Method, device and system for detecting the accuracy of parking space detection system

Abstract

The embodiments of the present application disclose a method, device and system for detecting the accuracy of a parking space detection system; the method comprises: obtaining a control value of the parking space parameter; determining the absolute value of the difference between the test value of the parking space parameter and the control value as an error; wherein the test value of the parking space parameter is obtained by the parking space detection system; determining a distance parameter between a vehicle and a parking space corresponding to the parking space parameter; using the distance parameter as an independent variable, determining a value of a function as a coefficient of the parking space parameter; wherein the value of the function is greater than zero, the derivative of the function is greater than zero and the derivative of the function is monotonically decreasing; determining the accuracy of the parking space detection system according to the product of the error and the coefficient; and obtaining the accuracy of the parking space detection system with higher accuracy.

Description

Technical Field

[0001] The present invention relates to the field of detection, and in particular to a method, device and system for detecting the accuracy of a parking space detection system. Background Art

[0002] With the development of science and technology and the improvement of people's living standards, cars have gradually become an integral part of people's lives, and parking is an important part of car use. When people need to park in a parking space, especially when parking spaces are scarce, parking detection systems are often used to improve parking safety. In this case, the accuracy of the parking detection system is a relatively important parameter.

[0003] In the prior art, there are two main methods for testing the accuracy of parking space detection systems. The first is to build a parking lot simulation scene using a hardware-in-the-loop test bench, and compare the real parking space information when the hardware-in-the-loop test bench builds the scene with the parking space information obtained by the parking space detection system to be tested, thereby obtaining the accuracy; the second is to use distance measurement tools such as rulers and laser rangefinders to measure the real parking space information, and compare it with the parking space information obtained by the parking space detection system to be tested, thereby obtaining the accuracy. The first method is difficult to represent the test conditions of the actual scene because the scene generated by the hardware-in-the-loop test bench is too ideal; the second method is difficult to perform when the vehicle is in motion because it is completed through manual measurement. Therefore, in the process of testing the accuracy of the parking space detection system in the prior art, it is difficult to accurately represent the real test conditions, or part of the real test conditions are lost, resulting in inaccurate accuracy of the parking space detection system. Summary of the Invention

[0004] In view of this, embodiments of the present application provide a method, device, and system for detecting the accuracy of a parking space detection system, so as to obtain the accuracy of the parking space detection system with higher accuracy.

[0005] In a first aspect, the present application provides a method for detecting the accuracy of a parking space detection system, the method comprising:

[0006] Obtaining a comparison value of the parking space parameter;

[0007] Determine the absolute value of the difference between the test value of the parking space parameter and the control value as an error; wherein the test value of the parking space parameter is obtained by a parking space detection system;

[0008] determining a distance parameter between the vehicle and the parking space corresponding to the parking space parameter;

[0009] Taking the distance parameter as an independent variable, determining a function value as a coefficient of the parking space parameter; wherein the value of the function is greater than zero, the derivative of the function is greater than zero, and the derivative of the function is monotonically decreasing;

[0010] The accuracy of the parking space detection system is determined according to the product of the error and the coefficient.

[0011] In a possible implementation, the parking space parameter includes a parking space angular coordinate, and determining the distance parameter between the vehicle and the parking space corresponding to the parking space parameter may include: determining a modulus of the parking space angular coordinate as the distance parameter.

[0012] In a possible implementation, the parking space parameter includes an inclination angle between the vehicle and the parking space, and determining the distance parameter between the vehicle and the parking space corresponding to the parking space parameter may include: determining the modulus value of the first parking space angular coordinate of the parking space entrance, and determining half of the sum of the modulus values ​​of the first parking space angular coordinate of the parking space entrance as the distance parameter.

[0013] In one possible implementation, the function may include:

[0014]

[0015] In a possible implementation, obtaining the reference value of the parking space parameter may include: obtaining the reference value of the parking space parameter by using an RT3000 detection device.

[0016] In a possible implementation manner, the base station calibrates the reference value of the parking space parameter, and the reference value of the parking space parameter is obtained.

[0017] The method may include: obtaining a comparison value of the parking space parameter within a preset detection range; wherein the preset detection range is a signal coverage range of the base station;

[0018] Obtaining the test value of the parking space parameter through the parking space detection system may include:

[0019] The test value of the parking space parameter is obtained by the parking space detection system within a preset detection range.

[0020] In a second aspect, the present application provides a device for detecting the accuracy of a parking space detection system, the device comprising:

[0021] A data acquisition unit, configured to obtain a comparison value of the parking space parameter;

[0022] an error determination unit, configured to determine an absolute value of a difference between a test value of the parking space parameter and the reference value as an error; wherein the test value of the parking space parameter is obtained by a parking space detection system;

[0023] a parameter determination unit, configured to determine a distance parameter between the vehicle and the parking space corresponding to the parking space parameter;

[0024] a coefficient determination unit, configured to use the distance parameter as an independent variable and determine a value of a function as a coefficient of the parking space parameter; wherein the value of the function is greater than zero, the derivative of the function is greater than zero, and the derivative of the function is monotonically decreasing;

[0025] An accuracy determination unit is used to determine the accuracy of the parking space detection system according to the product of the error and the coefficient.

[0026] In a third aspect, the present application provides a system for detecting the accuracy of a parking space detection system, the system comprising:

[0027] A parking space detection system, used to obtain test values ​​of the parking space parameters;

[0028] A detection device for obtaining a reference value of the parking space parameter;

[0029] A data processing device is used to determine the absolute value of the difference between the test value and the control value of the parking space parameter as an error; determine a distance parameter between the vehicle and the parking space corresponding to the parking space parameter; use the distance parameter as an independent variable to determine the value of a function as a coefficient of the parking space parameter; wherein the value of the function is greater than zero, the derivative of the function is greater than zero, and the derivative of the function is monotonically decreasing; and determine the accuracy of the parking space detection system based on the product of the error and the coefficient.

[0030] In a fourth aspect, the present application provides an electronic device for detecting the accuracy of a parking space detection system, the electronic device comprising a processor and a memory, wherein the memory stores code, and the processor is configured to call the code stored in the memory to implement the following functions:

[0031] Obtaining a comparison value of the parking space parameter;

[0032] Determine the absolute value of the difference between the test value of the parking space parameter and the control value as an error; wherein the test value of the parking space parameter is obtained by a parking space detection system;

[0033] determining a distance parameter between the vehicle and the parking space corresponding to the parking space parameter;

[0034] Taking the distance parameter as an independent variable, determining a function value as a coefficient of the parking space parameter; wherein the value of the function is greater than zero, the derivative of the function is greater than zero, and the derivative of the function is monotonically decreasing;

[0035] The accuracy of the parking space detection system is determined according to the product of the error and the coefficient.

[0036] In a fifth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store a computer program, and the computer program is used to execute any one of the above methods.

[0037] In an embodiment of the present application, the test value of the parking space parameter is obtained by the parking space detection system, and the error is determined as the absolute value of the difference between the test value and the control value of the parking space parameter. The value of the function is determined as the coefficient by taking the distance parameter between the vehicle and the parking space as the independent variable. The value of the function is greater than zero, the derivative of the function is greater than zero, and the derivative of the function is monotonically decreasing, and the product of the error and the coefficient is used as the accuracy of the parking space detection system.

[0038] It can be seen that the embodiments of the present application have the following beneficial effects:

[0039] Compared with the prior art in which the accuracy of the test system is obtained by setting up a scene, in the embodiment of the present application, the acquisition of the test value and the control value for determining the error does not rely on the scene setting or measuring tools such as a ruler. The test value and the control value under different scenes can be obtained, so that the accuracy of the parking space detection system obtained according to the product of the error and the coefficient has higher accuracy.

[0040] In addition, the embodiments of the present application have other beneficial effects.

[0041] Since the accuracy of the parking space detection system is derived from the product of the error and the coefficient, the error is in absolute value form; the coefficient is the value of a function with the distance parameter as the independent variable and is affected by the properties of the function. Therefore, the accuracy of the parking space detection system is also affected by the properties of the function; the derivative of the function is greater than zero and monotonically decreasing. First, because the value of the function is greater than zero, the error is not less than zero, and the accuracy increases with the increase of the error, satisfying the corresponding relationship between large error and low accuracy. Second, the derivative of the function is greater than zero and monotonically decreasing. Due to the characteristics of the function itself, for the same change in the distance between the vehicle and the parking space (vehicle-parking space distance), the corresponding change in the coefficient / precision will be greater when the vehicle-parking space distance is closer than when the vehicle-parking space distance is farther. In other words, the smaller the vehicle-parking space distance, the more sensitive the parking space detection system's accuracy is to distance. The above changes are consistent with the actual situation. That is, users are more concerned about the accuracy of the parking space detection system when the vehicle is close to the parking space (the vehicle-parking space distance is small) than when the vehicle is far away from the parking space (the vehicle-parking space distance is large). Therefore, the embodiment of the present application can better meet the user's analysis requirements for the accuracy of the parking space detection system. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 This is a flow chart of a method for detecting the accuracy of a parking space detection system provided in an embodiment of the present application;

[0043] Figure 2 1 is a schematic structural diagram of a device for detecting the accuracy of a parking space detection system provided in an embodiment of the present application;

[0044] Figure 3 This is a structural diagram of a system for detecting the accuracy of a parking space detection system provided in an embodiment of the present application;

[0045] Figure 4 A schematic diagram of the structure of an electronic device for detecting the accuracy of a parking space detection system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] In order to facilitate understanding and explanation of the technical solutions provided by the embodiments of the present application, the technical terms in the embodiments of the present application will be explained below.

[0047] Parking space detection: refers to the technology of detecting the parking situation based on the signal detected by the detector.

[0048] Accuracy: refers to the degree of closeness between the observed value and the true value; corresponding to the size of the error, the size of the error can be used to represent the level of accuracy. A small error means high accuracy, and a large error means low accuracy.

[0049] There are three main methods for detecting the accuracy of parking space detection systems in the prior art.

[0050] The first is a method using offline data testing. The collected four-way surround view fisheye original images are spliced ​​using surround view stitching parameters, and the true value / reference value of the parking space position is manually marked on the stitched image. The marked true value of the parking space position is then projected to the world coordinate system through the surround view stitching parameters, and compared with the detection value of the parking space detection module to obtain the accuracy of the parking space detection system. The disadvantages of this method are: since the test scene is usually limited to the scene where the data is collected, the scene constraints are high, and it is difficult to test any parking lot under various lighting and time periods in real time; the accuracy of the test depends on manual marking of the true value of the parking space position on the image, and the accuracy of the single pixel point of the stitched image is low, resulting in the accuracy being difficult to guarantee credibility; the default surround view stitching calibration parameter accuracy is the true value, but the actual surround view has errors in the calibration itself, resulting in inaccurate accuracy test results;

[0051] The second method is to use a hardware-in-the-loop (HIL) test bench test method. A parking lot simulation scene is built on the HIL bench, and the simulated four-way surround view fisheye original image generated by the HIL bench is used for surround view stitching. The parking space detection algorithm in the parking space detection system obtains the surround view stitching image and detects the parking space information, and projects it into the world coordinate system; the predicted parking space detection result is compared with the true value of the parking space when the HIL bench is built, and the accuracy of the parking space detection system is calculated. The disadvantages of this method are: the test scene is limited by the simulation scene capability of the HIL bench, and it is usually difficult to cover lighting, shadows and complex image information; the scene generated by the HIL bench is too ideal, and the scene is usually severely distorted, which is difficult to be consistent with the rich real data acquisition images in life, resulting in the test results being difficult to represent the test conditions of the actual scene;

[0052] The third method involves using distance measurement tools such as rulers and laser rangefinders. The distance measurement tool measures the actual distance between the vehicle and the parking space being measured, and the detection accuracy is compared with the actual result obtained by manual measurement. The disadvantages of this method include: selecting the vehicle body reference points is difficult, and the selection of reference points is affected by the flatness of the ground and the measurement method, making it difficult to guarantee the accuracy of manual measurement, and the accuracy test results may be seriously inaccurate; manual measurement often makes it difficult to obtain the true value of parking space information while the vehicle is in motion, resulting in the loss of dynamic detection parking space data; manual measurement operations are time-consuming and difficult, and the test scenarios are usually inconsistent, resulting in high testing costs.

[0053] To facilitate understanding of the technical solution provided in the embodiments of the present application, a method, device, and system for detecting the accuracy of a parking space detection system provided in the embodiments of the present application are described below with reference to the accompanying drawings.

[0054] Although the accompanying drawings show exemplary embodiments of the present application, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. Based on the embodiments of the present application, other embodiments obtained by those skilled in the art without making any creative contribution shall fall within the scope of protection of the present application.

[0055] In the claims and description and drawings of this application, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusions.

[0056] In the existing technology, there are two main methods for testing the accuracy of parking space detection systems. The first is to use a hardware-in-the-loop test bench to simulate a parking scene. However, since the scene generated by the hardware-in-the-loop test bench is too ideal, it is difficult to represent the actual test conditions in the actual scene. The second is to use distance measurement tools such as rulers and laser rangefinders to measure the actual parking space information, which is difficult to perform while the vehicle is in motion. Therefore, in the process of testing the accuracy of parking space detection systems in the existing technology, it is difficult to accurately represent the actual test conditions, or some of the actual test conditions are lost, resulting in inaccurate parking space detection system accuracy.

[0057] Based on this, in the embodiment of the present application provided by the inventor, the test value of the parking space parameter is obtained by the parking space detection system, and the error is determined as the absolute value of the difference between the test value and the control value of the parking space parameter. By taking the distance parameter between the vehicle and the parking space as the independent variable, the value of the function is determined as the coefficient, the value of the function is greater than zero, the derivative of the function is greater than zero, and the derivative of the function is monotonically decreasing, and the product of the error and the coefficient is used as the accuracy of the parking space detection system.

[0058] Compared with the prior art in which the accuracy of the test system is obtained by setting up a scene, in the embodiment of the present application, the acquisition of the test value and the control value for determining the error does not rely on the scene setting or measuring tools such as a ruler. The test value and the control value under different scenes can be obtained, so that the accuracy of the parking space detection system obtained according to the product of the error and the coefficient has higher accuracy.

[0059] See also Figure 1 , Figure 1 This is a flow chart of a method for detecting the accuracy of a parking space detection system provided by an embodiment of the present application. Figure 1 As shown, the method for detecting the accuracy of the parking space detection system in the embodiment of the present application includes the following steps:

[0060] S101, obtaining a comparison value of the parking space parameter;

[0061] In S101, the purpose of obtaining the reference value of the parking space parameter is to compare it with the reference value of the parking space parameter obtained by the parking space detection system to obtain the absolute value of the error, thereby obtaining the accuracy of the parking space detection system;

[0062] S102: Determine an absolute value of a difference between a test value of the parking space parameter and the control value as an error; wherein the test value of the parking space parameter is obtained by a parking space detection system;

[0063] In S102, the error is expressed as the absolute value of the difference between the test value of the parking space parameter and the control value. The error represents the degree of difference between the test value of the parking space parameter and the control value, providing a basis for subsequently determining the accuracy of the parking space detection system. The two processes of obtaining the test value of the parking space parameter and obtaining the control value of the parking space parameter are relatively independent, that is, the processes of obtaining the two sets of data, the test value and the control value, are relatively independent. The acquisition of the control value and the acquisition of the parking space detection result are separated to a certain extent, with essentially no overlapping areas, making the accuracy test more objective and accurate.

[0064] S103, determining a distance parameter between the vehicle and the parking space corresponding to the parking space parameter;

[0065] In S103, the distance parameter is a parameter representing the distance between the vehicle and the parking space, and is used as an independent variable of the function so that the obtained coefficient is correlated with the vehicle-parking space distance;

[0066] S104: Using the distance parameter as an independent variable, determining a function value as a coefficient of the parking space parameter; wherein the function value is greater than zero, the function derivative is greater than zero, and the function derivative is monotonically decreasing;

[0067] S105: Determine the accuracy of the parking space detection system according to the product of the error and the coefficient.

[0068] In S104-S105, the error represents the degree of difference between the test value of the parking space parameter and the control value. The accuracy of the parking space detection system can be determined by multiplying the error and the coefficient. The function used to determine the coefficient of the parking space parameter has a value greater than zero, a derivative greater than zero, and a monotonically decreasing derivative. Since the accuracy of the parking space detection system is obtained based on the product of the error and the coefficient, the error is in the form of an absolute value; the coefficient is the value of a function with the distance parameter as the independent variable and is affected by the properties of the function. Therefore, the accuracy of the parking space detection system is also affected by the properties of the function; the derivative of the function is greater than zero and monotonically decreasing. First, since the value of the function is greater than zero, the value of the error is not less than zero, and the numerical value of the precision increases with the increase of the error, satisfying the corresponding relationship between large error and low precision; due to the characteristics of the function itself, for the same change in the distance between the vehicle and the parking space (vehicle-parking space distance), the corresponding coefficient change / precision will be greater when the vehicle-parking space distance is closer than when the vehicle-parking space distance is farther, that is, the smaller the vehicle-parking space distance, the higher the sensitivity of the obtained parking space detection system to distance. The above changes are in line with the actual situation, that is, compared with the situation where the vehicle is far away from the parking space (the vehicle-parking space distance is large), the user is more concerned about the accuracy of the parking space detection system when the vehicle is close to the parking space (the vehicle-parking space distance is small). Enhance the importance of distance for parking space detection accuracy evaluation. Therefore, the embodiment of the present application can better meet the user's analysis needs for the accuracy of the parking space detection system.

[0069] Furthermore, since car owners usually pay more attention to the two parking angles at the entrance of the parking space when parking in the parking space, in order to better meet user needs, the two parking angles at the entrance of the parking space can be detected to obtain the coordinates of the two parking angles at the entrance of the parking space. One or two parking angle coordinates are used as the parking space parameters to determine the absolute value of the difference between the test value and the control value of the parking space parameter as the error, thereby obtaining the corresponding accuracy. Furthermore, since coordinates are usually divided into horizontal coordinates and vertical coordinates, when the parking angle coordinates are used as the parking space parameters, the accuracy of the horizontal coordinate of the parking angle coordinates and / or the accuracy of the vertical coordinate of the parking angle coordinates can be obtained respectively. It can be understood that whether the parking angle coordinates are used as the parking space parameters does not affect the implementation of the embodiments of the present application.

[0070] Furthermore, in Example S101 of the present application, the origin of the vehicle coordinate system can be set to the center of the vehicle's rear axle, that is, the intersection of the line connecting the vehicle's two rear wheels and the line connecting the front and rear center axes of the vehicle body. Setting the origin of the vehicle coordinate system at the center of the vehicle's rear axle, firstly, facilitates calculations in processing that requires the use of the vehicle coordinate system; secondly, it facilitates the consideration of the vehicle as a whole when describing the positional relationship between the vehicle and the outside world. It is understood that whether or not the origin of the vehicle coordinate system is set to the center of the vehicle's rear axle does not affect the implementation of the embodiments of the present application.

[0071] Furthermore, in the embodiments of the present application, detection can be performed in various scenarios to obtain corresponding control values ​​and test values, thereby determining the accuracy of the detection system. For example, the scenarios may include parking space detection during a vehicle's forward movement, parking space detection during a vehicle's reverse movement, parking space detection during a vehicle's turn, and parking space detection during a vehicle's entry into a parking space. It is understood that the implementation of the embodiments of the present application is not affected by the scenario in which the parking space detection is performed and the accuracy of the parking space detection system is obtained.

[0072] Furthermore, in the embodiments of the present application, the comparison value of the parking space parameter and the test value of the parking space parameter can be obtained in real time for real-time accuracy determination. It is understood that whether the comparison value of the parking space parameter and the test value of the parking space parameter are obtained in real time does not affect the implementation of the embodiments of the present application.

[0073] Furthermore, in embodiment S101 of the present application, obtaining the reference value of the parking space parameter may include: obtaining the reference value of the parking space parameter through an RT3000 detection device. The RT3000 detection device is a tool designed to perform high-precision measurements of the movement of vehicles, aircraft, and ships in real time, using mathematical algorithms developed for fighter jet navigation systems. Typically, the RT3000 includes an inertial sensor block consisting of three accelerometers and three gyroscopes (angular velocity sensors), which calculates the output of the RT3000 detection device. The RT3000 detection device has the following advantages: a high refresh rate of 100Hz, meeting real-time testing requirements; the ability to identify and ignore GPS jitter; and a unique strapdown navigation system with high-precision measurement capabilities. Therefore, using the RT3000 detection device can obtain relatively accurate reference values ​​of the parking space parameters, overcoming the difficulties in precision testing of parking space detection systems to a certain extent, and improving the user experience during parking space detection and automatic parking. The RT3000 detection equipment is equipped with a high-precision positioning device. It can measure parking detection accuracy in real time throughout the entire parking process in various scenarios and parking spaces, and conduct further evaluation tests. It can also perform high-precision parking detection system accuracy tests in underground / ground parking lots without GPS signals. It can relatively quickly, simply and accurately evaluate the detection accuracy of one or more parking spaces, and to a certain extent, solve the parking detection and evaluation function in real time throughout the entire process. Compared with existing technologies, the use of the RT3000 detection equipment reduces dependence on manual operation, eliminates human interference to a certain extent, and reduces the impact of human factors on accuracy testing.

[0074] Furthermore, the comparison values ​​of the parking space parameters can be obtained through multiple RT3000 detection devices. For example, RT3000 detection devices are placed at the two parking angles of the parking space entrance, the two parking angles of the parking space exit, and the center position of the vehicle's rear axle. Based on the data obtained by the RT3000 detection devices, the parking space angle coordinates, the inclination angle between the vehicle and the parking space and other values ​​can be obtained to complete the determination of the accuracy of the parking space detection system.

[0075] The present embodiment provides a method for obtaining values ​​such as parking space angular coordinates and the tilt angle between a vehicle and the parking space using an RT3000 detection device. The method parses the raw data obtained by the RT3000 detection device to obtain raw sensor data, including the RT3000 data of the vehicle and the parking space. The longitude and latitude of the RT3000 data are converted to a world coordinate system, and the parking space angular coordinates, the tilt angle between the vehicle and the parking space, and other values ​​in the world coordinate system are calculated. It is understood that whether or not the reference values ​​of the parking space parameters are obtained using the RT3000 detection device does not affect the implementation of the present embodiment.

[0076] Furthermore, in an embodiment of the present application, the parking space parameters may include parking space angular coordinates; in embodiment S103 of the present application, determining the distance parameter between the vehicle and the parking space corresponding to the parking space parameters may include: determining the modulus of the parking space angular coordinates as the distance parameter.

[0077] The parking space angle refers to the corners of the parking space, specifically including the four corners of the parking space. The parking space angle coordinates refer to the coordinates of the corners of the parking space. The coordinates here refer to the coordinates in the world coordinate system. Compared to other positions in the entire parking space, the parking space angle is a relatively clear location and is easy to detect coordinates. Therefore, the parking space parameters can be set as parking space angle coordinates.

[0078] When the parking space parameter is a parking space angular coordinate, in order to calculate the coefficient of the parking space parameter, it is necessary to first determine the distance parameter between the vehicle and the parking space corresponding to the parking space parameter. At this time, the modulus of the parking space angular coordinate can be determined as the distance parameter.

[0079] The modulus of the parking space angle coordinate can be used to represent the distance between the vehicle and the parking space angle, with the modulus of the parking space angle coordinate as the distance parameter and as the independent variable of the function. That is, the coefficient obtained by the function is related to the distance between the vehicle and the parking space angle (vehicle-parking space angle distance), so that the accuracy of the parking space detection system obtained by the coefficient is related to the vehicle-parking space angle distance, that is, the accuracy is related to the vehicle-parking space distance, which is more in line with the user's analysis requirements for the accuracy of the parking space detection system, that is, the user is more concerned about the accuracy of the parking space detection system when the vehicle is close to the parking space (vehicle-parking space distance is small).

[0080] The embodiment of the present application provides a specific example here, for example, the parking space angle coordinates included in the parking space parameters are the first parking space angle coordinates The distance parameter is obtained as

[0081] Furthermore, to obtain the parking space angle coordinates, the parking space angle coordinates can be obtained using an RT3000 detection device. Specifically, two RT3000 detection devices can be placed at two parking space angles at the parking space entrance. It is understood that whether the parking space parameters include the parking space angle coordinates and determining the modulus of the parking space angle coordinates as the distance parameter does not affect the implementation of the embodiments of the present application.

[0082] Furthermore, in an embodiment of the present application, the parking space parameter may include an inclination angle between the vehicle and the parking space; in embodiment S103 of the present application, determining the distance parameter between the vehicle and the parking space corresponding to the parking space parameter may include: determining the modulus value of the first parking space angular coordinate of the parking space entrance, and determining half of the sum of the modulus values ​​of the first parking space angular coordinate of the parking space entrance as the distance parameter.

[0083] The inclination angle between the vehicle and the parking space describes the angular relationship between the vehicle and the parking space. In the case where the parking space parameter is the inclination angle between the vehicle and the parking space, in order to calculate the coefficient of the parking space parameter, it is necessary to first determine the distance parameter between the vehicle and the parking space corresponding to the parking space parameter. In this case, the modulus of the first parking space angle coordinate of the parking space entrance and half of the sum of the modulus of the first parking space angle coordinate of the parking space entrance can be determined as the distance parameter. Similar to the description above, the above method of determining the distance parameter is more in line with the user's analysis requirements for the accuracy of the parking space detection system, that is, the user is more concerned about the accuracy of the parking space detection system when the vehicle is close to the parking space (the vehicle-parking space distance is small). In addition, when determining the distance parameter, the first parking space angle of the parking space entrance and the second parking space angle of the parking space entrance are simultaneously considered, and the weights of the first parking space angle and the second parking space angle are set to half in order to more accurately describe the angular relationship between the vehicle and the parking space.

[0084] The embodiment of the present application provides a specific example here, for example, the parking space angle coordinates included in the parking space parameters are the first parking space angle coordinates The parking angle coordinate is the second parking angle coordinate The distance parameter is obtained as

[0085]

[0086] The method of obtaining the parking space angle coordinates can be referred to the above description and will not be repeated here.

[0087] It can be understood that whether the parking space parameters include the inclination angle between the vehicle and the parking space, and determine the modulus value of the first parking space angular coordinate of the parking space entrance, and half of the sum of the modulus values ​​of the first parking space angular coordinate of the parking space entrance as the distance parameter, does not affect the implementation of the embodiment of the present application.

[0088] Furthermore, in embodiment S104 of the present application, the function may be:

[0089]

[0090] In Example S104 of the present application, x is the independent variable of the function f(x), and e is a natural constant. The function is used to determine the coefficient of the parking space parameter. The value of the function is greater than zero, the derivative of the function is greater than zero, and the derivative of the function is monotonically decreasing. Since the accuracy of the parking space detection system is obtained by multiplying the error and the coefficient, the error is in the form of an absolute value; the coefficient is the value of the function with the distance parameter as the independent variable and is affected by the properties of the function. Therefore, the accuracy of the parking space detection system is also affected by the properties of the function; the derivative of the function is greater than zero and the derivative of the function is monotonically decreasing. First, since the value of the function is greater than zero, the error is not less than zero, and the accuracy increases with the increase of the error, satisfying the corresponding relationship between large error and low accuracy. Due to the characteristics of the function itself, for the same change in the distance between the vehicle and the parking space (vehicle-parking space distance), the corresponding coefficient change / precision will be greater when the vehicle-parking space distance is closer than when the vehicle-parking space distance is farther. In other words, the smaller the vehicle-parking space distance, the more sensitive the parking space detection system accuracy is to distance. The above changes are consistent with the actual situation. That is, users are more concerned about the accuracy of the parking space detection system when the vehicle is close to the parking space (the vehicle-parking space distance is small) than when the vehicle is far away from the parking space (the vehicle-parking space distance is large). Therefore, the embodiment of the present application can better meet the user's analysis requirements for the accuracy of the parking space detection system.

[0091] function is the activation function / threshold function in deep learning, whose attenuation gradient decreases with the increase of distance, meeting the requirements that the value of the function is greater than zero, the derivative of the function is greater than zero, and the derivative of the function is monotonically decreasing. The function value is sensitive to the vehicle-parking space distance parameter as the independent variable. It can be understood that whether the function is It does not affect the implementation of the embodiments of this application.

[0092] Furthermore, in an embodiment of the present application, the base station calibrates the control value of the parking space parameter; in embodiment S101 of the present application, obtaining the control value of the parking space parameter may include: obtaining the control value of the parking space parameter within a preset detection range; wherein, the preset detection range is the signal coverage range of the base station; in embodiment S102 of the present application, obtaining the test value of the parking space parameter through the parking space detection system may include: obtaining the test value of the parking space parameter through the parking space detection system within the preset detection range.

[0093] Since the reference value of the parking space parameter is used to compare with the test value to obtain the error of the parking space parameter and thus obtain the accuracy, the accuracy of the reference value of the parking space parameter will affect the final accuracy; therefore, in order to improve the accuracy of the obtained accuracy, the reference value of the parking space parameter can be calibrated by the base station. At this time, the signal coverage range of the base station is set to the preset detection range, and the reference value of the parking space parameter and the test value of the parking space parameter are set to be obtained within the preset detection range. This is because if the detection range is larger than the preset detection range, the base station signal is weak, making it difficult to complete a relatively accurate calibration of the data. Furthermore, the base station can receive data sent by the satellite and perform calibration based on the data sent by the satellite.

[0094] Furthermore, multiple detection devices can be configured to obtain reference values ​​for the parking space parameters. In this case, data synchronization and calibration can be performed between the multiple devices via a base station. To achieve more accurate calibration of the data obtained by the multiple detection devices by the base station, reference values ​​for the parking space parameters are obtained within a preset detection range, and test values ​​for the parking space parameters are obtained within the preset detection range via the parking space detection system. It is understood that whether or not the above configuration is performed does not affect the implementation of the embodiments of the present application.

[0095] See also Figure 2 , Figure 2 Schematic diagram of a device for detecting the accuracy of a parking space detection system provided in an embodiment of the present application. Figure 2 As shown, the apparatus for detecting the accuracy of a parking space detection system in the embodiment of the present application includes: a data acquisition unit 201, an error determination unit 202, a parameter determination unit 203, a coefficient determination unit 204, and an accuracy determination unit 205; wherein:

[0096] The data acquisition unit 201 is used to obtain the reference value of the parking space parameter;

[0097] An error determination unit 202 is configured to determine an absolute value of a difference between a test value of the parking space parameter and the reference value as an error; wherein the test value of the parking space parameter is obtained by a parking space detection system;

[0098] a parameter determination unit 203, configured to determine a distance parameter between the vehicle and the parking space corresponding to the parking space parameter;

[0099] a coefficient determination unit 204 for determining a function value as a coefficient of the parking space parameter using the distance parameter as an independent variable; wherein the value of the function is greater than zero, the derivative of the function is greater than zero, and the derivative of the function is monotonically decreasing;

[0100] The accuracy determination unit 205 is configured to determine the accuracy of the parking space detection system according to the product of the error and the coefficient.

[0101] The units included in the device for detecting the accuracy of the parking space detection system and the connection relationship between the units can achieve the same technical effect as the above-mentioned method for detecting the accuracy of the parking space detection system. To avoid repetition, they will not be described here.

[0102] See also Figure 3 , Figure 3 This is a schematic diagram of the structure of a system for detecting the accuracy of a parking space detection system provided by an embodiment of the present application. Figure 3 As shown, the system for detecting the accuracy of the parking space detection system in the embodiment of the present application includes: a parking space detection system 301, a detection device 302 and a data processing device 303; wherein:

[0103] The parking space detection system 301 is used to obtain the test value of the parking space parameter;

[0104] Detection device 302, used to obtain a reference value of the parking space parameter;

[0105] The data processing device 303 is used to determine the absolute value of the difference between the test value and the control value of the parking space parameter as an error; determine the distance parameter between the vehicle and the parking space corresponding to the parking space parameter; use the distance parameter as an independent variable to determine the value of a function as the coefficient of the parking space parameter; wherein the value of the function is greater than zero, the derivative of the function is greater than zero, and the derivative of the function is monotonically decreasing; and determine the accuracy of the parking space detection system based on the product of the error and the coefficient.

[0106] The other systems / devices included in the system for detecting the accuracy of the parking space detection system and the connection relationship between the systems / devices can achieve the same technical effect as the above-mentioned method for detecting the accuracy of the parking space detection system. To avoid repetition, they will not be repeated here.

[0107] This application also provides an electronic device for detecting the accuracy of a parking space detection system. Figure 4 , Figure 4 This is a schematic diagram of the structure of an electronic device for detecting the accuracy of a parking space detection system provided in an embodiment of the present application. Figure 4 As shown, the electronic device 400 of the parking space detection system according to the embodiment of the present application includes a processor 401 and a memory 402, wherein the memory 402 stores a code, and the processor 401 is used to call the code stored in the memory 402 to implement the following functions:

[0108] Obtaining a comparison value of the parking space parameter;

[0109] Determine the absolute value of the difference between the test value of the parking space parameter and the control value as an error; wherein the test value of the parking space parameter is obtained by a parking space detection system;

[0110] determining a distance parameter between the vehicle and the parking space corresponding to the parking space parameter;

[0111] Taking the distance parameter as an independent variable, determining a function value as a coefficient of the parking space parameter; wherein the value of the function is greater than zero, the derivative of the function is greater than zero, and the derivative of the function is monotonically decreasing;

[0112] The accuracy of the parking space detection system is determined according to the product of the error and the coefficient.

[0113] The memory and processor included in the electronic device, as well as the functions implemented by the processor calling the code stored in the memory, can achieve the same technical effect as the above-mentioned method of parking space detection system accuracy. To avoid repetition, they will not be repeated here.

[0114] In an embodiment of the present application, a computer-readable storage medium is also provided, and the computer-readable storage medium is used to store a computer program, and the computer program is used to execute the above-mentioned method for detecting the accuracy of the parking space detection system, and can achieve the same technical effect. To avoid repetition, it will not be described here. Among them, the computer-readable storage medium is such as a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc. The above description of the disclosed embodiments enables professionals and technicians in this field to implement or use the present application. Various modifications to these embodiments will be obvious to professionals and technicians in this field, and the general principles defined in this article can be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, the present application will not be limited to the embodiments shown in this article, but will conform to the widest scope consistent with the principles and novel features disclosed in this article.

Claims

1. A method for detecting the accuracy of a parking space detection system, characterized in that: The method comprises: Obtaining comparison values ​​of parking space parameters; Determine the absolute value of the difference between the test value of the parking space parameter and the control value as an error; wherein the test value of the parking space parameter is obtained by a parking space detection system; determining a plurality of values ​​of a distance parameter between the vehicle and the parking space corresponding to the parking space parameter; Taking the distance parameter as an independent variable, determining a function value as a coefficient of the parking space parameter; wherein the value of the function is determined according to multiple values ​​of the distance parameter, the value of the function is greater than zero, the derivative of the function is greater than zero, and the derivative of the function is monotonically decreasing; The accuracy of the parking space detection system is determined according to the product of the error and the coefficient.

2. The method according to claim 1, characterized in that The parking space parameters include parking space angular coordinates, and determining the distance parameters between the vehicle and the parking space corresponding to the parking space parameters includes: The modulus of the parking space angle coordinate is determined as the distance parameter.

3. The method according to claim 1, characterized in that The parking space parameter includes an inclination angle between the vehicle and the parking space, and determining a distance parameter between the vehicle and the parking space corresponding to the parking space parameter includes: The modulus of the first parking space angular coordinate of the parking space entrance and half of the sum of the modulus of the first parking space angular coordinate of the parking space entrance are determined as the distance parameter.

4. The method according to claim 1, wherein The functions include: .

5. The method according to claim 1, wherein The step of obtaining the comparison value of the parking space parameter includes: The comparison values ​​of the parking space parameters are obtained through the RT3000 detection equipment.

6. The method according to claim 1, characterized in that The base station calibrates the reference value of the parking space parameter, and obtaining the reference value of the parking space parameter includes: Obtaining a comparison value of the parking space parameter within a preset detection range; wherein the preset detection range is a signal coverage range of the base station; Obtaining test values ​​of the parking space parameters through the parking space detection system includes: The test value of the parking space parameter is obtained by the parking space detection system within a preset detection range.

7. A device for detecting the accuracy of a parking space detection system, characterized in that: The device comprises: A data acquisition unit, used to obtain a comparison value of a parking space parameter; an error determination unit, configured to determine an absolute value of a difference between a test value of the parking space parameter and the reference value as an error; wherein the test value of the parking space parameter is obtained by a parking space detection system; a parameter determination unit, configured to determine a plurality of values ​​of a distance parameter between the vehicle and the parking space corresponding to the parking space parameter; a coefficient determination unit, configured to determine a function value as a coefficient of the parking space parameter using the distance parameter as an independent variable; wherein the value of the function is determined according to multiple values ​​of the distance parameter, the value of the function is greater than zero, the derivative of the function is greater than zero, and the derivative of the function is monotonically decreasing; An accuracy determination unit is used to determine the accuracy of the parking space detection system according to the product of the error and the coefficient.

8. A system for detecting the accuracy of a parking space detection system, characterized in that: The system for detecting the accuracy of the parking space detection system includes: Parking space detection system, used to obtain test values ​​of parking space parameters; A detection device for obtaining a reference value of the parking space parameter; A data processing device is used to determine the absolute value of the difference between the test value and the control value of the parking space parameter as an error; determine multiple values ​​of the distance parameter between the vehicle and the parking space corresponding to the parking space parameter; use the distance parameter as an independent variable to determine the value of a function as a coefficient of the parking space parameter; wherein the value of the function is determined according to the multiple values ​​of the distance parameter, the value of the function is greater than zero, the derivative of the function is greater than zero, and the derivative of the function is monotonically decreasing; and determine the accuracy of the parking space detection system according to the product of the error and the coefficient.

9. An electronic device for detecting the accuracy of a parking space detection system, characterized in that: The electronic device includes a processor and a memory, wherein the memory stores code, and the processor is configured to call the code stored in the memory to implement the following functions: Obtaining comparison values ​​of parking space parameters; Determine the absolute value of the difference between the test value of the parking space parameter and the control value as an error; wherein the test value of the parking space parameter is obtained by a parking space detection system; determining a plurality of values ​​of a distance parameter between the vehicle and the parking space corresponding to the parking space parameter; Taking the distance parameter as an independent variable, determining a function value as a coefficient of the parking space parameter; wherein the value of the function is determined according to multiple values ​​of the distance parameter, the value of the function is greater than zero, the derivative of the function is greater than zero, and the derivative of the function is monotonically decreasing; The accuracy of the parking space detection system is determined according to the product of the error and the coefficient.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium is used to store a computer program, and the computer program is used to execute the method according to any one of claims 1 to 6.

Images