Speed limit sign recognition method and device, vehicle and storage medium

Abstract

This application discloses a speed limit sign recognition method, device, vehicle, and storage medium. The method involves: acquiring a first distance between the vehicle and a target speed limit sign identified by the vehicle in its current lane; acquiring a second distance between the vehicle and each reference vehicle in the current lane using the vehicle's sensors; acquiring a third distance between the vehicle and each reference vehicle in the current lane using a server; determining a target distance between the vehicle and each reference vehicle in the current lane based on the second and third distances; and determining whether the target speed limit sign is a road speed limit sign based on the first and target distances. By combining the second distance acquired by the vehicle's sensors and the third distance acquired from the server, a more accurate target distance between the vehicle and each reference vehicle can be determined, thereby enabling a more accurate judgment of the target speed limit sign based on the target distance and the first distance between the vehicle and the target speed limit sign.

Description

Technical Field

[0001] This application relates to the field of vehicle-assisted driving technology, and more specifically, to a speed limit sign recognition method, device, vehicle, and storage medium. Background Technology

[0002] With the continuous development of vehicle driver assistance technology, the vehicle's traffic sign recognition (TSR) function has gradually improved. Typically, vehicles use a camera mounted on the windshield to identify the speed limit value on speed limit signs to assist driving. However, the speed limit signs actually recognized by the camera are not necessarily road speed limits. Some large vehicles may also have speed limit signs affixed to their rear, but these signs only limit the speed of the large vehicle itself. In such cases, the vehicle's camera can easily misidentify the speed limit sign affixed to a large vehicle ahead as a road speed limit sign, affecting the driver's judgment of the road speed limit and leading to speeding and other improper driving behaviors. Summary of the Invention

[0003] In view of the above problems, this application proposes a speed limit sign recognition method, device, vehicle and storage medium, which can obtain a more accurate distance between the vehicle and the vehicle in front, and thus make a more accurate judgment on the target speed limit sign.

[0004] In a first aspect, embodiments of this application provide a speed limit sign recognition method, the method comprising: obtaining a first distance between a vehicle and a target speed limit sign in the current lane identified by the vehicle; obtaining a second distance between the vehicle and each reference vehicle in the current lane using a vehicle sensor, and obtaining a third distance between the vehicle and each reference vehicle in the current lane from a server; determining a target distance between the vehicle and each reference vehicle in the current lane based on the second distance and the third distance; and determining whether the target speed limit sign is a road speed limit sign based on the first distance and the target distance.

[0005] Secondly, embodiments of this application provide a speed limit sign recognition device, the device comprising: a sign recognition module, a distance acquisition module, a distance determination module, and a sign judgment module. The sign recognition module is used to acquire a first distance between the vehicle and a target speed limit sign identified by the vehicle in the current lane; the distance acquisition module is used to acquire a second distance between the vehicle and each reference vehicle in the current lane using the vehicle's sensors, and to acquire a third distance between the vehicle and each reference vehicle in the current lane from a server; the distance determination module is used to determine a target distance between the vehicle and each reference vehicle in the current lane based on the second distance and the third distance; and the sign judgment module is used to determine whether the target speed limit sign is a road speed limit sign based on the first distance and the target distance.

[0006] Thirdly, embodiments of this application provide a vehicle, including: one or more processors; a memory; and one or more application programs, wherein the one or more application programs are stored in the memory and configured to be executed by the one or more processors, and the one or more application programs are configured to perform the speed limit sign recognition method provided in the first aspect above.

[0007] Fourthly, embodiments of this application provide a computer-readable storage medium storing program code, which can be called by a processor to execute the speed limit sign recognition method provided in the first aspect.

[0008] The solution provided in this application involves: acquiring a first distance between the vehicle and a target speed limit sign identified by the vehicle in the current lane; acquiring a second distance between the vehicle and each reference vehicle in the current lane using the vehicle's sensors; acquiring a third distance between the vehicle and each reference vehicle in the current lane using a server; determining a target distance between the vehicle and each reference vehicle in the current lane based on the second and third distances; and determining whether the target speed limit sign is a road speed limit sign based on the first and target distances. By combining the second distance acquired by the vehicle's sensors and the third distance acquired from the server, a more accurate target distance between the vehicle and each reference vehicle can be determined, thereby enabling a more accurate judgment of the target speed limit sign based on the target distance and the first distance between the vehicle and the target speed limit sign. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] Figure 1 A flowchart illustrating a speed limit sign recognition method provided in one embodiment of this application is shown.

[0011] Figure 2 A schematic diagram illustrating the determination of the current lane is shown in one embodiment of this application.

[0012] Figure 3 A flowchart illustrating a speed limit sign recognition method provided in another embodiment of this application is shown.

[0013] Figure 4 A schematic diagram illustrating the information interaction between the vehicle and the server in an embodiment of this application is shown.

[0014] Figure 5 A schematic diagram of the specific process of step S240 in another embodiment of this application is shown.

[0015] Figure 6 A schematic diagram of the structure of the speed limit sign recognition device provided in the embodiments of this application is shown.

[0016] Figure 7 A structural block diagram of a vehicle provided in an embodiment of this application is shown. Detailed Implementation

[0017] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0018] The TSR function of a vehicle is generally implemented by using a single camera installed on the windshield to automatically identify the speed limit value on the road speed limit sign in the current lane and display it to the driver through the instrument panel to help the driver better control the driving speed according to the road speed limit value and improve traffic efficiency.

[0019] However, in actual driving conditions, the speed limit signs in the current lane detected by the vehicle's camera are not necessarily the speed limit for that lane. This is because large vehicles such as school buses, coaches, and passenger vehicles typically display speed limit signs with different values ​​on their rear ends, according to national highway speed limits. For example, the maximum speed limits on Chinese highways are 90 km / h for trucks, 100 km / h for passenger vehicles, and 120 km / h for cars. Clearly, the speed limit signs on the rear of large vehicles only restrict the speed of the large vehicle itself, not the speed of all vehicles in the current lane. Therefore, for vehicles equipped with TSR (Traffic Speed ​​Reduction) functionality, if there is a large vehicle ahead with a speed limit sign on its rear, the vehicle's camera may misinterpret this sign as a speed limit for all vehicles in the current lane, thus affecting the driver's judgment of the current lane's speed limit and potentially leading to speeding or other improper driving.

[0020] Therefore, this application provides a speed limit sign recognition method, device, vehicle, and storage medium. By using a second distance obtained from the vehicle's sensors and a third distance obtained from a server, a more accurate target distance between the vehicle and each reference vehicle can be determined. Furthermore, based on the target distance and a first distance between the vehicle and the target speed limit sign, a more accurate judgment can be made regarding the target speed limit sign. The specific speed limit sign recognition method will be described in detail in subsequent embodiments.

[0021] Please see Figure 1 , Figure 1 This paper illustrates a flowchart of a speed limit sign recognition method according to an embodiment of this application. The following will focus on... Figure 1 The process shown is described in detail. The speed limit sign recognition method may specifically include the following steps:

[0022] Step S110: Obtain the first distance between the vehicle and the target speed limit sign in the current lane identified by the vehicle.

[0023] In this embodiment, the vehicle can use onboard sensors such as a forward-facing camera and an IFC module to identify all target speed limit signs in the current lane and the speed limit value on each sign, and determine a first distance between the vehicle and each identified target speed limit sign. Specifically, the first distance may include a first longitudinal distance between the vehicle's rear axle and the target speed limit sign in the direction of vehicle travel, and a first lateral distance between the vehicle's centerline and the target speed limit sign.

[0024] Specifically, the vehicle can identify all target speed limit signs within the current lane area based on onboard sensors. Figure 2 As shown, the vehicle can use its rear axle center as the origin, and move 2 meters to the left and right of its centerline as reference lines. The area formed by these two reference lines extending 150 meters from the rear axle center along the vehicle's direction of travel is defined as the vehicle's current lane area. Speed ​​limit signs detected by the vehicle's sensors within this current lane area are used as target speed limit signs for subsequent judgment operations.

[0025] In some implementations, after a vehicle detects a target speed limit sign ahead, it can also obtain a first height value between the target speed limit sign and the ground. This first height value can be used as a reference when determining whether the target speed limit sign is a road speed limit sign, making the judgment result more accurate.

[0026] Step S120: Obtain the second distance of the vehicle relative to each reference vehicle in the current lane through the vehicle's sensors, and obtain the third distance of the vehicle relative to each reference vehicle in the current lane from the server.

[0027] In this embodiment, in a real road environment, a target speed limit sign may be a road speed limit sign that restricts the speed of all vehicles on the road, or it may be a non-road speed limit sign affixed to the rear of a large vehicle to restrict the speed of the large vehicle itself. Therefore, after a vehicle detects the presence of a target speed limit sign in its current lane, it can further determine whether the sign is a road speed limit sign or a non-road speed limit sign, thus better assisting the vehicle's driving. Specifically, the vehicle can determine whether the target speed limit sign is affixed to the rear of a vehicle by obtaining the target distance between itself and each reference vehicle in the current lane, as well as the first distance between itself and the target speed limit sign obtained through the aforementioned steps. Furthermore, to make the target distance between itself and the reference vehicles more accurate, the vehicle can obtain a second distance between itself and each reference vehicle through its own sensors, and simultaneously obtain a third distance between itself and each reference vehicle from the server, so as to comprehensively determine a more accurate target distance between itself and the reference vehicles based on the second and third distances. Therefore, after obtaining the first distance between the vehicle and the target speed limit sign, the vehicle can further obtain the second distance between itself and each reference vehicle in the current lane through its own sensors, and obtain the third distance between itself and each reference vehicle in the current lane from the server.

[0028] Understandably, vehicles can obtain a second distance between themselves and each reference vehicle in the current lane using their own sensors. However, the accuracy of these sensors in determining this second distance, as well as in recognizing target speed limit signs, is heavily dependent on factors such as lighting conditions, sensor surface cleanliness, the angle of vehicles ahead, and the accuracy of the perception and recognition algorithm. If any of these factors changes, the accuracy of the second distance obtained by the sensors will be affected. Therefore, vehicles can also obtain a third distance from the server relative to each reference vehicle in the current lane, thereby making the target distance determined by the vehicle more accurate.

[0029] In some implementations, the vehicle and each reference vehicle in the current lane can upload their own vehicle information from the base station to the server through their own vehicle-to-everything (V2X) system to achieve data sharing of vehicle information. When it is determined that a vehicle needs to obtain the third distance between itself and each reference vehicle in the current lane, the server can determine the vehicle information corresponding to all reference vehicles in the current lane area corresponding to the vehicle based on the obtained vehicle information of each vehicle, and send this vehicle information directly or after processing to the vehicle.

[0030] In some implementations, the vehicle can use its own sensors to obtain the vehicle type of each vehicle in the current lane, and use vehicles of the target type as reference vehicles to determine a second distance between the vehicle and each reference vehicle. The target type is a vehicle type that may have a speed limit sign affixed to its rear, such as large vehicles like passenger buses, trucks, and school buses. Similarly, the server can pre-obtain vehicle information, including vehicle type, for each vehicle in the current lane, filter out vehicles of the target type as reference vehicles, determine a third distance between the vehicle and each reference vehicle, and transmit this third distance to the vehicle. Thus, the vehicle can directly obtain the third distance between itself and each reference vehicle of the target type in the current lane from the server.

[0031] In some implementations, the vehicle can directly obtain the coordinate data of each reference vehicle in the current lane from the server, and then calculate the third distance between the vehicle and each reference vehicle based on its own coordinate data. In other implementations, the vehicle can also directly obtain the third distance between itself and each reference vehicle from the server. In this case, the server calculates the third distance between itself and each reference vehicle based on the coordinate data of each reference vehicle and the vehicle information uploaded by the vehicle, and then sends the third distance to the vehicle.

[0032] Specifically, the second distance between the vehicle and each reference vehicle, determined by the vehicle's own sensors, can include the second lateral distance between the vehicle's centerline and the reference vehicle's centerline, and the second longitudinal distance between the vehicle's rear axle center and the reference vehicle's rear bumper. The third distance obtained by the vehicle from the server can also include the third lateral distance between the vehicle's centerline and the reference vehicle's centerline, and the third longitudinal distance between the vehicle's rear axle center and the reference vehicle's rear bumper. Specifically, the coordinate data obtained by the server from each vehicle is generally based on the vehicle's center of gravity. The server also typically obtains information such as the vehicle's body dimensions from each vehicle simultaneously. Therefore, based on the coordinate data corresponding to the reference vehicle's center of gravity, the server can calculate the coordinate data corresponding to the reference vehicle's rear bumper, and then calculate the third lateral and third longitudinal distances between the vehicle and each reference vehicle.

[0033] Step S130: Based on the second distance and the third distance, determine the target distance between the vehicle and each reference vehicle in the current lane.

[0034] In this embodiment, after acquiring a second distance based on its own sensors and a third distance from the server, the vehicle can comprehensively determine the target distance between itself and each reference vehicle in the current lane based on the second and third distances. Specifically, the vehicle can select corresponding weighting coefficients for the second and third distances based on the reliability of the coordinate data between the vehicle sensors and the server, and obtain the target distance by weighted summation of the second and third distances. The weighting coefficients are all calibrable coefficients between [0, 1], and are positively correlated with the reliability of the coordinate data acquired by the vehicle sensors and the server.

[0035] In some implementations, a vehicle may determine the target distance between itself and each reference vehicle by following these steps:

[0036] Obtain the first weight corresponding to the second distance and the second weight corresponding to the third distance; based on the first weight and the second weight, perform a weighted sum of the second distance and the third distance to obtain the target distance between the vehicle and each reference vehicle.

[0037] In some implementations, the second distance acquired by the vehicle based on its own sensors includes a second lateral distance and a second longitudinal distance, and the third distance acquired from the server also includes a third lateral distance and a third longitudinal distance. Therefore, when the vehicle determines the target distance based on the second and third distances, the determined target distance may also include the target lateral distance and the target longitudinal distance. Specifically, the vehicle can determine the target lateral distance based on the second lateral distance, the third lateral distance, and their respective weighting coefficients, and determine the target longitudinal distance based on the second longitudinal distance, the third longitudinal distance, and their respective weighting coefficients.

[0038] Step S140: Based on the first distance and the target distance, determine whether the target speed limit sign is a road speed limit sign.

[0039] In this embodiment of the application, after determining the target distance between the vehicle and each reference vehicle in the current lane, the vehicle can determine the type of the target speed limit sign based on the first distance between the vehicle and the target speed limit sign and the target distance. That is, based on the first distance and the target distance, the vehicle can determine whether the target speed limit sign is a road speed limit sign that limits the speed of all vehicles in the current lane or a non-road speed limit sign affixed to the rear of a large vehicle that only limits the speed of the large vehicle.

[0040] Obviously, if the vehicle determines that the target speed limit sign is a road speed limit sign, it can display the speed limit value on the vehicle's dashboard to remind the driver to control their speed and improve road traffic efficiency. On the other hand, if the vehicle determines that the target speed limit sign is not a road speed limit sign, it can ignore the speed limit value on the target sign. In this case, the vehicle can use the current road speed limit value determined by the main navigation map as the actual speed limit value and display it to the driver through the dashboard or head-up display to assist the user in controlling their speed.

[0041] The speed limit sign recognition method provided in this application involves: acquiring a first distance between the vehicle and a target speed limit sign identified by the vehicle in the current lane; acquiring a second distance between the vehicle and each reference vehicle in the current lane using the vehicle's sensors; acquiring a third distance between the vehicle and each reference vehicle in the current lane using a server; determining a target distance between the vehicle and each reference vehicle in the current lane based on the second and third distances; and determining whether the target speed limit sign is a road speed limit sign based on the first and target distances. By combining the second distance acquired by the vehicle's sensors and the third distance acquired by the server, a more accurate target distance between the vehicle and each reference vehicle can be determined, thereby enabling a more accurate judgment of the target speed limit sign based on the target distance and the first distance between the vehicle and the target speed limit sign.

[0042] Please see Figure 3 , Figure 3 A flowchart illustrating a speed limit sign recognition method according to another embodiment of this application is shown below. Figure 3 The process shown is described in detail. The speed limit sign recognition method may specifically include the following steps:

[0043] Step S210: Obtain the first distance between the vehicle and the target speed limit sign in the current lane identified by the vehicle.

[0044] In this embodiment, while the vehicle is traveling in the current lane, it can continuously detect whether a target speed limit sign exists in the current lane. If the vehicle detects a target speed limit sign in the current lane, since this target speed limit sign may be a non-road speed limit sign affixed to the vehicle body of another reference vehicle in the current lane, the vehicle can send a sign recognition command to the server to instruct the server to identify whether there is a vehicle with a speed limit sign affixed in the current lane. Specifically, the vehicle and reference vehicles can send vehicle information to the server in real time during travel. This vehicle information can include not only vehicle model, length, and height, but also information on whether a speed limit sign is affixed to the vehicle body. Therefore, after receiving the sign recognition command sent by the vehicle, the server can determine whether there is a reference vehicle with a speed limit sign affixed in the current lane based on the vehicle information corresponding to each reference vehicle in the current lane, especially the affixing information.

[0045] Clearly, if the server determines that there is a reference vehicle with a speed limit sign in the current lane, then the target speed limit sign recognized by the vehicle is likely to be this non-road speed limit sign affixed to the vehicle body, rather than a road speed limit sign that applies to all vehicles in the current lane. In this case, the vehicle can obtain the initial distance to the target speed limit sign and further determine whether the recognized target speed limit sign is a road speed limit sign or a non-road speed limit sign through subsequent steps.

[0046] Step S220: Obtain the vehicle type corresponding to each reference vehicle in the current lane from the server.

[0047] In this embodiment, since the target speed limit sign identified by the vehicle in the current lane may be a road speed limit sign or a non-road speed limit sign affixed to the rear of a large vehicle, the vehicle also needs to determine whether the target speed limit sign is a road speed limit sign. Specifically, the vehicle can determine whether the target speed limit sign is affixed to the rear of a reference vehicle based on a first distance between the vehicle and the target speed limit sign, and a target distance between the vehicle and a reference vehicle. However, it is clear that only reference vehicles of the target type (large vehicle) are likely to have speed limit signs affixed to their rear. Therefore, after determining that a target speed limit sign exists in the current lane, the vehicle can also obtain the vehicle type corresponding to each reference vehicle from the server. This allows for the elimination of all non-target type reference vehicles during subsequent steps in determining the target distance between the target speed limit sign and the reference vehicle, reducing the number of target distance calculations and thus improving the recognition efficiency of the target speed limit sign.

[0048] Step S230: Obtain the second distance of the vehicle relative to each reference vehicle in the current lane through the vehicle sensor, and obtain the third distance of the vehicle relative to each reference vehicle in the current lane whose vehicle type is the target type from the server.

[0049] In this embodiment, the vehicle can obtain the vehicle type corresponding to each reference vehicle in the current lane from the server. Before determining the target distance, the vehicle eliminates reference vehicles of non-target type and determines the third distance between the vehicle and each reference vehicle of the target type. In other embodiments, the server can directly eliminate non-target type vehicles based on the vehicle type corresponding to each reference vehicle and send relevant information such as the third distance to the vehicle for all reference vehicles of the target type. Here, the target type represents the type with a speed limit sign, and the vehicle type corresponding to the reference vehicle is determined by the server based on the vehicle information uploaded by the reference vehicle. The vehicle information includes at least whether a speed limit sign is affixed.

[0050] For example, such as Figure 4 As shown, a vehicle can send its own vehicle information to the server through the vehicle-to-everything (V2X) system. Each reference vehicle in the current lane can also send its own vehicle information to the server through its own V2X system. The vehicle can then obtain the processed vehicle information for each reference vehicle from the server to assist in determining the target speed limit sign.

[0051] Step S240: Based on the second distance and the third distance, determine the second distance and the third distance corresponding to the same first reference vehicle among all reference vehicles, where the first reference vehicle is any one of the reference vehicles.

[0052] In this embodiment, the reference vehicles in the current lane include at least two. That is, the second distance obtained by the vehicle based on its own sensors can include at least two, and the third distance obtained from the server also includes at least two. Furthermore, due to the varying detection accuracy of different devices, even for the same reference vehicle, the second distance determined by the vehicle's own sensors and the third distance determined by the positioning device may not be exactly the same. In this case, before determining the target distance, the vehicle can first match multiple second distances and multiple third distances, that is, determine the second distance and third distance corresponding to the same reference vehicle respectively. Only then can the target distance between the vehicle and the reference vehicle be determined based on the second distance and third distance corresponding to the same reference vehicle respectively. The vehicle can use the same reference vehicle as the first reference vehicle.

[0053] In some implementations, such as Figure 5 As shown, a vehicle can determine the second and third distances corresponding to the same first reference vehicle through the following steps:

[0054] Step S241: Determine the second distance corresponding to the first reference vehicle, where the first reference vehicle is any one of the reference vehicles.

[0055] In this embodiment of the application, during the process of matching the second distance and the third distance, one of the reference vehicles can be arbitrarily selected as the first reference vehicle, and the second distance corresponding to the first reference vehicle can be determined. Thus, the vehicle can use the first reference vehicle as a basis to traverse the third distances corresponding to all reference vehicles (including the first reference vehicle) to determine the third distance belonging to the first reference vehicle.

[0056] Step S242: Based on the second distance corresponding to the first reference vehicle and the third distance corresponding to each reference vehicle, determine the relative distance between the first reference vehicle and each reference vehicle.

[0057] In this embodiment, after selecting any one of all reference vehicles as the first reference vehicle and determining its corresponding second distance, the vehicle can obtain the relative distance between the first reference vehicle and each of the reference vehicles based on the third distances corresponding to each of the reference vehicles. The relative distance is the distance between the first reference vehicle and the reference vehicles. It is understandable that, for the same reference vehicle, even if there is a certain difference between the second distance obtained by the vehicle through its own sensors and the third distance obtained from the server, due to differences in device precision, this difference will not be too large because both values ​​are determined for the same reference vehicle. Therefore, if the relative distance between the first reference vehicle and one of the reference vehicles is small based on the second distance corresponding to the first reference vehicle and the third distance corresponding to each of the reference vehicles, then it is highly likely that these two reference vehicles are actually the same vehicle. Based on this, the vehicle can determine the relative distance between the first reference vehicle and each of the reference vehicles, thereby obtaining the third distance corresponding to the first reference vehicle.

[0058] In some implementations, after obtaining the relative distances between the first reference vehicle and each of the other reference vehicles, the vehicle can also obtain the license plate information corresponding to each reference vehicle. This allows for a more accurate determination of the third distance corresponding to the first reference vehicle based on the license plate information. In other words, only when the relative distances between the first reference vehicle and all the other reference vehicles are minimized, and the license plate information corresponding to the first reference vehicle matches the license plate information corresponding to the other reference vehicles, can the vehicle use the third distance corresponding to that reference vehicle as the third distance corresponding to the first reference vehicle.

[0059] Step S243: Determine the third distance corresponding to the first reference vehicle based on the smallest target relative distance among multiple relative distances corresponding to the first reference vehicle.

[0060] In this embodiment of the application, after determining the relative distance between the first reference vehicle and each of the reference vehicles, the vehicle assumes that the relative distance between the second reference vehicle and the first reference vehicle is the smallest relative distance among all the relative distances corresponding to the first reference vehicle. Then the vehicle can regard the first reference vehicle and the second reference vehicle as the same reference vehicle, and then take the third distance corresponding to the second reference vehicle as the third distance corresponding to the first reference vehicle.

[0061] In some implementations, if the vehicle also obtains the license plate information corresponding to each reference vehicle, then the vehicle can determine the third distance corresponding to the first reference vehicle by means of the following method:

[0062] The minimum target relative distance among multiple relative distances corresponding to the first reference vehicle is determined. The target relative distance is used to characterize the relative distance between the first reference vehicle and the second reference vehicle, which is any one of the reference vehicles. If the license plate information corresponding to the first reference vehicle matches the license plate information corresponding to the second reference vehicle, the third distance corresponding to the first reference vehicle is determined based on the third distance corresponding to the second reference vehicle.

[0063] In other words, determining the third distance corresponding to the first reference vehicle requires not only minimizing the relative distance between the first and second reference vehicles, but also ensuring that the license plate information of the second reference vehicle matches that of the first reference vehicle. This improves the accuracy of the second and third distances corresponding to the first reference vehicle, thereby making the target distance determined based on the second and third distances more accurate.

[0064] In some implementations, the second distance acquired by the vehicle may include a second lateral distance between the centerline of the vehicle and the centerline of the reference vehicle, acquired by the vehicle's sensors, and a second longitudinal distance between the rear axle center of the vehicle and the reference vehicle in the vehicle's direction of travel. Similarly, the third distance acquired by the vehicle may also include a third lateral distance between the centerline of the vehicle and the centerline of the reference vehicle, acquired from the server, and a third longitudinal distance between the rear axle center of the vehicle and the reference vehicle in the vehicle's direction of travel. Specifically, the vehicle can calculate the relative distance between any two reference vehicles (the first reference vehicle and the second reference vehicle) using the following formula:

[0065]

[0066]

[0067] Y_tota l=Y_a*Y_b

[0068] Wherein, the second lateral distance corresponding to the first reference vehicle is a_i, the second longitudinal distance corresponding to the first reference vehicle is a_j, the third lateral distance corresponding to the second reference vehicle is b_i, the third longitudinal distance corresponding to the second reference vehicle is b_j, and the product of Y_a and Y_b is the relative distance between the first reference vehicle and the second reference vehicle.

[0069] As can be seen from the above formula, the smaller the relative distance Y_to ta l between the second and third distances, the greater the probability that the first reference vehicle and the second reference vehicle actually represent the same reference vehicle. Therefore, the vehicle can directly select the smallest relative distance among the multiple relative distances corresponding to the first reference vehicle and all reference vehicles to determine the third distance corresponding to the first reference vehicle.

[0070] Step S250: Determine the target distance between the vehicle and the first reference vehicle based on the second distance and the third distance corresponding to the first reference vehicle.

[0071] In this embodiment, after determining the second and third distances corresponding to the first reference vehicle based on the above steps, the vehicle can determine the target distance between itself and the first reference vehicle based on the second and third distances. It is understood that the second distance is obtained by the vehicle based on its own sensors, and the third distance is obtained by the server based on the vehicle's positioning equipment; both can characterize the actual distance between the vehicle and the first reference vehicle to a certain extent. The target distance between the vehicle and the first reference vehicle determined by the vehicle based on a combination of the second and third distances simply makes the distance value more accurate and closer to the actual distance.

[0072] Specifically, the vehicle can pre-set a first weight for the second distance and a second weight for the third distance based on the reliability of the on-board sensors and positioning equipment. The second and third distances are then weighted and summed based on the first and second weights, and the result is used as the target distance between the vehicle and the first reference vehicle.

[0073] In some implementations, the second distance includes a second lateral distance and a second longitudinal distance, and the third distance includes a third lateral distance and a third longitudinal distance. Therefore, the target distance between the vehicle and the first reference vehicle determined by the vehicle also includes the target lateral distance and the target longitudinal distance. Specifically, the vehicle can determine the target lateral distance and the target longitudinal distance using the following formulas:

[0074] Di stance_a=a_i*α+a_j*β

[0075] Di stance_b=b_i*γ+b_j*δ

[0076] Where Di stance_a is the target lateral distance, Di stance_b is the target longitudinal distance, a_i is the second lateral distance, a_j is the second longitudinal distance, b_i is the third lateral distance, b_j is the third longitudinal distance, and α, β, γ, and δ are all calibrable values ​​between [0, 1].

[0077] Step S260: Obtain the first height value between the target speed limit sign and the ground through the vehicle's sensors, and obtain the second height value corresponding to each reference vehicle from the server.

[0078] In this embodiment, after obtaining the target distance between the vehicle and each reference vehicle, before determining the reference distance between the target speed limit sign and each reference vehicle, the vehicle can also obtain a first height value between the target speed limit sign and the ground through its own sensors, and obtain a second height value corresponding to each reference vehicle from the server. Therefore, the vehicle can simultaneously determine whether the target speed limit sign is affixed to the rear of the reference vehicle based on the first height value, the second height value, and the reference distance between the target speed limit sign and the reference vehicle, making the determination more accurate.

[0079] Understandably, each reference vehicle can upload its own vehicle information to the value server in real time, which may include information such as the corresponding body size of the reference vehicle.

[0080] Step S270: Based on the first distance and the target distance, determine the distance between the target speed limit sign and each reference vehicle, and use it as the reference distance for each reference vehicle.

[0081] In this embodiment, after obtaining the accurate target distance between the vehicle and each reference vehicle through the above steps, the vehicle can determine the reference distance between the target speed limit sign and each reference vehicle based on the first distance between the vehicle and the target speed limit sign. This allows for determining the probability that the target speed limit sign is affixed to the rear of each reference vehicle based on the reference distance corresponding to that reference vehicle. Clearly, if the reference distance to a particular reference vehicle is very small, the target speed limit sign is likely affixed to the rear of that reference vehicle, and therefore, this target speed limit sign is not used to limit the vehicle's speed; the vehicle can ignore it. Conversely, if the reference distance is large, the vehicle needs to remind the driver to limit the speed based on the speed limit value on the target speed limit sign.

[0082] Step S280: If there is a target reference vehicle in the current lane with a reference distance less than the first preset distance, then the target speed limit sign is determined to be a non-road speed limit sign.

[0083] In this embodiment of the application, after the vehicle determines the reference distance between the target speed limit sign and each reference vehicle, if there is a target reference vehicle whose reference distance is less than the first preset distance, that is, the distance between the target speed limit sign and the target reference vehicle is very small, the vehicle can consider the target speed limit sign to be a speed limit sign pasted on the rear of the target reference vehicle and used only to limit the driving speed of the target reference vehicle, that is, the target speed limit sign is determined to be a non-road speed limit sign.

[0084] Specifically, if the vehicle has also acquired the first height value corresponding to the target speed limit sign and the second height value corresponding to a reference vehicle, and if there is a target reference vehicle in the current lane with a reference distance less than a first preset distance, and the first height value corresponding to the target reference vehicle is less than the second height value corresponding to the target reference vehicle, then the target speed limit sign is determined to be a non-road speed limit sign. Clearly, by adding the height value as a criterion, the vehicle's judgment on whether a target speed limit sign is a road speed limit sign will be more accurate.

[0085] In some implementations, the first preset distance can be 0.1m, and the vehicle can calculate the reference distance between the target speed limit sign and the reference vehicle according to the algorithm for determining the relative distance between reference vehicles in the above steps.

[0086] Step S290: If there is no target reference vehicle in the current lane with a reference distance less than the first preset distance, then the target speed limit sign is determined to be the road speed limit sign.

[0087] In this embodiment of the application, if the reference distance between each reference vehicle in the current lane and the target speed limit sign is greater than or equal to the first preset distance, then the vehicle can assume that the target speed limit sign is not affixed to the rear of any reference vehicle. Thus, it can be determined that the target speed limit sign is a road speed limit sign, and the speed limit value on the road speed limit sign can be displayed to the driver.

[0088] Specifically, if the vehicle has also acquired the first height value corresponding to the target speed limit sign and the second height value corresponding to the reference vehicles, and if there are no reference vehicles in the current lane with a reference distance less than a first preset distance, or if there are no reference vehicles in the current lane with a first height value less than a second height value, then the target speed limit sign is determined to be a road speed limit sign. Obviously, if the first height value corresponding to the target speed limit sign is greater than or equal to the second height value corresponding to the reference vehicles, or if the reference distance between the target speed limit sign and each reference vehicle is greater than or equal to the first preset distance, then it can be concluded that the target speed limit sign is not affixed to the rear of any reference vehicle. In other words, this target speed limit sign does indeed limit the speed of all vehicles in the current lane. At this time, the vehicle can display the speed limit value corresponding to the target speed limit sign to the driver through the instrument panel or head-up display to assist the driver in controlling the driving speed.

[0089] In some implementations, after determining whether the target speed limit sign is a road speed limit sign or a non-road speed limit sign, the vehicle can display the determination result to the driver via the instrument panel or voice prompts. The driver can then confirm or deny the determination based on the driver's actions; that is, the vehicle can determine whether the determination of the target speed limit sign is correct based on the driver's different actions. If the determination is incorrect, the error data can be recorded so that technicians can analyze the error data and improve the vehicle's judgment procedure.

[0090] The speed limit sign recognition method provided in this application embodiment obtains a first distance between the vehicle and the target speed limit sign in the current lane, obtains the vehicle type corresponding to each reference vehicle in the current lane from the server, obtains a second distance between the vehicle and each reference vehicle in the current lane through the vehicle's sensors, and obtains a third distance between the vehicle and each reference vehicle in the current lane whose vehicle type is the target type from the server; based on the second and third distances, determines the second and third distances corresponding to the same first reference vehicle among all reference vehicles; based on the second and third distances corresponding to the first reference vehicle, determines the target distance between the vehicle and the first reference vehicle; obtains a first height value between the target speed limit sign and the ground through the vehicle's sensors, and obtains the second height value corresponding to each reference vehicle from the server; based on the first distance and the target distance, determines the distance between the target speed limit sign and each reference vehicle as the reference distance for each reference vehicle; if there is a target reference vehicle in the current lane with a reference distance less than a first preset distance, the target speed limit sign is determined to be a non-road speed limit sign; if there is no target reference vehicle in the current lane with a reference distance less than the first preset distance, the target speed limit sign is determined to be a road speed limit sign. This not only provides a more accurate target distance between the vehicle and each reference vehicle based on the second and third distances, but also allows for the determination of whether the target speed limit sign is a road speed limit sign based on the first height value corresponding to the target speed limit sign and the first height value corresponding to the reference vehicle. This makes the judgment of the target speed limit sign more accurate and can better assist the driver in controlling the driving speed.

[0091] Please see Figure 6This document illustrates a structural block diagram of a speed limit sign recognition device 200 provided in an embodiment of this application. The speed limit sign recognition device 200 includes: a sign recognition module 210, a distance acquisition module 220, a distance determination module 230, and a sign judgment module 240. Specifically, the sign recognition module 210 acquires a first distance between the vehicle and a target speed limit sign identified by the vehicle in the current lane; the distance acquisition module 220 acquires a second distance between the vehicle and each reference vehicle in the current lane using the vehicle's sensors, and acquires a third distance between the vehicle and each reference vehicle in the current lane from a server; the distance determination module 230 determines a target distance between the vehicle and each reference vehicle in the current lane based on the second and third distances; and the sign judgment module 240 determines whether the target speed limit sign is a road speed limit sign based on the first distance and the target distance.

[0092] In one possible implementation, the sign determination module 240 includes a distance calculation unit, a first situation unit, and a second situation unit. The distance calculation unit is used to determine the distance between the target speed limit sign and each reference vehicle based on a first distance and a target distance, and use this distance as a reference distance for each reference vehicle. The first situation unit is used to determine that the target speed limit sign is a non-road speed limit sign if there is a target reference vehicle in the current lane with a reference distance less than a first preset distance. The second situation unit is used to determine that the target speed limit sign is a road speed limit sign if there is no target reference vehicle in the current lane with a reference distance less than the first preset distance.

[0093] As one possible implementation, the speed limit sign recognition device 200 further includes a height acquisition module, used to acquire a first height value between the target speed limit sign and the ground through a vehicle sensor, and to acquire a second height value corresponding to each reference vehicle from a server; the first case unit is further used to determine that the target speed limit sign is a non-road speed limit sign if there is a target reference vehicle in the current lane with a reference distance less than a first preset distance, and the first height value corresponding to the target reference vehicle is less than the second height value corresponding to the target reference vehicle; the second case unit is further used to determine that the target speed limit sign is a road speed limit sign if there is no reference vehicle in the current lane with a reference distance less than the first preset distance, or if there is no reference vehicle in the current lane with a first height value less than the second height value.

[0094] In one possible implementation, the reference vehicles in the current lane include at least two, and the distance determination module 230 includes a distance matching unit and a distance determination unit. The distance matching unit is used to determine a second distance and a third distance corresponding to the same first reference vehicle among all reference vehicles, based on a second distance and a third distance, wherein the first reference vehicle is any one of the reference vehicles; the distance determination unit is used to determine the target distance between the vehicle and the first reference vehicle based on the second distance corresponding to the first reference vehicle and the third distance.

[0095] In one possible implementation, the distance matching unit is further configured to determine a second distance corresponding to a first reference vehicle, wherein the first reference vehicle is any one of the reference vehicles; determine a relative distance between the first reference vehicle and each reference vehicle based on the second distance corresponding to the first reference vehicle and a third distance corresponding to each reference vehicle; and determine a third distance corresponding to the first reference vehicle based on the smallest target relative distance among the multiple relative distances corresponding to the first reference vehicle.

[0096] As one possible implementation, the distance matching unit is also used to obtain the license plate information corresponding to each reference vehicle; determine the minimum target relative distance among multiple relative distances corresponding to the first reference vehicle, the target relative distance being used to characterize the relative distance between the first reference vehicle and the second reference vehicle, the second reference vehicle being any one of the reference vehicles; if the license plate information corresponding to the first reference vehicle matches the license plate information corresponding to the second reference vehicle, then the third distance corresponding to the first reference vehicle is determined based on the third distance corresponding to the second reference vehicle.

[0097] As one possible implementation, the distance determination unit is further configured to obtain a first weight corresponding to the second distance and a second weight corresponding to the third distance; based on the first weight and the second weight, the second distance and the third distance are weighted and summed to obtain the target distance between the vehicle and the first reference vehicle.

[0098] As one possible implementation, the speed limit sign recognition device 200 also includes a type acquisition module for acquiring the vehicle type corresponding to each reference vehicle in the current lane from the server; the distance acquisition module 220 is also used to acquire the third distance of the vehicle relative to each reference vehicle in the current lane whose vehicle type is the target type from the server.

[0099] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described device and module can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0100] In the several embodiments provided in this application, the coupling between modules can be electrical, mechanical, or other forms of coupling.

[0101] Furthermore, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0102] In summary, the solution provided in this application obtains a first distance between the vehicle and a target speed limit sign identified by the vehicle in the current lane; obtains a second distance between the vehicle and each reference vehicle in the current lane using the vehicle's sensors; and obtains a third distance between the vehicle and each reference vehicle in the current lane from a server. Based on the second and third distances, a target distance between the vehicle and each reference vehicle in the current lane is determined. Based on the first and target distances, it is determined whether the target speed limit sign is a road speed limit sign. By combining the second distance obtained from the vehicle's sensors and the third distance obtained from the server, a more accurate target distance between the vehicle and each reference vehicle can be determined, and thus, based on the target distance and the first distance between the vehicle and the target speed limit sign, a more accurate judgment can be made regarding the target speed limit sign.

[0103] Please see Figure 7 The diagram illustrates a structural block diagram of a vehicle 400 provided in an embodiment of this application. The vehicle 400 in this application may include one or more of the following components: a processor 410, a memory 420, and one or more application programs. The one or more application programs may be stored in the memory 420 and configured to be executed by one or more processors 410. The one or more programs are configured to perform the methods described in the foregoing method embodiments.

[0104] Processor 410 may include one or more processing cores. Processor 410 connects to various parts of the computer device using various interfaces and lines, and performs various functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in memory 420, and by calling data stored in memory 420. Optionally, processor 410 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). Processor 410 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the displayed content; and the modem handles wireless communication. It is understood that the modem may also not be integrated into processor 410 and may be implemented separately using a communication chip.

[0105] The memory 420 may include random access memory (RAM) or read-only memory (ROM). The memory 420 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 420 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as touch functionality, sound playback functionality, image playback functionality, etc.), and instructions for implementing the various method embodiments described below. The data storage area may also store data created during the use of the computer device (such as phone books, audio and video data, chat log data, etc.).

[0106] This application provides a structural block diagram of a computer-readable storage medium. The computer-readable medium stores program code that can be called by a processor to execute the methods described in the above method embodiments.

[0107] Computer-readable storage media can be electronic storage devices such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. Optionally, computer-readable storage media includes non-transitory computer-readable storage medium. The computer-readable storage medium has storage space for program code that performs any of the method steps described above. This program code can be read from or written to one or more computer program products. The program code can be compressed, for example, in a suitable form.

[0108] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for recognizing speed limit signs, characterized in that, The method includes: Obtain the first distance between the vehicle and the target speed limit sign in the current lane identified by the vehicle; The vehicle obtains a second distance relative to each reference vehicle in the current lane using its own sensors, and obtains a third distance relative to each of the reference vehicles in the current lane from the server. Based on the second distance and the third distance, a target distance is determined between the vehicle and each of the reference vehicles in the current lane; Based on the first distance and the target distance, determine whether the target speed limit sign is a road speed limit sign.

2. The method according to claim 1, characterized in that, Determining whether the target speed limit sign is a road speed limit sign based on the first distance and the target distance includes: Based on the first distance and the target distance, the distance between the target speed limit sign and each of the reference vehicles is determined as the reference distance for each of the reference vehicles; If there is a target reference vehicle in the current lane whose reference distance is less than the first preset distance, then the target speed limit sign is determined to be a non-road speed limit sign. If there is no target reference vehicle in the current lane whose reference distance is less than the first preset distance, then the target speed limit sign is determined to be the road speed limit sign.

3. The method according to claim 2, characterized in that, Before determining whether the target speed limit sign is a road speed limit sign based on the first distance and the target distance, the method further includes: The vehicle sensor obtains a first height value between the target speed limit sign and the ground, and obtains a second height value corresponding to each reference vehicle from the server; If there is a target reference vehicle in the current lane whose reference distance is less than a first preset distance, then determining that the target speed limit sign is a non-road speed limit sign includes: If there is a target reference vehicle in the current lane whose reference distance is less than the first preset distance, and the first height value corresponding to the target reference vehicle is less than the second height value corresponding to the target reference vehicle, then the target speed limit sign is determined to be a non-road speed limit sign. If there is no target reference vehicle in the current lane whose reference distance is less than a first preset distance, then determining the target speed limit sign as the road speed limit sign includes: If there is no reference vehicle in the current lane whose reference distance is less than the first preset distance, or if there is no reference vehicle in the current lane whose first height value is less than the second height value, then the target speed limit sign is determined to be the road speed limit sign.

4. The method according to claim 1, characterized in that, The reference vehicles in the current lane include at least two, and determining the target distance between the vehicle and each of the reference vehicles in the current lane based on the second distance and the third distance includes: Based on the second distance and the third distance, determine the second distance and the third distance corresponding to the same first reference vehicle among all the reference vehicles, wherein the first reference vehicle is any one of the reference vehicles; Based on the second distance and the third distance corresponding to the first reference vehicle, the target distance between the vehicle and the first reference vehicle is determined.

5. The method according to claim 4, characterized in that, The step of determining the second distance and the third distance corresponding to the same first reference vehicle among all the reference vehicles based on the second distance and the third distance includes: Determine a second distance corresponding to a first reference vehicle, wherein the first reference vehicle is any one of the reference vehicles; Based on the second distance corresponding to the first reference vehicle and the third distance corresponding to each of the reference vehicles, the relative distance between the first reference vehicle and each of the reference vehicles is determined; The third distance corresponding to the first reference vehicle is determined based on the smallest target relative distance among the multiple relative distances corresponding to the first reference vehicle.

6. The method according to claim 5, characterized in that, Before determining the third distance corresponding to the first reference vehicle based on the smallest target relative distance among the plurality of relative distances corresponding to the first reference vehicle, the method further includes: Obtain the license plate information corresponding to each of the reference vehicles; The step of determining the third distance corresponding to the first reference vehicle based on the smallest target relative distance among the plurality of relative distances corresponding to the first reference vehicle includes: Determine the target relative distance among the plurality of relative distances corresponding to the first reference vehicle, wherein the target relative distance is used to characterize the relative distance between the first reference vehicle and the second reference vehicle, and the second reference vehicle is any one of the reference vehicles; If the license plate information of the first reference vehicle matches the license plate information of the second reference vehicle, then the third distance of the first reference vehicle is determined based on the third distance of the second reference vehicle.

7. The method according to claim 4, characterized in that, Determining the target distance between the vehicle and the first reference vehicle based on the second distance and the third distance corresponding to the first reference vehicle includes: Obtain the first weight corresponding to the second distance and the second weight corresponding to the third distance; Based on the first weight and the second weight, the second distance and the third distance are weighted and summed to obtain the target distance between the vehicle and the first reference vehicle.

8. The method according to any one of claims 1-7, characterized in that, The method further includes: Obtain the vehicle type corresponding to each reference vehicle in the current lane from the server; The step of obtaining the third distance of the vehicle relative to each of the reference vehicles in the current lane from the server includes: Obtain the third distance of the vehicle relative to each of the reference vehicles of the target type in the current lane from the server.

9. The method according to any one of claims 1-7, characterized in that, Before obtaining the first distance between the vehicle and the target speed limit sign in the current lane identified by the vehicle, the method further includes: If a target speed limit sign is detected in the current lane, a sign recognition instruction is sent to the server. The sign recognition instruction is used to instruct the server to identify whether there is a vehicle with a speed limit sign in the current lane. The acquisition of the first distance between the vehicle and the target speed limit sign in the current lane identified by the vehicle includes: In response to the first indication information returned by the server, the first distance between the vehicle and the target speed limit sign in the current lane identified by the vehicle is obtained. The first indication information is used to indicate that there is a vehicle with a speed limit sign in the current lane. The first indication information is sent by the server after determining that there is a vehicle with a speed limit sign in the current lane based on the vehicle information uploaded by the vehicles in the current lane. The vehicle information includes the affixing information of the speed limit sign, which is used to indicate whether the vehicle has a speed limit sign affixed.

10. A speed limit sign recognition device, characterized in that, The device includes: The sign recognition module is used to obtain the first distance between the vehicle and the target speed limit sign in the current lane that the vehicle has recognized; The distance acquisition module is used to acquire a second distance of the vehicle relative to each reference vehicle in the current lane through the vehicle's sensors, and to acquire a third distance of the vehicle relative to each of the reference vehicles in the current lane from the server; A distance determination module is used to determine a target distance between the vehicle and each of the reference vehicles in the current lane based on the second distance and the third distance; The sign determination module is used to determine whether the target speed limit sign is a road speed limit sign based on the first distance and the target distance.

11. A vehicle, characterized in that, The vehicles include: One or more processors; Memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more applications being configured to perform the method as described in any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores program code that can be invoked by a processor to execute the method as described in any one of claims 1-9.

Images