking the trajectory. The number of nodes with a level ≥ threshold 2 in the small data window multiplied by the area Amesh is the area of ​​a foot, and its center of mass is the weighted average of the level degrees of all nodes and the coordinates. When the coordinate is closer to the left horizontal coordinate of the small data window, it is the left foot, and if it is closer to the right horizontal coordinate, it is the right foot.

[0042] The human flow detection method proposed by the present invention also includes: The different pressure-sensitivity level data of each floor mat unit in the sensor matrix are stored and recorded, and statistical analysis is performed on them to obtain the personnel's preference for different block entrances, as well as statistics on the entry and exit of people of different weights at the entrances of each block, to assist in the collection of non-privacy personnel information.

[0043] In a specific embodiment, the sensor matrix of the present invention can be designed with a cluster matrix of 12 columns and 20 rows to meet the force detection of a detection area of ​​500mm~800mm width. Through 20 pins to output high level, 12 ADC pins detect the ADC data after the pressure change obtained under the scanning state. So that the main control chip for developing the detection only needs to meet the chip with 32 functional pins. Each small detection unit of the floor mat sensor is mainly composed of 4*4 small detection points. As long as any detection point is turned on, this grid will have a corresponding pressure value. The more the number of contacts, the greater the pressure, and the smaller the detected value. The overall technical indicator of pressure change from 0.8kgf~7.5kgf on a contact area of ​​36mm*36mm is achieved.

[0044] Moreover, the floor mat units can be flexibly connected in series, with a maximum of 10 units, and the maximum size of a single processor is 5m wide, which meets the requirements of most shopping malls or activity entrances and exits. It will not cause the pedestrian passages on the road to be occupied by the equipment. The optimized method of counting people can use the pressure changes of the two feet when walking through, and the algorithm can calculate whether the person is entering or leaving.

[0045] Preferably, a communication line of up to 8m is connected to the front end of the floor mat unit, and the data of the electronic floor mat is transmitted to the gateway of the product through the RS485 communication line. The 8m communication line can meet the requirement of placing the gateway far away on the wall without affecting pedestrians or causing unsightly conditions. The gateway processes the data collected from the 10 electronic floor mat units through an algorithm and converts them into the number of people entering and leaving.

[0046] The design principle of the present invention is as follows: First, when the sensor on the floor mat unit is under pressure, the on-resistance of the contact between the upper and lower rows will decrease as the pressure increases, and the main control chip sends a high level at intervals, and reaches the main control board of the chip after passing through the "resistance" generated by the pressure on the sensor. There is a voltage divider resistor on the main control board to divide the resistance of the sensor, and the ADC pin of the chip detects the voltage change and records it in the chip. The chip detects the data of 240 grids in the sensor through matrix polling within 50ms, and packages the data to the gateway. The voltage divider resistor is selected according to the actual sensor pressure-resistance relationship. It is required that the entire force range to be detected is converted to a voltage in the range of 0.3~3.0V. In this way, the detection has enough width to divide each weight range more finely.

[0047] The gateway needs to analyze the data from each floor mat unit received. When people walk, the forefoot usually touches the ground first, then gradually transitions to the heel, or vice versa. At this time, the other foot also touches the ground with the forefoot first, and the heel touches the ground later. Therefore, the sensor matrix will detect that there will be pattern differences in the grid of the sole area, where different parts are pressed forward and backward, with values ​​and then the numbers gradually decrease. Then, as the entire sole is stepped on, the large area of ​​the sole is in different stress states, and the chip will be mainly subjected to heavy force on the forefoot and heel, and light force on other areas. In particular, the arch area is subjected to light force, so the direction of the foot can be determined. According to this change in walking, the gateway will process the data of each frame (50ms) received before and after the data is processed, and the data will be sorted and analyzed through a specific algorithm. If there is data of stepping within the front and back distance, and the direction of the arch when the entire sole is stressed is the same as the order of stepping of the two feet, it is judged that this person has entered, and one person is recorded as entering.

[0048] Further references Figure 5 As an implementation of the above method, in the second aspect, the present application provides a structural diagram of an embodiment of a human flow detection system 500, which can be specifically applied to various electronic devices. The system 500 includes the following modules: The node data acquisition module 510 is configured to electrically connect the plurality of floor mat units to form a sensor matrix, and acquire node data of the sensor matrix within a preset time period through the gateway; The contour matrix forming module 520 is configured to select nodes whose levels are greater than or equal to the pressure threshold from the node data, and add weights to the nodes and the nodes in the surrounding matrix to form a contour matrix; The window delineation module 530 is configured to identify a score peak cluster in the profile matrix, select a point in the score peak cluster closest to the origin as a calibration point, and delineate a small data window and a large data window with the calibration point as the center; The movement direction determination module 540 calculates the area of ​​the sole of the person's foot and the geometric center of mass based on the small data window, and determines the left and right feet of the person according to the coordinate position of the geometric center of mass; During the validity period of the big data window, the foot shape data of the small data window that is symmetrical to the current foot shape feature is identified to determine the walking data of the same person. The movement direction of the person is determined by analyzing the relationship between the geometric centroid coordinates of the data in the small data window and the geometric centroid coordinates of the corresponding data in the big data window. The human flow information acquisition module 550 counts the people in the inbound and outbound directions based on the movement direction, and accumulates the human flow information.

[0049] In a third aspect, the present invention proposes a terminal device, comprising a processor, a memory, and a computer program stored in the memory, wherein the computer program is executed by the processor to implement a human flow detection method as described in any one of the above items.

[0050] In a fourth aspect, the present invention proposes a computer-readable storage medium, wherein the medium stores a computer program, and when the computer program is executed by a processor, the human flow detection method as described in any one of the above is implemented.

[0051] Reference below Figure 6 , which shows a schematic diagram of the structure of a computer system 600 of a terminal device or server suitable for implementing an embodiment of the present application. Figure 6 The terminal device or server shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0052] like Figure 6 As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the computer system 600 are also stored. The CPU 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0053] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a liquid crystal display (LCD), etc. and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage section 608 as needed.

[0054] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the central processing unit (CPU) 601, the above functions defined in the method of the present application are executed. It should be noted that the computer-readable medium described in the present application can be a computer-readable signal medium or a computer-readable medium or any combination of the above two. The computer-readable medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable media may include, but are not limited to, an electrical connection with one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, an apparatus or a device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable medium, which may send, propagate, or transmit a program for use by or in combination with an instruction execution system, an apparatus or a device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0055] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0056] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0057] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above invention concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.

Claims

1. A method for detecting human flow, characterized in that: The method comprises the following steps: S1, electrically connecting a plurality of floor mat units to form a sensor matrix, and obtaining node data of the sensor matrix within a preset time period through a gateway; S2, selecting nodes whose levels are greater than or equal to the pressure threshold from the node data, and adding weights to the nodes and nodes in the surrounding matrix to form a contour matrix; S3, identifying a score peak cluster in the profile matrix, selecting a point in the score peak cluster closest to the origin as a calibration point, and defining a small data window and a large data window with the calibration point as the center; S4, calculating the area of ​​the sole of the person's foot and the geometric center of mass based on the small data window, and determining the left and right feet of the person according to the coordinate position of the geometric center of mass; During the validity period of the big data window, the foot shape data of the small data window symmetrical to the current foot shape feature is identified to determine the walking data of the same person, and the movement direction of the person is determined by analyzing the relationship between the geometric centroid coordinates of the data in the small data window and the geometric centroid coordinates of the corresponding data in the big data window; S5. Count the people in the inbound and outbound directions based on the movement direction, and accumulate to obtain the flow information of people.

2. The method for detecting human flow according to claim 1, characterized in that: In step S1, electrically connecting a plurality of floor mat units to form a sensor matrix specifically includes the following sub-steps: S11, electrically connecting multiple floor mat units to each other, and sending a configuration data packet to the first floor mat unit by the gateway; S12, after receiving the configuration data packet, the first floor mat unit transmits the configuration data packet and the sorting data packet with a sending identification bit to the next floor mat unit through the connection interface; S13, after each floor mat unit receives the sorting data packet transmitted by the previous floor mat unit, it updates its own ID according to the sequence information in the sorting data packet, and continues to transmit the updated sorting data packet to the subsequent floor mat units until all floor mat units complete the ID allocation, and the terminal floor mat unit feeds back the updated sorting data packet to the gateway; S14. The gateway parses the IDs of all floor mat units and the number of current floor mat units according to the updated sorted data packet to form the sensor matrix.

3. The method for detecting human flow according to claim 2, characterized in that: Step S13 specifically includes the following sub-steps: S131, each floor mat unit takes the next sequence number as its own ID and records it according to the non-blank bit sequence in the received sorted data packet; S132, if there is a newly connected floor mat unit after the current floor mat unit, continue to transmit the updated configuration data packet and sorting data packet backward; S133: If the current ground pad unit has no subsequent ground pad unit, the indication bit of the sorting data packet is changed to an upload flag, and the sorting data packet is forwarded to the gateway.

4. The method for detecting human flow according to claim 2, characterized in that: In step S14, the gateway parses the IDs of all floor mat units and the number of current floor mat units according to the updated sorted data packet to form the sensor matrix, further comprising: The gateway receives the uploaded updated sorted data packet, identifies the IDs of all floor mat units, and determines the number of currently connected floor mat units by counting all non-blank bit sequences; If the floor mat unit is replaced, the MCU of the replaced floor mat unit resets the gateway ID, current ID and sequence length, and when the replaced floor mat unit receives the sorted data packet transmitted by the previous floor mat unit, it compares the ID information, queue information and local MCUID information. If there is no match, the current position and ID information are redetermined.

5. The method for detecting human flow according to claim 2, characterized in that: The configuration data packet in step S11 includes: gateway ID, current sequence length key, upload information time interval, ID length and system synchronization clock information.

6. The method for detecting human flow according to claim 1, characterized in that: In step S4, the area of ​​the sole of the person's foot and the geometric center of mass are calculated based on the small data window, and the left and right feet of the person are determined according to the coordinate position of the geometric center of mass, which specifically includes the following steps: The number of nodes in the small data window whose levels are greater than or equal to a preset threshold is multiplied by an area coefficient to obtain the area of ​​the sole of the person's foot; The coordinates of the geometric centroid are obtained by weightedly averaging the level degrees and coordinates of all nodes in the small data window; The left foot or the right foot of the person is determined based on the relative position of the coordinates of the geometric centroid and the left and right horizontal coordinates of the small data window.

7. The method for detecting human flow according to claim 1, characterized in that: Also includes: The different pressure-sensitivity level data of each floor mat unit in the sensor matrix are stored and recorded and statistically analyzed to obtain the selection preferences of people for different block entrances, and to count the entry and exit of people of different weights at the entrances of each block.

8. A human flow detection system, characterized in that: The system comprises: A node data acquisition module, configured to electrically connect a plurality of floor mat units to form a sensor matrix, and acquire node data of the sensor matrix within a preset time period through a gateway; A contour matrix forming module is configured to select nodes whose levels are greater than or equal to the pressure threshold from the node data, and add weights to the nodes and nodes in the surrounding matrix to form a contour matrix; A window delineation module is configured to identify a score peak cluster in the profile matrix, select a point in the score peak cluster closest to the origin as a calibration point, and delineate a small data window and a large data window with the calibration point as the center; A movement direction determination module calculates the area of ​​the sole of the person's foot and the geometric center of mass based on the small data window, and determines the left and right feet of the person according to the coordinate position of the geometric center of mass; During the validity period of the big data window, the foot shape data of the small data window symmetrical to the current foot shape feature is identified to determine the walking data of the same person, and the movement direction of the person is determined by analyzing the relationship between the geometric centroid coordinates of the data in the small data window and the geometric centroid coordinates of the corresponding data in the big data window; The human flow information acquisition module counts the people in the inbound and outbound directions based on the movement direction, and accumulates the human flow information.

9. A terminal device, characterized in that: The method comprises a processor, a memory and a computer program stored in the memory, wherein the computer program is executed by the processor to implement the human flow detection method as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium, wherein a computer program is stored in the medium, and when the computer program is executed by a processor, the human flow detection method according to any one of claims 1 to 7 is implemented.

Images