Detection method, device, simulation method, vehicle and medium for abnormal road surface

Abstract

This application relates to a method, device, simulation method, vehicle, and medium for detecting abnormal road surfaces. The method comprises: obtaining real road surface information of a target road; identifying abnormal road surfaces on the target road based on the real road surface information; and, upon identifying the abnormal road surface, determining the currently unidentified abnormal road surface on the target road based on the correlation between the abnormal road surface and currently unidentified abnormal road surfaces on the target road. This method can address the issue of under-identification of abnormal road surfaces, thereby effectively improving the authenticity of abnormal road surface identification.

Description

Technical Field

[0001] The present application relates to the field of computer vision technology, and in particular to a method, device, simulation method, vehicle, and medium for detecting abnormal road surfaces. Background Art

[0002] Because simulation testing can simulate various real-world road scenarios, addressing the incompleteness of real-world vehicle testing due to limited testing sites, it is incorporated into the development process of vehicles, especially intelligent vehicles, to enable simulation testing of various scenarios. During simulation testing, it is necessary to first obtain real-world road scenario information, simulate a virtual road scenario based on this information, and then perform simulation testing on the vehicle within this virtual scenario.

[0003] In related technologies, roadside sensing devices perceive the actual road scene and determine whether there are any abnormal road surfaces. If so, a simulated image of the abnormal road surface is displayed. However, limitations such as the layout and performance of the roadside sensing devices and the simulation platform's simulation capabilities can result in incomplete recognition of abnormal road surfaces, which in turn leads to incomplete simulation of abnormal road surfaces, thus failing to accurately reflect the actual road scene. Summary of the Invention

[0004] Based on this, it is necessary to provide a detection method, device, simulation method, vehicle and medium for abnormal road surfaces that can solve the problem of missing abnormal road surface identification in response to the above technical problems.

[0005] A method for detecting abnormal road surface comprises the following steps:

[0006] Obtain the real road surface information of the target road;

[0007] Identify abnormal road surfaces on target roads based on real road surface information;

[0008] When an abnormal road surface is identified, the currently unidentified abnormal road surface on the target road is determined based on the correlation between the abnormal road surface and the currently unidentified abnormal road surface on the target road.

[0009] A device for detecting abnormal road surface, comprising:

[0010] An acquisition module is used to obtain the real road surface information of the target road;

[0011] A recognition module is used to identify abnormal road surfaces on the target road based on real road surface information;

[0012] The determination module is used to determine the current unidentified abnormal road surface on the target road based on the correlation between the abnormal road surface and the current unidentified abnormal road surface on the target road when an abnormal road surface is identified.

[0013] A method for simulating abnormal road surfaces comprises the following steps:

[0014] Obtain the real road surface information of the target road;

[0015] Identify abnormal road surfaces on target roads based on real road surface information;

[0016] When an abnormal road surface is identified, determining the current unidentified abnormal road surface on the target road based on the correlation between the abnormal road surface and the current unidentified abnormal road surface on the target road;

[0017] Simulate and display abnormal road surfaces and currently unidentified abnormal road surfaces.

[0018] A vehicle includes a memory and a processor. The memory stores a computer program. The processor implements the steps of the above-mentioned detection method when executing the computer program.

[0019] A computer-readable storage medium stores a computer program, which implements the steps of the above-mentioned detection method or simulation method when executed by a processor.

[0020] The above-mentioned abnormal road surface detection method, device, simulation method, vehicle and medium can effectively solve the problem of missing abnormal road surface identification and then missing abnormal road surface simulation due to limitations of the layout and performance of the roadside sensing device and the simulation performance of the simulation platform, by estimating the currently unidentified abnormal road surface that may exist on the target road based on the correlation between the abnormal road surface that has been identified and the abnormal road surface on the target road. This effectively improves the authenticity of the abnormal road surface simulation and then improves the authenticity of the simulation of real road scenes. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a diagram showing an application scenario of a method for detecting abnormal road surfaces in one embodiment;

[0022] Figure 2 This is a system architecture diagram of a method for detecting abnormal road surfaces in one embodiment;

[0023] Figure 3 1 is a flow chart of a method for detecting abnormal road surfaces in one embodiment;

[0024] Figure 4 This is a schematic flow chart of step S306 in the first embodiment;

[0025] Figure 5 A flowchart for obtaining correlation coefficients between abnormal road surfaces in one embodiment;

[0026] Figure 6This is a flow chart of step S306 in the second embodiment;

[0027] Figure 7 Schematic diagram of the process of step S602 in one embodiment;

[0028] Figure 8 Schematic diagram of the process of step S606 in one embodiment;

[0029] Figure 9 is a structural block diagram of a device for detecting abnormal road surface in one embodiment;

[0030] Figure 10 Flowchart of a method for simulating abnormal road surfaces in one embodiment. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solutions and advantages of this application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0032] The method for detecting abnormal road surface provided by this application can be applied to Figure 1 In the application scenario shown, the application scenario is an autonomous driving simulation scenario, in which the simulation system simulates the real abnormal road surface on the target road for the autonomous driving simulator to perform vehicle performance simulation testing.

[0033] Based on the above application scenarios, the method for detecting abnormal road surface provided by this application can be Figure 2 The system architecture shown is implemented. The roadside sensing device 102, simulation platform 104, and transmission channel 106 constitute a simulation system, which can be a digital twin simulation system. Digital twins fully utilize data such as physical models, sensor updates, and operational history to integrate multidisciplinary, multi-physical, multi-scale, and multi-probability simulation processes, mapping them in virtual space to reflect the entire lifecycle of the corresponding physical equipment. A digital twin simulation system is a simulation system built based on digital twin technology.

[0034] In this system, a roadside sensing device 102 collects real-world road surface information on a target road and transmits it to a simulation platform 104 via a transmission channel 106. The simulation platform 104 obtains the real-world road surface information on the target road and, based on the real-world road surface information, identifies abnormal road surfaces on the target road. Upon identifying an abnormal road surface, the simulation platform 104 determines the currently unidentified abnormal road surface on the target road based on the correlation between the abnormal road surface and the currently unidentified abnormal road surface on the target road. The roadside sensing device 102 can be one or more roadside cameras located on one or both sides of the target road; the simulation platform 104 can be a terminal device such as a personal computer, laptop, or tablet equipped with a simulator or simulation software; and the transmission channel 106 can be a 3G, 4G, or 5G network channel. Furthermore, the vehicle 108 can also obtain road surface information ahead of the vehicle using an in-vehicle camera and transmit this information to the simulation platform 104 via the transmission channel 106 to determine the accuracy of the abnormal road surface detected by the simulation platform 104 using the aforementioned detection method. In addition, the simulation platform 104 can also send the abnormal road surface obtained by the above detection method to the vehicle 108 through the transmission channel 106, so that the vehicle 108 can be warned in advance based on the abnormal road surface so that the driver or the unmanned vehicle can take corresponding measures.

[0035] The following describes in detail the implementation details of the technical solutions of the embodiments of the present application.

[0036] In one embodiment, Figure 3 As shown, a method for detecting abnormal road surface is provided, and the method is applied to Figure 2 Taking the simulation platform in

[15] as an example, the method for detecting abnormal road surface may include the following steps:

[0037] Step S302: Acquire the actual road surface information of the target road.

[0038] Target roads are real roads where abnormal road surfaces need to be detected. These can include expressways, first-class highways, second-class highways, and third-class highways, with no specific restrictions. Expressways are the highest level and primarily serve as a means of high-speed travel for vehicles. First-class highways, located below expressways, primarily connect major economic and political centers. Second-class highways, located below first-class highways, primarily serve specific functional areas. Third-class highways, located below second-class highways, primarily connect local counties and towns.

[0039] Real road surface refers to the road surface on a real road, such as a real road surface on a highway. Real road surface information refers to information that reflects the real road surface, and may be image information, video information, data information, etc., and may be obtained by roadside sensing device 102. For example, real road surface information may be acquired by roadside sensing device 102, such as a roadside camera, in the form of image information. This real road surface information is then transmitted to simulation platform 104 via transmission channel 106, and simulation platform 104 receives the real road surface information.

[0040] Step S304: Identify abnormal road surfaces on the target road based on the real road surface information.

[0041] Abnormal road surface refers to a road surface with abnormal conditions. In contrast to normal road surface, it may include road surfaces with abnormal conditions such as potholes, bumps, broken speed bumps, diseases, and missing manhole covers.

[0042] After obtaining the actual road surface information of the target road, the simulation platform 104 can identify whether there are any abnormal road surfaces on the target road according to a preset analysis strategy based on the actual road surface information. For example, if the actual road surface information is image information, the image information can be processed to obtain characteristic information of the road surface in the image. This information can then be compared with pre-stored characteristic information of abnormal road surfaces to determine whether there are any abnormal road surfaces in the image. If so, it indicates that there are abnormal road surfaces on the target road; otherwise, it indicates that there are no abnormal road surfaces on the target road.

[0043] Step S306 : When an abnormal road surface is identified, the currently unidentified abnormal road surface on the target road is determined based on the correlation between the abnormal road surface and the currently unidentified abnormal road surface on the target road.

[0044] It is understandable that in actual roads, if a road is of good quality, then there will be fewer abnormal road surfaces on that road, and conversely, there will be more abnormal road surfaces. For example, if the quality of a highway is good, then the possibility of abnormalities is smaller and there will be fewer abnormal road surfaces. However, if the quality of a third-class highway is poor, then the possibility of abnormalities is greater and there will be more abnormal road surfaces. Therefore, if one abnormal road surface appears on a certain road, then the possibility of another abnormal road surface will be higher. In other words, there is a certain correlation between abnormal road surfaces on the same type of road. Based on this correlation, after obtaining one abnormal road surface, the possibility of the existence of another abnormal road surface can be inferred. Therefore, when the simulation platform 104 identifies the presence of an abnormal road surface on the target road, it can infer whether there is a currently unidentified abnormal road surface on the target road based on the abnormal road surface and the correlation between the abnormal road surface and the currently unidentified abnormal road surface on the target road.

[0045] The term "same-class road" refers to roads of the same type, specifically roads with similar road surface quality. For example, all highways are of the same class, all first-class roads are of the same class, and all second-class roads are of the same class. Correlation refers to the degree of association between two variables. The correlation between abnormal road surfaces refers to the degree of correlation between the same or different abnormal road surfaces on roads of the same class. The correlation between abnormal road surfaces identified based on real road surface information and currently unidentified abnormal road surfaces refers to the degree of correlation between already identified abnormal road surfaces and currently unidentified abnormal road surfaces. Currently unidentified abnormal road surfaces refer to abnormal road surfaces on the target road other than those identified based on real road surface information. Here, these refer to inferred abnormal road surfaces, which can be the same or different from the type of abnormal road surfaces identified based on real road surface information. For example, both the identified abnormal road surface and the currently unidentified abnormal road surface may have potholes, or the identified abnormal road surface may have potholes while the currently unidentified abnormal road surface may have bumps.

[0046] In this example, since the currently unidentified abnormal road surface that may exist on the target road can be inferred based on the already identified abnormal road surface and the correlation between the abnormal road surface and the currently unidentified abnormal road surface, it can effectively solve the problem of missing abnormal road surface recognition caused by uncontrollable factors such as abnormality of the roadside sensing device 102 (such as failure), abnormality of the transmission channel 106 (such as network instability leading to data loss), insufficient simulation performance of the simulation platform 104 (such as poor information restoration capability), incomplete coverage of the roadside sensing device 102 (such as only part of the road is equipped with a roadside sensing device 102), or obstruction of the roadside sensing device 102 (such as obstruction by obstacles), which in turn leads to missing abnormal road surface simulation, so that the abnormal road surface obtained by simulation can truly reflect the actual abnormal road surface conditions.

[0047] Furthermore, the simulation platform 104 can also virtually display the identified and inferred abnormal road surfaces. For example, the simulation platform 104 retrieves virtual images corresponding to the identified and inferred abnormal road surfaces from a simulation image database and then displays the virtual images. It should be noted that all abnormal road surfaces encountered by real vehicles can be stored in the simulation system's database and virtual images can be generated. After the simulation platform 104 has determined all abnormal road surfaces on the target road, it can retrieve virtual images of the corresponding abnormal road surfaces from the database for display.

[0048] In this embodiment, by estimating the currently unidentified abnormal road surface based on the existing abnormal road surfaces and the correlation between the abnormal road surfaces, it is possible to effectively solve the problem of missing abnormal road surface identification and thus missing abnormal road surface simulation due to limitations on the layout and performance of the roadside sensing device and the simulation performance of the simulation platform, thereby effectively improving the authenticity of the abnormal road surface simulation and thus improving the authenticity of the real road scene simulation.

[0049] In one embodiment of the present invention, reference Figure 4 As shown, according to the correlation between the abnormal road surface and the currently unidentified abnormal road surface on the target road, determining the currently unidentified abnormal road surface on the target road includes:

[0050] Step S402 : determining a first correlation coefficient between the abnormal road surface and a currently unidentified abnormal road surface based on the correlation coefficient between the abnormal road surface and a preset abnormal road surface.

[0051] The correlation coefficient is a quantity that studies the degree of linear correlation between variables. The simple correlation coefficient is also called the correlation coefficient, which is used to measure the linear relationship between two variables. The correlation coefficient between abnormal road surfaces refers to the correlation coefficient between the same or different abnormal road surfaces on the same type of road. This correlation coefficient can be set in advance.

[0052] In one embodiment of the present invention, reference Figure 5 As shown in Figure 2, the correlation coefficients between abnormal road surfaces can be obtained by the following methods:

[0053] Step S502: Obtain the road type of an abnormal road surface on the target road or on a road of the same type as the target road.

[0054] Step S504 , obtaining the number of times the vehicle encounters each type of abnormal road surface while traveling on the target road or a road of the same type as the target road within a preset time period.

[0055] In one embodiment of the present invention, obtaining the number of times a vehicle encounters each type of abnormal road surface while traveling on a target road or a road of the same type as the target road within a preset time period includes obtaining from a historical database the number of times a vehicle encounters each type of abnormal road surface while traveling on a target road or a road of the same type as the target road within a historical preset time period.

[0056] It should be noted that the types of abnormal road surfaces that usually appear on different road types are different. For example, there are no manhole covers and speed bumps on highways, so there will be no abnormal road surfaces with missing manhole covers and damaged speed bumps. However, tertiary roads usually have manhole covers, speed bumps, etc., so there are abnormal road surfaces with missing manhole covers and damaged speed bumps. Therefore, the correlation between the abnormal road surfaces obtained based on the number of times a vehicle encounters each type of abnormal road surface when driving on the target road or a road of the same type as the target road within a preset time period is more in line with the actual situation, and can make the inferred abnormal road surfaces more reliable.

[0057] Specifically, the simulation platform 104 may obtain the number of times each type of abnormal road surface is encountered by all real vehicles on the target road or on roads of the same type as the target road. For example, when the target road is a highway, the number of times each type of abnormal road surface is encountered by all real vehicles on the highway is obtained. Due to the large number of highways, the number of times each type of abnormal road surface is encountered by all real vehicles on the highway may be obtained from a portion of a particular highway or from portions of several highways. There is no specific limitation here, as long as the abnormal road surfaces encountered by all real vehicles are in areas with similar road quality.

[0058] Since abnormal road surfaces can easily cause vehicle driving abnormalities or even traffic accidents, in actual driving, every time a real vehicle (there may be more than one vehicle driving on a real road) encounters an abnormal road surface, it will automatically report this situation to a road monitoring platform such as a vehicle network cloud server. The road monitoring platform records the number of times all real vehicles encounter each type of abnormal road surface (the situation of abnormal road surfaces may change dynamically due to reasons such as road maintenance, but this has no effect on this application). Assume that there are n types of abnormal road surfaces encountered by real vehicles, namely abnormal road surface 1, abnormal road surface 2, ..., abnormal road surface n. Further, the road monitoring platform counts the number of abnormal road surfaces 1, abnormal road surface 2, ..., abnormal road surface n encountered by all real vehicles within a historical preset time period (the selection of the historical preset time period depends on the specific situation and is based on the time span recorded by the road monitoring platform). Then, the simulation platform 104 obtains the number of abnormal road surfaces 1, abnormal road surface 2, ..., abnormal road surface n encountered by all real vehicles within the historical preset time period from the road monitoring platform.

[0059] It should be noted that this step determines the frequency of abnormal road surfaces through the vehicle's "historical encounters". In fact, "historical encounters" is only a way to obtain the frequency of abnormal road surfaces.

[0060] In another embodiment of the present invention, the number of times a vehicle encounters each type of abnormal road surface while traveling on a target road or a road of the same type as the target road within a preset time period is obtained, including: estimating the number of times a vehicle encounters each type of abnormal road surface while traveling on the target road or a road of the same type as the target road within a future preset time period based on the vehicle's driving route.

[0061] For example, if a roadside sensing device, such as a roadside camera, captures an abnormal road surface on a target road or a road of the same type, and another roadside sensing device, such as a roadside camera, on the target road or a road of the same type detects that a vehicle will inevitably pass through the section of road where the abnormal road surface is located, it can be determined that the vehicle will inevitably encounter the abnormal road surface. This method can then be used to determine the number of times the vehicle encounters each type of abnormal road surface on the target road or a road of the same type within a preset time period in the future. Thus, the frequency of abnormal road surface occurrences can be determined by predicting the vehicle's route.

[0062] It should be noted that this step determines the frequency of abnormal road surfaces based on the vehicle's "driving route." In reality, the "driving route" is only one way to determine the frequency of abnormal road surfaces. In practical applications, other methods can also be used to determine the frequency of abnormal road surfaces, and this is not a limitation here.

[0063] Step S506: Determine the correlation coefficients between abnormal road surfaces based on the number of times.

[0064] In one embodiment of the present invention, the correlation coefficients between abnormal road surfaces are obtained according to the number of times in the following manner: a preset time length is divided into intervals to obtain a plurality of sub-time lengths; a plurality of first numbers are obtained by obtaining the number of times a vehicle encounters a first type of abnormal road surface while traveling on a target road or a road of the same type as the target road in each sub-time length, and a plurality of second numbers are obtained by obtaining the number of times a vehicle encounters a second type of abnormal road surface while traveling on a target road or a road of the same type as the target road in each sub-time length; the mean square error of the plurality of first numbers is obtained as a first mean square error, the mean square error of the plurality of second numbers is obtained as a second mean square error, and the covariance between the plurality of first numbers and the plurality of second numbers is obtained; and the correlation coefficients between the first type of abnormal road surface and the second type of abnormal road surface are determined according to the first mean square error, the second mean square error and the covariance.

[0065] For example, after obtaining the number of times a vehicle encounters each type of abnormal road surface on a target road or a road of the same type as the target road within a preset time period in the above manner, the simulation platform 104 can evenly divide the preset time period into m sub-time periods (m is greater than or equal to 2, and there is no specific limit here), and record the number of times all real vehicles encounter abnormal road surface 1, abnormal road surface 2, ..., abnormal road surface n within the t-th sub-time period as x, respectively. 1,t 、x 2,t ,…,x n,t , that is, in the t-th sub-time, the number of times all real vehicles encounter abnormal road surface 1 is x 1,t , the number of times the abnormal road surface 2 is encountered is x 2,t ,…, the number of times the abnormal road surface n is encountered is x n,t .

[0066] Then, based on probability theory and quantitative statistics, the correlation coefficient between any two different abnormal road surfaces, i.e., any two types of abnormal road surfaces, can be determined using the times obtained in the above steps. i With abnormal road surface j The correlation coefficient between them can be obtained by the above method firstly to obtain the abnormal road conditions encountered by all vehicles in the entire preset time. i times to get multiple first numbers x i,1 、x i,2 ,…,x i,m , and all vehicles encountering abnormal road conditions j times to get multiple second numbers x j,1 、x j,2 ,…,x j,m , and then calculate the mean square error of multiple first numbers as the first mean square error And calculate the mean square error of multiple second numbers as the second mean square error And calculate the covariance between multiple first numbers and multiple second numbers Finally, based on the first mean square error, the second mean square error and the covariance, the correlation coefficient between abnormal road surface i and abnormal road surface j is determined in the following way:

[0067]

[0068] Where c i,j It represents the correlation coefficient between abnormal road surface i and abnormal road surface j. The correlation coefficient satisfies the symmetry, that is, c i,j =c j,i , m represents the number of sub-periods, t represents the t-th sub-period, x i,t represents the number of abnormal road surface i encountered by all real vehicles in the t-th sub-period, x j,tIt is the number of times that all real vehicles encounter abnormal road surface j in the t-th sub-time. It should be noted that the correlation coefficient between two identical abnormal road surfaces, i.e., the same type of abnormal road surfaces, is 1. i,i =1.

[0069] It should be noted that the process of obtaining the correlation coefficients between other abnormal road surfaces is similar to the process of obtaining the correlation coefficients between abnormal road surface i and abnormal road surface i. j The process of obtaining the correlation coefficients between them is the same and will not be repeated here.

[0070] After obtaining the correlation coefficients between abnormal road surfaces in the above manner, the correlation coefficients, the road surface types corresponding to the correlation coefficients, and the road types corresponding to the correlation coefficients are stored in the database of the simulation platform 104. During actual use, the simulation platform 104 calls the correlation coefficients and determines the first correlation coefficient between the abnormal road surface and the currently unidentified abnormal road surface based on the correlation coefficients.

[0071] In one embodiment of the present invention, a first correlation coefficient between the abnormal road surface and a currently unidentified abnormal road surface is determined based on a correlation coefficient between the abnormal road surface and a pre-set abnormal road surface, including: obtaining a road surface type of the abnormal road surface and a road type of a target road; and obtaining a first correlation coefficient between the abnormal road surface and the currently unidentified abnormal road surface from the pre-set correlation coefficients between the abnormal road surfaces based on the road surface type of the abnormal road surface and the road type of the target road.

[0072] After identifying an abnormal road surface based on real road surface information, simulation platform 104 may further determine the road type of the abnormal road surface based on its characteristic information. Simultaneously, it may determine the road type of the target road based on user-input parameters or the characteristic information of the target road. Simulation platform 104 may then retrieve a correlation coefficient between the abnormal road surface and the currently unidentified abnormal road surface from a database based on the road type of the abnormal road surface and the road type of the target road, to be used as a first correlation coefficient.

[0073] Step S404: determining the currently unidentified abnormal road surface on the target road according to the first correlation coefficient.

[0074] Assume that the abnormal road surface obtained by the simulation platform 104 based on the real road surface information of the target road is abnormal road surface i. Then, when all possible abnormal road surfaces on the target road and roads of the same type as the target road include the abnormal road surface 1, abnormal road surface 2, ..., abnormal road surface n, the first correlation coefficients between the abnormal road surface i and the abnormal road surfaces 1, 2, ..., n are c 1,i 、c 2,i ,...,c n,iThen, the simulation platform 104 obtains the first correlation coefficient c 1,i 、c 2,i ,...,c n,i Sort them, and then use the abnormal road surface corresponding to the first correlation coefficient at the top of the sort as the current unidentified abnormal road surface.

[0075] In the above embodiment, the currently unidentified abnormal road surface can be estimated based on the road surface type of the existing abnormal road surface, the road type of the target road, and the pre-set correlation coefficients between the abnormal road surfaces. The pre-set correlation coefficients between the abnormal road surfaces are obtained based on the number of times the vehicle encounters each type of abnormal road surface while traveling on the target road or a road of the same type as the target road within a preset time period. The pre-set correlation coefficients between the abnormal road surfaces correspond to the target road, thereby making the estimated abnormal road surface more reliable.

[0076] In one embodiment of the present invention, reference Figure 6 As shown, the method of determining a previously unidentified abnormal road surface on the target road based on the correlation between the abnormal road surface and the currently unidentified abnormal road surface on the target road further includes:

[0077] Step S602: Obtain the true rate of abnormal road surface.

[0078] The authenticity rate of an abnormal road surface refers to the probability that the abnormal road surface determined based on the real road surface information of the target road can reflect the real road surface on the target road. Specifically, it can be the probability that the abnormal road surface determined by the simulation platform 104 based on the real road surface information can reflect the real road surface on the target road. It is affected by many factors, such as the acquisition performance of the roadside perception device 102, the transmission performance of the transmission channel 106 and the simulation performance of the simulation platform 104. Therefore, the authenticity rate of the abnormal road surface can be determined based on these influencing information.

[0079] In one embodiment of the present invention, reference Figure 7 As shown, the true rate of abnormal road surface is obtained, including:

[0080] Step S702: obtaining the collection authenticity rate, transmission loss rate, and restoration success rate of the real road information.

[0081] The acquisition accuracy rate refers to the probability that the collected road surface information is authentic. Specifically, it can be the probability that the road surface information captured by the roadside sensing device 102, such as a roadside camera, is authentic. This is an attribute parameter of the roadside sensing device 102 and can be obtained from the device's manual or through pre-testing. In practical applications, the failure rate of the roadside sensing device 102 can be used as the acquisition accuracy rate.

[0082] The transmission loss rate refers to the rate at which real road surface information is lost during transmission. Specifically, it can be the probability that real road surface information captured by roadside sensing device 102, such as a roadside camera, is lost during transmission to simulation platform 104 via transmission channel 106, such as a network. This is a property parameter of transmission channel 106 and can be obtained in advance through experimental testing. In practical applications, the packet loss rate of transmission channel 106 can be used as the transmission loss rate.

[0083] The restoration success rate refers to the success rate of restoring the received real road surface information, specifically, it can be the success rate of the simulation platform 104 restoring the received real road surface information. It is an attribute parameter of the simulation platform 104 and can be obtained from the manual of the simulation platform 104 or through experimental testing in advance.

[0084] Step S704 : Obtaining a true rate of the abnormal road surface according to one or more of the acquisition true rate, the transmission loss rate, and the restoration success rate.

[0085] From the above, it can be seen that the acquisition truth rate corresponds to the roadside sensing device 102, the transmission loss rate corresponds to the transmission channel 106, and the restoration success rate corresponds to the simulation platform 104. The roadside sensing device 102, the transmission channel 106 and the simulation platform 104 are three related independent devices, which can be considered to be related and independent when working. Therefore, after obtaining the acquisition truth rate, transmission loss rate and restoration success rate of the real road information, the probability statistics method can be used to calculate the truth rate of the abnormal road surface based on one or more of the acquisition truth rate, transmission loss rate and restoration success rate. Assume that the acquisition truth rate is p sensor , the transmission loss rate is p transmission , the restoration success rate is p refresh , then the calculated true rate of abnormal road surface can be p real =(1-p sensor )(1-p transmission )(1-p refresh ). It is understandable that the ideal case is 1.

[0086] It should be noted that the authenticity rate of abnormal road surfaces can be obtained in advance through the above method, and then stored in the database of the simulation platform 104, and can be directly called when used; or, the collection authenticity rate, transmission loss rate and restoration success rate of real road information can be first determined through the above method, and these three can be stored in the database of the simulation platform 104. When used, one or more of them can be selected according to actual needs to calculate and obtain the authenticity rate of abnormal road surfaces.

[0087] Step 604 : determining the existence rate of the currently unidentified abnormal road surface based on the true rate of the abnormal road surface and the first correlation coefficient between the abnormal road surface and the currently unidentified abnormal road surface.

[0088] The existence rate of the currently unidentified abnormal road surface refers to the probability that any type of abnormal road surface that may exist on the target road or on a road of the same type as the target road exists on the target road.

[0089] When the simulation platform 104 determines that there is an abnormal road surface i on the target road based on the real road surface information, it determines that the authenticity rate of the abnormal road surface i is p reali If the correlation between abnormal road surface j and abnormal road surface i is large, then the probability of abnormal road surface j existing on the target road is large, otherwise it is small. This means that the probability of abnormal road surface j existing on the target road is proportional to the correlation coefficient between it and abnormal road surface i. Therefore, when abnormal road surface i is obtained, the probability of abnormal road surface j existing on the target road, that is, the existence rate, is p. reali c i,j , and so on, the probability of the occurrence of the above abnormal road surface 1, abnormal road surface 2, ..., abnormal road surface n is p reali c 1,i 、p reali c 2,i ,…,p reali c n,i , that is, the existence rates of currently unidentified abnormal roads are p reali c 1,i 、p reali c 2,i ,…,p reali c n,i It should be noted that, due to c i,i =1, so p reali c i,i =p reali .

[0090] Step S606: Determine the current unidentified abnormal road surface on the target road based on the existence rate of the current unidentified abnormal road surface.

[0091] After obtaining the current presence rate of unidentified abnormal roads, the simulation platform 104 can determine whether there is a current unidentified abnormal road on the target road based on this presence rate. For example, the presence rates of abnormal road 1, abnormal road 2, ..., and abnormal road n can be ranked, and the top-ranked abnormal road surfaces can be used as the current unidentified abnormal road on the target road. Alternatively, the presence rates of abnormal road 1, abnormal road 2, ..., and abnormal road n can be sequentially determined to determine whether they are higher than a preset presence rate. If so, the corresponding abnormal road is considered to be present on the target road. Of course, other methods can also be used to determine whether there is a current unidentified abnormal road on the target road based on the presence rate of the current unidentified abnormal road.

[0092] In one embodiment of the present invention, reference Figure 8As shown, according to the existence rate of the current unidentified abnormal road surface, determining the current unidentified abnormal road surface on the target road includes:

[0093] Step S802 : obtaining a random rate of a currently unidentified abnormal road surface, wherein the random rate is determined according to a random number, and the random number obeys a uniform distribution of 0-1.

[0094] The random rate refers to the probability of the current unidentified abnormal road surface randomly appearing, which can be represented by a random number. For the above abnormal road surface 1, abnormal road surface 2, ..., abnormal road surface n, the simulation platform 104 will generate n random numbers that obey the 0-1 uniform distribution, which are recorded as ε1, ε2, ..., ε n Among them, the random number generation method can adopt existing tools, such as simulation software MATLAB.

[0095] Step S804: determining the current unidentified abnormal road surface on the target road according to the existence rate and random rate of the current unidentified abnormal road surface.

[0096] According to one embodiment of the present invention, the current unidentified abnormal road surface on the target road is determined based on the existence rate and random rate of the current unidentified abnormal road surface, including: when the random rate is less than the existence rate, determining that there is a current unidentified abnormal road surface on the target road.

[0097] The simulation platform 104 obtains random numbers ε1, ε2, ..., ε n Afterwards, these random numbers can be compared with the existence rate of the corresponding abnormal road surface to determine whether there is an abnormal road surface that has not been identified on the target road. reali c 1,i 、ε2≤p reali c 2,i ,…,ε n ≤p reali c n,i Is it true? If so, the corresponding abnormal road surface is regarded as the currently unidentified abnormal road surface that may exist on the target road. Assume that ε k ≤p reali c k,i If it is established, it is determined that there will be an abnormal road surface k on the target road.

[0098] Therefore, on the premise that the existence of abnormal road surfaces on the target road is determined based on the real road surface information of the target road, the currently unidentified abnormal road surfaces that may exist on the target road can be effectively determined based on the correlation between the abnormal road surfaces and the abnormal road surfaces. That is, the abnormal road surfaces that have not been photographed can be estimated or predicted based on the abnormal road surfaces that have been photographed, which can assist the simulation system to comprehensively judge which abnormal road surfaces exist on the target road, and then make up for the lack of road surface simulation caused by uncontrollable factors such as insufficient simulation performance of the simulation system's roadside sensing device, transmission channel or simulation platform itself, or incomplete coverage of the roadside sensing device or occlusion, thereby effectively improving the authenticity of the simulation.

[0099] In order to verify whether the abnormal road surface detection method of the present application is effective, a test can be conducted on a simulation platform to count the abnormal road surfaces that can be simulated by the simulation platform at one time. The statistical results are shown in Table 1:

[0100] Table 1

[0101] Experimental level sequence The number of abnormal road surfaces simulated by existing technologies The number of abnormal road surfaces simulated in this application First experiment 1 3 Second experiment 1 4 The third experiment 1 3 The fourth experiment 1 3

[0102] By comparing with real roads, it is obvious that the performance of this application is better than existing technologies, and the abnormal road surface simulated is more comprehensive.

[0103] It should be understood that although Figure 3-8 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in an order that is not currently recognized. Figure 3-8 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with the currently unidentified step or at least part of the sub-steps or stages of the currently unidentified step.

[0104] In summary, the method for detecting abnormal road surfaces according to an embodiment of the present invention can effectively solve the problem of missing abnormal road surface simulation due to limitations on the layout and performance of roadside perception devices and the simulation performance of the simulation platform, by estimating the currently unidentified abnormal road surfaces based on the already identified abnormal road surfaces and the correlation between the abnormal road surfaces. This effectively improves the authenticity of the abnormal road surface simulation and further improves the authenticity of the simulation of real road scenes.

[0105] It should be noted that the abnormal road surface detection method of the present application can be used not only in simulation tests, such as in an autonomous driving simulation system, by simulating real abnormal road surfaces on the road for autonomous driving simulator testing, but also in vehicle control, such as predicting potential abnormal road surfaces on the road to provide a reference for safe driving to drivers or autonomous driving vehicles.

[0106] In one embodiment, a device for detecting abnormal road surface is provided, referring to Figure 9 As shown, the abnormal road surface detection device 900 may include: an acquisition module 902 , an identification module 904 and a determination module 906 .

[0107] Among them, the acquisition module 902 is used to obtain the real road surface information of the target road; the identification module 904 is used to identify abnormal road surfaces on the target road based on the real road surface information; the determination module 906 is used to determine the current unidentified abnormal road surface on the target road based on the correlation between the abnormal road surface and the currently unidentified abnormal road surface on the target road when an abnormal road surface is identified.

[0108] In one embodiment, the determination module 906 is specifically used to determine a first correlation coefficient between the abnormal road surface and the currently unidentified abnormal road surface based on the correlation coefficient between the abnormal road surface and a preset abnormal road surface; and determine the currently unidentified abnormal road surface on the target road based on the first correlation coefficient.

[0109] Furthermore, the determination module 906 is specifically used to obtain the road surface type of the abnormal road surface and the road type of the target road; based on the road surface type of the abnormal road surface and the road type of the target road, obtain a first correlation coefficient between the abnormal road surface and the currently unidentified abnormal road surface from the pre-set correlation coefficients between the abnormal road surfaces.

[0110] In another embodiment, the determination module 906 is specifically used to obtain the true rate of abnormal road surfaces; determine the existence rate of the current unidentified abnormal road surface based on the true rate of the abnormal road surface and the first correlation coefficient between the abnormal road surface and the current unidentified abnormal road surface; and determine the current unidentified abnormal road surface on the target road based on the existence rate of the current unidentified abnormal road surface.

[0111] Furthermore, the determination module 906 is specifically used to obtain the collection authenticity rate, transmission loss rate and restoration success rate of real road information; and obtain the authenticity rate of abnormal road surface according to one or more of the collection authenticity rate, transmission loss rate and restoration success rate.

[0112] In another embodiment, the determination module 906 is specifically configured to obtain a random rate of the presence of a currently unidentified abnormal road surface; and determine the currently unidentified abnormal road surface on the target road based on the presence rate and the random rate of the currently unidentified abnormal road surface. The random rate is determined based on a random number that follows a uniform distribution between 0 and 1.

[0113] Furthermore, the determination module 906 is specifically configured to determine that there is an unidentified abnormal road surface on the target road when the random rate is less than the existence rate.

[0114] The specific definitions of the device for detecting abnormal road surfaces can be found in the definitions of the method for detecting abnormal road surfaces above and will not be repeated here. Each module in the device for detecting abnormal road surfaces can be implemented in whole or in part via software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in hardware form, or stored in a computer device memory in software form, allowing the processor to call and execute the corresponding operations of each module.

[0115] In one embodiment, a method for simulating abnormal road surfaces is provided, referring to Figure 10 As shown, the following steps may be included:

[0116] Step S1002: Acquire the actual road surface information of the target road.

[0117] Step S1004: Identify abnormal road surfaces on the target road based on real road surface information.

[0118] Step S1006 , when an abnormal road surface is identified, determining the current unidentified abnormal road surface on the target road based on the correlation between the abnormal road surface and the current unidentified abnormal road surface on the target road.

[0119] Step S1008 , performing simulation display on the abnormal road surface and the currently unidentified abnormal road surface determined.

[0120] In one embodiment, the current unidentified abnormal road surface on the target road is determined based on the correlation between the abnormal road surface and the current unidentified abnormal road surface on the target road, including: determining a first correlation coefficient between the abnormal road surface and the current unidentified abnormal road surface based on the correlation coefficient between the abnormal road surface and a pre-set abnormal road surface; and determining the current unidentified abnormal road surface on the target road based on the first correlation coefficient.

[0121] In one embodiment, a first correlation coefficient between the abnormal road surface and a currently unidentified abnormal road surface is determined based on a correlation coefficient between the abnormal road surface and a pre-set abnormal road surface, including: obtaining a road surface type of the abnormal road surface and a road type of a target road; and obtaining a first correlation coefficient between the abnormal road surface and the currently unidentified abnormal road surface from the pre-set correlation coefficients between the abnormal road surfaces based on the road surface type of the abnormal road surface and the road type of the target road.

[0122] In one embodiment, the correlation coefficients between abnormal road surfaces are obtained in the following manner: the road surface types of abnormal road surfaces existing on a target road or on a road of the same type as the target road are obtained; the number of times a vehicle encounters each type of abnormal road surface while traveling on the target road or on a road of the same type as the target road within a preset time period is obtained; and the correlation coefficients between the abnormal road surfaces are determined based on the number of times.

[0123] In one embodiment, obtaining the number of times a vehicle encounters each type of abnormal road surface while traveling on a target road or a road of the same type as the target road within a preset time period includes: obtaining from a historical database the number of times a vehicle encounters each type of abnormal road surface while traveling on the target road or a road of the same type as the target road within a historical preset time period; or estimating the number of times a vehicle encounters each type of abnormal road surface while traveling on the target road or a road of the same type as the target road within a future preset time period based on the vehicle's driving route.

[0124] In one embodiment, based on the number of times, the correlation coefficients between abnormal road surfaces are obtained in the following manner: a preset time length is divided into intervals to obtain multiple sub-time lengths; a plurality of first numbers are obtained by obtaining the number of times a vehicle encounters a first type of abnormal road surface while traveling on a target road or a road of the same type as the target road in each sub-time length, and a plurality of second numbers are obtained by obtaining the number of times a vehicle encounters a second type of abnormal road surface while traveling on a target road or a road of the same type as the target road in each sub-time length; the mean square error of the multiple first numbers is obtained as a first mean square error, the mean square error of the multiple second numbers is obtained as a second mean square error, and the covariance between the multiple first numbers and the multiple second numbers is obtained; and the correlation coefficient between the first type of abnormal road surface and the second type of abnormal road surface is determined based on the first mean square error, the second mean square error, and the covariance.

[0125] In one embodiment, determining the current unidentified abnormal road surface on the target road based on the correlation between the abnormal road surface and the current unidentified abnormal road surface on the target road also includes: obtaining the true rate of the abnormal road surface; determining the existence rate of the current unidentified abnormal road surface based on the true rate of the abnormal road surface and the first correlation coefficient between the abnormal road surface and the current unidentified abnormal road surface; and determining the current unidentified abnormal road surface on the target road based on the existence rate of the current unidentified abnormal road surface.

[0126] In one embodiment, obtaining the authenticity rate of abnormal road surfaces includes: obtaining the acquisition authenticity rate, transmission loss rate and restoration success rate of real road surface information; and obtaining the authenticity rate of abnormal road surfaces based on one or more of the acquisition authenticity rate, transmission loss rate and restoration success rate.

[0127] In one embodiment, the current unidentified abnormal road surface on the target road is determined based on the existence rate of the current unidentified abnormal road surface, including: obtaining the random rate of the existence of the current unidentified abnormal road surface; and determining the current unidentified abnormal road surface on the target road based on the existence rate and random rate of the current unidentified abnormal road surface.

[0128] In one embodiment, determining the current unidentified abnormal road surface on the target road based on the existence rate and random rate of the current unidentified abnormal road surface includes: when the random rate is less than the existence rate, determining that the current unidentified abnormal road surface exists on the target road.

[0129] In one embodiment, the random rate is determined according to a random number, and the random number obeys a uniform distribution between 0 and 1.

[0130] In one embodiment, a simulation display of an abnormal road surface and a determined currently unidentified abnormal road surface includes: obtaining a first virtual image corresponding to the abnormal road surface, and obtaining a second virtual image corresponding to the determined currently unidentified abnormal road surface; and displaying the first virtual image and the second virtual image.

[0131] In one embodiment, a vehicle is provided, including a memory and a processor. The memory stores a computer program, and the processor implements a method for detecting abnormal road surfaces when executing the computer program.

[0132] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, a method for detecting an abnormal road surface or a method for simulating an abnormal road surface is implemented.

[0133] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or currently unidentified medium used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0134] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0135] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A method for detecting abnormal road surface, characterized in that: The following steps are involved: Obtain the actual road surface information of the target road; identifying abnormal road surfaces on the target road based on the real road surface information; When the abnormal road surface is identified, obtaining the road type of the abnormal road surface and the road type of the target road; Based on the road type of the abnormal road surface and the road type of the target road, obtaining a first correlation coefficient between the identified abnormal road surface and all possible abnormal road surfaces on the target road and on roads of the same type as the target road from preset correlation coefficients between abnormal road surfaces, the correlation coefficient being determined based on the number of times a vehicle encounters each type of abnormal road surface on the target road or on roads of the same type as the target road within a preset time period; According to the first correlation coefficient, it is determined whether there is a currently unidentified abnormal road surface on the target road, where the currently unidentified abnormal road surface is an abnormal road surface on the target road other than the abnormal road surface identified according to the real road surface information.

2. The method for detecting abnormal road surface according to claim 1, characterized in that: The correlation coefficients between the abnormal road surfaces are obtained by: Acquire a road surface type of an abnormal road surface existing on the target road or on a road of the same type as the target road; Obtaining the number of times a vehicle encounters each type of abnormal road surface while traveling on the target road or a road of the same type as the target road within a preset time period; According to the number of times, correlation coefficients between the abnormal road surfaces are determined.

3. The method for detecting abnormal road surface according to claim 2, characterized in that: The obtaining of the number of times the vehicle encounters each type of abnormal road surface while traveling on the target road or a road of the same type as the target road within a preset time period includes: Obtaining from a historical database the number of times a vehicle encounters each type of abnormal road surface while traveling on the target road or a road of the same type as the target road within a preset historical period; or The number of times the vehicle encounters each type of abnormal road surface while driving on the target road or on a road of the same type as the target road within a preset time period in the future is estimated based on the vehicle's driving route.

4. The method for detecting abnormal road surface according to claim 3, characterized in that: According to the number of times, the correlation coefficients between the abnormal road surfaces are obtained in the following manner: Dividing the preset duration into intervals to obtain a plurality of sub-durations; A plurality of first numbers are obtained by obtaining the number of times the vehicle encounters a first type of abnormal road surface while traveling on the target road or a road of the same type as the target road in each sub-duration, and a plurality of second numbers are obtained by obtaining the number of times the vehicle encounters a second type of abnormal road surface while traveling on the target road or a road of the same type as the target road in each sub-duration; Obtaining a mean square error of the plurality of first numbers as a first mean square error, obtaining a mean square error of the plurality of second numbers as a second mean square error, and obtaining a covariance between the plurality of first numbers and the plurality of second numbers; A correlation coefficient between the first type of abnormal road surface and the second type of abnormal road surface is determined according to the first mean square error, the second mean square error, and the covariance.

5. The method for detecting abnormal road surface according to any one of claims 1 to 4, characterized in that: The determining, based on the first correlation coefficient, whether there is an unidentified abnormal road surface on the target road further includes: Obtaining a true rate of the abnormal road surface; determining the existence rate of the currently unidentified abnormal road surface according to the true rate of the abnormal road surface and a first correlation coefficient between the abnormal road surface and the currently unidentified abnormal road surface; According to the existence rate of the currently unidentified abnormal road surface, it is determined whether there is a currently unidentified abnormal road surface on the target road.

6. The method for detecting abnormal road surface according to claim 5, characterized in that: The obtaining of the true rate of the abnormal road surface includes: Obtaining the collection accuracy rate, transmission loss rate and restoration success rate of the real road information; The authenticity rate of the abnormal road surface is obtained according to one or more of the acquisition authenticity rate, the transmission loss rate, and the restoration success rate.

7. The method for detecting abnormal road surface according to claim 5, characterized in that: The determining, based on the existence rate of the currently unidentified abnormal road surface, whether there is a currently unidentified abnormal road surface on the target road comprises: Obtaining a random rate at which the currently unidentified abnormal road surface exists; It is determined whether there is a currently unidentified abnormal road surface on the target road according to the existence rate of the currently unidentified abnormal road surface and the random rate.

8. The method for detecting abnormal road surface according to claim 7, characterized in that: The determining whether the currently unidentified abnormal road surface exists on the target road according to the existence rate of the currently unidentified abnormal road surface and the random rate includes: When the random rate is less than the existence rate, it is determined that the currently unidentified abnormal road surface exists on the target road.

9. The method for detecting abnormal road surface according to claim 7, characterized in that: The random rate is determined according to a random number, and the random number obeys a uniform distribution of 0-1.

10. A device for detecting abnormal road surface, characterized in that: include: An acquisition module is used to obtain the real road surface information of the target road; an identification module, configured to identify abnormal road surfaces on the target road based on the real road surface information; a determination module, configured to, when the abnormal road surface is identified, obtain the road type of the abnormal road surface and the road type of the target road; Based on the road type of the abnormal road surface and the road type of the target road, obtaining a first correlation coefficient between the identified abnormal road surface and all possible abnormal road surfaces on the target road and on roads of the same type as the target road from preset correlation coefficients between abnormal road surfaces, the correlation coefficient being determined based on the number of times a vehicle encounters each type of abnormal road surface on the target road or on roads of the same type as the target road within a preset time period; According to the first correlation coefficient, it is determined whether there is a currently unidentified abnormal road surface on the target road, where the currently unidentified abnormal road surface is an abnormal road surface on the target road other than the abnormal road surface identified according to the real road surface information.

11. A method for simulating abnormal road surfaces, characterized in that: The following steps are involved: Obtain the actual road surface information of the target road; identifying abnormal road surfaces on the target road based on the real road surface information; When the abnormal road surface is identified, obtaining the road type of the abnormal road surface and the road type of the target road; Based on the road type of the abnormal road surface and the road type of the target road, obtaining a first correlation coefficient between the identified abnormal road surface and all possible abnormal road surfaces on the target road and on roads of the same type as the target road from preset correlation coefficients between abnormal road surfaces, the correlation coefficient being determined based on the number of times a vehicle encounters each type of abnormal road surface on the target road or on roads of the same type as the target road within a preset time period; determining, based on the first correlation coefficient, a currently unidentified abnormal road surface on the target road, wherein the currently unidentified abnormal road surface is an abnormal road surface on the target road other than an abnormal road surface identified based on real road surface information; The abnormal road surface and the determined currently unidentified abnormal road surface are simulated and displayed.

12. A vehicle comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 9 are implemented.

13. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented, or when the computer program is executed, the steps of the method according to claim 11 are implemented.

Images