Methods, devices, equipment, and storage media for precise personnel positioning at border inspection ladders

Abstract

The application provides a personnel precise positioning method, device and equipment in a border inspection ladder opening and a storage medium. The method comprises the following steps: acquiring a plurality of historical signal strengths of Beidou in a target border inspection ladder opening and video images of each channel in the target border inspection ladder opening; based on the plurality of historical signal strengths, a signal fusion diagram is drawn; based on the video images of each channel, a passing coefficient of each channel is determined; based on the signal fusion diagram, a region where the Beidou signal has no obvious fluctuation is determined as a first region, and a region where the Beidou signal has obvious attenuation is determined as a second region; based on the passing coefficient of each channel and the second region, a third region and a fourth region are determined; and positioning information is provided for a target personnel according to the region where the target personnel is located. The application can accurately provide positioning information for the target personnel, reduce redundant positioning beacons, reduce resource waste and the workload of operation and maintenance personnel.

Description

Technical Field

[0001] This invention relates to the field of electronic digital data processing technology, and in particular to a method, device, equipment and storage medium for precise positioning of personnel in a border inspection ladder. Background Technology

[0002] Existing technologies for locating people at border inspection exits face several pressing technical challenges: First, BeiDou satellite positioning signals are prone to signal attenuation and multipath effects in indoor environments or high-density building areas, leading to a significant decrease in positioning accuracy or even complete failure. Second, while traditional UWB tag positioning solutions can provide relatively accurate indoor positioning, they suffer from inherent drawbacks such as high hardware deployment costs and complex system maintenance. This is especially true in scenarios like border inspection exits, which are typically one or a few narrow passages, making it difficult to achieve positioning using just a few UWB tags. Furthermore, existing technologies generally lack sufficient flexibility and struggle to effectively address the dynamic changes in border inspection exit areas. For example, when unexpected situations arise, such as temporary passage closures or changes in passenger flow direction, existing guidance systems often fail to adapt in a timely manner.

[0003] Therefore, in order to address the problems of BeiDou positioning technology, existing technologies typically consider combining BeiDou positioning with UWB tag positioning to achieve the goal of providing positioning information for people in the stairwell even in areas where BeiDou signals are missing. However, due to the uncertainty of BeiDou signal attenuation, this solution still requires a large number of UWB tags. Although it meets the positioning needs of personnel, there are still a large number of redundant positioning beacons, and a lot of maintenance work is still required. Summary of the Invention

[0004] This invention provides a method, device, equipment, and storage medium for precise positioning of border inspection ladder entrances, which reduces redundant positioning beacons, resource waste, and workload of maintenance personnel while accurately providing positioning information to target personnel.

[0005] In a first aspect, embodiments of the present invention provide a method for precise positioning of personnel at a border inspection ladder, comprising:

[0006] Acquire multiple historical signal strengths of BeiDou navigation in the target border inspection ladder gate, as well as video images of each channel in the target border inspection ladder gate.

[0007] A signal fusion diagram is drawn based on multiple historical signal intensities.

[0008] Based on the video images of each channel, the throughput coefficient of each channel is determined.

[0009] Based on the signal fusion map, the area where the BeiDou signal has no significant fluctuations is identified and denoted as the first area, and the area where the BeiDou signal shows significant attenuation is identified and denoted as the second area.

[0010] Based on the passage coefficient of each channel and the second region, the third and fourth regions are determined; the passage coefficients corresponding to the third and fourth regions are different.

[0011] When the target person is in the first area, location information is provided based on real-time data from the BeiDou signal; when the target person is in the third area, location information is calculated based on multiple historical BeiDou signals and neural network algorithms; when the target person is in the fourth area, location information is calculated based on UWB tags and BeiDou signals.

[0012] In one possible implementation, a signal fusion map is plotted based on multiple historical signal intensities, including:

[0013] Based on multiple historical signal strengths, signal strength maps are plotted at multiple times.

[0014] Based on the signal intensity maps at multiple times, a signal fusion map is calculated using a moving average algorithm.

[0015] In one possible implementation, a signal fusion map is calculated based on signal intensity maps at multiple times using a moving average algorithm, including:

[0016] The weights of the signal strength map at each time step are determined based on the moving average algorithm.

[0017] For each pixel in the signal fusion graph, the sum of the products of the pixel value of the corresponding pixel in the signal strength graph at each time step and the weight of the signal strength graph at each time step is used as the pixel value of the pixel in the signal fusion graph.

[0018] The signal fusion map is drawn based on the pixel value of each pixel in the signal fusion map.

[0019] In one possible implementation, the pass factor for each channel is determined based on the video image of each channel, including:

[0020] The number of people in each channel is determined based on the video images from each channel.

[0021] Based on the number of people in each channel, a passage coefficient for each channel is determined; where, when the number of people in a channel is greater than a first threshold, the passage coefficient for that channel is a first preset parameter; when the number of people in a channel is less than or equal to the first threshold, the passage coefficient for that channel is a second preset parameter.

[0022] In one possible implementation, the third and fourth regions are determined based on the throughput coefficient of each channel and the second region, including:

[0023] Based on the passage coefficient of each channel, the second region is divided. The overlapping part of the channel corresponding to the first preset parameter and the second region is recorded as the third region, and the overlapping part of the channel corresponding to the second preset parameter and the second region is recorded as the fourth region.

[0024] In one possible implementation, based on the signal fusion map, regions where the BeiDou signal shows no significant fluctuations are identified, denoted as the first region, and regions where the BeiDou signal shows significant attenuation are identified, denoted as the second region, including:

[0025] Based on the pixel value of each pixel in the signal fusion image, the region consisting of pixels with pixel values ​​greater than or equal to the third threshold is defined as the first region; the region consisting of pixels with pixel values ​​less than the third threshold is defined as the second region.

[0026] Secondly, embodiments of the present invention provide a device for precise positioning of personnel at a border inspection ladder, comprising:

[0027] The first processing module is used to acquire multiple historical signal strengths of Beidou navigation in the target border inspection ladder gate, as well as video images of each channel in the target border inspection ladder gate.

[0028] The second processing module is used to draw a signal fusion diagram based on multiple historical signal strengths.

[0029] The third processing module is used to determine the throughput coefficient of each channel based on the video image of each channel.

[0030] The fourth processing module is used to determine, based on the signal fusion map, the area where the BeiDou signal has no obvious fluctuations, denoted as the first area, and the area where the BeiDou signal shows obvious attenuation, denoted as the second area.

[0031] The fifth processing module is used to determine the third and fourth regions based on the passage coefficient of each channel and the second region; wherein the passage coefficients corresponding to the third and fourth regions are different.

[0032] The sixth processing module is used to provide location information for the target person based on real-time data of BeiDou signals when the target person is in the first area; to calculate the target person's location information based on multiple historical BeiDou signals and neural network algorithms when the target person is in the third area; and to calculate the target person's location information based on UWB tags and BeiDou signals when the target person is in the fourth area.

[0033] Thirdly, embodiments of the present invention provide an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method described in the first aspect or any possible implementation thereof.

[0034] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in the first aspect or any possible implementation thereof.

[0035] Fifthly, embodiments of the present invention provide a computer program product, including a computer program that, when executed by a processor, implements the method described in the first aspect or any possible implementation thereof.

[0036] In this embodiment of the invention, a signal fusion map drawn using multiple historical signal strengths can deeply fuse historical signal strengths to obtain a relatively accurate signal strength at each location within a similar time period. Based on the signal strength, a first region and a second region are defined. Then, based on the video images of each channel, the passage coefficient of each channel is determined. Based on the passage coefficient of each channel, the second region is further divided into a third region and a fourth region. This fully utilizes the characteristics of pedestrian congestion in the channels, integrates neural network algorithms, and increases the accuracy of neural network algorithm calculations, making the calculation of positioning information in the third region more accurate. This allows for accurate positioning information to be provided to target personnel while reducing the use of positioning beacons, thus reducing resource waste and the workload of maintenance personnel. Attached Figure Description

[0037] Figure 1 This is a flowchart illustrating the implementation of the method for precise personnel positioning at the border inspection ladder provided in this embodiment of the invention.

[0038] Figure 2 This is a schematic diagram of the structure of the precise personnel positioning device in the border inspection ladder provided in an embodiment of the present invention;

[0039] Figure 3 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0040] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0041] See Figure 1 The flowchart illustrating the implementation of the method for precise personnel positioning at border inspection ladders provided in this embodiment of the invention is described in detail below:

[0042] Step 101: Obtain multiple historical signal strengths of BeiDou navigation in the target border inspection ladder gate, as well as video images of each channel in the target border inspection ladder gate.

[0043] For example, video images of each channel in the target border inspection elevator gate can be acquired by any camera within that channel. The multiple historical signal strengths of BeiDou navigation in the target border inspection elevator gate refer to the signal strength of BeiDou navigation at each location within the target border inspection elevator gate over a historical period.

[0044] Step 102: Draw a signal fusion diagram based on multiple historical signal intensities.

[0045] In one possible implementation, step 102 may include:

[0046] Based on multiple historical signal strengths, signal strength maps are plotted at multiple times.

[0047] Based on the signal intensity maps at multiple times, a signal fusion map is calculated using a moving average algorithm.

[0048] In one possible implementation, a signal fusion map is calculated based on signal intensity maps at multiple times using a moving average algorithm, which may include:

[0049] The weights of the signal strength map at each time step are determined based on the moving average algorithm.

[0050] For each pixel in the signal fusion graph, the sum of the products of the pixel value of the corresponding pixel in the signal strength graph at each time step and the weight of the signal strength graph at each time step is used as the pixel value of the pixel in the signal fusion graph.

[0051] The signal fusion map is drawn based on the pixel value of each pixel in the signal fusion map.

[0052] For example, although BeiDou satellite positioning is prone to problems such as signal attenuation and multipath effects, the areas affected by these problems in a short period of time can be basically determined. Therefore, a signal fusion map can be drawn by using a moving average algorithm. The signal strength at different locations shown in the signal fusion map can be used as a reference for the signal strength in the future.

[0053] Step 103: Determine the throughput coefficient for each channel based on the video image of each channel.

[0054] In one possible implementation, step 103 may include:

[0055] The number of people in each channel is determined based on the video images from each channel.

[0056] Based on the number of people in each channel, a passage coefficient for each channel is determined; where, when the number of people in a channel is greater than a first threshold, the passage coefficient for that channel is a first preset parameter; when the number of people in a channel is less than or equal to the first threshold, the passage coefficient for that channel is a second preset parameter.

[0057] For example, the first threshold can be 20, the first preset parameter can be 1, and the second preset parameter can be 0.5.

[0058] Step 104: Based on the signal fusion map, determine the area where the BeiDou signal has no obvious fluctuations, and record it as the first area; determine the area where the BeiDou signal shows obvious attenuation, and record it as the second area.

[0059] In one possible implementation, step 104 may include:

[0060] Based on the pixel value of each pixel in the signal fusion image, the region consisting of pixels with pixel values ​​greater than or equal to the third threshold is defined as the first region; the region consisting of pixels with pixel values ​​less than the third threshold is defined as the second region.

[0061] For example, since the signal fusion map represents the signal strength, the pixel value of each pixel corresponds to the signal strength. The area composed of pixels with a pixel value greater than or equal to the third threshold (the first area) is a region with strong signal strength, and BeiDou signal navigation can fully meet the requirements in these areas. The area composed of pixels with a pixel value less than the third threshold (the second area) is a region with weak signal strength, and BeiDou signal navigation cannot be used to provide location information for the target personnel.

[0062] Step 105: Based on the passage coefficient of each channel and the second region, determine the third region and the fourth region; wherein the passage coefficients corresponding to the third region and the fourth region are different.

[0063] In one possible implementation, determining the third and fourth regions based on the throughput coefficient of each channel and the second region may include:

[0064] Based on the passage coefficient of each channel, the second region is divided. The overlapping part of the channel corresponding to the first preset parameter and the second region is recorded as the third region, and the overlapping part of the channel corresponding to the second preset parameter and the second region is recorded as the fourth region.

[0065] For example, the second area is divided into a third area and a fourth area using a first preset parameter and a second preset parameter. This facilitates the subsequent determination of different positioning schemes for different areas and the provision of positioning information to personnel. The third area is a densely populated area, and the fourth area is a sparsely populated area.

[0066] Step 106: When the target person is in the first area, location information is provided to the target person based on real-time data of BeiDou signals; when the target person is in the third area, the location information of the target person is calculated based on multiple historical BeiDou signals and neural network algorithms; when the target person is in the fourth area, the location information of the target person is calculated based on UWB tags and BeiDou signals.

[0067] For example, when the target person is in the first area, which is an area with strong BeiDou signal, location information can be provided to the target person based on real-time data of BeiDou signal.

[0068] For example, when the target person is in the third area, it can be assumed that the target person is in a densely populated area. At this time, due to the dense population, the movement of the person will have a regular speed and direction, which is not easy to change. Therefore, multiple movement directions and speeds can be obtained based on the person's multiple historical Beidou signals (before entering the area), and then the movement direction, speed and trajectory in the third area can be predicted by neural network algorithm.

[0069] Specifically, the process of predicting the direction, speed, and trajectory of movement within the third region using neural network algorithms can include:

[0070] 1. Data Preparation

[0071] Collect historical trajectory data (position, speed, orientation angle, timestamp), clean up outliers (such as GPS drift), interpolate to complete missing frames, and smooth the trajectory.

[0072] Feature engineering: Decompose the direction angle into (sinθ, cosθ) to avoid periodic jumps (eliminate the effect of the jump from 359° to 0°); normalize the velocity; extract spatiotemporal features (such as acceleration and relative position).

[0073] 2. Model Building

[0074] Temporal models (LSTM / GRU) are used to capture individual motion patterns, or spatiotemporal fusion models (such as Social-GAN, GNN) are used to model pedestrian / environment interactions.

[0075] Input: The historical sequence of the sliding window (e.g., position + speed + direction in the past 3 seconds).

[0076] Output: Future position (x, y) or velocity + direction combination.

[0077] 3. Training and Optimization

[0078] Loss functions: Mean squared error (MSE) is used for position; cosine similarity loss is used for direction; multi-target loss (such as ADE, FDE) is introduced to evaluate the overall trajectory deviation.

[0079] Interaction modeling: Encodes pedestrian avoidance and following behaviors through graph neural networks (GNNs) or attention mechanisms.

[0080] 4. Trajectory Generation

[0081] Recursive prediction: Using the current prediction result as the input for the next time step, the future trajectory is generated iteratively.

[0082] Multimodal output: Generates multiple possible trajectories (such as GAN generating different intentional paths), and uses probability to represent the likelihood.

[0083] For example, when the target person is in the fourth area, which is a sparsely populated area, there may still be a BeiDou signal due to the sparse population. In this case, it is necessary to determine the target person's location information based on the existing BeiDou signal and the UWB tag set in the fourth area. If the BeiDou signal is still not detected, the location information can be obtained directly through the UWB tag.

[0084] The aforementioned method for precise personnel positioning at border inspection gates utilizes a signal fusion map drawn from multiple historical signal strengths. This deep fusion of historical signal strengths yields a relatively accurate signal strength at each location within a similar timeframe. Based on the signal strength, a first and second region are defined. Then, based on video images from each channel, the passage coefficient for each channel is determined. The second region is further divided into a third and fourth region based on the passage coefficient. This method fully leverages the characteristics of pedestrian congestion in the channels and incorporates neural network algorithms to enhance the accuracy of neural network calculations. This makes the positioning information for the third region more accurate, reducing the use of positioning beacons and minimizing resource waste and maintenance workload while providing accurate positioning information for target personnel.

[0085] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0086] The following are device embodiments of the present invention. For details not described in detail, please refer to the corresponding method embodiments described above.

[0087] Figure 2 A schematic diagram of the personnel precise positioning device in the border inspection ladder gate provided in an embodiment of the present invention is shown. For ease of explanation, only the parts related to the embodiment of the present invention are shown, and are described in detail below:

[0088] like Figure 2 As shown, the precise personnel positioning device in the border inspection ladder entrance includes:

[0089] The first processing module 201 is used to acquire multiple historical signal strengths of Beidou navigation in the target border inspection ladder gate, as well as video images of each channel in the target border inspection ladder gate.

[0090] The second processing module 202 is used to draw a signal fusion diagram based on multiple historical signal strengths.

[0091] The third processing module 203 is used to determine the passage coefficient of each channel based on the video image of each channel.

[0092] The fourth processing module 204 is used to determine, based on the signal fusion map, the area where the BeiDou signal has no obvious fluctuations, denoted as the first area, and the area where the BeiDou signal shows obvious attenuation, denoted as the second area.

[0093] The fifth processing module 205 is used to determine the third region and the fourth region based on the passage coefficient of each channel and the second region; wherein the passage coefficients corresponding to the third region and the fourth region are different.

[0094] The sixth processing module 206 is used to provide location information to the target person based on real-time data of Beidou signals when the target person is in the first area; to calculate the location information of the target person based on multiple historical Beidou signals and neural network algorithms when the target person is in the third area; and to calculate the location information of the target person based on UWB tags and Beidou signals when the target person is in the fourth area.

[0095] In one possible implementation, the second processing module 202 can be used for:

[0096] Based on multiple historical signal strengths, signal strength maps are plotted at multiple times.

[0097] Based on the signal intensity maps at multiple times, a signal fusion map is calculated using a moving average algorithm.

[0098] In one possible implementation, the second processing module 202 can be used for:

[0099] The weights of the signal strength map at each time step are determined based on the moving average algorithm.

[0100] For each pixel in the signal fusion graph, the sum of the products of the pixel value of the corresponding pixel in the signal strength graph at each time step and the weight of the signal strength graph at each time step is used as the pixel value of the pixel in the signal fusion graph.

[0101] The signal fusion map is drawn based on the pixel value of each pixel in the signal fusion map.

[0102] In one possible implementation, the third processing module 203 can be used for:

[0103] The number of people in each channel is determined based on the video images from each channel.

[0104] Based on the number of people in each channel, a passage coefficient for each channel is determined; where, when the number of people in a channel is greater than a first threshold, the passage coefficient for that channel is a first preset parameter; when the number of people in a channel is less than or equal to the first threshold, the passage coefficient for that channel is a second preset parameter.

[0105] In one possible implementation, the fifth processing module 205 can be used for:

[0106] Based on the passage coefficient of each channel, the second region is divided. The overlapping part of the channel corresponding to the first preset parameter and the second region is recorded as the third region, and the overlapping part of the channel corresponding to the second preset parameter and the second region is recorded as the fourth region.

[0107] In one possible implementation, the fourth processing module 204 can be used for:

[0108] Based on the pixel value of each pixel in the signal fusion image, the region consisting of pixels with pixel values ​​greater than or equal to the third threshold is defined as the first region; the region consisting of pixels with pixel values ​​less than the third threshold is defined as the second region.

[0109] Figure 3 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Figure 3 As shown, the electronic device 3 of this embodiment includes a processor 30 and a memory 31. The memory 31 stores a computer program 32. When the processor 30 executes the computer program 32, it implements the steps in the various method embodiments described above. Alternatively, when the processor 30 executes the computer program 32, it implements the functions of each module / unit in the various device embodiments described above.

[0110] For example, computer program 32 may be divided into one or more modules / units, which are stored in memory 31 and executed by processor 30 to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of computer program 32 in electronic device 3.

[0111] Electronic device 3 may include, but is not limited to, processor 30 and memory 31. Those skilled in the art will understand that... Figure 3This is merely an example of electronic device 3 and does not constitute a limitation on electronic device 3. It may include more or fewer components than shown, or combine certain components, or different components. For example, electronic device 3 may also include input / output devices, network access devices, buses, etc.

[0112] The processor 30 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0113] The memory 31 can be an internal storage unit of the electronic device 3, such as a hard disk or memory of the electronic device 3. The memory 31 can also be an external storage device of the electronic device 3, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the electronic device 3. Furthermore, the memory 31 can include both internal and external storage units of the electronic device 3. The memory 31 is used to store the computer program 32 and other programs and data required by the electronic device 3. The memory 31 can also be used to temporarily store data that has been output or will be output.

[0114] For the sake of simplicity and clarity, only the above-described functional modules / units are used as examples. In practical applications, the functions described above can be assigned to different functional modules / units as needed. These modules / units can be implemented in hardware, software, or a combination of both.

[0115] This invention also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the methods described in the above-described method embodiments.

[0116] This invention also provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements the methods described in the above-described method embodiments.

[0117] Computer programs include computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. Computer-readable media can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0118] In the above embodiments, the descriptions of each embodiment have their own emphasis. Parts not detailed or described in a particular embodiment can be referred to in the relevant descriptions of other embodiments. Unless otherwise specified or in conflict with logic, the terminology and / or descriptions between different embodiments are consistent and can be referenced interchangeably. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0119] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A method for accurate positioning of personnel in a border crossing ladder opening, characterized by, The method comprises: obtaining a plurality of historical signal strengths of Beidou navigation in a target border inspection ladder port and video images of each channel in the target border inspection ladder port; based on the plurality of historical signal strengths, drawing a signal fusion graph; based on the video images of each channel, determining a passing coefficient of each channel; based on the signal fusion graph, determining a region where the Beidou signal has no obvious fluctuation, which is recorded as a first region, and a region where the Beidou signal has obvious attenuation, which is recorded as a second region; based on the passing coefficient of each channel and the second region, determining a third region and a fourth region; wherein the passing coefficients corresponding to the third region and the fourth region are different; when the target personnel is in the first region, providing positioning information for the target personnel based on real-time data of the Beidou signal; when the target personnel is in the third region, calculating the positioning information of the target personnel based on a plurality of historical Beidou signals and a neural network algorithm; when the target personnel is in the fourth region, calculating the positioning information of the target personnel based on a UWB tag and a Beidou signal.

2. The method of claim 1, wherein, The method comprises: based on the plurality of historical signal strengths, drawing a plurality of signal strength graphs at different times; based on the plurality of signal strength graphs at different times, calculating a signal fusion graph through a sliding average algorithm.

3. The method of claim 2, wherein, The method comprises: based on the sliding average algorithm, determining the weight of the signal strength graph at each time; for each pixel point in the signal fusion graph, taking the sum of the product of the pixel value of the corresponding pixel point in the signal strength graph at each time and the weight of the signal strength graph at each time as the pixel value of the pixel point in the signal fusion graph; based on the pixel value of each pixel point in the signal fusion graph, drawing the signal fusion graph.

4. The method of claim 1, wherein, The method comprises: based on the video images of each channel, determining the number of people in each channel; based on the number of people in each channel, determining the passing coefficient of each channel; wherein when the number of people in a channel is greater than a first threshold, the passing coefficient corresponding to the channel is a first preset parameter; and when the number of people in a channel is less than or equal to the first threshold, the passing coefficient corresponding to the channel is a second preset parameter.

5. The method of claim 4, wherein, The method comprises: based on the passing coefficient of each channel, dividing the second region, and recording the overlapping part of the channel corresponding to the first preset parameter and the second region as the third region, and recording the overlapping part of the channel corresponding to the second preset parameter and the second region as the fourth region.

6. The method of claim 1, wherein, The method comprises: Based on the pixel value of each pixel point in the signal fusion graph, a region composed of pixel points with pixel values greater than or equal to a third threshold value is defined as a first region; and a region composed of pixel points with pixel values less than the third threshold value is defined as a second region.

7. A personnel precise positioning device in a border inspection ladder opening, characterized in that, Comprise: The first processing module is used for acquiring a plurality of historical signal strengths of Beidou navigation in a target border inspection ladder port and video images of each channel in the target border inspection ladder port; The second processing module is used for drawing a signal fusion graph based on the plurality of historical signal strengths; The third processing module is used for determining a passing coefficient of each channel based on the video images of each channel; The fourth processing module is used for determining a region with no obvious fluctuation of Beidou signal as a first region and a region with obvious attenuation of Beidou signal as a second region based on the signal fusion graph; The fifth processing module is used for determining a third region and a fourth region based on the passing coefficient of each channel and the second region; wherein the third region and the fourth region correspond to different passing coefficients; The sixth processing module is used for providing positioning information for a target person based on real-time data of Beidou signal when the target person is in the first region, calculating the positioning information of the target person based on a plurality of historical Beidou signals and a neural network algorithm when the target person is in the third region, and calculating the positioning information of the target person based on a UWB tag and Beidou signal when the target person is in the fourth region.

8. An electronic device, comprising: The computer readable storage medium stores a computer program, and the processor executes the computer program to realize the method in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, and the processor executes the computer program to realize the method in any one of claims 1 to 6.

10. A computer program product, characterised in that, The computer readable storage medium stores a computer program, and the processor executes the computer program to realize the method in any one of claims 1 to 6.

Images