Geomagnetic detection method and system for parking space vehicle

Abstract

The invention relates to the technical field of data processing, in particular to a geomagnetic detection method and system for a parking space vehicle, and the method comprises the steps: obtaining a geomagnetic signal component obtained through the decomposition of a geomagnetic signal of each parking space in a parking lot, and obtaining a geomagnetic signal component of a main parking space according to the comparison condition of all geomagnetic signal components corresponding to the main parking space; the method comprises the following steps: determining a magnetic field disturbance influence factor caused by vehicle state change on a parking space adjacent to a main parking space, thereby determining the action degree of each geomagnetic signal component corresponding to the main parking space on parking space state judgment, then determining a reconstruction weight of each geomagnetic signal component corresponding to the main parking space, carrying out weighted reconstruction on all the geomagnetic signal components of the main parking space, and obtaining a reconstruction result; and the updated geomagnetic signal is used for determining the state of the vehicle in the parking space. According to the method, the updated geomagnetic signal is obtained through weighted reconstruction, so that the interference of magnetic field disturbance caused by the state change of the vehicle on the adjacent parking space is reduced, and the accuracy of geomagnetic detection of the vehicle on the parking space is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly relates to a geomagnetic detection method and system for vehicles in parking spaces. Background Art

[0002] Outdoor parking space detection mostly uses geomagnetic detection technology. The core principle of geomagnetic detection is that vehicles disturb the Earth's magnetic field, and geomagnetic sensors determine whether a vehicle is parked in a parking space by detecting this disturbance. Specifically, when a vehicle drives into or parks in a parking space, its metal structure changes the intensity of the local geomagnetic field, and the geomagnetic sensor can capture this change.

[0003] Existing problems: Since geomagnetic sensors are highly sensitive to magnetic fields when detecting vehicles, in a parking lot with dense vehicles or a roadside parking area where the distances between multiple parking spaces are relatively close, the driving in or out of a vehicle in one parking space will cause significant magnetic field disturbances to the geomagnetic sensors in adjacent parking spaces. Due to the existence of magnetic field interference, the geomagnetic sensor may misinterpret the magnetic field change in the adjacent parking space as the vehicle state in the current parking space, resulting in false detection. Summary of the Invention

[0004] The present invention provides a geomagnetic detection method and system for vehicles in parking spaces to solve the existing problems.

[0005] The geomagnetic detection method and system for vehicles in parking spaces of the present invention adopt the following technical solutions: An embodiment of the present invention provides a geomagnetic detection method for vehicles in parking spaces, and the method includes the following steps: Obtain the geomagnetic signals, geomagnetic background values of each parking space in the parking lot, and the distances between parking spaces; the horizontal axis of the geomagnetic signal is time, and the vertical axis is the geomagnetic field intensity; Decompose the geomagnetic signal of each parking space into several geomagnetic signal components; designate any one parking space as the main parking space; determine the magnetic field disturbance influence factor caused by the change in the vehicle state on the adjacent parking spaces of the main parking space according to the comparison of all the geomagnetic signal components corresponding to the main parking space; Determine the influence degree of each geomagnetic signal component corresponding to the main parking space on the judgment of the parking space state according to the similarity between all the geomagnetic signal components corresponding to the main parking space and the adjacent parking spaces and the distances between the parking spaces, in combination with the magnetic field disturbance influence factor caused by the change in the vehicle state on the adjacent parking spaces of the main parking space; Determine the reconstruction weight of each geomagnetic signal component corresponding to the main parking space according to the magnitude of the influence degree of each geomagnetic signal component corresponding to the main parking space on the judgment of the parking space state; for the main parking space, perform weighted reconstruction on all the geomagnetic signal components according to the reconstruction weight of each geomagnetic signal component to obtain an updated geomagnetic signal; determine the state of the vehicle in the parking space according to the difference between the updated geomagnetic signal and the geomagnetic background value.

[0006] Further, the steps for determining the magnetic field disturbance influence factor caused by the change in the vehicle state on the adjacent parking space of the main parking space are as follows: Preset a window length H. In any geomagnetic signal component, with any moment as the center, form a window with a duration of H, and obtain the normalized value of the variance of the geomagnetic field intensity at all moments within the window as the high-frequency disturbance value at any moment. Mark the moments with high-frequency disturbance values greater than the preset disturbance threshold as high-frequency disturbance moments, and mark the moments with high-frequency disturbance values less than or equal to the preset disturbance threshold as low-frequency stable moments. Assign a label of 1 to the high-frequency disturbance moments and a label of 0 to the low-frequency stable moments, and form a 01 sequence in chronological order; In the 01 sequences corresponding to all geomagnetic signal components of the main parking space, obtain the number of 1s at the same moment, and the component set composed of all geomagnetic signal components corresponding to all 1s at the same moment. In chronological order, form a quantity sequence with the number of 1s at all moments; According to the component sets at all moments corresponding to each non-zero quantity value in the quantity sequence, determine the complexity of the component types for each non-zero quantity value; According to the number of occurrences of non-zero quantity values in the quantity sequence and the complexity of the component types for each non-zero quantity value, determine the magnetic field disturbance influence factor caused by the change in the vehicle state on the adjacent parking space of the main parking space.

[0007] Further, the steps for determining the complexity of the component types for each non-zero quantity value according to the component sets at all moments corresponding to each non-zero quantity value in the quantity sequence are as follows: In the component set at all moments corresponding to the i-th non-zero quantity value in the quantity sequence, count the number of types of different geomagnetic signal components , then count the number of each geomagnetic signal component, and take the maximum value and the minimum value ; Obtain the inverse normalized value of the maximum value , denoted as the first quantization value, obtain the normalized value of the minimum value , denoted as the second quantization value, obtain the difference between the number of types minus the i-th non-zero quantity value, denoted as the first difference. The normalized value of the product of the mean of the first quantization value and the second quantization value and the first difference is denoted as the complexity of the component types for the i-th non-zero quantity value in the quantity sequence.

[0008] Further, the steps for determining the magnetic field disturbance influence factor caused by the change in the vehicle state on the adjacent parking space of the main parking space according to the number of occurrences of non-zero quantity values in the quantity sequence and the complexity of the component types for each non-zero quantity value are as follows: Obtain the ratio of the number of occurrences of all non-zero quantity values in the quantity sequence to the length of the quantity sequence, denoted as the first ratio. Obtain the ratio of the number of occurrences of the i-th non-zero quantity value in the quantity sequence to the length of the quantity sequence, denoted as the second ratio. Denote the product of the component type complexity of the i-th non-zero quantity value in the quantity sequence, the i-th non-zero quantity value, and the second ratio as the first product of the i-th non-zero quantity value in the quantity sequence. Obtain the product of the sum value of the first products of all non-zero quantity values in the quantity sequence and the first ratio, denoted as the magnetic field disturbance influence factor caused by the vehicle state change on the adjacent parking spaces of the main parking space.

[0009] Furthermore, the specific steps for determining the influence degree of each geomagnetic signal component corresponding to the main parking space on the parking space state judgment are as follows: Preset a parking space quantity threshold M, and obtain the first M parking spaces closest to the main parking space, all denoted as adjacent parking spaces; Among all the geomagnetic signal components of the main parking space and all adjacent parking spaces, use the inverse value of the Pearson correlation coefficient between any two geomagnetic signal components as the clustering distance to cluster all the geomagnetic signal components, and obtain several clustering clusters; Obtain the energy value of each geomagnetic signal component at different frequencies, and use the sum value of the energy values at all frequencies as the total energy value of each geomagnetic signal component; In the x-th clustering cluster, obtain the parking space corresponding to the geomagnetic signal component with the largest total energy value, denoted as the generating parking space of the x-th clustering cluster. Determine the credibility of the generating parking space of the x-th clustering cluster according to the magnitude of the total energy value of the geomagnetic signal component and the distance between the parking space corresponding to the geomagnetic signal component and the generating parking space of the x-th clustering cluster; Determine the influence degree of the j-th geomagnetic signal component corresponding to the main parking space on the parking space state judgment according to the credibility of the generating parking space of the clustering cluster where the j-th geomagnetic signal component is located, the total energy value of the j-th geomagnetic signal component, and the magnetic field disturbance influence factor caused by the vehicle state change on the adjacent parking spaces of the main parking space.

[0010] Furthermore, the specific steps for determining the credibility of the generating parking space of the x-th clustering cluster according to the magnitude of the total energy value of the geomagnetic signal component and the distance between the parking space corresponding to the geomagnetic signal component and the generating parking space of the x-th clustering cluster are as follows: In the x-th clustering cluster, arrange the total energy values of all geomagnetic signal components from large to small to obtain a total energy value sequence. In the total energy value sequence, obtain the distance between the parking space corresponding to each total energy value and the generating parking space of the x-th clustering cluster, and obtain a distance sequence; Obtain the inverse value of the Pearson correlation coefficient between the total energy value sequence and the distance sequence of the x-th clustering cluster, and then obtain the average value of the Pearson correlation coefficients between any two geomagnetic signal components in the x-th clustering cluster. Denote the normalized value of the product of the inverse value and the average value as the credibility of the generated parking space in the x-th clustering cluster.

[0011] Further, determining the influence degree of the j-th geomagnetic signal component on the parking space state judgment according to the credibility of the generated parking space in the clustering cluster where the j-th geomagnetic signal component corresponding to the main parking space is located, the total energy value of the j-th geomagnetic signal component, and the magnetic field disturbance influence factor caused by the vehicle state change on the adjacent parking spaces of the main parking space includes the following specific steps: For the j-th geomagnetic signal component corresponding to the main parking space, obtain the normalized value of the product of the credibility of the generated parking space in the clustering cluster where the j-th geomagnetic signal component is located and the total energy value of the j-th geomagnetic signal component, and denote it as the first normalized value. Denote the normalized value of the product of the first normalized value and the magnetic field disturbance influence factor caused by the vehicle state change on the adjacent parking spaces of the main parking space as the parking space state judgment adjustment coefficient; If the generated parking space in the clustering cluster where the j-th geomagnetic signal component corresponding to the main parking space is located is the main parking space, denote the sum value of the preset constant and the parking space state judgment adjustment coefficient as the influence degree of the j-th geomagnetic signal component on the parking space state judgment; If the generated parking space in the clustering cluster where the j-th geomagnetic signal component corresponding to the main parking space is located is not the main parking space, denote the difference value of the preset constant minus the parking space state judgment adjustment coefficient as the influence degree of the j-th geomagnetic signal component on the parking space state judgment.

[0012] Further, determining the reconstruction weight of each geomagnetic signal component corresponding to the main parking space includes the following specific steps: Obtain the sum value of the influence degrees of all geomagnetic signal components corresponding to the main parking space on the parking space state judgment, and denote the ratio of the influence degree of the j-th geomagnetic signal component corresponding to the main parking space on the parking space state judgment to the sum value as the reconstruction weight of the j-th geomagnetic signal component corresponding to the main parking space.

[0013] Further, determining the state of the vehicle in the parking space according to the difference between the updated geomagnetic signal and the geomagnetic background value includes the following specific steps: When the difference between the geomagnetic field intensity at the current moment in the updated geomagnetic signal of the main parking space and the geomagnetic background value of the main parking space is greater than the preset state judgment threshold, it is determined that the state of the main parking space at the current moment is the occupied state; When the difference between the geomagnetic field intensity at the current moment in the updated geomagnetic signal of the main parking space and the geomagnetic background value of the main parking space is less than or equal to the preset state judgment threshold, it is determined that the state of the main parking space at the current moment is the vacant state.

[0014] The present invention also provides a geomagnetic detection system for vehicles in parking spaces, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor. The processor executes the computer program stored in the memory to implement the steps of the aforementioned geomagnetic detection method for vehicles in parking spaces.

[0015] The beneficial effects of the technical solution of the present invention are as follows: In the embodiment of the present invention, the geomagnetic signals of each parking space in the parking lot are obtained, and each geomagnetic signal is decomposed into several geomagnetic signal components. Any one parking space is designated as the main parking space. According to the comparison of all the geomagnetic signal components corresponding to the main parking space, the magnetic field disturbance influence factor caused by the change in the vehicle state on the adjacent parking space of the main parking space is determined. Thus, the magnitude of the magnetic field disturbance caused by the change in the vehicle state on the adjacent parking space existing in the geomagnetic signal of the main parking space is determined, which is used to ensure the subsequent effect of reducing the interference of adjacent parking spaces. Then, by combining the similarity between all the geomagnetic signal components corresponding to the main parking space and the adjacent parking space and the distance between the parking spaces, the degree of influence of each geomagnetic signal component corresponding to the main parking space on the judgment of the parking space state is determined, and thus the reconstruction weight of each geomagnetic signal component corresponding to the main parking space is determined. The weighted reconstruction of all the geomagnetic signal components of the main parking space is performed to obtain an updated geomagnetic signal. Thus, a larger reconstruction weight is assigned to the geomagnetic signal component corresponding to the magnetic field disturbance caused by the change in the vehicle state on the main parking space, and a smaller reconstruction weight is assigned to the geomagnetic signal component corresponding to the magnetic field disturbance caused by the change in the vehicle state on the adjacent parking space, which is used to reduce the interference of the magnetic field disturbance caused by the change in the vehicle state on the adjacent parking space and highlight the magnetic field disturbance information caused by the change in the vehicle state on the main parking space, so as to obtain the accurate state of the vehicle in the parking space. So far, the present invention obtains an updated geomagnetic signal through weighted reconstruction to reduce the interference of the magnetic field disturbance caused by the change in the vehicle state on the adjacent parking space and ensure the accuracy rate of the geomagnetic detection of the vehicle in the parking space. Description of the Drawings

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0017] Figure 1 It is a flowchart of the steps of a geomagnetic detection method for vehicles in a parking space according to the present invention; Figure 2 It is a schematic diagram of a geomagnetic sensor installed at each parking space; Figure 3 It is a schematic diagram of the 01 sequence corresponding to all the geomagnetic signal components of the main parking space. Detailed implementation manners

[0018] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following combines the accompanying drawings and preferred embodiments to detail the specific implementation manners, structures, features and effects of a geomagnetic detection method and system for vehicles in a parking space according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs.

[0020] The following specifically describes the specific scheme of a geomagnetic detection method and system for vehicles in a parking space provided by the present invention with reference to the accompanying drawings.

[0021] Please refer to Figure 1 , which shows a flowchart of the steps of a geomagnetic detection method for vehicles in a parking space provided by an embodiment of the present invention. The method includes the following steps: Step S001: Obtain the geomagnetic signals, geomagnetic background values of each parking space in the parking lot, and the distances between the parking spaces; the horizontal axis of the geomagnetic signal is time, and the vertical axis is the geomagnetic field strength.

[0022] In any parking lot, a geomagnetic sensor is used to collect the geomagnetic signals at each parking space in real time. The horizontal axis of the geomagnetic signal is time, and the vertical axis is the geomagnetic field strength. The collection frequency is 1 hertz (Hz), and the collection duration is the most recent 5 minutes before the current moment. This is used as an example for description. And the position coordinates of the geomagnetic sensor at each parking space are obtained through GPS (Global Positioning System), and the distances between the position coordinates of the geomagnetic sensors at the parking spaces are used as the distances between the parking spaces.

[0023] It should be noted that when there is no vehicle in the parking space, the geomagnetic sensor will record a reference value, that is, the geomagnetic background value. This geomagnetic background value represents the intensity of the earth's magnetic field when there is no vehicle. In this embodiment, the reference value of each parking space when there is no vehicle will be continuously obtained and updated, so as to adapt to environmental changes and improve the accuracy of detection. When a vehicle enters or exits the parking space, its metal structure will disturb the earth's magnetic field, resulting in a change in the magnetic field intensity detected by the geomagnetic sensor. The geomagnetic sensor converts the detected magnetic field change into an electrical signal and sends it to the main controller or communication module, and then uploads it to the backend management platform through the wireless network. The backend management platform determines whether the parking space is occupied according to the feedback signal and updates the parking space status information. That is, by comparing the measured value and the reference value, it is judged whether the parking space is occupied. Finally, the user can obtain the parking space status information, such as the number of available parking spaces and their locations, through devices such as a mobile phone APP or an LED display. The schematic diagram of the geomagnetic sensor installed at each parking space is as Figure 2 shown.

[0024] Step S002: Decompose the geomagnetic signal of each parking space into several geomagnetic signal components; Denote any one parking space as the main parking space; According to the comparison situation among all the geomagnetic signal components corresponding to the main parking space, determine the magnetic field disturbance influence factor caused by the change in the vehicle state on the adjacent parking spaces of the main parking space.

[0025] It should be noted that in a parking lot with dense vehicles or a roadside parking area, the distance between multiple parking spaces is relatively close. The entry or exit of a vehicle in one parking space will cause a significant magnetic field disturbance to the geomagnetic sensors of adjacent parking spaces. That is, the magnetic field disturbance caused by the change in the vehicle state on adjacent parking spaces may be superimposed on the geomagnetic signal of the geomagnetic sensor at one parking space. When a vehicle enters or exits the parking space, its metal structure will cause an instantaneous high-frequency disturbance to the earth's magnetic field. This disturbance is manifested as a mutation and peak of the geomagnetic signal, which is usually most obvious when the vehicle approaches or leaves the geomagnetic sensor. The background signal of the geomagnetic sensor itself when there is no vehicle is a low-frequency stable signal, and when the vehicle is completely stationary in the parking space, its disturbance to the earth's magnetic field tends to be stable, and the signal detected by the geomagnetic sensor will enter a stable low-frequency state. Therefore, in this embodiment, the geomagnetic signal is first decomposed to obtain the magnetic field disturbance signal components caused by the change in the vehicle state on a certain parking space and its surrounding parking spaces, and further, a significant magnetic field disturbance period is divided from each magnetic field disturbance signal component, that is, the entry and exit periods of the vehicle on the corresponding parking space of each component, so as to determine the magnetic field disturbance influence factor caused by the change in the vehicle state on the adjacent parking spaces of each parking space.

[0026] Preferably, in an embodiment of the present invention, the method for obtaining the magnetic field disturbance influence factor caused by the change in the vehicle state on the adjacent parking spaces of the main parking space includes: Using the bidimensional empirical mode decomposition method, the geomagnetic signals of each parking space are decomposed into a number of geomagnetic signal components.

[0027] Among them, bidimensional empirical mode decomposition (BEMD) is an analysis method for processing non-linear and non-stationary signals. It decomposes a complex signal into a number of intrinsic mode functions (IMFs) arranged from high frequency to low frequency and a residue (Res). This is a well-known technology, and the specific method will not be introduced here.

[0028] The preset window length H is 5, and this will be used as an example for description.

[0029] In any geomagnetic signal component, taking any moment as the center, a window with a duration of H is formed, and the normalized value of the variance of the geomagnetic field intensity at all moments within the window is obtained as the high-frequency perturbation value at that arbitrary moment.

[0030] In this embodiment, the minimum-maximum normalization method is used to normalize the variance of the geomagnetic field intensity at all moments within the window. This is a well-known technology, and the specific method will not be introduced here.

[0031] The preset perturbation threshold is 0.6, and this will be used as an example for description.

[0032] In any geomagnetic signal component, the moments with high-frequency perturbation values greater than the preset perturbation threshold are recorded as high-frequency perturbation moments, and the moments with high-frequency perturbation values less than or equal to the preset perturbation threshold are recorded as low-frequency stable moments. The label 1 is assigned to the high-frequency perturbation moments, and the label 0 is assigned to the low-frequency stable moments, forming a 01 sequence in chronological order.

[0033] Any parking space is designated as the main parking space.

[0034] In the 01 sequences corresponding to all the geomagnetic signal components of the main parking space, the number of 1s at the same moment is obtained, and the component set composed of all the geomagnetic signal components corresponding to all the 1s at the same moment is obtained. In chronological order, a number sequence is formed with the number of 1s at all moments.

[0035] In the component set at all moments corresponding to the i-th non-zero number value in the number sequence, the number of types of different geomagnetic signal components is counted and then the number of each geomagnetic signal component is counted, and the maximum value among the numbers of all types of geomagnetic signal components is taken and the minimum value .

[0036] It should be noted that: the schematic diagram of the 01 sequence corresponding to all geomagnetic signal components of the main parking space is as follows Figure 3 shown, Figure 3 in which MIF1, MIF2, MIF3, MIF4, and MIF5 are respectively five geomagnetic signal components decomposed from the geomagnetic signal of the main parking space, arranged from high frequency to low frequency. Figure 3 In the first moment, the number of 1s is 2. The component set composed of the geomagnetic signal components corresponding to all 1s in the first moment is {IMF1, IMF3}. According to the time sequence, the number sequence formed by the number of 1s in all moments is {2, 2, 4, 3, 1, 2, 3, 3}. If the i-th non-zero quantity value is 2, then the component sets corresponding to the i-th non-zero quantity value in the number sequence for all moments are {{IMF1, IMF3}, {IMF1, IMF3}, {IMF2, IMF4}}, is 4, is 2, is 1. Among them, in the number sequence, the magnitude of each quantity value represents the number of high-frequency disturbances superimposed on different parking spaces at the corresponding moment. The more the number of high-frequency disturbances superimposed, the more necessary it is to highlight the components corresponding to the main parking space and suppress the interference components corresponding to adjacent parking spaces. If the quantity value is 0, it means that there is no high-frequency disturbance on the main parking space at this moment.

[0037] Obtain the maximum value of the inverse proportional normalization value, denoted as the first quantization value, obtain the normalization value of the minimum value denoted as the second quantization value, obtain the difference between the number of types minus the i-th non-zero quantity value, denoted as the first difference, and the product of the mean of the first quantization value and the second quantization value and the first difference of the normalization value, denoted as the complexity of the component types corresponding to the i-th non-zero quantity value in the number sequence.

[0038] It should be noted that: in this embodiment, is used as the inverse proportional normalization value of the maximum value , and is used as the normalization value of the minimum value , where is the number of occurrences of the i-th non-zero quantity value in the number sequence, and is used as the normalization value of the product , is a linear normalization function used to normalize the data value between 0 and 1, and this is used as an example for description. When the first difference is larger, it means that in the different moments with only two high-frequency disturbances superimposed, the source of the high-frequency disturbance is more complex, and a better signal interference removal effect is required. And the maximum value is smaller, and the minimum value The larger it is, it indicates that in the set of components at all moments corresponding to the i-th non-zero quantity value, each geomagnetic signal component appears a lot, that is, the superposition of high-frequency disturbances is more complex. Therefore, the first difference is adjusted with the average value of the first quantization value and the second quantization value to obtain the complexity of the component type corresponding to the i-th non-zero quantity value.

[0039] Obtain the ratio of the number of occurrences of all non-zero quantity values in the quantity sequence to the length of the quantity sequence, denoted as the first ratio. Obtain the ratio of the number of occurrences of the i-th non-zero quantity value in the quantity sequence to the length of the quantity sequence, denoted as the second ratio. Multiply the complexity of the component type corresponding to the i-th non-zero quantity value in the quantity sequence, the i-th non-zero quantity value and the second ratio, denoted as the first product of the i-th non-zero quantity value in the quantity sequence. Obtain the product of the sum value of the first products of all non-zero quantity values in the quantity sequence and the first ratio, denoted as the magnetic field disturbance influence factor caused by the change in the vehicle state on the adjacent parking spaces of the main parking space.

[0040] It should be noted that: the larger the first ratio, it indicates that there are more moments with high-frequency disturbances in the geomagnetic signal. The larger the non-zero quantity value, it indicates that the number of superposed high-frequency disturbances at the same moment is more. The larger the second ratio, it indicates that there are more moments with superposed high-frequency disturbances. And the greater the complexity of the component type, it indicates that the complexity of the component type under this superposed quantity of high-frequency disturbances is greater, that is, the greater the magnetic field disturbance influence caused by the change in the vehicle state on the adjacent parking spaces, and the more necessary it is to highlight the components corresponding to the main parking space and suppress the interference components corresponding to the adjacent parking spaces.

[0041] Step S003: According to the similarity between all geomagnetic signal components corresponding to the main parking space and the adjacent parking spaces and the distance between the parking spaces, combined with the magnetic field disturbance influence factor caused by the change in the vehicle state on the adjacent parking spaces of the main parking space, determine the degree of influence of each geomagnetic signal component corresponding to the main parking space on the judgment of the parking space state.

[0042] It should be noted that: the above analyzes the influence of the magnetic field disturbance caused by the change in the vehicle state on the adjacent parking spaces superimposed on the geomagnetic signal of the main parking space. Further, it is necessary to analyze the possibility that each geomagnetic signal component is a magnetic field disturbance component caused by the change in the vehicle state on the adjacent parking spaces, and the superimposed interference influence on the geomagnetic signal of the main parking space, so as to reduce the influence of the magnetic field disturbance caused by the change in the vehicle state on the adjacent parking spaces, that is, to assign a smaller weight to the component with a larger superimposed interference during the component reconstruction process to highlight the components corresponding to the main parking space.

[0043] Preferably, in an embodiment of the present invention, the method for obtaining the degree of influence of each geomagnetic signal component corresponding to the main parking space on the judgment of the parking space state includes: Preset the parking space quantity threshold M as 10, and take this as an example for description.

[0044] Obtain the first M parking spaces closest to the main parking space, all of which are recorded as adjacent parking spaces.

[0045] Among all the geomagnetic signal components of the main parking space and all adjacent parking spaces, use the inverse value of the Pearson correlation coefficient between any two geomagnetic signal components as the clustering distance, and use the K-means clustering algorithm to cluster all the geomagnetic signal components to obtain several clustering clusters.

[0046] It should be noted that: both the Pearson correlation coefficient and the K-means clustering algorithm are well-known technologies, and the specific methods will not be introduced here. The value range of the Pearson correlation coefficient is between -1 and 1. Therefore, in this embodiment, the difference between 1 and the Pearson correlation coefficient is used as the inverse value of the Pearson correlation coefficient, and this is used as an example for description. Since the Pearson correlation coefficient is related to the trend of the data and has nothing to do with the absolute size of the data. Therefore, the data change trends of the components in the clustering cluster are similar, while the data size differences are unknown. When the geomagnetic sensor detects a vehicle, its signal strength is closely related to the distance between the vehicle and the sensor. As the distance increases, the signal energy rapidly decays, resulting in a decrease in the signal energy of high-frequency disturbances.

[0047] Use the fast Fourier transform to obtain the energy values of each geomagnetic signal component at different frequencies, and use the sum value of the energy values at all frequencies as the total energy value of each geomagnetic signal component.

[0048] Among them, the fast Fourier transform is a well-known technology, and the specific method will not be introduced here.

[0049] In the x-th clustering cluster, obtain the parking space corresponding to the geomagnetic signal component with the largest total energy value, and record it as the generating parking space of the x-th clustering cluster.

[0050] It should be noted that: the geomagnetic signal components in this clustering cluster are generated by this generating parking space, and thus are collected by the geomagnetic sensors of adjacent parking spaces, interfering with adjacent parking spaces. Although BEMD is a powerful signal decomposition tool, it cannot guarantee that it can completely and accurately decompose all the superimposed interferences in all cases. Therefore, it is necessary to further analyze whether the signal components in the clustering cluster are geomagnetic disturbances caused by changes in the vehicle state on the same parking space collected by different geomagnetic sensors, and determine the credibility of the generating parking space of each clustering cluster.

[0051] In the x-th clustering cluster, arrange the total energy values of all geomagnetic signal components from largest to smallest to obtain a total energy value sequence. In the total energy value sequence, obtain the distance between the parking space corresponding to each total energy value and the generating parking space of the x-th clustering cluster to obtain a distance sequence. Among them, the distance between the same parking spaces is 0.

[0052] Obtain the inverse value of the Pearson correlation coefficient between the total energy value sequence and the distance sequence of the x-th cluster, and then obtain the average value of the Pearson correlation coefficients between all any two geomagnetic signal components in the x-th cluster. Take the product of this inverse value and this average value The normalized value of is denoted as the credibility of the generated parking space of the x-th cluster.

[0053] It should be noted that in this embodiment, the difference of 1 minus the Pearson correlation coefficient is still used as the inverse value of the Pearson correlation coefficient, and is used as the product The normalized value of is is a linear normalization function used to normalize the data value between 0 and 1. Among them, the closer the Pearson correlation coefficient between the total energy value sequence and the distance sequence is to -1, it indicates that the energy gradually decreases with the increase of the distance, and the more credible the generated parking space of the x-th cluster is. The larger this average value is, it indicates that the change trends of the geomagnetic signal components in the cluster are more similar, that is, it is more likely that the geomagnetic disturbances collected by different geomagnetic sensors are from the same parking space. Therefore, this average value is used as the adjustment value of this inverse value to obtain the credibility of the generated parking space.

[0054] For the j-th geomagnetic signal component corresponding to the main parking space, obtain the normalized value of the product of the credibility of the generated parking space of the cluster where the j-th geomagnetic signal component is located and the total energy value of the j-th geomagnetic signal component, denoted as the first normalized value. The normalized value of the product of the first normalized value and the magnetic field disturbance influence factor caused by the vehicle state change on the adjacent parking space of the main parking space is denoted as the parking space state judgment adjustment coefficient.

[0055] The preset constant is 1, and this is used as an example for description.

[0056] If the generated parking space of the cluster where the j-th geomagnetic signal component corresponding to the main parking space is located is the main parking space, then denote the sum value of the preset constant and the parking space state judgment adjustment coefficient as the degree of influence of the j-th geomagnetic signal component on the parking space state judgment.

[0057] If the generated parking space of the cluster where the j-th geomagnetic signal component corresponding to the main parking space is located is not the main parking space, then denote the difference value of the preset constant minus the parking space state judgment adjustment coefficient as the degree of influence of the j-th geomagnetic signal component on the parking space state judgment.

[0058] It should be noted that: when the generating parking space of the clustering cluster where the j-th geomagnetic signal component corresponding to the main parking space is located is the main parking space, the greater the influence factor of the magnetic field disturbance caused by the change of the vehicle state on the adjacent parking space of the main parking space, the more necessary it is to highlight the component corresponding to the main parking space. And the greater the credibility of the generating parking space of the clustering cluster where the j-th geomagnetic signal component is located, the more likely the j-th geomagnetic signal component is the magnetic field disturbance caused by the change of the vehicle state on the main parking space. At this time, the greater the total energy value of the j-th geomagnetic signal component, it indicates that the energy in the j-th geomagnetic signal component is greater, and the more necessary it is to highlight this component during reconstruction. Therefore, the sum value of the preset constant and the parking space state judgment adjustment coefficient is used as the influence degree of the j-th geomagnetic signal component on the parking space state judgment. When the generating parking space of the clustering cluster where the j-th geomagnetic signal component corresponding to the main parking space is located is not the main parking space, the greater the influence factor of the magnetic field disturbance caused by the change of the vehicle state on the adjacent parking space of the main parking space, the more necessary it is to suppress the interference component corresponding to the adjacent parking space. The greater the credibility of the generating parking space of the clustering cluster where the j-th geomagnetic signal component is located, the more likely the j-th geomagnetic signal component is the magnetic field disturbance caused by the change of the vehicle state on the adjacent parking space of the main parking space. At this time, the greater the total energy value of the j-th geomagnetic signal component, the greater the interference of the adjacent parking space. Therefore, the difference value obtained by subtracting the parking space state judgment adjustment coefficient from the preset constant is used as the influence degree of the j-th geomagnetic signal component on the parking space state judgment.

[0059] According to the above method, obtain the influence degree of each geomagnetic signal component corresponding to the main parking space on the parking space state judgment.

[0060] Step S004: Determine the reconstruction weight of each geomagnetic signal component corresponding to the main parking space according to the magnitude of the influence degree of each geomagnetic signal component corresponding to the main parking space on the parking space state judgment; for the main parking space, perform weighted reconstruction on all geomagnetic signal components according to the reconstruction weight of each geomagnetic signal component to obtain an updated geomagnetic signal; determine the state of the vehicle in the parking space according to the difference between the updated geomagnetic signal and the geomagnetic background value.

[0061] Preferably, in an embodiment of the present invention, the method for obtaining the state of the vehicle in the parking space includes: Obtain the sum value of the influence degrees of all geomagnetic signal components corresponding to the main parking space on the parking space state judgment, and record the ratio of the influence degree of the j-th geomagnetic signal component corresponding to the main parking space on the parking space state judgment to this sum value as the reconstruction weight of the j-th geomagnetic signal component corresponding to the main parking space.

[0062] For the main parking space, perform weighted reconstruction on all geomagnetic signal components according to the reconstruction weight of each geomagnetic signal component to obtain an updated geomagnetic signal.

[0063] It should be noted that: The reconstruction process is a key step in the two-dimensional empirical mode decomposition method. Its core idea is to recombine all the decomposed IMFs and the residual components to approximate the original signal as closely as possible. In this embodiment, by assigning reconstruction weights, in the updated geomagnetic signal, the interference of the magnetic field disturbance caused by the change of the vehicle state on the adjacent parking space is reduced, and the magnetic field disturbance information caused by the change of the vehicle state on the main parking space is highlighted.

[0064] The preset state judgment threshold is 20, and this will be used as an example for description.

[0065] When the difference between the geomagnetic field intensity at the current moment in the updated geomagnetic signal of the main parking space and the geomagnetic background value of the main parking space is greater than the preset state judgment threshold, it is determined that the state of the main parking space at the current moment is the occupied state.

[0066] When the difference between the geomagnetic field intensity at the current moment in the updated geomagnetic signal of the main parking space and the geomagnetic background value of the main parking space is less than or equal to the preset state judgment threshold, it is determined that the state of the main parking space at the current moment is the vacant state.

[0067] Thus, the state information of each parking space in the parking lot at each moment can be obtained, enabling users to obtain the parking space state information, such as the number of vacant parking spaces and their locations, through devices such as mobile phone APPs and LED displays.

[0068] The present invention also provides a geomagnetic detection system for parking space vehicles, including a memory, a processor, and a computer program stored on the memory and executable on the processor. The processor executes the computer program stored in the memory to implement the steps of the aforementioned geomagnetic detection method for parking space vehicles.

[0069] So far, the present invention is completed.

[0070] In summary, in the embodiment of the present invention, the geomagnetic signals of each parking space in the parking lot are obtained, the geomagnetic signals of each parking space are decomposed into several geomagnetic signal components, and any one parking space is designated as the main parking space. According to the comparison of all the geomagnetic signal components corresponding to the main parking space, the influence factor of the magnetic field disturbance caused by the change of the vehicle state on the adjacent parking space of the main parking space is determined. Combining the similarity between all the geomagnetic signal components corresponding to the main parking space and the adjacent parking space and the distance between the parking spaces, the degree of influence of each geomagnetic signal component corresponding to the main parking space on the parking space state judgment is determined, so as to determine the reconstruction weight of each geomagnetic signal component corresponding to the main parking space, and perform weighted reconstruction on all the geomagnetic signal components of the main parking space to obtain the updated geomagnetic signal for determining the state of the parking space vehicle. The present invention obtains the updated geomagnetic signal through weighted reconstruction to reduce the interference of the magnetic field disturbance caused by the change of the vehicle state on the adjacent parking space and ensure the accuracy of the geomagnetic detection of the parking space vehicle.

[0071] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A geomagnetic detection method for vehicles in a parking space, characterized in that, The method includes the following steps: Obtain the geomagnetic signals, geomagnetic background values of each parking space in the parking lot, and the distances between the parking spaces; the horizontal axis of the geomagnetic signal is time, and the vertical axis is geomagnetic field strength; Decompose the geomagnetic signal of each parking space into several geomagnetic signal components; designate any one parking space as the main parking space; determine the magnetic field disturbance influence factor caused by the change in the vehicle state on the adjacent parking space of the main parking space according to the comparison situation among all the geomagnetic signal components corresponding to the main parking space; Determine the influence degree of each geomagnetic signal component corresponding to the main parking space on the judgment of the parking space state according to the similarity between all the geomagnetic signal components corresponding to the main parking space and the adjacent parking spaces and the distances between the parking spaces, in combination with the magnetic field disturbance influence factor caused by the change in the vehicle state on the adjacent parking space of the main parking space; Determine the reconstruction weight of each geomagnetic signal component corresponding to the main parking space according to the magnitude of the influence degree of each geomagnetic signal component corresponding to the main parking space on the judgment of the parking space state; for the main parking space, perform weighted reconstruction on all the geomagnetic signal components according to the reconstruction weight of each geomagnetic signal component to obtain an updated geomagnetic signal; determine the state of the vehicle in the parking space according to the difference between the updated geomagnetic signal and the geomagnetic background value.

2. The geomagnetic detection method for a vehicle in a parking space according to claim 1, wherein The specific steps included in determining the magnetic field disturbance influence factor caused by the change in the vehicle state on the adjacent parking space of the main parking space are as follows: Preset a window length H. In any one geomagnetic signal component, with any one moment as the center, form a window with a duration of H, and obtain the normalized value of the variance of the geomagnetic field strength at all moments within the window as the high-frequency disturbance value at the any one moment. Mark the moment with a high-frequency disturbance value greater than the preset disturbance threshold as a high-frequency disturbance moment, and mark the moment with a high-frequency disturbance value less than or equal to the preset disturbance threshold as a low-frequency stable moment. Assign the label 1 to the high-frequency disturbance moment and the label 0 to the low-frequency stable moment, and form a 01 sequence in chronological order; In the 01 sequences corresponding to all the geomagnetic signal components of the main parking space, obtain the number of 1s at the same moment and the component set formed by all the geomagnetic signal components corresponding to all the 1s at the same moment. In chronological order, form a quantity sequence with the number of 1s at all moments; Determine the complexity of the component types of each non-zero quantity value according to the component sets at all moments corresponding to each non-zero quantity value in the quantity sequence; Determine the magnetic field disturbance influence factor caused by the change in the vehicle state on the adjacent parking space of the main parking space according to the number of occurrences of non-zero quantity values in the quantity sequence and the complexity of the component types of each non-zero quantity value.

3. The geomagnetic detection method for a vehicle in a parking space according to claim 2, wherein, The specific steps included in determining the complexity of the component types of each non-zero quantity value according to the component sets at all moments corresponding to each non-zero quantity value in the quantity sequence are as follows: In the set of components at all moments corresponding to the i-th non-zero quantity value in the quantity sequence, count the number of types of different geomagnetic signal components , then count the number of each geomagnetic signal component, and take the maximum value among the numbers of all geomagnetic signal components and the minimum value ; Obtain the said maximum value The inverse normalization value of, denoted as the first quantization value, obtain the said minimum value The normalization value of, denoted as the second quantization value, obtain the said number of types The difference obtained by subtracting the non - zero quantity value of the i - th type, denoted as the first difference, the normalization value of the product of the mean of the first quantization value and the second quantization value and the first difference, is denoted as the component type complexity of the non - zero quantity value of the i - th type in the quantity sequence.

4. The geomagnetic detection method for a vehicle in a parking space according to claim 2, wherein, The specific steps included in determining the magnetic field disturbance influence factor caused by the change in the vehicle state on the adjacent parking space of the main parking space according to the number of occurrences of non-zero quantity values in the quantity sequence and the complexity of the component types of each non-zero quantity value are as follows: Obtain the ratio of the number of occurrences of all non-zero quantity values in the quantity sequence to the length of the quantity sequence, denoted as the first ratio. Obtain the ratio of the number of occurrences of the i-th non-zero quantity value in the quantity sequence to the length of the quantity sequence, denoted as the second ratio. Denote the product of the component type complexity of the i-th non-zero quantity value in the quantity sequence, the i-th non-zero quantity value, and the second ratio as the first product of the i-th non-zero quantity value in the quantity sequence. Obtain the product of the sum value of the first products of all types of non-zero quantity values in the quantity sequence and the first ratio, denoted as the magnetic field disturbance influence factor caused by the vehicle state change on the adjacent parking spaces of the main parking space.

5. The geomagnetic detection method for a vehicle in a parking space according to claim 1, characterized in that, The specific steps for determining the influence degree of each geomagnetic signal component corresponding to the main parking space on the parking space state judgment are as follows: Preset a parking space quantity threshold M, and obtain the first M parking spaces closest to the main parking space, all denoted as adjacent parking spaces; In all geomagnetic signal components of the main parking space and all adjacent parking spaces, use the inverse value of the Pearson correlation coefficient between any two geomagnetic signal components as the clustering distance to cluster all geomagnetic signal components, and obtain several clustering clusters; Obtain the energy value of each geomagnetic signal component at different frequencies, and use the sum value of the energy values at all frequencies as the total energy value of each geomagnetic signal component; In the x-th clustering cluster, obtain the parking space corresponding to the geomagnetic signal component with the largest total energy value, denoted as the generating parking space of the x-th clustering cluster. Determine the credibility of the generating parking space of the x-th clustering cluster according to the magnitude of the total energy value of the geomagnetic signal component and the distance between the parking space corresponding to the geomagnetic signal component and the generating parking space of the x-th clustering cluster; Determine the influence degree of the j-th geomagnetic signal component corresponding to the main parking space on the parking space state judgment according to the credibility of the generating parking space of the clustering cluster where the j-th geomagnetic signal component corresponding to the main parking space is located, the total energy value of the j-th geomagnetic signal component, and the magnetic field disturbance influence factor caused by the vehicle state change on the adjacent parking spaces of the main parking space.

6. The geomagnetic detection method for a vehicle in a parking space according to claim 5, wherein, The specific steps for determining the credibility of the generating parking space of the x-th clustering cluster according to the magnitude of the total energy value of the geomagnetic signal component and the distance between the parking space corresponding to the geomagnetic signal component and the generating parking space of the x-th clustering cluster are as follows: In the x-th clustering cluster, arrange the total energy values of all geomagnetic signal components from large to small to obtain a total energy value sequence. In the total energy value sequence, obtain the distance between the parking space corresponding to each total energy value geomagnetic signal component and the generating parking space of the x-th clustering cluster, and obtain a distance sequence; Obtain the inverse value of the Pearson correlation coefficient between the total energy value sequence and the distance sequence of the x-th clustering cluster, and then obtain the mean value of the Pearson correlation coefficients between any two geomagnetic signal components in the x-th clustering cluster. Denote the normalized value of the product of the inverse value and the mean value as the credibility of the generating parking space of the x-th clustering cluster.

7. The geomagnetic detection method for a vehicle in a parking space according to claim 5, characterized in that, Determine the influence degree of the j-th geomagnetic signal component corresponding to the main parking space on the judgment of the parking space state according to the credibility of the generated parking space of the clustering cluster where the j-th geomagnetic signal component is located, the total energy value of the j-th geomagnetic signal component, and the magnetic field disturbance influence factor caused by the change of the vehicle state on the adjacent parking space of the main parking space. The specific steps are as follows: For the j-th geomagnetic signal component corresponding to the main parking space, obtain the normalized value of the product of the credibility of the generated parking space of the clustering cluster where the j-th geomagnetic signal component is located and the total energy value of the j-th geomagnetic signal component, denoted as the first normalized value. The normalized value of the product of the first normalized value and the magnetic field disturbance influence factor caused by the change of the vehicle state on the adjacent parking space of the main parking space is denoted as the parking space state judgment adjustment coefficient; If the generated parking space of the clustering cluster where the j-th geomagnetic signal component corresponding to the main parking space is located is the main parking space, denote the sum value of the preset constant and the parking space state judgment adjustment coefficient as the influence degree of the j-th geomagnetic signal component on the judgment of the parking space state; If the generated parking space of the clustering cluster where the j-th geomagnetic signal component corresponding to the main parking space is located is not the main parking space, denote the difference value obtained by subtracting the parking space state judgment adjustment coefficient from the preset constant as the influence degree of the j-th geomagnetic signal component on the judgment of the parking space state.

8. The geomagnetic detection method for a vehicle in a parking space according to claim 1, characterized in that The specific steps for determining the reconstruction weight of each geomagnetic signal component corresponding to the main parking space are as follows: Obtain the sum value of the influence degrees of all geomagnetic signal components corresponding to the main parking space on the judgment of the parking space state. Denote the ratio of the influence degree of the j-th geomagnetic signal component corresponding to the main parking space on the judgment of the parking space state to the sum value as the reconstruction weight of the j-th geomagnetic signal component corresponding to the main parking space.

9. The geomagnetic detection method for vehicles in a parking space according to claim 1, characterized in that, The specific steps for determining the state of the vehicle in the parking space according to the difference between the updated geomagnetic signal and the geomagnetic background value are as follows: When the difference between the geomagnetic field intensity at the current moment in the updated geomagnetic signal of the main parking space and the geomagnetic background value of the main parking space is greater than the preset state judgment threshold, determine that the state of the main parking space at the current moment is the occupied state; When the difference between the geomagnetic field intensity at the current moment in the updated geomagnetic signal of the main parking space and the geomagnetic background value of the main parking space is less than or equal to the preset state judgment threshold, determine that the state of the main parking space at the current moment is the vacant state.

10. A geomagnetic detection system for vehicles in a parking space, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the computer program is executed by the processor, it realizes the steps of a geomagnetic detection method for vehicles in a parking space as described in any one of claims 1-9.

Images