A multi-feature fusion vehicle detection method based on geomagnetic sensor

Abstract

The application discloses a multi-feature fusion vehicle detection method based on geomagnetic sensors, and comprises the following steps: acquiring the geomagnetic field component values in the X-axis and Y-axis directions through a first geomagnetic sensor group and a second geomagnetic sensor group, and calculating the geomagnetic field information of parking spaces; performing feature extraction according to the geomagnetic field information to obtain a target feature group; and performing multi-feature fusion judgment according to the target feature group to obtain a vehicle detection result. The application improves the accuracy and can be widely applied to the computer technology field.

Description

Technical Field

[0001] This invention relates to the field of computer technology, and in particular to a multi-feature fusion vehicle detection method based on a geomagnetic sensor. Background Technology

[0002] With the continuous increase in car ownership, a large proportion of motor vehicles can only choose to park on the roadside or in temporary parking areas in residential areas. Roadside temporary parking lots account for approximately 58% of the total public parking lot area. Roadside parking spaces are a public resource, and charging for on-street parking has become a consensus. The current state of roadside parking fee collection typically involves manual and unmanned payment methods. Both methods require a sensor to detect whether a vehicle is parked in the space. In the manual payment method, a detector is installed under each parking space, which reduces the workload of manual payment. In the unmanned payment method, sensors can effectively detect whether a vehicle is parked in the space, enabling self-service payment, self-reporting, and unmanned management.

[0003] There are various methods for detecting vehicles in parking spaces, such as laser infrared detection, ultrasonic detection, and magnetic field detection. For detecting vehicles in roadside parking spaces, using a geomagnetic field sensor is the optimal method, and the detection method based on this is currently the most widely accepted and effective. A car is a metal-encased vehicle, and a magnetic field exists around it. The movement of a car affects changes in the surrounding magnetic field. Similarly, when a vehicle is parked in a parking space, the surrounding magnetic field changes. Sensors that detect changes in the magnetic field to determine whether a vehicle is parked in a space are known in the industry as geomagnetic field sensors, or simply geomagnetic sensors.

[0004] Geomagnetic measurement technology utilizes geomagnetic sensors to measure changes in the Earth's magnetic field when a vehicle enters a specific area, thereby determining the vehicle's status. It is a key technology in intelligent transportation systems. In recent years, advancements in geomagnetic measurement technology have resulted in geomagnetic sensors that are small in size, low in power consumption, cost-effective, easy to install (with minimal damage to the ground surface), and easy to maintain. These sensors have found wide application in intelligent transportation, parking space vehicle detection, and intelligent toll collection systems. However, in roadside parking space vehicle detection, relying solely on geomagnetic measurement technology, also known as geomagnetic-based single-mode recognition technology, suffers from poor anti-interference capabilities, difficulty in determining discrimination thresholds for different locations, and a relatively high error probability. Currently, roadside parking space vehicle detection commonly employs geomagnetic-based dual-mode recognition technology, which combines geomagnetic measurement technology with an additional supplementary technology. For example, vehicle detection based on geomagnetism and radar technology utilizes parking space sensors that integrate both detection technologies, combining geomagnetism for static detection and radar for dynamic detection to improve vehicle detection accuracy. Detection based on geomagnetism and ultrasonic sensors involves geomagnetic sensors detecting magnetic field changes when a vehicle enters or leaves, activating the ultrasonic unit to measure the distance from the vehicle chassis to the detector and ultimately confirm the vehicle's status. Parking space vehicle detection based on geomagnetism and UWB technology uses UWB ranging technology to detect changes in geomagnetic signal intensity and performs data fusion to confirm vehicle information, effectively reducing interference from vehicles in adjacent parking spaces and improving detection accuracy. Vehicle detection based on geomagnetism and optical sensor technology uses extremely low-power optical sensors to detect the shadow cast by a vehicle entering a parking space, thereby activating the geomagnetic detection unit; this technology significantly reduces the power consumption of the detection system. In addition, vehicle detection based on geomagnetism and inductive loops, and vehicle detection based on geomagnetism and infrared sensors, have also been researched and applied. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide a highly accurate multi-feature fusion vehicle detection method based on a geomagnetic sensor.

[0006] One aspect of this invention provides a multi-feature fusion vehicle detection method based on a geomagnetic sensor, comprising:

[0007] The geomagnetic field components in the X and Y axes are obtained by using the first and second geomagnetic sensor groups to calculate the geomagnetic field information of the parking space.

[0008] Based on the geomagnetic field information, feature extraction is performed to obtain the target feature group;

[0009] The vehicle detection result is obtained by performing multi-feature fusion judgment based on the target feature group.

[0010] Optionally, the step of obtaining the geomagnetic field component values ​​in the X and Y axes through the first and second geomagnetic sensor groups and calculating the geomagnetic field information of the parking space includes:

[0011] The geomagnetic field components in the X and Y axes are obtained by using the first geomagnetic sensor group and the second geomagnetic sensor group.

[0012] The first-order difference of the geomagnetic measurement value in the X direction is calculated based on the X-axis geomagnetic field component value output by the first geomagnetic sensor group and the X-axis geomagnetic field component value output by the second geomagnetic sensor.

[0013] The first-order difference of the geomagnetic measurement value in the Y direction is calculated based on the Y-axis geomagnetic field component value output by the first geomagnetic sensor group and the Y-axis geomagnetic field component value output by the second geomagnetic sensor.

[0014] Calculate the systematic error of the first-order difference in the X-direction based on the first-order difference of the geomagnetic measurement values.

[0015] Calculate the systematic error of the first-order difference in the Y-direction based on the first-order difference of the geomagnetic measurement values.

[0016] Based on the first-order difference of the geomagnetic measurement values ​​in the X direction and the systematic error of the first-order difference in the X direction, calculate the deviation of the first-order difference of the geomagnetic measurement values ​​in the X direction.

[0017] Based on the first-order difference of the geomagnetic measurement values ​​in the Y direction and the systematic error of the first-order difference in the Y direction, calculate the deviation of the first-order difference of the geomagnetic measurement values ​​in the Y direction.

[0018] Based on the deviation of the first-order difference of the geomagnetic measurement values ​​in the X direction and the deviation of the first-order difference of the geomagnetic measurement values ​​in the Y direction, calculate the sum of the deviations of the first-order difference of the geomagnetic measurement values ​​in the X and Y directions.

[0019] Based on the X-axis geomagnetic field component value output by the first geomagnetic sensor group and the Y-axis geomagnetic field component value output by the first geomagnetic sensor, calculate the XY plane geomagnetic vector direction angle measured by the first geomagnetic sensor group;

[0020] Based on the X-axis geomagnetic field component value output by the second geomagnetic sensor group and the Y-axis geomagnetic field component value output by the second geomagnetic sensor, calculate the XY plane geomagnetic vector direction angle measured by the second geomagnetic sensor group.

[0021] The first-order difference of the XY plane geomagnetic vector direction angle is calculated based on the XY plane geomagnetic vector direction angle measured by the first geomagnetic sensor group and the XY plane geomagnetic vector direction angle measured by the second geomagnetic sensor group.

[0022] Optionally, the method further includes a step of signal preprocessing based on the geomagnetic field information, which includes:

[0023] A sensor unit is positioned at the geometric center of the roadside parking space;

[0024] When the X component value or Y component value measured by the sensor unit exceeds the preset strong geomagnetic threshold, it is determined that a non-target vehicle has passed by.

[0025] When there are no vehicles in the parking space, the X, Y, and Z components of the geomagnetic field are measured over multiple cycles to determine the baseline value of the geomagnetic field and the interference signals caused by the surrounding environment of the parking space.

[0026] Optionally, the step of extracting features based on the geomagnetic field information to obtain a target feature group includes:

[0027] Based on the geomagnetic field component values ​​in the X and Y axes obtained from the first and second geomagnetic sensor groups, the first-order difference deviation of the geomagnetic measurement values ​​in the X direction and the first-order difference deviation of the geomagnetic measurement values ​​in the Y direction are determined.

[0028] Based on the deviation of the first-order difference of the geomagnetic measurement values ​​in the X direction and the deviation of the first-order difference of the geomagnetic measurement values ​​in the Y direction, determine the sum of the deviations of the first-order difference of the geomagnetic measurement values ​​in the X and Y directions.

[0029] Based on the XY plane geomagnetic vector direction angle obtained from the first geomagnetic sensor group and the second geomagnetic sensor group, the first-order difference of the XY plane geomagnetic vector direction angle is determined.

[0030] The deviation of the Y-axis geomagnetic field component value is determined based on the geomagnetic field component value obtained from the second geomagnetic sensor.

[0031] The target feature set is constructed based on the deviation of the first-order difference of the geomagnetic measurement values ​​in the X direction, the deviation of the first-order difference of the geomagnetic measurement values ​​in the Y direction, the sum of the deviations of the first-order differences of the geomagnetic measurement values ​​in the X and Y directions, the first-order difference of the geomagnetic vector direction angle in the XY plane, and the deviation of the Y-axis geomagnetic field component value.

[0032] Optionally, the step of performing multi-feature fusion judgment based on the target feature group to obtain the vehicle detection result includes:

[0033] When a parking space is not occupied, multiple different features are used to determine whether a vehicle has entered, and the results of these multiple determinations are fused to obtain the final judgment result.

[0034] When a parking space is occupied by a vehicle, multiple different features are used to determine whether the vehicle has left. The results of these multiple determinations are then fused to obtain the final determination.

[0035] Optionally, when the parking space is unoccupied, multiple different features are used to determine whether a vehicle has entered, and the multiple determination results are fused to obtain a discrimination result, including:

[0036] First, obtain the sum of the first-order difference deviations of the geomagnetic measurement values ​​in the X and Y directions. When the sum of the first-order difference deviations of the geomagnetic measurement values ​​in the X and Y directions is greater than 25, geomagnetic value anomaly is determined, and the first determination is that a vehicle has entered the parking space.

[0037] Secondly, the first-order difference of the geomagnetic vector direction angle in the XY plane is obtained. When the first-order difference of the geomagnetic vector direction angle in the XY plane is greater than 0.2, geomagnetic value anomaly is determined, and it is determined that a vehicle has entered.

[0038] Secondly, if the deviation of the Y-axis geomagnetic field component value output by the second geomagnetic sensor is greater than or equal to 30, it is again determined that the vehicle has entered the parking space.

[0039] Finally, if the deviation of the first-order difference of the geomagnetic measurement value in the X direction is greater than or equal to a positive threshold, or the deviation of the first-order difference of the geomagnetic measurement value in the Y direction is greater than or equal to a positive threshold, or the deviation of the first-order difference of the geomagnetic measurement value in the X direction is less than or equal to a negative threshold, or the deviation of the first-order difference of the geomagnetic measurement value in the Y direction is less than or equal to a negative threshold, it is ultimately determined that the vehicle has entered the parking space, and the vehicle status of the parking space is adjusted to the state of being occupied by a vehicle.

[0040] Optionally, when a parking space is occupied, multiple different features are used to determine whether the vehicle has left, and the multiple determination results are fused to obtain a determination result, including:

[0041] The deviations of the first-order difference of the geomagnetic measurement values ​​in the X direction, the first-order difference of the geomagnetic measurement values ​​in the Y direction, and the deviations of the Y-axis geomagnetic field component values ​​output by the second geomagnetic sensor are obtained.

[0042] When the deviation of the first-order difference of the geomagnetic measurement value in the X direction is in [-10, 10], and the deviation of the first-order difference of the geomagnetic measurement value in the Y direction is in [-10, 10], and the deviation of the Y-axis geomagnetic field component value output by the second geomagnetic sensor is less than or equal to 30, it is determined that the vehicle has left the parking space, and the vehicle status of the parking space is adjusted to a vehicle-free status.

[0043] Another aspect of this invention provides a multi-feature fusion vehicle detection device based on a geomagnetic sensor, comprising:

[0044] The first module is used to obtain the geomagnetic field component values ​​in the X-axis and Y-axis directions through the first geomagnetic sensor group and the second geomagnetic sensor group, and to calculate the geomagnetic field information of the parking space.

[0045] The second module is used to extract features based on the geomagnetic field information to obtain a target feature group.

[0046] The third module is used to perform multi-feature fusion judgment based on the target feature group to obtain the vehicle detection result.

[0047] Another aspect of the present invention provides an electronic device, including a processor and a memory;

[0048] The memory is used to store programs;

[0049] The processor executes the program to implement the method described above.

[0050] Another aspect of this invention provides a computer-readable storage medium storing a program that is executed by a processor to implement the methods described above.

[0051] This invention also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium and execute the computer instructions, causing the computer device to perform the aforementioned method.

[0052] In embodiments of the present invention, geomagnetic field component values ​​in the X and Y axes are obtained through a first geomagnetic sensor group and a second geomagnetic sensor group to calculate the geomagnetic field information of the parking space; feature extraction is performed based on the geomagnetic field information to obtain a target feature group; and multi-feature fusion judgment is performed based on the target feature group to obtain the vehicle detection result. The present invention improves detection accuracy. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0054] Figure 1 This is a schematic diagram of the hardware layout architecture of the geomagnetic sensor provided in an embodiment of the present invention;

[0055] Figure 2 This is a schematic diagram of the connection principle of a geomagnetic sensor provided in an embodiment of the present invention;

[0056] Figure 3 This is a schematic diagram of the MSP430 connection principle provided in an embodiment of the present invention;

[0057] Figure 4 A circuit schematic diagram of a power supply provided for an embodiment of the present invention;

[0058] Figure 5 The overall process flowchart provided for embodiments of the present invention. Detailed Implementation

[0059] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0060] To address the problems existing in the prior art, one aspect of the present invention provides a multi-feature fusion vehicle detection method based on a geomagnetic sensor, comprising:

[0061] The geomagnetic field components in the X and Y axes are obtained by using the first and second geomagnetic sensor groups to calculate the geomagnetic field information of the parking space.

[0062] Based on the geomagnetic field information, feature extraction is performed to obtain the target feature group;

[0063] The vehicle detection result is obtained by performing multi-feature fusion judgment based on the target feature group.

[0064] Optionally, the step of obtaining the geomagnetic field component values ​​in the X and Y axes through the first and second geomagnetic sensor groups and calculating the geomagnetic field information of the parking space includes:

[0065] The geomagnetic field components in the X and Y axes are obtained by using the first geomagnetic sensor group and the second geomagnetic sensor group.

[0066] The first-order difference of the geomagnetic measurement value in the X direction is calculated based on the X-axis geomagnetic field component value output by the first geomagnetic sensor group and the X-axis geomagnetic field component value output by the second geomagnetic sensor.

[0067] The first-order difference of the geomagnetic measurement value in the Y direction is calculated based on the Y-axis geomagnetic field component value output by the first geomagnetic sensor group and the Y-axis geomagnetic field component value output by the second geomagnetic sensor.

[0068] Calculate the systematic error of the first-order difference in the X-direction based on the first-order difference of the geomagnetic measurement values.

[0069] Calculate the systematic error of the first-order difference in the Y-direction based on the first-order difference of the geomagnetic measurement values.

[0070] Based on the first-order difference of the geomagnetic measurement values ​​in the X direction and the systematic error of the first-order difference in the X direction, calculate the deviation of the first-order difference of the geomagnetic measurement values ​​in the X direction.

[0071] Based on the first-order difference of the geomagnetic measurement values ​​in the Y direction and the systematic error of the first-order difference in the Y direction, calculate the deviation of the first-order difference of the geomagnetic measurement values ​​in the Y direction.

[0072] Based on the deviation of the first-order difference of the geomagnetic measurement values ​​in the X direction and the deviation of the first-order difference of the geomagnetic measurement values ​​in the Y direction, calculate the sum of the deviations of the first-order difference of the geomagnetic measurement values ​​in the X and Y directions.

[0073] Based on the X-axis geomagnetic field component value output by the first geomagnetic sensor group and the Y-axis geomagnetic field component value output by the first geomagnetic sensor, calculate the XY plane geomagnetic vector direction angle measured by the first geomagnetic sensor group;

[0074] Based on the X-axis geomagnetic field component value output by the second geomagnetic sensor group and the Y-axis geomagnetic field component value output by the second geomagnetic sensor, calculate the XY plane geomagnetic vector direction angle measured by the second geomagnetic sensor group.

[0075] The first-order difference of the XY plane geomagnetic vector direction angle is calculated based on the XY plane geomagnetic vector direction angle measured by the first geomagnetic sensor group and the XY plane geomagnetic vector direction angle measured by the second geomagnetic sensor group.

[0076] Optionally, the method further includes a step of signal preprocessing based on the geomagnetic field information, which includes:

[0077] A sensor unit is positioned at the geometric center of the roadside parking space;

[0078] When the X component value or Y component value measured by the sensor unit exceeds the preset strong geomagnetic threshold, it is determined that a non-target vehicle has passed by.

[0079] When there are no vehicles in the parking space, the X, Y, and Z components of the geomagnetic field are measured over multiple cycles to determine the baseline value of the geomagnetic field and the interference signals caused by the surrounding environment of the parking space.

[0080] Optionally, the step of extracting features based on the geomagnetic field information to obtain a target feature group includes:

[0081] Based on the geomagnetic field component values ​​in the X and Y axes obtained from the first and second geomagnetic sensor groups, the first-order difference deviation of the geomagnetic measurement values ​​in the X direction and the first-order difference deviation of the geomagnetic measurement values ​​in the Y direction are determined.

[0082] Based on the deviation of the first-order difference of the geomagnetic measurement values ​​in the X direction and the deviation of the first-order difference of the geomagnetic measurement values ​​in the Y direction, determine the sum of the deviations of the first-order difference of the geomagnetic measurement values ​​in the X and Y directions.

[0083] Based on the XY plane geomagnetic vector direction angle obtained from the first geomagnetic sensor group and the second geomagnetic sensor group, the first-order difference of the XY plane geomagnetic vector direction angle is determined.

[0084] The deviation of the Y-axis geomagnetic field component value is determined based on the geomagnetic field component value obtained from the second geomagnetic sensor.

[0085] The target feature set is constructed based on the deviation of the first-order difference of the geomagnetic measurement values ​​in the X direction, the deviation of the first-order difference of the geomagnetic measurement values ​​in the Y direction, the sum of the deviations of the first-order differences of the geomagnetic measurement values ​​in the X and Y directions, the first-order difference of the geomagnetic vector direction angle in the XY plane, and the deviation of the Y-axis geomagnetic field component value.

[0086] Optionally, the step of performing multi-feature fusion judgment based on the target feature group to obtain the vehicle detection result includes:

[0087] When a parking space is not occupied, multiple different features are used to determine whether a vehicle has entered, and the results of these multiple determinations are fused to obtain the final judgment result.

[0088] When a parking space is occupied by a vehicle, multiple different features are used to determine whether the vehicle has left. The results of these multiple determinations are then fused to obtain the final determination.

[0089] Optionally, when the parking space is unoccupied, multiple different features are used to determine whether a vehicle has entered, and the multiple determination results are fused to obtain a discrimination result, including:

[0090] First, obtain the sum of the first-order difference deviations of the geomagnetic measurement values ​​in the X and Y directions. When the sum of the first-order difference deviations of the geomagnetic measurement values ​​in the X and Y directions is greater than 25, geomagnetic value anomaly is determined, and the first determination is that a vehicle has entered the parking space.

[0091] Secondly, the first-order difference of the geomagnetic vector direction angle in the XY plane is obtained. When the first-order difference of the geomagnetic vector direction angle in the XY plane is greater than 0.2, geomagnetic value anomaly is determined, and it is determined that a vehicle has entered.

[0092] Secondly, if the deviation of the Y-axis geomagnetic field component value output by the second geomagnetic sensor is greater than or equal to 30, it is again determined that the vehicle has entered the parking space;

[0093] Finally, if the deviation of the first-order difference of the geomagnetic measurement value in the X direction is greater than or equal to a positive threshold, or the deviation of the first-order difference of the geomagnetic measurement value in the Y direction is greater than or equal to a positive threshold, or the deviation of the first-order difference of the geomagnetic measurement value in the X direction is less than or equal to a negative threshold, or the deviation of the first-order difference of the geomagnetic measurement value in the Y direction is less than or equal to a negative threshold, it is ultimately determined that the vehicle has entered the parking space, and the vehicle status of the parking space is adjusted to the state of being occupied by a vehicle.

[0094] Optionally, when a parking space is occupied, multiple different features are used to determine whether the vehicle has left, and the multiple determination results are fused to obtain a determination result, including:

[0095] The deviations of the first-order difference of the geomagnetic measurement values ​​in the X direction, the first-order difference of the geomagnetic measurement values ​​in the Y direction, and the deviations of the Y-axis geomagnetic field component values ​​output by the second geomagnetic sensor are obtained.

[0096] When the deviation of the first-order difference of the geomagnetic measurement value in the X direction is in [-10, 10], and the deviation of the first-order difference of the geomagnetic measurement value in the Y direction is in [-10, 10], and the deviation of the Y-axis geomagnetic field component value output by the second geomagnetic sensor is less than or equal to 30, it is determined that the vehicle has left the parking space, and the vehicle status of the parking space is adjusted to a vehicle-free status.

[0097] Another aspect of this invention provides a multi-feature fusion vehicle detection device based on a geomagnetic sensor, comprising:

[0098] The first module is used to obtain the geomagnetic field component values ​​in the X-axis and Y-axis directions through the first geomagnetic sensor group and the second geomagnetic sensor group, and to calculate the geomagnetic field information of the parking space.

[0099] The second module is used to extract features based on the geomagnetic field information to obtain a target feature group.

[0100] The third module is used to perform multi-feature fusion judgment based on the target feature group to obtain the vehicle detection result.

[0101] Another aspect of the present invention provides an electronic device, including a processor and a memory;

[0102] The memory is used to store programs;

[0103] The processor executes the program to implement the method described above.

[0104] Another aspect of this invention provides a computer-readable storage medium storing a program that is executed by a processor to implement the methods described above.

[0105] This invention also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium and execute the computer instructions, causing the computer device to perform the aforementioned method.

[0106] The specific implementation process of the present invention will now be described in detail with reference to the accompanying drawings:

[0107] To address the problems of existing technologies, this invention is based on geomagnetic single-mode detection technology. It incorporates two sets of geomagnetic sensors in the detection unit and designs a method where each set of sensors independently measures the X, Y, and Z geomagnetic components of the parking space. Through differential calculations, it obtains the X-axis differential value and its deviation, the Y-axis differential value and its deviation, the Z-axis value, and the XY-plane geomagnetic vector direction angle and its difference, forming a discrimination vector. This multi-level fusion discrimination achieves the goal of significantly improving the probability of vehicle detection in roadside parking spaces using single-mode geomagnetic technology, overcoming the shortcomings of current dual-mode geomagnetic vehicle detection algorithms for roadside parking spaces.

[0108] The implementation process of this invention includes two parts: first, the hardware layout of the geomagnetic sensor, and second, the vehicle detection algorithm based on the geomagnetic sensor. The first part is the basis for the implementation of the second part.

[0109] Part 1: (Detection System Based on Geomagnetic Differential Measurement Technology) The hardware layout of the geomagnetic sensor consists of four parts: sensor unit (two sets of geomagnetic sensors), central processing unit (MSP430 microcontroller system), power supply module, and data wireless transmission module.

[0110] refer to Figure 1 The sensor unit comprises two independent sensors, using the PNI3100 geomagnetic sensor (Note: PNI3100 is the product model). This sensor consists of two X / Y axis magnetic field sensors (Sen-XY-f, product model: 13104), one Z-axis magnetic field sensor (Sen-Zf, product model: 13101), and one ASIC controller (Mag12C, product model: 13156). They are mounted 12cm apart on the system circuit board and independently measure the changes in the geomagnetic field as a vehicle enters the parking space. The sensor's measurement range is -800nT to +800nT, with a sensitivity of 26nT. Its high resolution and low noise make it one of the best-performing geomagnetic sensors in its class. Its connection principle is as follows... Figure 2 As shown.

[0111] The central processing unit (CPU) uses a 16-bit MSP430 series microcontroller, featuring ultra-low power consumption, wide voltage range, Reduced Instruction Set Computing (RISC), high-speed communication at low clock frequencies, strong interrupt capability, and strong anti-interference capability. Also known as a mixed-signal processor, it integrates multiple analog and digital circuit modules with different functions and a microprocessor onto a single chip, effectively performing tasks such as receiving, processing, and transmitting measurement data. Its connection schematic is shown below. Figure 3 As shown.

[0112] Because this system needs to be installed underground in the parking space, high power requirements are placed on it to reduce maintenance costs. The system uses an ER34615 capacity lithium thionyl chloride (Li-SOCI2) battery with a capacity of 19000mAh. Its connection diagram is shown below. Figure 4 As shown.

[0113] The data wireless transmission unit adopts Narrow Band Internet of Things (NB-IoT) technology, which is mature. It only consumes approximately 180kHz of bandwidth and can be directly deployed on GSM, UMTS, or LTE networks. When a vehicle enters or leaves a parking space, the system uploads real-time geomagnetic measurement data and judgment results to a host computer for billing, analysis, and decision-making.

[0114] Part Two: The vehicle detection algorithm based on geomagnetic sensors includes three parts: signal preprocessing, feature extraction, and multi-feature fusion judgment. For example... Figure 5 As shown, the vehicle inspection process includes the following steps:

[0115] S1. Obtain the geomagnetic field component values ​​in the X and Y directions through the first geomagnetic sensor group and the second geomagnetic sensor group, and calculate the geomagnetic field information of the parking space;

[0116] S2. Based on the geomagnetic field information, feature extraction is performed to obtain the target feature group;

[0117] S3. Perform multi-feature fusion judgment based on the target feature group to obtain the vehicle detection result.

[0118] Specifically, in this embodiment, let BX1 and BY1 be the geomagnetic field component values ​​in the X and Y axes output by the first geomagnetic sensor group; and let BX2 and BY2 be the geomagnetic field component values ​​in the X and Y axes output by the second geomagnetic sensor group. Then, the relevant quantities of the geomagnetic field at the parking space can be calculated as follows:

[0119] First-order difference of geomagnetic measurements in the X direction:

[0120] DiffX=BX1-BX2 (1)

[0121] First-order difference of geomagnetic measurements in the Y direction:

[0122] DiffY = BY1 - BY2 (2)

[0123] The systematic error of the first-order difference in the X direction is the initial value of the first-order difference when there is no car in the parking space:

[0124] SystemX = DiffX (3)

[0125] The systematic error of the first-order difference in the Y direction is the initial value of the first-order difference when there is no car in the parking space:

[0126] SystemY = DiffY (4)

[0127] The first-order difference bias of the geomagnetic measurement in the X direction:

[0128] deltX = DiffX - SystemX (5)

[0129] The first-order difference bias of the geomagnetic measurement in the Y direction:

[0130] deltY = DiffY - SystemY (6)

[0131] The sum of the first-order difference deviations of the geomagnetic measurements in the X and Y directions:

[0132] deltXY=deltX+deltY (7)

[0133] According to equation (3), the first-order difference of the geomagnetic vector direction angle in the XY plane is:

[0134]

[0135] The change in the Y component (BY2) of the geomagnetic field measured by the second geomagnetic sensor group:

[0136] deltBY2=BY2-SystemBY2 (9)

[0137] (1) Signal preprocessing

[0138] The sensor unit and its control system are fixed in a sleeve and installed at the geometric center of the roadside parking space, buried at a depth of 5-15cm. After system startup, a strong geomagnetic threshold is first set. When the X or Y component value BX (BY) measured by the sensor exceeds this threshold, it is determined that a non-target vehicle has passed by, and the system waits for a certain period of time, i.e., until the non-target vehicle leaves. Secondly, when there is no vehicle in the parking space, the X, Y, and Z component values ​​BX, BY, and BZ of the geomagnetic field are measured at multiple intervals. These measurements include the baseline geomagnetic value B. E Interference signals B caused by the surrounding environment of the parking space N The system average value of the Y component of the geomagnetic field BY2 measured by the second geomagnetic sensor group in the vehicle-free state is:

[0139]

[0140] Where n is the number of measurement cycles, SystemX(i) and SystemY(i) for each cycle are determined according to equations (1)-(4), and the final system errors of the first-order difference in the X and Y directions are:

[0141]

[0142] (2) Feature extraction

[0143] The sensors measure the X and Y component values ​​of the geomagnetic signal, BX and BY. The first-order difference deviations deltX and deltY of the geomagnetic measurements in the X and Y directions are calculated according to equations (5)-(6). These values ​​reflect the abnormal changes in the geomagnetic field caused by the vehicle entering the parking space. Further, deltXY is calculated according to equation (7). Simultaneously, the geomagnetic vector direction angles in the XY plane of the two sensor groups are calculated according to equation (8), yielding the first-order difference diffA of the XY plane geomagnetic vector direction angles. The change in the Y component value BY2 of the geomagnetic field measured by the second geomagnetic sensor group is calculated according to equation (9).

[0144] (3) Multi-feature fusion judgment

[0145] When a parking space is empty, the system determines whether a vehicle has entered it by using multiple different features, each independently assessed. The results are then fused to provide a final judgment. Similarly, when a parking space is occupied, the system determines whether a vehicle has left it by using multiple different features, each independently assessed. The results are then fused to provide a final judgment. The specific process is described below.

[0146] After system initialization, when there are no cars in the parking spaces:

[0147] First, based on deltXY, if deltXY>25, anomalies in the geomagnetic value are identified, and the initial determination is that a vehicle has entered the parking space;

[0148] Secondly, based on diffA, if diffA > 0.2, the geomagnetic value is considered abnormal, indicating that a vehicle has entered.

[0149] Secondly, if deltBY2≥30, it is again determined that the vehicle has entered the parking space;

[0150] Finally, if deltX≥K, or deltY≥K, or deltX≤-K, or deltY≤-K (K is a threshold determined based on the system's installation location), the vehicle is ultimately determined to have entered the parking space, and the parking space's vehicle status is adjusted to "occupied".

[0151] When it has been determined that a parking space is occupied:

[0152] Based on the three characteristics deltX, deltY, and deltBY2, if -10≤deltX≤10, -10≤deltY≤10, and deltBY2≤30, it is determined that the vehicle has left the vehicle and the system returns to the state of no vehicle occupation.

[0153] In summary, compared with the prior art, the present invention has the following advantages:

[0154] (1) A single geomagnetic detection mode with extremely low power consumption, which can eliminate the need to replace the battery for a long time. Theoretically, it can eliminate the need to replace the battery of the sensor unit and its control system buried underground for 8-10 years.

[0155] (2) The single geomagnetic detection mode has low sensor unit cost and low failure rate, which reduces the sensor unit maintenance cost.

[0156] (3) Improved the accuracy of vehicle detection results in parking spaces.

[0157] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this invention are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is altered and sub-operations described as part of a larger operation are executed independently.

[0158] Furthermore, although the invention has been described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the described functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the invention. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of conventional skill of an engineer. Therefore, those skilled in the art can implement the invention as set forth in the claims using ordinary techniques without excessive experimentation. It is also understood that the specific concepts disclosed are merely illustrative and not intended to limit the scope of the invention, which is determined by the full scope of the appended claims and their equivalents.

[0159] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0160] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0161] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0162] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0163] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0164] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

[0165] The above is a detailed description of the preferred embodiments of the present invention, but the present invention is not limited to the embodiments described. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention, and these equivalent modifications or substitutions are all included within the scope defined by the claims of this application.

Claims

1. A multi-feature fusion vehicle detection method based on a geomagnetic sensor, characterized in that, include: The geomagnetic field components in the X and Y axes are obtained by using the first and second geomagnetic sensor groups to calculate the geomagnetic field information of the parking space. Based on the geomagnetic field information, feature extraction is performed to obtain the target feature group; Based on the target feature group, multi-feature fusion judgment is performed to obtain the vehicle detection result; The process of acquiring geomagnetic field component values ​​in the X and Y axes using a first geomagnetic sensor group and a second geomagnetic sensor group, and calculating the geomagnetic field information of the parking space, includes: The geomagnetic field components in the X and Y axes are obtained by using the first geomagnetic sensor group and the second geomagnetic sensor group. The first-order difference of the geomagnetic measurement value in the X direction is calculated based on the X-axis geomagnetic field component value output by the first geomagnetic sensor group and the X-axis geomagnetic field component value output by the second geomagnetic sensor. The first-order difference of the geomagnetic measurement value in the Y direction is calculated based on the Y-axis geomagnetic field component value output by the first geomagnetic sensor group and the Y-axis geomagnetic field component value output by the second geomagnetic sensor. Calculate the systematic error of the first-order difference in the X-direction based on the first-order difference of the geomagnetic measurement values; Calculate the systematic error of the first-order difference in the Y-direction based on the first-order difference of the geomagnetic measurements. Based on the first-order difference of the geomagnetic measurement values ​​in the X direction and the systematic error of the first-order difference in the X direction, calculate the deviation of the first-order difference of the geomagnetic measurement values ​​in the X direction. Based on the first-order difference of the geomagnetic measurement values ​​in the Y direction and the systematic error of the first-order difference in the Y direction, calculate the deviation of the first-order difference of the geomagnetic measurement values ​​in the Y direction. Based on the deviation of the first-order difference of the geomagnetic measurement values ​​in the X direction and the deviation of the first-order difference of the geomagnetic measurement values ​​in the Y direction, calculate the sum of the deviations of the first-order difference of the geomagnetic measurement values ​​in the X and Y directions. Based on the X-axis geomagnetic field component value and the Y-axis geomagnetic field component value output by the first geomagnetic sensor group, calculate the XY plane geomagnetic vector direction angle measured by the first geomagnetic sensor group; Based on the X-axis geomagnetic field component value output by the second geomagnetic sensor group and the Y-axis geomagnetic field component value output by the second geomagnetic sensor, calculate the XY plane geomagnetic vector direction angle measured by the second geomagnetic sensor group. Calculate the first-order difference of the XY plane geomagnetic vector direction angle based on the XY plane geomagnetic vector direction angle measured by the first geomagnetic sensor group and the XY plane geomagnetic vector direction angle measured by the second geomagnetic sensor group; The step of extracting features based on the geomagnetic field information to obtain a target feature group includes: Based on the geomagnetic field component values ​​in the X and Y axes obtained from the first and second geomagnetic sensor groups, the first-order difference deviation of the geomagnetic measurement values ​​in the X direction and the first-order difference deviation of the geomagnetic measurement values ​​in the Y direction are determined. Based on the deviation of the first-order difference of the geomagnetic measurement values ​​in the X direction and the deviation of the first-order difference of the geomagnetic measurement values ​​in the Y direction, determine the sum of the deviations of the first-order difference of the geomagnetic measurement values ​​in the X and Y directions. Based on the XY plane geomagnetic vector direction angle obtained from the first geomagnetic sensor group and the second geomagnetic sensor group, the first-order difference of the XY plane geomagnetic vector direction angle is determined. Based on the geomagnetic field component values ​​in the Y-axis direction obtained from the second geomagnetic sensor group, the deviation of the Y-axis geomagnetic field component values ​​is determined. The target feature set is constructed based on the deviation of the first-order difference of the geomagnetic measurement values ​​in the X direction, the deviation of the first-order difference of the geomagnetic measurement values ​​in the Y direction, the sum of the deviations of the first-order differences of the geomagnetic measurement values ​​in the X and Y directions, the first-order difference of the geomagnetic vector direction angle in the XY plane, and the deviation of the geomagnetic field component value in the Y axis. The step of performing multi-feature fusion judgment based on the target feature group to obtain the vehicle detection result includes: When a parking space is not occupied, multiple different features are used to determine whether a vehicle has entered, and the results of these multiple determinations are fused to obtain the final judgment result. When a parking space is occupied by a vehicle, multiple different features are used to determine whether the vehicle has left. The results of these multiple determinations are then fused to obtain the final determination.

2. The multi-feature fusion vehicle detection method based on a geomagnetic sensor according to claim 1, characterized in that, The method further includes a signal preprocessing step based on the geomagnetic field information, which includes: A sensor unit is positioned at the geometric center of the roadside parking space; When the X component value or Y component value measured by the sensor unit exceeds the preset strong geomagnetic threshold, it is determined that a non-target vehicle has passed by. When there are no vehicles in the parking space, the X, Y, and Z components of the geomagnetic field are measured over multiple cycles to determine the baseline value of the geomagnetic field and the interference signals caused by the surrounding environment of the parking space.

3. The multi-feature fusion vehicle detection method based on a geomagnetic sensor according to claim 1, characterized in that, When a parking space is unoccupied, multiple different features are used to determine whether a vehicle has entered. These multiple determinations are then fused to obtain a final judgment result, including: First, obtain the sum of the first-order difference deviations of the geomagnetic measurement values ​​in the X and Y directions. When the sum of the first-order difference deviations of the geomagnetic measurement values ​​in the X and Y directions is greater than 25, geomagnetic value anomaly is determined, and the first determination is that a vehicle has entered the parking space. Secondly, the first-order difference of the geomagnetic vector direction angle in the XY plane is obtained. When the first-order difference of the geomagnetic vector direction angle in the XY plane is greater than 0.2, geomagnetic value anomaly is determined, and it is determined that a vehicle has entered. Secondly, if the deviation of the Y-axis geomagnetic field component value output by the second geomagnetic sensor is greater than or equal to 30, it is again determined that the vehicle has entered the parking space; Finally, if the deviation of the first-order difference of the geomagnetic measurement value in the X direction is greater than or equal to a positive threshold, or the deviation of the first-order difference of the geomagnetic measurement value in the Y direction is greater than or equal to a positive threshold, or the deviation of the first-order difference of the geomagnetic measurement value in the X direction is less than or equal to a negative threshold, or the deviation of the first-order difference of the geomagnetic measurement value in the Y direction is less than or equal to a negative threshold, it is ultimately determined that the vehicle has entered the parking space, and the vehicle status of the parking space is adjusted to the state of being occupied by a vehicle.

4. The multi-feature fusion vehicle detection method based on a geomagnetic sensor according to claim 1, characterized in that, When a parking space is occupied, multiple different features are used to determine whether the vehicle has left. These multiple determinations are then fused to obtain a final determination, including: The deviations of the first-order difference of the geomagnetic measurement values ​​in the X direction, the first-order difference of the geomagnetic measurement values ​​in the Y direction, and the deviations of the Y-axis geomagnetic field component values ​​output by the second geomagnetic sensor are obtained. When the deviation of the first-order difference of the geomagnetic measurement value in the X direction is in [-10, 10], and the deviation of the first-order difference of the geomagnetic measurement value in the Y direction is in [-10, 10], and the deviation of the Y-axis geomagnetic field component value output by the second geomagnetic sensor is less than or equal to 30, it is determined that the vehicle has left the parking space, and the vehicle status of the parking space is adjusted to an unoccupied state.

5. An apparatus for implementing the multi-feature fusion vehicle detection method based on a geomagnetic sensor as described in any one of claims 1-4, characterized in that, include: The first module is used to obtain the geomagnetic field component values ​​in the X-axis and Y-axis directions through the first geomagnetic sensor group and the second geomagnetic sensor group, and to calculate the geomagnetic field information of the parking space. The second module is used to extract features based on the geomagnetic field information to obtain a target feature group. The third module is used to perform multi-feature fusion judgment based on the target feature group to obtain the vehicle detection result.

6. An electronic device, characterized in that, Including the processor and memory; The memory is used to store programs; The processor executes the program to implement the method as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The storage medium stores a program that is executed by a processor to implement the method as described in any one of claims 1 to 4.

Images