Positioning methods, devices, computer equipment, and storage media

Abstract

This application relates to a positioning method, apparatus, computer device, and storage medium. The positioning method includes: acquiring target echo signals collected in a target environment; if the target echo signals indicate the presence of a moving target object in the target environment, identifying the target object; when the target object is identified to change from a moving state to a stationary state, performing stationary target detection on the current target echo signals in the target environment based on a regionalized background signal model to obtain the positioning result of the target object in a stationary state; the background signal model is pre-established based on background echo signals collected when there is no target object in the target environment. Using this method, apparatus, computer device, and storage medium can improve the accuracy of positioning.

Description

Technical Field

[0001] This application relates to the field of detection technology, and in particular to a positioning method, apparatus, computer equipment, and storage medium. Background Technology

[0002] With the development of detection technology, various positioning methods have emerged, such as image recognition positioning technology and radar positioning technology, to adapt to different scenarios, such as gaming scenarios and smart home scenarios.

[0003] However, existing positioning methods cannot accurately locate target objects, such as a stationary human body, and suffer from low accuracy. Summary of the Invention

[0004] Therefore, it is necessary to provide a positioning method, apparatus, computer equipment, and storage medium that can improve the accuracy of positioning in response to the above-mentioned technical problems.

[0005] A positioning method, the positioning method comprising:

[0006] Acquire target echo signals collected in the target environment;

[0007] If it is determined from the target echo signal that a target object in motion exists in the target environment, then the target object is identified;

[0008] When the target object is identified to change from a moving state to a stationary state, a stationary target detection is performed on the current target echo signal in the target environment based on a regionalized background signal model to obtain the positioning result of the target object in the stationary state; the background signal model is pre-established based on the background echo signal collected when there is no target object in the target environment.

[0009] A positioning device, the positioning device comprising:

[0010] The signal acquisition module is used to acquire target echo signals collected in the target environment;

[0011] The identification module is used to identify the target object when it is determined from the target echo signal that the target object is in motion in the target environment;

[0012] The positioning module is used to perform static target detection on the current target echo signal in the target environment based on a regionalized background signal model when the target object changes from a moving state to a stationary state, so as to obtain the positioning result of the target object in the stationary state.

[0013] The background signal model is pre-established based on the background echo signal collected when there is no target object in the target environment.

[0014] In one embodiment, the identification module is used to acquire target echo signals from multiple adjacent frames, and to identify the positional changes of a moving target object based on the target echo signals whose velocity changes are greater than a velocity change threshold within a preset period.

[0015] In one embodiment, the positioning device further includes a state determination module, which is used to determine that the target object changes from a moving state to a stationary state when the position change is less than a position change threshold within a first preset time period.

[0016] In one embodiment, the positioning module is used to obtain the background signal intensity value of the background echo signal corresponding to each region in the background signal model, and based on the background signal intensity value, to perform stationary target detection on the target signal intensity value corresponding to the current target echo signal, so as to obtain the positioning information of the target object in a stationary state.

[0017] In one embodiment, the background signal model includes background signal intensity values ​​corresponding to each grid region. The positioning module is used to compare the target signal intensity value corresponding to the current target echo signal of each grid region with the background signal intensity value of the background echo signal corresponding to each grid region to obtain the signal intensity difference corresponding to each grid region. When the signal intensity difference corresponding to the target grid region reaches a preset difference, the positioning result of the target object in a stationary state is determined based on the position of the target grid region.

[0018] In one embodiment, the positioning device further includes a difference acquisition module. The difference acquisition module is used to obtain the fluctuation range corresponding to the target grid region based on the difference between the maximum and minimum values ​​among multiple background signal intensity values ​​of the acquired target grid region, and to obtain the preset difference value corresponding to the target grid based on the fluctuation range corresponding to the target grid in the background signal model.

[0019] In one embodiment, the positioning module includes a target grid acquisition unit and a positioning unit. The target grid acquisition unit is used to acquire information about the grid area where the target object is located when it is stationary, and to designate grid areas whose distance from the grid area where the target object is located when it is stationary as the target grid area. The positioning unit is used to determine the positioning result of the target object in a stationary state based on the position corresponding to the target grid area.

[0020] In one embodiment, the positioning device further includes a model building module, which is used to acquire background echo signals collected when there are no target objects in the background environment, and after acquiring the distance information and azimuth information of stationary non-target objects in the background environment, perform regionalization processing based on the distance information and the azimuth information to obtain the background signal intensity value corresponding to each region, and construct a regionalized background signal model based on the background signal intensity value corresponding to each region.

[0021] In one embodiment, the model building module includes a coordinate map acquisition unit, an intensity value acquisition unit, and a model building unit. The coordinate map acquisition unit performs rasterization processing on the distance information and the azimuth information to obtain a raster coordinate map including each raster region. The intensity value acquisition unit repeatedly acquires the background signal intensity value corresponding to the first raster region in the raster coordinate map, and uses the average of the acquired background signal intensity values ​​of the first raster region as the background signal intensity value corresponding to the first raster in the background signal model. The model building unit constructs a regionalized background signal model based on the background signal intensity value corresponding to each raster.

[0022] In one embodiment, the positioning device further includes a model update module. The model update module is used to acquire the current background signal intensity value of each region when there is no target object in the target environment, or when a slightly moving non-target object remains stationary for a preset second time, and to update the background signal model based on the current background signal intensity value of each region.

[0023] In one embodiment, the model update module performs a weighted summation of the current background signal intensity value corresponding to each region with the corresponding background signal intensity value in the background signal model to obtain the updated background signal intensity value for each region, and updates the background signal model based on the updated background signal intensity value for each region.

[0024] A computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program performing the following steps:

[0025] Acquire target echo signals collected in the target environment;

[0026] If it is determined from the target echo signal that a target object in motion exists in the target environment, then the target object is identified;

[0027] When the target object is identified to change from a moving state to a stationary state, a stationary target detection is performed on the current target echo signal in the target environment based on a regionalized background signal model to obtain the positioning result of the target object in the stationary state; the background signal model is pre-established based on the background echo signal collected when there is no target object in the target environment.

[0028] In one embodiment, when the processor performs the step of: if it is determined from the target echo signal that there is a target object in motion in the target environment, then when identifying the target object, the steps include: acquiring target echo signals of multiple adjacent frames; identifying the position change of the target object in motion based on the target echo signal whose speed change is greater than a speed change threshold within a preset period; the method further includes: if the identified position change is less than a position change threshold within a first preset time period, then determining that the target object has changed from a motion state to a stationary state.

[0029] In one embodiment, when the processor executes the step: when it identifies that the target object has changed from a moving state to a stationary state, it performs stationary target detection on the current target echo signal in the target environment based on a regionalized background signal model to obtain the positioning result of the target object in the stationary state, the step includes: acquiring the background signal intensity value of the background echo signal corresponding to each region in the background signal model; and performing stationary target detection on the target signal intensity value corresponding to the current target echo signal based on the background signal intensity value to obtain the positioning information of the target object in the stationary state.

[0030] In one embodiment, the background signal model includes background signal intensity values ​​corresponding to each grid region. When the processor executes the step: based on the background signal intensity values, performs stationary target detection on the target signal intensity values ​​corresponding to the current target echo signal to obtain the positioning information of the target object in a stationary state, the process includes: comparing the target signal intensity values ​​corresponding to the current target echo signal in each grid region with the background signal intensity values ​​of the background echo signal corresponding to each grid region to obtain the signal intensity difference between each grid region; if the signal intensity difference between the target grid regions reaches a preset difference, then the positioning result of the target object in a stationary state is determined based on the position of the target grid region.

[0031] In one embodiment, before executing the step: if the signal strength difference corresponding to the target grid region reaches a preset difference, then determine the positioning result of the target object in a stationary state based on the position of the target grid region, the processor further executes the following steps: obtaining the fluctuation range corresponding to the target grid region based on the difference between the maximum and minimum values ​​among multiple background signal strength values ​​of the target grid region; and obtaining the preset difference corresponding to the target grid based on the fluctuation range corresponding to the target grid in the background signal model.

[0032] In one embodiment, when the processor executes the step: if the signal strength difference corresponding to the target grid area reaches a preset difference, then determining the positioning result of the target object in a stationary state based on the position of the target grid area, the steps include: acquiring information about the grid area where the target object is located when it is stationary; taking the grid area whose distance from the grid area where the target object is located when it is stationary as the target grid area as the target grid area; and determining the positioning result of the target object in a stationary state based on the position corresponding to the target grid area.

[0033] In one embodiment, the processor performs a background signal model establishment step, which includes the following steps: acquiring background echo signals collected when there are no target objects in the background environment; acquiring distance information and azimuth information of stationary non-target objects in the background environment; performing regionalization processing based on the distance information and the azimuth information to obtain the background signal intensity value corresponding to each region; and constructing a regionalized background signal model based on the background signal intensity value corresponding to each region.

[0034] In one embodiment, when the processor performs the step of: performing regionalization processing based on the distance information and the azimuth information to obtain the background signal intensity value corresponding to each region, and constructing a regionalized background signal model based on the background signal intensity value corresponding to each region, the process includes: performing rasterization processing on the distance information and the azimuth information to obtain a raster coordinate map including each raster region; repeatedly obtaining the background signal intensity value corresponding to the first raster region in the raster coordinate map; taking the average value of the background signal intensity value of the first raster region obtained each time as the background signal intensity value corresponding to the first raster in the background signal model; and constructing a regionalized background signal model based on the background signal intensity value corresponding to each raster.

[0035] In one embodiment, the processor further performs the following steps: when there is no target object in the target environment, or when a slightly moving non-target object remains stationary for a preset second duration, the processor acquires the current background signal intensity value corresponding to each region; and updates the background signal model based on the current background signal intensity value corresponding to each region.

[0036] In one embodiment, when the processor updates the background signal model based on the current background signal intensity value corresponding to each region, the process includes: performing a weighted summation process on the current background signal intensity value corresponding to each region and the corresponding background signal intensity value in the background signal model to obtain the updated background signal intensity value for each region; and updating the background signal model based on the updated background signal intensity value for each region. A computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0037] Acquire target echo signals collected in the target environment;

[0038] If it is determined from the target echo signal that a target object in motion exists in the target environment, then the target object is identified;

[0039] When the target object is identified to change from a moving state to a stationary state, a stationary target detection is performed on the current target echo signal in the target environment based on a regionalized background signal model to obtain the positioning result of the target object in the stationary state; the background signal model is pre-established based on the background echo signal collected when there is no target object in the target environment.

[0040] In one embodiment, the computer program is executed by a processor in the following steps: if it is determined from the target echo signal that a target object in motion exists in the target environment, then when identifying the target object, the steps include: acquiring target echo signals from multiple adjacent frames; identifying the position change of the target object in motion based on the target echo signal whose velocity change is greater than a velocity change threshold within a preset period; the method further includes: if the identified position change is less than a position change threshold within a first preset time period, then determining that the target object has changed from a motion state to a stationary state.

[0041] In one embodiment, the computer program is executed by a processor to implement the following steps: when the target object is identified to change from a moving state to a stationary state, stationary target detection is performed on the current target echo signal in the target environment based on a regionalized background signal model to obtain the positioning result of the target object in the stationary state, including: acquiring the background signal intensity value of the background echo signal corresponding to each region in the background signal model; and performing stationary target detection on the target signal intensity value corresponding to the current target echo signal based on the background signal intensity value to obtain the positioning information of the target object in the stationary state.

[0042] In one embodiment, the background signal model includes background signal intensity values ​​corresponding to each grid region. The computer program, executed by a processor, implements the following steps: based on the background signal intensity values, performing stationary target detection on the target signal intensity values ​​corresponding to the current target echo signal to obtain the positioning information of the target object in a stationary state, including: comparing the target signal intensity values ​​corresponding to the current target echo signal of each grid region with the background signal intensity values ​​of the background echo signal corresponding to each grid region to obtain the signal intensity difference corresponding to each grid region; if the signal intensity difference corresponding to the target grid region reaches a preset difference, then determining the positioning result of the target object in a stationary state based on the position of the target grid region.

[0043] In one embodiment, the computer program is executed by the processor to implement the following steps: if the signal strength difference corresponding to the target grid area reaches a preset difference, before determining the positioning result of the target object in a stationary state based on the position of the target grid area, the processor further executes the following steps: based on the difference between the maximum and minimum values ​​among the multiple background signal strength values ​​of the target grid area, the fluctuation range corresponding to the target grid area is obtained; based on the fluctuation range corresponding to the target grid in the background signal model, the preset difference value corresponding to the target grid is obtained.

[0044] In one embodiment, the computer program is executed by a processor to implement the following steps: if the signal strength difference corresponding to the target grid area reaches a preset difference, then when determining the positioning result of the target object in a stationary state based on the position of the target grid area, the steps include: obtaining information about the grid area where the target object is located when it is stationary; taking the grid area whose distance from the grid area where the target object is located when it is stationary as the target grid area as the target grid area; and determining the positioning result of the target object in a stationary state based on the position corresponding to the target grid area.

[0045] In one embodiment, the computer program is executed by a processor to implement the background signal model establishment step, including the following steps: acquiring background echo signals collected when there are no target objects in the background environment; acquiring distance information and azimuth information of stationary non-target objects in the background environment; performing regionalization processing based on the distance information and the azimuth information to obtain the background signal intensity value corresponding to each region; and constructing a regionalized background signal model based on the background signal intensity value corresponding to each region.

[0046] In one embodiment, the computer program is executed by a processor to implement the following steps: performing regionalization processing based on the distance information and the azimuth information to obtain the background signal intensity value corresponding to each region, and constructing a regionalized background signal model based on the background signal intensity value corresponding to each region, including: performing rasterization processing on the distance information and the azimuth information to obtain a raster coordinate map including each raster region; repeatedly obtaining the background signal intensity value corresponding to the first raster region in the raster coordinate map; taking the average of the background signal intensity values ​​of the first raster region obtained each time as the background signal intensity value corresponding to the first raster in the background signal model; and constructing a regionalized background signal model based on the background signal intensity value corresponding to each raster.

[0047] In one embodiment, the computer program executed by the processor further performs the following steps: when there is no target object in the target environment, or when a slightly moving non-target object remains stationary for a preset second duration, the background signal intensity value corresponding to each region is obtained; and the background signal model is updated according to the background signal intensity value corresponding to each region.

[0048] In one embodiment, the computer program is executed by a processor to implement the following steps: updating the background signal model based on the current background signal intensity value corresponding to each region, including: performing a weighted summation process on the current background signal intensity value corresponding to each region and the corresponding background signal intensity value in the background signal model to obtain the updated background signal intensity value for each region; and updating the background signal model based on the updated background signal intensity value for each region. The above-described positioning method, apparatus, computer equipment, and storage medium acquire target echo signals collected in a target environment. If the target echo signals determine that a target object exists in motion in the target environment, the target object is identified. When the target object is identified to change from motion to stillness, a stationary target detection is performed on the current target echo signals in the target environment based on the regionalized background signal model to obtain the positioning result of the target object in a stationary state. Therefore, when the positioning method, device, and computer equipment of the present invention identify that the target object changes from a moving state to a stationary state, they perform stationary target detection on the current target echo signal in the target environment based on a regionalized background signal model to obtain the positioning result of the target object in a stationary state. This can accurately achieve the positioning result of the target object in a stationary state (e.g., the positioning result of a human body in a stationary state) with high accuracy. Attached Figure Description

[0049] Figure 1 This is a diagram illustrating the application environment of the positioning method in one embodiment;

[0050] Figure 2 This is a flowchart illustrating the positioning method in one embodiment;

[0051] Figure 3 This is a schematic diagram of a distance-azimuth map in one embodiment;

[0052] Figure 4 This is a schematic diagram of a raster coordinate graph in one embodiment;

[0053] Figure 5 This is a flowchart illustrating the positioning method in another embodiment;

[0054] Figure 6 This is a structural block diagram of the positioning device in one embodiment;

[0055] Figure 7 This is a structural block diagram of the positioning device in another embodiment;

[0056] Figure 8 This is an internal structural diagram of a computer device in one embodiment;

[0057] Figure 9 This is a diagram of the internal structure of a computer device in another embodiment. Detailed Implementation

[0058] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0059] Figure 1 For an application environment diagram of the localization method in one embodiment, please refer to [link / reference]. Figure 1 The positioning method provided in this application embodiment can be applied to, for example, Figure 1 The IoT system shown includes sensors 10, terminal devices 11, cloud devices 12, gateway devices 13, routers 14, and smart home devices 15.

[0060] Specifically, terminal device 11 can be any smart device with communication and storage functions, such as a smartphone, desktop computer, laptop computer, tablet computer, or other smart communication device with network connectivity. Cloud 12 can be a network access server, database server, cloud server, etc. Optionally, gateway device 13 can be built based on the ZigBee protocol, and smart home device 15 can be controlled by sensor 10, terminal device 11, or cloud 12. It can also be pre-installed with gateway device 13. For example, smart home device 15 can be a device in the kit to which gateway device 13 belongs when it leaves the factory; or it can be a device that is subsequently connected to gateway device 13 through user operation.

[0061] Optionally, the terminal device 11 is equipped with a client that can manage the smart home device 15. The client can be an application client (such as a mobile phone APP) or a web client, which is not limited here.

[0062] Optionally, sensor 10 can establish a network connection with gateway device 13 based on the ZigBee protocol, thereby joining the ZigBee network.

[0063] Optionally, sensor 10, terminal device 11, and smart home device 15 can all be connected to the Ethernet via gateway device 13. Gateway device 13 can connect to cloud 12 via wired or wireless communication. For example, gateway device 13 and terminal device 11 can store the acquired information in cloud 12. Optionally, terminal device 11 can also establish a network connection with cloud 12 via 2G / 3G / 4G / 5G, WiFi, etc., thereby obtaining data sent from cloud 12.

[0064] Optionally, the terminal device 11, gateway device 13, and sensor 10 can be in the same local area network (LAN) or in the same wide area network (WAN) as the cloud 12. When the terminal device 11 and gateway device 13 are in the same LAN, the terminal device 11 can interact with the gateway device 13 and the sensor 10 connected to it via the LAN or WAN. When the terminal device 11 and gateway device 13 are not in the same LAN, the terminal device 11 can interact with the gateway device 13 and the sensor 10 connected to it via the WAN. The smart home device 15 can include, but is not limited to, smart lighting, automatic curtains, air conditioners, and other smart home products.

[0065] Automation refers to the interconnected applications built between gateway device 13 or devices connected to gateway device 13. Automation includes triggering conditions and execution actions. The devices that realize automated scene control include triggering devices and controlled devices (or execution devices), which can communicate with each other through gateway device 13. When the triggering device meets the triggering conditions, gateway device 13 controls the controlled device to execute the corresponding action. The triggering device can be various sensors such as radar sensors, pressure sensors, etc. The controlled device can be various smart home devices 15 such as switches, televisions, sockets, and lights.

[0066] Suppose an IoT system is configured with an automated scene control mechanism: automatically turning on the lights when a human is detected in the target environment. The condition for this scene is the detection of a human in the target environment, and the action performed is for a smart switch to control the light bulb to turn on. Based on this application scenario, a radar sensor can be set as the triggering device, and the smart switch connected to the light fixture can be set as the controlled device. The specific execution principle is as follows: If the automation is executed locally on the gateway via a local area network (LAN), the radar sensor detects a human and reports this event to the gateway. Upon receiving the human detection event, the gateway, based on its stored automation configuration information, finds the corresponding device for the action (in this example, the smart switch) and notifies the smart switch to turn on the lights, thus achieving the automated linkage of automatically turning on the lights when a human is detected in the target environment. If the automation is executed in the cloud via a wide area network (WAN), the radar sensor senses a human and reports this event to the gateway. Upon receiving the human detection event, the gateway reports this event to the cloud. The cloud, based on its stored scene configuration information, finds the corresponding device for the action (in this example, the smart switch) and notifies the smart switch to turn on the lights through the gateway.

[0067] In one embodiment, such as Figure 2 As shown, a positioning method is provided. This embodiment illustrates the application of this method to a sensor. It is understood that this method can also be applied to a terminal device or a server, and can also be applied to a system including at least two of the sensor, terminal device, and server, and can be implemented through the interaction of at least two of the sensor, terminal device, and server. In this embodiment, the method includes the following steps:

[0068] Step S201: Acquire the target echo signal collected in the target environment;

[0069] The target environment refers to the environment in which the target object needs to be located and detected; specifically, it can be a specified environmental space.

[0070] In one embodiment, the target environment may be, but is not limited to, a home environment such as a bedroom, living room, or garage, or an office environment such as an office or meeting room.

[0071] Here, the target echo signal refers to the echo signal reflected back from an object detected by a signal monitoring device in the target environment. In one embodiment, the target echo signal can be acquired, but is not limited to, using millimeter-wave radar.

[0072] Step S202: If it is determined from the target echo signal that there is a target object in motion in the target environment, then the target object is identified;

[0073] The target object refers to the object to be detected, which can be either in motion or at rest. Specifically, the target object can be a human body, an animal, etc. A motion state indicates that the target object is in a dynamically changing state relative to a fixed reference frame. A at rest state indicates that the target object is relatively stationary relative to a fixed reference frame. It can be understood that an at rest state can also include a micro-motion state, i.e., a state with a very small amplitude of motion or a very small relative motion frequency. When the target object is in motion, its relative motion amplitude is greater than a preset amplitude or frequency. If the target object's relative motion amplitude is less than a preset amplitude or frequency, then the target object is determined to be at rest. For example, taking a human body as the target object, a motion state can include running, walking, strolling, or extending an arm; an at rest state can include a continuously standing or lying down position.

[0074] In one embodiment, step S202, if it is determined from the target echo signal that there is a target object in motion in the target environment, then the identification of the target object may include, but is not limited to: acquiring target echo signals of multiple adjacent frames; and identifying the position change of the target object in motion based on the target echo signal whose velocity change is greater than a velocity change threshold within a preset period.

[0075] Specifically, for example, by detecting target echo signals in multiple consecutive frames, signals with zero velocity change within a preset period are removed to obtain target echo signals with greater velocity change within a preset period. This allows the detection of target echo signals corresponding to moving target objects, and then continuous identification is performed based on the position (including orientation) of the target object's target echo signal.

[0076] In one embodiment, the method may further include, but is not limited to, the following: if the detected position change is less than a position change threshold within a first preset time period (i.e., the target object stays at a certain position for more than a preset time period), then the target object is determined to have changed from a moving state to a stationary state.

[0077] Step S203: When the target object is identified to change from a moving state to a stationary state, the target echo signal in the target environment is used to perform stationary target detection based on the regionalized background signal model to obtain the positioning result of the target object in the stationary state.

[0078] The background signal model is pre-established based on the background echo signal collected when there is no target object in the target environment.

[0079] In one embodiment, based on the background signal intensity values ​​of the background echo signals corresponding to each region in the background signal model, stationary target detection is performed on the target signal intensity value corresponding to the current target echo signal to obtain the positioning information of the target object in a stationary state. Specifically, in step S203, when it is identified that the target object changes from a moving state to a stationary state, stationary target detection is performed on the current target echo signal in the target environment based on the regionalized background signal model to obtain the positioning result of the target object in a stationary state, including: obtaining the background signal intensity values ​​of the background echo signals corresponding to each region in the background signal model;

[0080] Based on the background signal strength value, the target signal strength value corresponding to the current target echo signal is used to perform stationary target detection, thereby obtaining the positioning information of the target object in a stationary state.

[0081] In one embodiment, the background signal model includes background signal intensity values ​​corresponding to each grid region. The step of performing stationary target detection based on the background signal intensity values ​​and the target signal intensity values ​​corresponding to the current target echo signal to obtain the positioning information of the target object in a stationary state includes:

[0082] The target signal intensity value corresponding to the current target echo signal of each grid area is compared with the background signal intensity value of the background echo signal corresponding to each grid area to obtain the signal intensity difference corresponding to each grid area.

[0083] If the signal strength difference corresponding to the target grid area reaches a preset difference, the positioning result of the target object in a stationary state is determined based on the position of the target grid area.

[0084] In one embodiment, the step of establishing the background signal model includes:

[0085] Acquire background echo signals when there are no target objects in the background environment;

[0086] Obtain the distance and azimuth information of stationary non-target objects in the background environment;

[0087] Based on the distance information and the azimuth information, regionalization processing is performed to obtain the background signal intensity value corresponding to each region. A regionalized background signal model is then constructed based on the background signal intensity value corresponding to each region.

[0088] In one embodiment, the step of performing regionalization processing based on the distance information and the azimuth information to obtain the background signal intensity value corresponding to each region, and constructing a regionalized background signal model based on the background signal intensity value corresponding to each region, includes:

[0089] The distance information and the azimuth information are rasterized to obtain a raster coordinate map including each raster region;

[0090] The background signal intensity value corresponding to the first grid region in the grid coordinate map is obtained multiple times;

[0091] The average value of the background signal intensity of the first grid region acquired each time is taken as the background signal intensity value corresponding to the first grid in the background signal model.

[0092] A regionalized background signal model is constructed based on the background signal intensity value corresponding to each grid.

[0093] Specifically, such as Figure 3 As shown, a radar, such as a millimeter-wave radar, transmits a frequency-modulated continuous wave (FMCH) signal via a transmitter. This FMCH signal is reflected by stationary non-target objects in the background environment (i.e., the environment in which there are no target objects), resulting in a background echo signal. This background echo signal is received by a receiver and mixed with the FMCH signal through a frequency-modulated continuous wave signal filtering process to obtain a beat signal, i.e., an intermediate frequency (IF) signal. This IF signal is then processed (e.g., Fourier transform processing), and the background echo signal is subjected to processing such as digital beamforming to obtain a radar coordinate map. Specifically, the radar coordinate map can be, for example, a range-azimuth map obtained based on the range and azimuth information of each stationary non-target object point.

[0094] Specifically, if the target environment is a rectangular area with a width of W meters and a length of L meters, a coordinate system is established with the width direction of the target environment as the X-axis and the length direction as the Y-axis. After dividing the rectangular area into multiple grid areas, the distance-orientation map is rasterized to obtain the position of each stationary non-target object point in the XY-axis coordinate system, thereby obtaining a raster coordinate map (please refer to...). Figure 4 , Figure 4 The diagram only shows one grid coordinate point, but the invention is not limited to this. When the target environment is a region of other shapes, such as a circular region, the principle of rasterization transformation is similar to that for a rectangular region, and will not be repeated here.

[0095] In one embodiment, each grid region is the same size and is a square grid region, for example, each 10 cm by 10 cm. In other embodiments, at least one grid region in the grid coordinate graph may also be of other shapes, such as a rectangular grid region, etc., and / or at least two grid regions may be of different sizes.

[0096] Specifically, the background signal intensity value corresponding to each grid area in the grid coordinate diagram is the sum of the background signal intensity values ​​(i.e., energy magnitude) of the background echo signals corresponding to all stationary non-target objects falling within that grid area.

[0097] In one embodiment, to avoid interference from background disturbances and improve the accuracy of the background signal model, the average value of the background signal intensity of the first grid region acquired multiple times is used as the background signal intensity value corresponding to the first grid region in the background signal model. In other embodiments, the median value of the background signal intensity of the first grid region acquired each time can also be used as the background signal intensity value corresponding to the first grid region in the background signal model, etc., and the present invention is not limited thereto. If the background signal intensity value of the nth grid region acquired in the mth time is Image(n, m), and the background signal intensity value of the nth grid region in the grid coordinate diagram has been acquired L times, then the background signal intensity value of the nth grid region can be calculated using the following formula: B(n).

[0098]

[0099] For example, if the background signal intensity value of the first grid region in the grid coordinate diagram is acquired three times, and the background signal intensity value of the first grid region acquired in the first acquisition is represented as Image(1,1), the background signal intensity value of the first grid region acquired in the second acquisition is represented as Image(1,2), and the background signal intensity value of the first grid region acquired in the third acquisition is represented as Image(1,3), then the average of the sums of Image(1,1), Image(1,2), and Image(1,3) can be used as the background signal intensity value corresponding to the first grid region.

[0100] In one embodiment, the method for obtaining the corresponding background signal intensity value for the remaining grid regions in the grid coordinate diagram is the same as the method for obtaining the corresponding background signal intensity value for the first grid region. In other embodiments, the method for obtaining the corresponding background signal intensity value for some grid regions in the remaining grid regions of the grid coordinate diagram is the same as the method for obtaining the corresponding background signal intensity value for the first grid region, and is not limited here.

[0101] The target raster region can be all raster regions in the raster coordinate map, or it can be a portion of the raster coordinate map.

[0102] In one embodiment, if the signal strength difference corresponding to the target grid area reaches a preset difference, the positioning result of the target object in a stationary state is determined based on the position of the target grid area, including:

[0103] Obtain information about the grid region where the target object is located when it is stationary;

[0104] The grid region whose distance from the grid region where the target object is stationary is less than a preset distance is defined as the target grid region.

[0105] Based on the position corresponding to the target grid area, the positioning result of the target object in a stationary state is determined.

[0106] Specifically, if the target object in the target environment is detected to be at a certain location (e.g., the 21st grid region) when it changes from a moving state to a stationary state, then the 21st grid region and multiple surrounding grid regions (e.g., 10 grid regions) can all be considered as target grid regions. The target signal intensity value of each target grid region is then compared with the corresponding background signal intensity value in the background signal model to determine whether a target object exists at the location corresponding to each target grid. This approach adapts to the width of the target object (e.g., a human body), thereby accurately locating the target object while improving data processing efficiency.

[0107] The threshold values ​​for each target grid region can be the same or different. The threshold values ​​for each target grid region can be preset, stored empirical values, or values ​​determined by the fluctuation range of the corresponding background signal intensity value under the background environment.

[0108] In one embodiment, before determining the positioning result of the target object in a stationary state based on the position of the target grid area if the signal strength difference corresponding to the target grid area reaches a preset difference, the method further includes:

[0109] The fluctuation range corresponding to the target grid area is obtained by the difference between the maximum and minimum values ​​among multiple background signal intensity values ​​of the target grid area.

[0110] Based on the fluctuation range of the target grid region in the background signal model, the preset difference corresponding to the target grid is obtained.

[0111] Specifically, if the fluctuation range corresponding to the target grid region is Z(n), the maximum value among multiple background signal intensity values ​​is MaxImage(n, p), and the minimum value among multiple background signal intensity values ​​is MinImage(n, q), then Z(n) = MaxImage(n, p) - MinImage(n, q). Specifically, in one embodiment, it can be determined whether the difference between the target signal intensity value corresponding to at least one target grid region and the corresponding background signal intensity value in the background signal model is greater than a threshold N times. If the difference is greater than the threshold M times out of the N determinations, then it is determined that a target object exists at the location corresponding to this target grid; otherwise, it is determined that a false target object exists.

[0112] In the above positioning method, when the target object is identified to change from a moving state to a stationary state, a stationary target detection is performed on the current target echo signal in the target environment based on a regionalized background signal model to obtain the positioning result of the target object in a stationary state. Therefore, the positioning method, device, and computer equipment of this embodiment achieve positioning through echo signals, which can avoid the information security risks of positioning through image recognition. Moreover, by performing stationary target detection on the current target echo signal in the target environment through a regionalized background signal model to obtain the positioning result of the target object in a stationary state, the positioning of the target object (e.g., a human body in a stationary state) can be accurately achieved with high accuracy.

[0113] Furthermore, in one embodiment, the average value of the background signal intensity of the grid area can be used as the corresponding background signal intensity value, thereby avoiding interference from background disturbances and improving the accuracy of the background signal model; and / or the target grid can be identified based on the position of the grid where the target object changes from a moving state to a stationary state, thereby accurately locating the target object while improving the efficiency of data processing; and / or the threshold corresponding to the target grid can be determined based on the fluctuation range of the background signal intensity value, so as to further improve the accuracy of the determination of the target object (e.g., a human body in a stationary state); and / or in N repeated judgments, if the difference between the target signal intensity value and the corresponding background signal intensity value in the background signal model is greater than the threshold in M ​​judgments, it is finally determined that there is a target object in this target grid area; otherwise, it is determined that there is a false target object, which can further improve the accuracy of the location of the target object (e.g., a human body in a stationary state).

[0114] Figure 5 This is a flowchart illustrating the positioning method in another embodiment. Figure 5 As shown, the positioning method in this embodiment includes the following steps:

[0115] Step S301: Establish a regionalized background signal model;

[0116] Step S302: When there is no target object in the target environment, or the non-target object with slight movement remains stationary for a second preset time, obtain the current background signal intensity value of each region, and update the background signal model according to the current background signal intensity value of each region.

[0117] Step S303: Based on the updated background signal model, perform stationary target detection on the current target echo signal in the target environment to obtain the positioning result of the target object in a stationary state. Specifically, the existence of the target object and / or whether a slightly moving object is stationary can be detected by methods such as coherent accumulation and breathing feature recognition. The coherent accumulation method includes: acquiring the target echo signal of two adjacent frames; if the difference between the target signal intensities corresponding to the target echo signals of two adjacent frames is greater than a set difference, incrementing the count value by 1; if the count value is greater than a pre-designed value, it is determined that the target object exists, or that a slightly moving non-target object is not stationary. The longer the time interval between two adjacent frames, the slower the movement can be detected. For example, when the time difference between two adjacent frames is set to 6 seconds, slower movements such as writing and breathing can be detected. The shorter the time interval between two adjacent frames, the faster the movement can be detected. For example, when the time difference between two adjacent frames is set to 100 milliseconds, faster movements such as walking and waving can be detected. Specifically, the slightly moving non-target object can be a curtain swaying in a breeze, or other non-target objects in a slightly moving state. The background signal model is updated when there is no target object in the target environment, or when the slightly moving non-target object remains stationary for a second preset time. This allows for timely updates to the background signal model when the background environment in the target environment is stable, thereby improving the accuracy of the background signal model and ultimately improving the accuracy of target object localization and detection.

[0118] In one embodiment, updating the background signal model based on the current background signal intensity value corresponding to each region in step S302 includes:

[0119] The current background signal intensity value of each region is weighted and summed with the corresponding background signal intensity value in the background signal model to obtain the updated background signal intensity value of each region.

[0120] The background signal model is updated based on the updated background signal intensity value for each region.

[0121] Specifically, in one embodiment, the updated background signal intensity value of the nth grid in the background signal model can be obtained using the following formula: B(n) k = (1-μ)*B(n) k-1 +μ*Image(n) k .

[0122] Where B(n)k represents the background signal intensity value of the nth grid region in the updated background signal model, u represents the adaptive coefficient, and 0 < μ < 1, B(n)k-1 represents the background signal intensity value in the current background signal model, and Image(n) k This represents the current background signal intensity value corresponding to the nth grid region, which is the real-time background signal intensity value acquired when there is no target object in the target environment, or when a non-target object with slight movement remains stationary for a preset duration. Since this embodiment obtains the updated background signal intensity value by weighted summing the background signal intensity value corresponding to the current background signal model with the currently acquired background signal intensity value, it can smooth changes in the background signal model and filter out abrupt interference.

[0123] Specifically, the specific implementation of steps S301 and S303 in this embodiment can be, but is not limited to, the description in the previous embodiment, and will not be repeated here.

[0124] The positioning method of this embodiment can update the background signal model, thereby adapting to the target environment with changing backgrounds and improving positioning accuracy. Furthermore, in this embodiment, the update process can be limited to updating based on the corresponding background signal intensity value in the background signal model before the update, thus smoothing changes in the background signal model, filtering out abrupt interference, and further improving positioning accuracy.

[0125] It should be understood that, although Figure 2 and Figure 5 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 2 and Figure 5 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0126] In one embodiment, such as Figure 6As shown, a positioning device 60 is provided, including: a signal acquisition module 601, an identification module 602, and a positioning module 603. The signal acquisition module 601 is used to acquire target echo signals collected in a target environment. The identification module 602 is used to identify the target object when it is determined from the target echo signals that a target object in motion exists in the target environment. The positioning module 603 is used to perform stationary target detection on the current target echo signals in the target environment based on a regionalized background signal model when the target object changes from a moving state to a stationary state, thereby obtaining the positioning result of the target object in a stationary state.

[0127] The background signal model is pre-established based on the background echo signal collected when there is no target object in the target environment.

[0128] In another embodiment, such as Figure 7 As shown, a positioning device 70 is provided, including a signal acquisition module 701, an identification module 702, and a positioning module 703. In one embodiment, the identification module 702 is used to acquire target echo signals from multiple adjacent frames, and to identify the positional changes of a moving target object based on target echo signals whose velocity changes are greater than a velocity change threshold within a preset period.

[0129] In one embodiment, the positioning device 70 further includes a state determination module 704. The state determination module 704 is used to determine that the target object has changed from a moving state to a stationary state when the position change is less than a position change threshold within a first preset time period.

[0130] In one embodiment, the positioning module 703 is used to obtain the background signal intensity value of the background echo signal corresponding to each region in the background signal model, and based on the background signal intensity value, to perform stationary target detection on the target signal intensity value corresponding to the current target echo signal, so as to obtain the positioning information of the target object in a stationary state.

[0131] In one embodiment, the background signal model includes background signal intensity values ​​corresponding to each grid region. The positioning module 703 is used to compare the target signal intensity value corresponding to the current target echo signal of each grid region with the background signal intensity value of the background echo signal corresponding to each grid region to obtain the signal intensity difference corresponding to each grid region. When the signal intensity difference corresponding to the target grid region reaches a preset difference, the positioning result of the target object in a stationary state is determined based on the position of the target grid region.

[0132] In one embodiment, the positioning device 70 further includes a difference acquisition module 705. The difference acquisition module 705 is used to acquire the fluctuation range corresponding to the target grid area based on the difference between the maximum and minimum values ​​among multiple background signal intensity values ​​of the acquired target grid area, and to acquire the preset difference value corresponding to the target grid based on the fluctuation range corresponding to the target grid in the background signal model.

[0133] In one embodiment, the positioning module 703 includes a target grid acquisition unit 7031 and a positioning unit 7032. The target grid acquisition unit 7031 acquires information about the grid area where the target object is stationary, and designates grid areas whose distance from the grid area where the target object is stationary is less than a preset distance as the target grid area. The positioning unit 7032 determines the positioning result of the target object in a stationary state based on the position corresponding to the target grid area.

[0134] In one embodiment, the positioning device 70 further includes a model building module 706, which is used to acquire background echo signals collected when there are no target objects in the background environment, and after acquiring the distance information and azimuth information of stationary non-target objects in the background environment, perform regionalization processing based on the distance information and the azimuth information to obtain the background signal intensity value corresponding to each region, and construct a regionalized background signal model based on the background signal intensity value corresponding to each region.

[0135] In one embodiment, the model building module 706 includes a coordinate map acquisition unit 7061, an intensity value acquisition unit 7062, and a model building unit 7063. The coordinate map acquisition unit 7061 is used to rasterize the distance information and the azimuth information to obtain a raster coordinate map including each raster region. The intensity value acquisition unit 7062 is used to repeatedly acquire the background signal intensity value corresponding to the first raster region in the raster coordinate map, and take the average of the background signal intensity values ​​of the first raster region acquired each time as the background signal intensity value corresponding to the first raster in the background signal model. The model building unit 7063 is used to construct a regionalized background signal model based on the background signal intensity value corresponding to each raster.

[0136] In one embodiment, the positioning device 70 further includes a model update module 707. The model update module 707 is used to acquire the current background signal intensity value of each region when there is no target object in the target environment, or when a non-target object with slight movement remains stationary for a preset second time, and update the background signal model according to the current background signal intensity value of each region.

[0137] In one embodiment, the model update module 707 performs a weighted summation process on the current background signal intensity value corresponding to each region and the corresponding background signal intensity value in the background signal model to obtain the updated background signal intensity value for each region, and updates the background signal model based on the updated background signal intensity value for each region.

[0138] For specific limitations regarding the positioning device, please refer to the limitations on the positioning method above, which will not be repeated here. Each module in the aforementioned positioning device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in hardware or independently of the processor in the computer device, or stored in software in the memory of the computer device, so that the processor can call and execute the operations corresponding to each module.

[0139] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 8 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores data used in the positioning method. The network interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a positioning method.

[0140] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 9 As shown, the computer device includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used to communicate with external terminals via a network connection. When the computer program is executed by the processor, it implements a positioning method. The display screen can be an LCD screen or an e-ink display screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0141] Those skilled in the art will understand that Figure 8 and Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0142] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0143] Acquire target echo signals collected in the target environment;

[0144] If it is determined from the target echo signal that a target object in motion exists in the target environment, then the target object is identified;

[0145] When the target object is identified to change from a moving state to a stationary state, a stationary target detection is performed on the current target echo signal in the target environment based on a regionalized background signal model to obtain the positioning result of the target object in the stationary state; the background signal model is pre-established based on the background echo signal collected when there is no target object in the target environment.

[0146] In one embodiment, when the processor performs the step of: if it is determined from the target echo signal that there is a target object in motion in the target environment, then when identifying the target object, the steps include: acquiring target echo signals of multiple adjacent frames; identifying the position change of the target object in motion based on the target echo signal whose speed change is greater than a speed change threshold within a preset period; the method further includes: if the identified position change is less than a position change threshold within a first preset time period, then determining that the target object has changed from a motion state to a stationary state.

[0147] In one embodiment, when the processor executes the step: when it identifies that the target object has changed from a moving state to a stationary state, it performs stationary target detection on the current target echo signal in the target environment based on a regionalized background signal model to obtain the positioning result of the target object in the stationary state, the step includes: acquiring the background signal intensity value of the background echo signal corresponding to each region in the background signal model; and performing stationary target detection on the target signal intensity value corresponding to the current target echo signal based on the background signal intensity value to obtain the positioning information of the target object in the stationary state.

[0148] In one embodiment, the background signal model includes background signal intensity values ​​corresponding to each grid region. When the processor executes the step: based on the background signal intensity values, performs stationary target detection on the target signal intensity values ​​corresponding to the current target echo signal to obtain the positioning information of the target object in a stationary state, the process includes: comparing the target signal intensity values ​​corresponding to the current target echo signal in each grid region with the background signal intensity values ​​of the background echo signal corresponding to each grid region to obtain the signal intensity difference between each grid region; if the signal intensity difference between the target grid regions reaches a preset difference, then the positioning result of the target object in a stationary state is determined based on the position of the target grid region.

[0149] In one embodiment, before executing the step: if the signal strength difference corresponding to the target grid region reaches a preset difference, then determine the positioning result of the target object in a stationary state based on the position of the target grid region, the processor further executes the following steps: obtaining the fluctuation range corresponding to the target grid region based on the difference between the maximum and minimum values ​​among multiple background signal strength values ​​of the target grid region; and obtaining the preset difference corresponding to the target grid based on the fluctuation range corresponding to the target grid in the background signal model.

[0150] In one embodiment, when the processor executes the step: if the signal strength difference corresponding to the target grid area reaches a preset difference, then determining the positioning result of the target object in a stationary state based on the position of the target grid area, the steps include: acquiring information about the grid area where the target object is located when it is stationary; taking the grid area whose distance from the grid area where the target object is located when it is stationary as the target grid area as the target grid area; and determining the positioning result of the target object in a stationary state based on the position corresponding to the target grid area.

[0151] In one embodiment, the processor performs a background signal model establishment step, which includes the following steps: acquiring background echo signals collected when there are no target objects in the background environment; acquiring distance information and azimuth information of stationary non-target objects in the background environment; performing regionalization processing based on the distance information and the azimuth information to obtain the background signal intensity value corresponding to each region; and constructing a regionalized background signal model based on the background signal intensity value corresponding to each region.

[0152] In one embodiment, when the processor performs the step of: performing regionalization processing based on the distance information and the azimuth information to obtain the background signal intensity value corresponding to each region, and constructing a regionalized background signal model based on the background signal intensity value corresponding to each region, the process includes: performing rasterization processing on the distance information and the azimuth information to obtain a raster coordinate map including each raster region; repeatedly obtaining the background signal intensity value corresponding to the first raster region in the raster coordinate map; taking the average value of the background signal intensity value of the first raster region obtained each time as the background signal intensity value corresponding to the first raster in the background signal model; and constructing a regionalized background signal model based on the background signal intensity value corresponding to each raster.

[0153] In one embodiment, the processor further performs the following steps: when there is no target object in the target environment, or when a slightly moving non-target object remains stationary for a preset second duration, the processor acquires the current background signal intensity value corresponding to each region; and updates the background signal model based on the current background signal intensity value corresponding to each region.

[0154] In one embodiment, when the processor updates the background signal model based on the current background signal intensity value corresponding to each region, the process includes: performing a weighted summation of the current background signal intensity value corresponding to each region with the corresponding background signal intensity value in the background signal model to obtain the updated background signal intensity value for each region; and updating the background signal model based on the updated background signal intensity value for each region. Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0155] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0156] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A positioning method, characterized in that, The positioning method includes: Acquire target echo signals collected in the target environment; If it is determined from the target echo signal that a target object in motion exists in the target environment, then the target object is identified; When the target object is identified to change from a moving state to a stationary state, based on the current target echo signal in the target environment and the change of the background echo signal corresponding to the regionalized background signal model, the current target echo signal is used to perform stationary target detection, and the positioning result of the target object in the stationary state is obtained. The background signal model is pre-established based on the background echo signal collected when there is no target object in the target environment, and is updated when conditions are met; the regionalized background signal model includes multiple regions divided based on the distance information and azimuth information of the target environment, and each region corresponds to background signal features determined based on the background echo signal when there is no target object. The static target detection includes: comparing the target signal intensity value of the current target echo signal in each region with the background signal intensity value of the background echo signal in the corresponding region in the background signal model, and determining the positioning result of the target object in a static state based on the comparison result.

2. The positioning method according to claim 1, characterized in that, If the target echo signal indicates the presence of a moving target object in the target environment, then identifying the target object includes: Acquire target echo signals from multiple adjacent frames; Based on the target echo signal whose velocity change is greater than the velocity change threshold within a preset period, the position change of the target object in motion is identified; The method further includes: If the position change is detected to be less than the position change threshold within a first preset time period, then it is determined that the target object has changed from a moving state to a stationary state.

3. The positioning method according to claim 1, characterized in that, The background signal model includes the background signal intensity value corresponding to each grid region; The target signal intensity value of the current target echo signal in each region is compared with the background signal intensity value of the background echo signal in the corresponding region in the background signal model. Based on the comparison result, the positioning result of the target object in a stationary state is determined. include: The target signal intensity value corresponding to the current target echo signal of each grid area is compared with the background signal intensity value of the background echo signal corresponding to each grid area to obtain the signal intensity difference corresponding to each grid area. If the signal strength difference corresponding to the target grid area reaches a preset difference, the positioning result of the target object in a stationary state is determined based on the position of the target grid area.

4. The positioning method according to claim 3, characterized in that, Before determining the positioning result of the target object in a stationary state based on the position of the target grid area if the signal strength difference corresponding to the target grid area reaches a preset difference, the method further includes: The fluctuation range corresponding to the target grid area is obtained by the difference between the maximum and minimum values ​​among multiple background signal intensity values ​​of the target grid area. Based on the fluctuation range of the target grid region in the background signal model, the preset difference corresponding to the target grid region is obtained.

5. The positioning method according to claim 3, characterized in that, If the signal strength difference corresponding to the target grid area reaches a preset difference, the positioning result of the target object in a stationary state is determined based on the position of the target grid area, including: Obtain information about the grid region where the target object is located when it is stationary; The grid region whose distance from the grid region where the target object is stationary is less than a preset distance is defined as the target grid region. Based on the position corresponding to the target grid area, the positioning result of the target object in a stationary state is determined.

6. The positioning method according to any one of claims 1 to 5, characterized in that, The steps for establishing the background signal model include: Acquire background echo signals when there are no target objects in the background environment; Obtain the distance and azimuth information of stationary non-target objects in the background environment; Based on the distance information and the azimuth information, regionalization processing is performed to obtain the background signal intensity value corresponding to each region. A regionalized background signal model is then constructed based on the background signal intensity value corresponding to each region.

7. The positioning method according to claim 6, characterized in that, The process of performing regionalization based on the distance information and the azimuth information to obtain the background signal intensity value corresponding to each region, and constructing a regionalized background signal model based on the background signal intensity value corresponding to each region, includes: The distance information and the azimuth information are rasterized to obtain a raster coordinate map including each raster region; The background signal intensity value corresponding to the first grid region in the grid coordinate map is obtained multiple times; The average value of the background signal intensity of the first grid region acquired each time is taken as the background signal intensity value corresponding to the first grid in the background signal model. A regionalized background signal model is constructed based on the background signal intensity value corresponding to each grid.

8. The positioning method according to claim 6, characterized in that, The positioning method further includes: When there is no target object in the target environment, or when a slightly moving non-target object remains stationary for a preset second duration, the current background signal intensity value of each region is obtained; The background signal model is updated based on the current background signal intensity value of each region.

9. The positioning method according to claim 8, characterized in that, The step of updating the background signal model based on the current background signal intensity value of each region includes: The current background signal intensity value of each region is weighted and summed with the corresponding background signal intensity value in the background signal model to obtain the updated background signal intensity value of each region. The background signal model is updated based on the updated background signal intensity value for each region.

10. A positioning device, characterized in that, The positioning device includes: The signal acquisition module is used to acquire target echo signals collected in the target environment; The identification module is used to identify the target object when it is determined from the target echo signal that the target object is in motion in the target environment; The positioning module is used to perform static target detection on the current target echo signal based on the current target echo signal in the target environment and the change of the background echo signal corresponding to the regionalized background signal model when the target object changes from a moving state to a stationary state, so as to obtain the positioning result of the target object in the stationary state. The background signal model is pre-established based on the background echo signal collected when there is no target object in the target environment, and is updated when conditions are met; the regionalized background signal model includes multiple regions divided based on the distance information and azimuth information of the target environment, and each region corresponds to background signal features determined based on the background echo signal when there is no target object. The positioning module compares the target signal intensity value of the current target echo signal in each region with the background signal intensity value of the background echo signal in the corresponding region in the background signal model, and determines the positioning result of the target object in a stationary state based on the comparison result.

11. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 9.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 9.

Images