Lane speed attribute generation method and system, storage medium and program product

Abstract

The invention relates to the technical field of computers, in particular to a lane speed attribute generation method and system, a storage medium and a program product. Receiving sign information corresponding to the traffic sign sent by the vehicle end; identifying the sign information, and determining target sign information corresponding to a speed sign in the traffic sign; and according to the target sign information, determining a target lane corresponding to the speed sign and lane speed attribute information corresponding to the target lane. The accuracy of the target lane corresponding to the determined speed sign and the lane speed attribute information corresponding to the target lane is ensured, so that a map drawing person does not need to manually add traffic signs related to lane speed limit, the labor cost is saved, and the efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a lane speed attribute generation method, system, storage medium and program product. Background Art

[0002] HD maps can provide accurate lane-level maps for key steps of intelligent driving, such as high-precision positioning and decision-making planning, and are the most important part of the current mainstream intelligent driving technology solutions. The speed limit attribute in the HD map provides information such as the maximum speed and recommended minimum speed of the lane. Therefore, accurate and consistent lane speed limit information is a necessary prerequisite for ensuring the legal and smooth driving of intelligent driving vehicles.

[0003] In the traditional high-precision map making mode, the speed limit attribute of the lane is determined by the cartographer looking at the raw data such as the video and lidar point cloud collected by the collection vehicle, finding the traffic signs related to the lane speed limit, and then filling in the speed limit attribute of the lane according to the speed limit information indicated by the traffic signs. For lanes without speed limit-related traffic signs, the default speed limit is filled in according to traffic regulations.

[0004] The above method requires cartographers to manually add traffic signs related to lane speed limits, so it has the problems of huge labor costs and low efficiency. Summary of the invention

[0005] In view of this, the present invention provides a lane speed attribute generation method, system, storage medium and program product to solve the problem of huge labor cost and low efficiency due to the need for cartographers to manually add traffic signs related to lane speed limits.

[0006] In a first aspect, the present invention provides a lane speed attribute generation method, which is applied to a server side, and the method comprises:

[0007] Receiving sign information corresponding to the traffic sign sent by the vehicle end;

[0008] Identify the sign information and determine the target sign information corresponding to the speed sign in the traffic sign;

[0009] According to the target sign information, a target lane corresponding to the speed sign and lane speed attribute information corresponding to the target lane are determined.

[0010] The lane speed attribute generation method provided in the embodiment of the present application receives the sign information corresponding to the traffic sign sent by the vehicle side, rather than millions or tens of millions of image data, and therefore can reduce the amount of resources occupied by the server side. The sign information is identified, and the target sign information corresponding to the speed sign in the traffic sign is determined, thereby ensuring the accuracy of the target sign information corresponding to the determined speed sign. According to the target sign information, the target lane corresponding to the speed sign and the lane speed attribute information corresponding to the target lane are determined, thereby ensuring the accuracy of the target lane corresponding to the determined speed sign and the lane speed attribute information corresponding to the target lane, thereby eliminating the need for cartographers to manually add traffic signs related to lane speed limits, thereby saving labor costs and improving efficiency.

[0011] In an optional implementation manner, the sign information includes category information corresponding to the traffic sign, and identifying the sign information to determine the target sign information corresponding to the speed sign in the traffic sign includes:

[0012] De-duplication processing is performed on the flag information to obtain backup flag information;

[0013] The category information in the backup mark information is identified to obtain the target mark information.

[0014] The lane speed attribute generation method provided in the embodiment of the present application performs deduplication processing on the sign information to obtain the spare sign information, thereby ensuring the accuracy of the spare sign information and avoiding duplicate sign information occupying resources and increasing the workload. The category information in the spare sign information is identified to obtain the target sign information, thereby ensuring the accuracy of the obtained target sign information.

[0015] In an optional implementation, the target sign information includes geographic location information and description information corresponding to the speed sign, the description information is used to characterize the applicable vehicle type corresponding to the speed sign, and determining the target lane corresponding to the speed sign according to the target sign information includes:

[0016] According to the description information, determine the candidate lane corresponding to the target sign information;

[0017] Determine a candidate distance between the speed sign and the candidate lane according to the geographic location information corresponding to the speed sign;

[0018] The candidate lane corresponding to the minimum candidate distance is determined as the target lane.

[0019] The lane speed attribute generation method provided in the embodiment of the present application determines the candidate lane corresponding to the target sign information based on the description information, thereby ensuring the accuracy of the candidate lane corresponding to the determined target sign information. According to the geographic location information corresponding to the speed sign, the candidate distance between the speed sign and the candidate lane is determined, thereby ensuring the accuracy of the candidate distance between the speed sign and the candidate lane. The candidate lane corresponding to the minimum candidate distance is determined as the target lane, thereby ensuring that the distance between the target lane and the speed sign is minimized, thereby ensuring the accuracy of the match between the target lane and the speed sign.

[0020] In an optional implementation manner, the target sign information further includes text information, and the lane speed attribute information corresponding to the target lane is determined according to the target sign information, including:

[0021] Identify the text information in the target sign information and determine the speed category and target speed value corresponding to the speed sign;

[0022] According to the geographic location information, the point closest to the speed sign in the target lane is determined as the target effective point corresponding to the target sign information;

[0023] Mark the speed category, target speed value and applicable vehicle model at the target effective point.

[0024] The lane speed attribute generation method provided in the embodiment of the present application identifies the text information in the target sign information, determines the speed category and target speed value corresponding to the speed sign, and ensures the accuracy of the speed category and target speed value corresponding to the determined speed sign. According to the geographic location information, the point closest to the speed sign in the target lane is determined as the target effective point corresponding to the target sign information, and ensures the accuracy of the determined target effective point. The speed category, target speed value and applicable vehicle model are marked on the target effective point, thereby completing the marking of the lane speed attribute information for the target lane, and ensuring the accuracy of the lane speed attribute information for the target lane. It saves labor costs and improves efficiency.

[0025] In an optional embodiment, the method further comprises:

[0026] Detect whether there is an identical effective point within a preset range corresponding to the target effective point on the target lane, and the speed category, target speed value, applicable vehicle model and effective range marked on the identical effective point are the same as those of the target effective point;

[0027] If there is an identical effective point within the preset range corresponding to the target effective point on the target lane, the identical effective point is deleted.

[0028] The lane speed attribute generation method provided in the embodiment of the present application detects whether there is an identical effective point within a preset range corresponding to a target effective point on a target lane, thereby ensuring the accuracy of the detection result. If there is an identical effective point within a preset range corresponding to a target effective point on a target lane, the identical effective point is deleted, thereby avoiding duplication of lane speed attribute information marked within the preset range of the target lane.

[0029] In an optional embodiment, the method further includes:

[0030] Detect the scope of the target sign information corresponding to the target lane;

[0031] If the effective range of the target sign information corresponding to the target lane includes other lanes, then detecting whether there is target sign information identical to the target sign information in the adjacent lane in the same direction corresponding to the target lane;

[0032] If there is no target sign information identical to the target sign information in the adjacent lane in the same direction, the lane speed attribute information corresponding to the target lane is determined as the lane speed attribute information corresponding to other lanes.

[0033] The lane speed attribute generation method provided in the embodiment of the present application detects the scope of the target sign information corresponding to the target lane, so that the lane speed attribute information of other lanes can be determined based on the detection result. If the scope of the target sign information corresponding to the target lane includes other lanes, it is detected whether there is target sign information identical to the target sign information in the adjacent lane in the same direction corresponding to the target lane; if there is no target sign information identical to the target sign information in the adjacent lane in the same direction, the lane speed attribute information corresponding to the target lane is determined as the lane speed attribute information corresponding to other lanes, thereby ensuring the accuracy of the lane speed attribute information corresponding to other lanes.

[0034] In an optional embodiment, the method further includes:

[0035] Check whether the subsequent lane corresponding to the target lane meets the reasoning termination condition;

[0036] If the subsequent lane does not meet the reasoning termination condition, then check whether there is corresponding target sign information in the subsequent lane;

[0037] If the corresponding target sign information does not exist in the successor lane, the lane speed attribute information corresponding to the target lane is determined as the lane speed attribute information corresponding to the successor lane;

[0038] If corresponding target sign information exists in the successor lane, lane speed attribute information corresponding to the successor lane is determined according to the target sign information corresponding to the successor lane.

[0039] The lane speed attribute generation method provided in the embodiment of the present application detects whether the successor lane corresponding to the target lane satisfies the reasoning termination condition, so that the lane speed attribute information of the successor lane can be determined based on the detection result. If the successor lane does not satisfy the reasoning termination condition, it is detected whether there is corresponding target sign information in the successor lane. If there is no corresponding target sign information in the successor lane, the lane speed attribute information corresponding to the target lane is determined as the lane speed attribute information corresponding to the successor lane; if there is corresponding target sign information in the successor lane, the lane speed attribute information corresponding to the successor lane is determined based on the target sign information corresponding to the successor lane. The accuracy of the determined lane speed attribute information corresponding to the successor lane is guaranteed.

[0040] In a second aspect, the present invention provides a lane speed attribute generation method, which is applied to a vehicle side, and the method includes:

[0041] Obtaining a traffic sign image and coordinate information of the traffic sign image in an image coordinate system;

[0042] Recognize the traffic sign image and determine the category information of the traffic sign included in the traffic sign image and the text information included in the traffic sign;

[0043] According to the coordinate information of the traffic sign image in the image coordinate system, the three-dimensional coordinates of the traffic sign in the vehicle coordinate system are reconstructed to generate the geographical location information of the traffic sign;

[0044] generating sign information corresponding to the traffic sign based on the category information, the text information and the geographic location information;

[0045] The sign information is transmitted to a server side; the server side is used to generate lane attribute information according to the method according to any one of claims 1-7.

[0046] The lane speed attribute generation method provided in the embodiment of the present application obtains a traffic sign image and the coordinate information of the traffic sign image in the image coordinate system; recognizes the traffic sign image, determines the category information of the traffic sign included in the traffic sign image and the text information included in the traffic sign, thereby ensuring the accuracy of the category information of the traffic sign included in the determined traffic sign image and the text information included in the traffic sign. Based on the coordinate information of the traffic sign image in the image coordinate system, the three-dimensional coordinates of the traffic sign in the vehicle coordinate system are reconstructed to generate the geographic location information of the traffic sign, thereby ensuring the accuracy of the generated geographic location information. Based on the category information, text information and geographic location information, the sign information corresponding to the traffic sign is generated, thereby ensuring the accuracy of the generated sign information, and the sign information is transmitted to the server side; thereby ensuring the accuracy of the lane speed attribute information corresponding to the target lane determined by the server side according to the sign information.

[0047] In a third aspect, the present invention provides a lane speed attribute generation system, comprising: a server end and a vehicle end; wherein the server end comprises: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the lane speed attribute generation method of the first aspect or any corresponding embodiment thereof by executing the computer instructions;

[0048] The vehicle end includes: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the lane speed attribute generation method of the second aspect by executing the computer instructions.

[0049] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the lane speed attribute generation method of the first aspect or any corresponding embodiment thereof and the lane speed attribute generation method of the second aspect.

[0050] In a fifth aspect, the present invention provides a computer program product, comprising computer instructions for causing a computer to execute the lane speed attribute generation method of the first aspect or any corresponding embodiment thereof and the lane speed attribute generation method of the second aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0052] Figure 1 is a schematic diagram of an application scenario of a lane speed attribute generation method according to an embodiment of the present invention;

[0053] Figure 2 is a schematic flow chart of a lane speed attribute generation method according to an embodiment of the present invention;

[0054] Figure 3 is a flow chart of another lane speed attribute generation method according to an embodiment of the present invention;

[0055] Figure 4 is a schematic diagram of a result of binding target flag information with description information according to an embodiment of the present invention;

[0056] Figure 5 is a schematic diagram of speed categories according to an embodiment of the present invention;

[0057] Figure 6 is a flow chart of another lane speed attribute generation method according to an embodiment of the present invention;

[0058] Figure 7 is a flow chart of another lane speed attribute generation method according to an embodiment of the present invention;

[0059] Figure 8 is an overall schematic diagram of an optical character recognition algorithm according to an embodiment of the present invention;

[0060] Fig. 9 is a schematic diagram of a specific structure of an optical character recognition algorithm according to an embodiment of the present invention;

[0061] Fig.10 is a schematic diagram of an interactive process of a lane speed attribute generation method according to an embodiment of the present invention;

[0062] Fig.11 is a structural block diagram of a lane speed attribute generating device according to an embodiment of the present invention;

[0063] Fig.12 is a structural block diagram of another lane speed attribute generating device according to an embodiment of the present invention;

[0064] Fig.13 It is a schematic diagram of the hardware structure of the server according to an embodiment of the present invention. DETAILED DESCRIPTION

[0065] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0066] HD maps can provide accurate lane-level maps for key steps of intelligent driving, such as high-precision positioning and decision-making planning, and are the most important part of the current mainstream intelligent driving technology solutions. The speed limit attribute in the HD map provides information such as the maximum speed and recommended minimum speed of the lane. Therefore, accurate and consistent lane speed limit information is a necessary prerequisite for ensuring the legal and smooth driving of intelligent driving vehicles.

[0067] In the traditional high-precision map making mode, traffic signs are collected using collection vehicles equipped with high-precision sensors. Because of the high accuracy of their sensors, an area can be mapped after only one collection vehicle has passed through it, so only a small number of collection vehicles are needed to meet the requirements. Therefore, in the traditional mapping mode, the amount of data collected by sensors is generally controllable, and the transmission and storage costs are acceptable. However, the crowd-source mapping mode uses low-cost collection vehicles, whose sensor accuracy is not high. To complete the mapping of an area, it is often necessary for the collection vehicle to pass through the area dozens or even hundreds of times. Therefore, the size of the collection fleet will become very large, and the cost of transmitting and storing raw data will become unacceptable.

[0068] In addition, the speed limit attribute of the lane is determined by the cartographer looking at the original data such as the video and lidar point cloud collected by the collection vehicle, finding the traffic signs related to the lane speed limit, and then filling the speed limit attribute of the lane according to the speed limit information indicated by the traffic signs. For lanes without speed limit-related traffic signs, the default speed limit is filled in according to traffic regulations.

[0069] The above method requires cartographers to manually add traffic signs related to lane speed limits, so it has the problems of huge labor costs and low efficiency.

[0070] Based on the above problems, an embodiment of the present application provides a lane speed attribute generation method, which receives sign information corresponding to traffic signs sent by the vehicle side, rather than millions or tens of millions of image data, thereby reducing the amount of resources occupied by the server side. The sign information is identified, and the target sign information corresponding to the speed sign in the traffic sign is determined, thereby ensuring the accuracy of the target sign information corresponding to the determined speed sign. According to the target sign information, the target lane corresponding to the speed sign and the lane speed attribute information corresponding to the target lane are determined, thereby ensuring the accuracy of the target lane corresponding to the determined speed sign and the lane speed attribute information corresponding to the target lane, thereby eliminating the need for cartographers to manually add traffic signs related to lane speed limits, thereby saving labor costs and improving efficiency.

[0071] The lane speed attribute generation method provided in this application can be applied to Figure 1 In the application environment shown in the figure, the vehicle end 102 communicates with the server end 104 through the network. The vehicle end 102 sends the sign information to the server end 104, and the server end 104 determines the lane speed attribute information corresponding to the target lane based on the sign information. The server end 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0072] According to an embodiment of the present invention, an embodiment of a lane speed attribute generation method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0073] In this embodiment, a lane speed attribute generation method is provided, which can be used in the above-mentioned server side. Figure 2 is a flow chart of a method for generating lane speed attributes according to an embodiment of the present invention. Figure 2 As shown, the process includes the following steps:

[0074] Step S101, receiving sign information corresponding to a traffic sign sent by a vehicle terminal.

[0075] The sign information includes at least one of category information, geographic location information, and text information corresponding to the traffic sign. The category information may include speed category, indication category, and road sign.

[0076] Specifically, the server side can receive sign information corresponding to the traffic sign sent by the vehicle side based on the communication connection with the vehicle side, thereby reducing the memory occupied by the server and reducing the workload of the server.

[0077] In an optional implementation of the present application, the location information included in the sign information corresponding to the traffic sign sent by the vehicle is not the geographical location information corresponding to the traffic sign, but the location information of the traffic sign relative to the vehicle. Therefore, after receiving the sign information corresponding to the traffic sign, the server needs to convert the location information of the traffic sign relative to the vehicle into location information relative to the earth, so as to generate the geographical location information corresponding to the traffic sign.

[0078] Step S102: Identify the sign information and determine the target sign information corresponding to the speed sign in the traffic sign.

[0079] Specifically, the server may identify the category information in the sign information, and determine the target sign information corresponding to the speed sign in the traffic sign.

[0080] This step will be described in detail below.

[0081] Step S103: determining the target lane corresponding to the speed sign and the lane speed attribute information corresponding to the target lane according to the target sign information.

[0082] Specifically, the server may determine the target lane corresponding to the speed sign according to the geographic location information included in the target sign information, and determine the lane speed attribute information corresponding to the target lane according to the content included in the target sign information.

[0083] This step will be described in detail below.

[0084] The lane speed attribute generation method provided in this embodiment receives the sign information corresponding to the traffic sign sent by the vehicle side, rather than millions or tens of millions of image data, and thus can reduce the amount of resources occupied by the server side. The sign information is identified, and the target sign information corresponding to the speed sign in the traffic sign is determined, thereby ensuring the accuracy of the target sign information corresponding to the determined speed sign. According to the target sign information, the target lane corresponding to the speed sign and the lane speed attribute information corresponding to the target lane are determined, thereby ensuring the accuracy of the target lane corresponding to the determined speed sign and the lane speed attribute information corresponding to the target lane, thereby eliminating the need for cartographers to manually add traffic signs related to lane speed limits, thereby saving labor costs and improving efficiency.

[0085] In this embodiment, a lane speed attribute generation method is provided, which can be used in the above-mentioned mobile terminal, such as a mobile phone, a tablet computer, etc. Figure 3 is a flow chart of a method for generating lane speed attributes according to an embodiment of the present invention. Figure 3 As shown, the process includes the following steps:

[0086] Step S201, receiving sign information corresponding to a traffic sign sent by a vehicle terminal.

[0087] For details, please see Figure 2 Step S101 of the illustrated embodiment will not be described in detail here.

[0088] Step S202: Identify the sign information and determine the target sign information corresponding to the speed sign in the traffic sign.

[0089] Specifically, the sign information includes category information corresponding to the traffic sign. The above step S202 may include the following steps:

[0090] Step S2021, deduplicate the flag information to obtain backup flag information.

[0091] Specifically, since the server can receive the sign information corresponding to the traffic signs sent by many vehicles, there may be duplicate traffic signs. The server identifies the geographical location information, category information and text information included in each sign information, determines the duplicate sign information with the same geographical location information, category information and text information, and then removes the duplicate sign information to obtain the backup sign information.

[0092] Step S2022, identifying the category information in the backup mark information to obtain the target mark information.

[0093] Specifically, the server may identify the category information in the spare flag information and obtain the target flag information corresponding to the speed flag.

[0094] In an optional implementation of the present application, there may be a problem that the description information corresponding to the speed sign is not bound to the target sign information corresponding to the speed sign. The description information can be used to characterize the applicable vehicle model corresponding to the speed sign. The applicable vehicle models may include "passenger car", "medium and large vehicle", "dangerous goods vehicle", "all vehicle models", etc. Exemplarily, the current speed limit sign is applicable to small cars.

[0095] Therefore, the electronic device can identify each descriptive information, determine the geographic location information corresponding to each descriptive information, and then calculate the distance between the geographic location information corresponding to each descriptive information and the geographic location information included in the target mark information based on the Hungarian algorithm, and bind the target mark information with the descriptive information with the smallest distance, so that the target identification information can also include the descriptive information.

[0096] For example, Figure 4 The following is a schematic diagram of the binding result. Specifically, the server obtains the target flag information corresponding to the speed flag, and then Figure 4 The words and images of "small passenger car" and "large vehicle" in the target sign information are all description information corresponding to the target sign information, which are used to describe the applicable vehicle type corresponding to the speed sign. Therefore, the server can use the geographical location information corresponding to the description information and the geographical location information included in the target sign information, based on the Hungarian algorithm, to bind the target sign information with the description information, and then add the description information to the target sign information, so that the target sign information can also include the description information.

[0097] Step S203: determining the target lane corresponding to the speed sign and the lane speed attribute information corresponding to the target lane according to the target sign information.

[0098] Specifically, the target sign information includes geographic location information and description information corresponding to the speed sign, and the description information is used to characterize the applicable vehicle type corresponding to the speed sign. The above step S203 of "determining the target lane corresponding to the speed sign according to the target sign information" may include the following steps:

[0099] Step S2031, determining the candidate lane corresponding to the target sign information according to the description information.

[0100] Specifically, the server may determine the candidate lane corresponding to the target sign information according to the description information.

[0101] Exemplarily, if the description information is "small car", the candidate lane corresponding to the target sign information is determined to be the leftmost lane.

[0102] Step S2032: determining a candidate distance between the speed sign and the candidate lane according to the geographical location information corresponding to the speed sign.

[0103] Specifically, the server may calculate the candidate distance between the speed sign and the candidate lane according to the geographical location information corresponding to the speed sign.

[0104] Step S2033: determine the candidate lane corresponding to the minimum candidate distance as the target lane.

[0105] Specifically, the server may determine that the candidate lane corresponding to the minimum candidate distance is the target lane.

[0106] Specifically, the target sign information also includes text information. The "determining lane speed attribute information corresponding to the target lane according to the target sign information" in the above step S203 may include the following steps:

[0107] Step S2034, identifying the text information in the target mark information, and determining the speed category and target speed value corresponding to the speed mark.

[0108] Specifically, the server may use a text recognition algorithm to recognize text information in the target mark information, and determine the speed category and target speed value corresponding to the speed mark.

[0109] Among them, the text recognition algorithm can be a classification algorithm based on the BERT pre-trained language model. The embodiment of the present application does not specifically limit the text recognition algorithm.

[0110] Among them, it should be noted that the speed category may include speed limit, speed limit removal, minimum speed limit, etc.

[0111] For example, Figure 5 As shown, from left to right are the speed limit sign, the speed restriction relief sign and the minimum speed limit sign.

[0112] Step S2035: According to the geographic location information, determine the point in the target lane that is closest to the speed sign as the target effective point corresponding to the target sign information.

[0113] Specifically, the server can determine the point in the target lane closest to the speed sign based on the geographic location information included in the target sign information, and determine the point as the target effective point corresponding to the target sign information, that is, starting from this point, the speed limit is set, or the speed limit is lifted, or the minimum speed is set.

[0114] Step S2036, marking the speed category, target speed value and applicable vehicle model at the target effective point.

[0115] Specifically, the server may mark the speed category, target speed value, and applicable vehicle model at the target effective point.

[0116] Step S2037, detecting whether there is an identical effective point within a preset range corresponding to the target effective point on the target lane.

[0117] Among them, the speed category, target speed value, applicable vehicle model and scope of application marked at the same effective point are the same as those of the target effective point.

[0118] Specifically, after marking the speed category, target speed value, and applicable vehicle model at the target effective point, the server can detect whether there is an identical effective point within a preset range corresponding to the target effective point on the target lane.

[0119] Step S2038: If there is an identical effective point within the preset range corresponding to the target effective point on the target lane, the identical effective point is deleted.

[0120] Specifically, if there is an identical effective point within a preset range corresponding to the target effective point on the target lane, the server deletes the identical effective point.

[0121] Optionally, the server can also determine the position information corresponding to the same effective point, and then determine the position between the same effective point and the target effective point as the final effective point based on the position information corresponding to the same effective point and the position information corresponding to the target effective point, and mark the speed category, target speed value and applicable vehicle model corresponding to the speed sign to the final effective point.

[0122] The lane speed attribute generation method provided by the embodiment of the present application performs deduplication processing on the sign information to obtain the spare sign information, thereby ensuring the accuracy of the spare sign information, avoiding the duplicate sign information from occupying resources and increasing the workload. The category information in the spare sign information is identified to obtain the target sign information, thereby ensuring the accuracy of the obtained target sign information. According to the description information, the candidate lane corresponding to the target sign information is determined, thereby ensuring the accuracy of the candidate lane corresponding to the determined target sign information. According to the geographic location information corresponding to the speed sign, the candidate distance between the speed sign and the candidate lane is determined, thereby ensuring the accuracy of the candidate distance between the determined speed sign and the candidate lane. The candidate lane corresponding to the minimum candidate distance is determined as the target lane, thereby ensuring the minimum distance between the target lane and the speed sign, and then ensuring the accuracy of the match between the target lane and the speed sign. The text information in the target sign information is identified to determine the speed category and target speed value corresponding to the speed sign, thereby ensuring the accuracy of the speed category and target speed value corresponding to the determined speed sign. According to the geographic location information, the point closest to the speed sign in the target lane is determined as the target effective point corresponding to the target sign information, thereby ensuring the accuracy of the determined target effective point. The speed category, target speed value and applicable vehicle model are marked at the target effective point, thereby completing the marking of lane speed attribute information for the target lane and ensuring the accuracy of the lane speed attribute information for the target lane. This saves labor costs and improves efficiency.

[0123] In addition, the accuracy of the detection result is ensured by detecting whether there is an identical effective point within the preset range corresponding to the target effective point on the target lane. If there is an identical effective point within the preset range corresponding to the target effective point on the target lane, the identical effective point is deleted, thereby avoiding duplication of lane speed attribute information marked within the preset range of the target lane.

[0124] In this embodiment, a lane speed attribute generation method is provided, which can be used in the above-mentioned server side. Figure 6 is a flow chart of a method for generating lane speed attributes according to an embodiment of the present invention. Figure 6 As shown, the process includes the following steps:

[0125] Step S301, receiving sign information corresponding to a traffic sign sent by a vehicle.

[0126] For more information about this step, see Figure 3 The introduction of step S201 is not repeated here.

[0127] Step S302: Identify the sign information and determine the target sign information corresponding to the speed sign in the traffic sign.

[0128] For more information about this step, see Figure 3The introduction of step S202 is not repeated here.

[0129] Step S303: Determine the target lane corresponding to the speed sign and the lane speed attribute information corresponding to the target lane according to the target sign information.

[0130] For more information about this step, see Figure 3 The introduction of step S203 is not repeated here.

[0131] Step S304: Detect the effective range of the target sign information corresponding to the target lane.

[0132] Specifically, the target sign information may also include the scope of action corresponding to the speed sign, wherein the scope of action may include ramp, none, other, etc., wherein "ramp" is used to indicate that the speed sign can act on the ramp, "none" is used to indicate that the speed sign does not act on other lanes, and "other" is used to indicate that the speed sign can act on other lanes.

[0133] Step S305: If the effective range of the target sign information corresponding to the target lane includes other lanes, it is detected whether there is target sign information identical to the target sign information in the adjacent lane in the same direction corresponding to the target lane.

[0134] Specifically, if the effective range of the target sign information corresponding to the target lane includes other lanes, the server detects whether there is target sign information identical to the target sign information in the adjacent lane in the same direction corresponding to the target lane.

[0135] Step S306: If there is no target sign information identical to the target sign information in the adjacent lane in the same direction, the lane speed attribute information corresponding to the target lane is determined as the lane speed attribute information corresponding to other lanes.

[0136] Specifically, if there is no target sign information identical to the target sign information in the adjacent lane in the same direction, the lane speed attribute information corresponding to the target lane is determined as the lane speed attribute information corresponding to other lanes.

[0137] Step S307, detecting whether the successor lane corresponding to the target lane satisfies the reasoning termination condition.

[0138] Specifically, the server may detect whether the successor lane corresponding to the target lane satisfies the reasoning termination condition.

[0139] Among them, the reasoning termination conditions may include that the successor lane is a city road intersection, a three-way intersection or other large intersection; the successor lane is an entrance and exit ramp of a highway / city expressway; the successor lane has a speed limit release attribute, but the previous speed limit attribute cannot be found; the successor lane has been traversed. The embodiment of the present application does not specifically limit the reasoning termination conditions.

[0140] Step S308: If the subsequent lane does not meet the reasoning termination condition, it is detected whether there is corresponding target sign information in the subsequent lane.

[0141] Specifically, if the successor lane does not meet the reasoning termination condition, it is detected whether there is corresponding target sign information in the successor lane.

[0142] Step S309: If the corresponding target sign information does not exist in the successor lane, the lane speed attribute information corresponding to the target lane is determined as the lane speed attribute information corresponding to the successor lane.

[0143] Specifically, if the corresponding target sign information does not exist in the successor lane, the lane speed attribute information corresponding to the target lane is determined as the lane speed attribute information corresponding to the successor lane.

[0144] Step S310: If there is corresponding target sign information in the successor lane, then lane speed attribute information corresponding to the successor lane is determined according to the target sign information corresponding to the successor lane.

[0145] Specifically, if there is corresponding target sign information in the successor lane, the lane speed attribute information corresponding to the successor lane is determined according to the target sign information corresponding to the successor lane.

[0146] In this embodiment, a lane speed attribute generation method is provided, which can be used in the above-mentioned server side. Figure 7 is a flow chart of a method for generating lane speed attributes according to an embodiment of the present invention. Figure 7 As shown, the process includes the following steps:

[0147] Step S401: Acquire a traffic sign image and coordinate information of the traffic sign image in an image coordinate system.

[0148] Specifically, the vehicle can collect traffic sign images based on the on-board camera, and process the traffic sign images taken by the on-board camera based on the target detection algorithm to determine the coordinates of the traffic sign image in the coordinate system.

[0149] Among them, the target detection algorithm includes but is not limited to: Faster R-CNN, Fully Convolutional One-Stage Object Detection (FCOS), etc. The embodiment of the present application does not specifically limit the target detection algorithm.

[0150] Step S402: Recognize the traffic sign image to determine the category information of the traffic sign included in the traffic sign image and the text information included in the traffic sign.

[0151] Specifically, the vehicle side can use the target detection algorithm to identify the traffic sign image and determine the category information of the traffic sign included in the traffic sign image.

[0152] Among them, the target detection algorithm includes but is not limited to: Faster R-CNN, Fully Convolutional One-Stage Object Detection (FCOS), You Only Look Once version 8 (YOLOv8), DETR with Improved Non-maximal Suppression (DINO), etc. The embodiment of the present application does not specifically limit the target detection algorithm.

[0153] The vehicle side can use a preset optical character recognition algorithm to recognize the traffic sign image and determine the text information included in the traffic sign image.

[0154] The preset optical character recognition algorithm adopts a deep learning algorithm, whose input is the traffic sign image and output is the text contained in the traffic sign. The model adopts an encoder-decoder structure, such as Figure 8 As shown, the encoder encodes the input traffic sign image into image features, and the decoder decodes the text content from the image features.

[0155] Specifically, Fig. 9 As shown in the figure, the encoder is a mixture of a convolutional neural network and an attention neural network. The traffic sign image first passes through two convolutional network blocks to obtain intermediate features, and the intermediate features then pass through three attention / convolutional hybrid network blocks to obtain new intermediate features, and finally pass through the pooling layer and the linear layer to obtain the image features. Among them, in the attention / convolutional hybrid network block, the attention layer is used for context information association, and the convolution layer is used for feature dimensionality reduction; the QKV input of the attention layer uses the output of the previous layer.

[0156] The decoder consists of a character occurrence feature enhancement module, a character order feature enhancement module, and a final decoding module, all of which use attention modules. The character occurrence feature enhancement module and the character order feature enhancement module use two additional information, the character occurrence and character order, to enhance the image features output by the encoder to improve the accuracy of character recognition.

[0157] During model training, the output features of the two modules are processed by the linear layer to obtain the probability distribution of character occurrences and character order, which are then compared with the actual labels of the training set to form a loss function. During model inference, the linear layers of the two feature enhancement modules are removed to speed up the model inference. The Q input of the attention layer of the feature enhancement module uses a learnable embedding vector, and the KV input uses the image features output by the encoder; the Q input of the attention layer of the final decoding module uses the output of the character order enhancement module, and the KV input uses the output of the character occurrence module. Finally, the word vector of the text is output, and the text content of the corresponding character is obtained by looking up the table.

[0158] Step S403 , reconstructing the three-dimensional coordinates of the traffic sign in the vehicle coordinate system according to the coordinate information of the traffic sign image in the image coordinate system, and generating the geographical location information of the traffic sign.

[0159] Specifically, the vehicle side can use a target tracking algorithm to track the traffic sign image output by the perception part between different frames, and then use a mapping algorithm or a depth estimation algorithm to restore the depth information of the traffic sign image and reconstruct the three-dimensional coordinates of the traffic sign in the vehicle coordinate system.

[0160] Among them, the target tracking algorithms include but are not limited to: Fairness of Detection and Re-Identification in Multiple Object Tracking (FairMOT), Byte-level Tracking (ByteTrack), Observation-Centric Simple Online and Realtime Tracking (OC_SORT). The available mapping algorithms include but are not limited to: Visual-Inertial Navigation System-Monocular (VINS-Mono), the third generation of visual positioning mapping algorithm based on ORB features (Oriented FAST and Rotated BRIEF-Simultaneous Localization and Mapping 3, ORB-SLAM3); the available depth estimation algorithms include but are not limited to: real-time stereo matching algorithm based on hierarchical iterative tile refinement network (HITNet), monocular depth estimation algorithm based on enhanced visual perception (EVP) network.

[0161] Exemplarily, the vehicle side can use the classic SLAM algorithm. Its input is the internal and external parameters of the vehicle-mounted camera and the continuous traffic sign image frames taken. In the continuous traffic sign image frames taken by the vehicle-mounted camera, there is usually overlapping content. Feature point matching is performed in the overlapping content, and then the rough pose of the camera is obtained based on the matched feature point pairs based on the epipolar geometry method. Then, the reprojection error of all feature points is minimized based on the bundle adjustment method to obtain the pose of the camera, and then the camera extrinsic parameters and the positioning data of sensors such as the vehicle-mounted IMU / GNSS are combined to obtain the precise pose information of the vehicle. Then, based on the vehicle pose and the position of the traffic sign on the corresponding frame image, the depth information of the traffic sign is obtained based on the triangulation method, and the three-dimensional coordinates of the traffic sign are restored.

[0162] Step S404: Generate sign information corresponding to the traffic sign based on the category information, text information and geographic location information.

[0163] Specifically, the vehicle side can generate sign information corresponding to the traffic sign based on category information, text information and geographic location information.

[0164] Step S405: Transmit the flag information to the server.

[0165] Among them, the server side is used to generate lane attribute information according to any method in the implementation mode.

[0166] Specifically, the vehicle side can transmit the sign information to the server side based on the communication connection between the vehicle side and the server side.

[0167] The lane speed attribute generation method provided in the embodiment of the present application obtains a traffic sign image and the coordinate information of the traffic sign image in the image coordinate system; recognizes the traffic sign image, determines the category information of the traffic sign included in the traffic sign image and the text information included in the traffic sign, thereby ensuring the accuracy of the category information of the traffic sign included in the determined traffic sign image and the text information included in the traffic sign. Based on the coordinate information of the traffic sign image in the image coordinate system, the three-dimensional coordinates of the traffic sign in the vehicle coordinate system are reconstructed to generate the geographic location information of the traffic sign, thereby ensuring the accuracy of the generated geographic location information. Based on the category information, text information and geographic location information, the sign information corresponding to the traffic sign is generated, thereby ensuring the accuracy of the generated sign information, and the sign information is transmitted to the server side; thereby ensuring the accuracy of the lane speed attribute information corresponding to the target lane determined by the server side according to the sign information.

[0168] In an optional implementation of the present application, in order to better introduce the lane speed attribute generation method provided in the embodiment of the present application. The embodiment of the present application provides a flowchart of the lane speed attribute generation method, such as Fig.10 As shown. Specifically, the vehicle side collects traffic sign images based on the on-board camera. Then, the vehicle side uses the target detection algorithm to process the traffic sign images taken by the on-board camera, determines the category of the traffic sign contained in the traffic sign image and the coordinates in the image coordinate system, and then uses the optical character recognition algorithm to recognize the text contained in the traffic sign image. Then, the vehicle side uses the target tracking algorithm to track the traffic signs output by the perception part between different frames, and then uses the mapping algorithm or the depth estimation algorithm to restore the depth information of the traffic signs and reconstruct the three-dimensional coordinates of the traffic signs in the vehicle coordinate system. The vehicle side uploads the category (original information), local three-dimensional coordinates and contained text of the traffic signs perceived and tracked to the cloud.

[0169] The cloud first converts the three-dimensional coordinates of the traffic signs uploaded by the vehicle into global coordinates (using the positioning information of the collection vehicle), and clusters and fuses the same traffic signs observed by multiple collection vehicles into one according to the category and global coordinates of the traffic signs; then the auxiliary signs in the fused traffic signs are associated with the main signs through Hungarian matching, and the traffic signs related to the speed limit are screened out; for speed limit signs with text auxiliary signs, a text classification algorithm is used to identify the vehicle type and lane that the sign affects, and then the speed limit sign is associated with the nearest lane, and the speed limit attribute is generated for the nearest lane; finally, the speed limit attribute of the lane is inferred to its adjacent and subsequent lanes.

[0170] In this embodiment, a lane speed attribute generating device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0171] This embodiment provides a lane speed attribute generation device, which is applied to a server side, such as Fig.11 As shown, including:

[0172] The receiving module 501 is used to receive the sign information corresponding to the traffic sign sent by the vehicle end;

[0173] The first recognition module 502 is used to recognize the sign information and determine the target sign information corresponding to the speed sign in the traffic sign;

[0174] The determination module 503 is used to determine the target lane corresponding to the speed sign and the lane speed attribute information corresponding to the target lane according to the target sign information.

[0175] This embodiment provides a lane speed attribute generation device, which is applied to a vehicle end, such as Fig.12 As shown, including:

[0176] An acquisition module 601 is used to acquire a traffic sign image and coordinate information of the traffic sign image in an image coordinate system;

[0177] A second recognition module 602 is used to recognize the traffic sign image and determine the category information of the traffic sign included in the traffic sign image and the text information included in the traffic sign;

[0178] The reconstruction module 603 is used to reconstruct the three-dimensional coordinates of the traffic sign in the vehicle coordinate system according to the coordinate information of the traffic sign image in the image coordinate system, and generate the geographical location information of the traffic sign;

[0179] A generating module 604, configured to generate sign information corresponding to the traffic sign based on the category information, the text information and the geographic location information;

[0180] The transmission module 605 is used to transmit the sign information to the server side; the server side is used to generate lane attribute information according to any method in the above-mentioned implementation manner.

[0181] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0182] The lane speed attribute generating X device in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and a memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0183] The present invention provides a lane speed attribute generation system, comprising: a server end and a vehicle end; wherein the server end comprises: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the lane speed attribute generation method of any of the above embodiments by executing the computer instructions;

[0184] The vehicle end includes: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the above lane speed attribute generation method by executing the computer instructions.

[0185] The embodiment of the present invention also provides a server having the above Fig.11 The lane speed attribute generating device shown.

[0186] See also Fig.13 , Fig.13 is a schematic diagram of the structure of a server provided by an optional embodiment of the present invention, such as Fig.13As shown, the server includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the server, including instructions stored in or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple servers can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Fig.13 A processor 10 is taken as an example.

[0187] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0188] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0189] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required by at least one function; the data storage area may store data created according to the use of the server, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the server via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0190] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0191] The server further comprises a communication interface 30 for the server to communicate with other devices or a communication network.

[0192] The embodiment of the present invention also provides an intelligent vehicle having the above Fig.13 The lane speed attribute generating device shown.

[0193] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0194] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0195] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A lane speed attribute generation method, characterized in that: Applied to the server side, the method includes: Receiving sign information corresponding to the traffic sign sent by the vehicle end; Identify the sign information and determine the target sign information corresponding to the speed sign in the traffic sign; A target lane corresponding to the speed sign and lane speed attribute information corresponding to the target lane are determined according to the target sign information.

2. The method according to claim 1, characterized in that The sign information includes category information corresponding to the traffic sign, and the identifying the sign information to determine target sign information corresponding to the speed sign in the traffic sign includes: Deduplication processing is performed on the flag information to obtain standby flag information; The category information in the backup flag information is identified to obtain the target flag information.

3. The method according to claim 1, characterized in that The target sign information includes geographic location information and description information corresponding to the speed sign, and the description information is used to characterize the applicable vehicle model corresponding to the speed sign. Determining the target lane corresponding to the speed sign according to the target sign information includes: Determine, according to the description information, a candidate lane corresponding to the target sign information; determining a candidate distance between the speed sign and the candidate lane according to the geographical location information corresponding to the speed sign; The candidate lane corresponding to the minimum candidate distance is determined as the target lane.

4. The method according to claim 3, characterized in that The target sign information also includes text information. The determining, based on the target sign information, lane speed attribute information corresponding to the target lane includes: Identify the text information in the target mark information, and determine the speed category and target speed value corresponding to the speed mark; According to the geographic location information, determining from the target lane a point closest to the speed sign as a target effective point corresponding to the target sign information; The speed category, the target speed value and the applicable vehicle model are marked on the target effective point.

5. The method according to claim 4, characterized in that The method further comprises: Detect whether there is an identical effective point within a preset range corresponding to the target effective point on the target lane, and the speed category, target speed value, applicable vehicle model and effective range marked on the identical effective point are the same as those of the target effective point; If the same effective point exists within the preset range corresponding to the target effective point on the target lane, the same effective point is deleted.

6. The method according to claim 1, characterized in that The method further comprises: Detecting the effective range of the target sign information corresponding to the target lane; If the effective range of the target sign information corresponding to the target lane includes other lanes, detecting whether there is target sign information identical to the target sign information in the adjacent lane in the same direction corresponding to the target lane; If the target sign information identical to the target sign information does not exist in the adjacent lane in the same direction, the lane speed attribute information corresponding to the target lane is determined as the lane speed attribute information corresponding to the other lane.

7. The method according to claim 1, characterized in that The method further comprises: Detecting whether a subsequent lane corresponding to the target lane satisfies a reasoning termination condition; If the successor lane does not meet the reasoning termination condition, detecting whether there is corresponding target sign information in the successor lane; If the corresponding target sign information does not exist in the successor lane, the lane speed attribute information corresponding to the target lane is determined as the lane speed attribute information corresponding to the successor lane; If the corresponding target sign information exists in the successor lane, the lane speed attribute information corresponding to the successor lane is determined according to the target sign information corresponding to the successor lane.

8. A method for generating lane speed attributes, characterized in that: Applied to the vehicle side, the method includes: Acquire a traffic sign image and coordinate information of the traffic sign image in an image coordinate system; Recognizing the traffic sign image, and determining the category information of the traffic sign included in the traffic sign image and the text information included in the traffic sign; Reconstructing the three-dimensional coordinates of the traffic sign in the vehicle coordinate system according to the coordinate information of the traffic sign image in the image coordinate system, and generating the geographical location information of the traffic sign; generating sign information corresponding to the traffic sign based on the category information, the text information and the geographic location information; The sign information is transmitted to a server side; the server side is used to generate lane attribute information according to the method described in any one of claims 1-7.

9. A lane speed attribute generation system, characterized in that: include: A server side and a vehicle side; wherein the server side comprises: a memory and a processor, the memory and the processor are connected to each other in communication, the memory stores computer instructions, and the processor executes the lane speed attribute generation method according to any one of claims 1 to 7 by executing the computer instructions; The vehicle end includes: a memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the lane speed attribute generation method described in claim 8 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the lane speed attribute generation method according to any one of claims 1 to 8.

11. A computer program product, characterized in that The method comprises computer instructions for causing a computer to execute the lane speed attribute generating method according to any one of claims 1 to 8.

Images