Method, device, equipment, and medium for binding traffic lights and stop lines in high-precision maps

Abstract

This disclosure provides a method, apparatus, device, and medium for binding traffic lights and stop lines in high-precision maps, relating to the field of high-precision map technology, and particularly to the fields of autonomous driving, cloud computing, artificial intelligence, the Internet of Things, intelligent transportation, big data, and computer vision. The specific implementation scheme is as follows: target traffic lights in a preset map that meet set filtering conditions are selected; target roads matching the target traffic lights and their corresponding information are obtained; based on the target road information, lane association information for each lane in the target road is obtained; target lanes that meet preset binding conditions are determined based on the lane association information, and the target traffic lights are bound to target stop lines within the target lanes. This disclosure greatly simplifies the batch binding process of stop lines and traffic lights in high-precision map annotation, ensuring binding efficiency and accuracy, and significantly improving the production efficiency of high-precision maps.

Description

Technical Field

[0001] This disclosure relates to the field of map annotation technology, and in particular to a method, apparatus, device, medium and computer program product for automatically binding traffic lights and stop lines in high-precision maps. Background Technology

[0002] Current high-precision map annotation work involves drawing lane, traffic light, and stop line information on a point cloud reflectance base map. Establishing the association between all the annotated traffic lights and their corresponding stop lines is a crucial step in high-precision map production. To improve binding efficiency, a set of automated binding rules for traffic lights and stop lines is established to achieve batch binding processing.

[0003] Currently, the main implementation scheme is: the binding of traffic lights and stop lines requires the operator to manually select a traffic light and a stop line in the annotation tool for binding; however, this scheme has the following problems: (1) manual binding is prone to omissions or misbinding; (2) the efficiency is very low when binding a large number of traffic lights and stop lines, which seriously affects the production efficiency of high-precision maps. Summary of the Invention

[0004] This disclosure provides a method, system, device, medium, and computer program product for automatically binding traffic lights and stop lines in high-precision maps. It simplifies the batch association and binding process of stop lines and traffic lights in the high-precision map annotation process, ensures the binding efficiency and accuracy of the two, and significantly improves the production efficiency of high-precision maps.

[0005] According to one aspect of this disclosure, a method for binding traffic lights and stop lines is provided, the binding method comprising:

[0006] Filter out target traffic lights in the preset map that meet the set filtering criteria;

[0007] Obtain the target road that matches the target traffic light and the corresponding target road information;

[0008] Based on the target road information, obtain the lane association information corresponding to each lane in the target road;

[0009] Based on the lane association information, a target lane that meets the preset binding conditions is determined, and the target traffic light is bound to the target stop line within the target lane.

[0010] According to another aspect of this disclosure, a binding device for traffic lights and stop lines is provided, the binding device comprising:

[0011] The target traffic light acquisition module is used to filter out target traffic lights in the preset map that meet the set filtering conditions;

[0012] The target road information acquisition module is used to acquire the target road that matches the target traffic light and the corresponding road information;

[0013] The lane association information acquisition module is used to acquire lane association information corresponding to each lane in the target road based on the target road information;

[0014] The target lane determination module is used to determine the target lane that meets the preset binding conditions based on the lane association information;

[0015] The binding control module is used to bind the target traffic light to the target stop line in the target lane.

[0016] According to another aspect of this disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program in accordance with the above-described method for binding traffic lights and stop lines.

[0017] According to another aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the above-described method for binding traffic lights and stop lines.

[0018] According to another aspect of this disclosure, a computer program product is provided, including a computer program that is executed by a processor to implement the above-described method for binding traffic lights and stop lines.

[0019] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. Attached Figure Description

[0020] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0021] Figure 1 This is a first schematic diagram of a binding method according to a first embodiment of the present disclosure;

[0022] Figure 2 This is a schematic diagram of a non-target traffic light according to the first embodiment of this disclosure;

[0023] Figure 3 This is a schematic diagram of the target traffic light according to the first embodiment of this disclosure;

[0024] Figure 4 This is a second schematic diagram of the binding method according to the first embodiment of the present disclosure;

[0025] Figure 5This is a third schematic diagram of the binding method according to the first embodiment of this disclosure;

[0026] Figure 6 This is a schematic diagram of a first scenario between a target traffic light and a lane in a target road, according to a first embodiment of this disclosure.

[0027] Figure 7 This is a schematic diagram of a second scenario between a target traffic light and a lane in a target road, according to the first embodiment of this disclosure.

[0028] Figure 8 This is a schematic diagram of a third scenario between a target traffic light and a lane in a target road, according to the first embodiment of this disclosure.

[0029] Figure 9 This is a fourth flowchart of the binding method according to the first embodiment of this disclosure;

[0030] Figure 10 This is a fifth flowchart of the binding method according to the first embodiment of this disclosure;

[0031] Figure 11 This is a schematic diagram of the first module of the binding device according to the second embodiment of the present disclosure;

[0032] Figure 12 This is a schematic diagram of the second module of the binding device according to the second embodiment of the present disclosure;

[0033] Figure 13 This is a block diagram of an electronic device used to implement the binding method of the embodiments of this disclosure. Detailed Implementation

[0034] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0035] Example 1

[0036] like Figure 1 As shown, the method for binding traffic lights and stop lines in this embodiment includes:

[0037] S101. Filter out the target traffic lights in the preset map that meet the set filtering conditions;

[0038] Among them, the preset map includes, but is not limited to, a high-precision map. The annotation work of the high-precision map will draw the lane, traffic light, stop line and other element information on the point cloud reflectance base map.

[0039] S102. Obtain the target road that matches the target traffic light and the corresponding target road information;

[0040] S103. Based on the target road information, obtain the lane association information corresponding to each lane in the target road;

[0041] S104. Determine the target lane that meets the preset binding conditions based on lane association information;

[0042] S105. Bind the target traffic light to the target stop line in the target lane, that is, establish a set of automatic binding rules for traffic lights and stop lines, which can realize automatic and batch binding processing, greatly improve the binding accuracy of the two, and effectively shorten the binding time.

[0043] The binding scheme in this embodiment can be applied, but is not limited to, in high-precision map annotation operations in the field of autonomous driving, to improve the production accuracy and efficiency of high-precision maps.

[0044] The solution in this embodiment is applied to the high-precision map annotation process, which can significantly reduce labor costs, greatly simplify the operation process of batch associating and binding stop lines and traffic lights in the high-precision map annotation process, ensure the binding efficiency and accuracy of the two, and significantly improve the production efficiency of high-precision maps.

[0045] The method for binding traffic lights and stop lines in this embodiment is... Figure 1 Further improvements to the corresponding solution, specifically:

[0046] In one feasible embodiment, step S101 includes:

[0047] Obtain the attribute information corresponding to each traffic light in the preset map;

[0048] Filter out target traffic lights whose attribute information meets the first set filtering conditions;

[0049] The first set filtering condition indicates that the traffic light can perform a binding operation;

[0050] Alternatively, remove traffic lights whose attribute information meets the second set filtering conditions from all traffic lights in the preset map to obtain the target traffic lights;

[0051] The second set of filtering conditions indicates that the traffic light cannot perform binding operations.

[0052] The purpose of this solution is to eliminate traffic lights that do not need to participate in the binding operation in autonomous driving scenarios, thereby avoiding unnecessary calculation processes and ensuring that the traffic lights selected in the final process do indeed have practical value in the application scenario. In other words, it ensures that the selected traffic lights are usable and reliable, thus improving the reliability and accuracy of the final binding result.

[0053] For example, if the attribute information of a traffic light corresponds to any of the following conditions, it will be determined not to bind it: (1) it indicates an abnormal state, such as being out of service; (2) it indicates "for non-motorized vehicle lanes"; (3) its installation location is not "suspended light"; (4) its light frame type is not "regular light"; among which, (3) and (4) are used to exclude similar conditions. Figure 2 The traffic lights shown are of this type; this filters out all traffic lights that are normally used in the motor vehicle lanes and are either hanging lights or conventional lights, such as... Figure 3 As shown. Of course, other conditions can also be included, as long as the selected traffic lights meet the binding requirements, which will not be elaborated here.

[0054] In a feasible solution, such as Figure 4 As shown, step S103 includes:

[0055] S10311. Obtain the horizontal position information of the target traffic light;

[0056] S10312. Determine whether there is a situation where the outer contour of a road includes the location range of the location information. If so, determine the corresponding road as the target road and obtain the corresponding target road information.

[0057] In this solution, the road's outer geometry is determined by projecting the traffic light's location onto the ground. If the projection includes the traffic light's location, the corresponding road is identified as the target road, and its information is obtained. If the projection does not include the traffic light, the search stops, the binding fails, and the binding operation is terminated.

[0058] In a feasible solution, such as Figure 5 As shown, step S103 includes:

[0059] S10321. Obtain the attribute information corresponding to each traffic light in the preset map;

[0060] S10322. Based on attribute information and preset search methods, obtain multiple target traffic lights that are in the same row and in the same direction;

[0061] Among them, multiple target traffic lights are arranged in sequence according to their spatial location;

[0062] S10323. Obtain the horizontal position information of each target traffic light;

[0063] S10324. Based on the sorting rules, determine in turn whether there is a case where the outer contour of a road includes the location range of any target traffic light. If so, use the existing road as the target road for matching multiple target traffic lights and obtain the corresponding target road information.

[0064] In one feasible solution, the binding method also includes:

[0065] If it is determined that the outer contour of the road does not encompass the location range of any target traffic light, then the binding is deemed to have failed and the binding operation is stopped.

[0066] In this solution, the preset search methods include, but are not limited to: within a 15m distance, normal attribute status, for motor vehicle lanes, and in the same direction (the vertical angle between the traffic lights is less than 5 degrees, defined as in the same direction), to search for multiple traffic lights in the same row and in the same direction, such as... Figure 3 As shown, the searched traffic lights are sorted from closest to farthest from one side of the road (e.g., for...). Figure 3 The three traffic lights in the row are ordered from right to left as A, B, and C. If any traffic light finds a road with a value greater than 0, the search stops, and that road becomes the target road for matching the remaining three traffic lights. If none of the three traffic lights find a matching road, the binding operation fails and stops. The entire road matching process is automated and requires no human intervention, ensuring the feasibility and efficiency of subsequent binding operations.

[0067] In a feasible solution, such as Figure 6 As shown, step S104 includes:

[0068] S1041. Determine whether the target lane belongs to the front-wheel drive lane based on lane association information. If it does, execute S1042.

[0069] S1042. Determine whether a front-wheel drive road exists in the front-wheel drive lane. If it does, proceed to S1043.

[0070] S1043. Determine that the current lane is a target lane that meets the preset binding conditions;

[0071] S1044. Traverse each lane in the target road to obtain all target lanes that meet the preset binding conditions.

[0072] In this solution, by determining the presence of front-wheel drive lanes and roads with front-wheel drive, unnecessary lane binding operations are avoided. This ensures that all lanes bound to traffic lights have driving guidance value, effectively guaranteeing the rationality of the binding process and ensuring the accuracy and reliability of the final binding result.

[0073] In one feasible embodiment, step S1041 includes:

[0074] Based on lane association information, determine whether the outer contour of the corresponding lane contains a stop line and is a straight-ahead lane. If so, the corresponding lane is determined to be a front-wheel drive lane; otherwise, the corresponding lane is determined not to be a front-wheel drive lane. See details below. Figure 7 and Figure 8 .

[0075] For each lane, the system can search multiple times to ensure the reliability of front-wheel drive lane determination; at the same time, setting an upper limit for the search (no more than 5 times) also ensures the efficiency and rationality of the entire process.

[0076] In one feasible solution, the binding method also includes:

[0077] If none of the lanes in the target road being traversed belong to the front-drive lane, then the binding is determined to have failed and the binding operation is stopped; otherwise, proceed to step S1042.

[0078] This solution promptly identifies lanes that do not need to be bound, avoiding unnecessary processing operations, skipping the binding process, simplifying the binding process, and ensuring its efficiency.

[0079] In one feasible solution, after determining that there is no front-wheel drive road in the front-wheel drive lane, the binding method also includes:

[0080] Continue to check the next front-wheel drive lane. If no front-wheel drive road exists after traversing all front-wheel drive lanes, then the binding has failed and the binding operation has stopped.

[0081] This solution promptly identifies lanes that do not need to be bound, avoiding unnecessary processing operations, skipping the binding process, simplifying the binding process, and ensuring its efficiency.

[0082] In one feasible solution, the binding method also includes:

[0083] Determine whether there is a stop line in the subsequent lane of each lane in the target road. If there is, proceed to step S104; if not, determine that the binding has failed and stop the binding operation, and continue to determine the next lane until all lanes in the target road have been traversed.

[0084] For details, please refer to this plan. Figure 9 By checking whether there is a stop line in the next lane of each lane, if not, it is impossible to effectively distinguish the next lane from the current lane. In order to avoid binding the traffic lights of the next lane to the current lane, the straight-ahead operation of the current lane is not bound, thereby realizing the deduplication of all lanes and further ensuring the accuracy and reliability of the binding operation.

[0085] In a feasible solution, such as Figure 10As shown, step S105 includes:

[0086] S1051. Associate the direction association information corresponding to each target lane with the corresponding target stop line to obtain the target stop line information;

[0087] S1052. Based on the target attribute information of the target traffic light and the target stop line information of each target stop line, bind the target traffic light to the target stop line in the target lane.

[0088] In one feasible embodiment, step S1052 includes:

[0089] If there is an overlap between the traffic light control direction information in the target attribute information and the direction association information in the target stop line information, then the target traffic light will be bound to the target stop line in the target lane.

[0090] In this scheme, the directional information associated with the target lane includes one or more combinations of left turn, right turn, straight, and U-turn information. This information for each target lane is associated with the stop line in the corresponding lane. Then, when there is an intersection with the control direction of the traffic light, the target traffic light is automatically bound to the corresponding target stop line, without the need for manual intervention throughout the process.

[0091] Example 2

[0092] like Figure 11 As shown, the traffic light and stop line binding system in this embodiment includes:

[0093] Target traffic light acquisition module 1 is used to filter out target traffic lights in the preset map that meet the set filtering conditions;

[0094] Among them, the preset map includes, but is not limited to, a high-precision map. The annotation work of the high-precision map will draw the lane, traffic light, stop line and other element information on the point cloud reflectance base map.

[0095] Target road information acquisition module 2 is used to acquire the target road that matches the target traffic light and the corresponding target road information;

[0096] Lane association information acquisition module 3 is used to acquire lane association information corresponding to each lane in the target road based on the target road information;

[0097] Target lane determination module 4 is used to determine target lanes that meet preset binding conditions based on lane association information;

[0098] The binding control module 5 is used to bind the target traffic light to the target stop line in the target lane; that is, to establish a set of automatic binding rules for traffic lights and stop lines, which can realize automatic and batch binding processing, greatly improve the binding accuracy of the two, and effectively shorten the binding time.

[0099] The binding scheme in this embodiment can be applied, but is not limited to, in high-precision map annotation operations in the field of autonomous driving, to improve the production accuracy and efficiency of high-precision maps.

[0100] The solution in this embodiment is applied to the high-precision map annotation process, which can significantly reduce labor costs, greatly simplify the operation process of batch associating and binding stop lines and traffic lights in the high-precision map annotation process, ensure the binding efficiency and accuracy of the two, and significantly improve the production efficiency of high-precision maps.

[0101] like Figure 12 As shown, the traffic light and stop line binding system in this embodiment is... Figure 11 Further improvements to the binding system, specifically:

[0102] In one feasible solution, the target traffic light acquisition module 1 includes:

[0103] The attribute information acquisition unit 6 is used to acquire the attribute information corresponding to each traffic light in the preset map;

[0104] The target traffic light acquisition unit 7 is used to filter out target traffic lights whose attribute information meets the first set filtering conditions.

[0105] The first set filtering condition indicates that the traffic light can perform a binding operation;

[0106] Alternatively, the target traffic light acquisition unit 7 is also used to remove traffic lights whose attribute information meets the second set filtering conditions from all traffic lights in the preset map, so as to obtain the target traffic light;

[0107] The second set of filtering conditions indicates that the traffic light cannot perform binding operations.

[0108] The purpose of this solution is to eliminate traffic lights that do not need to participate in the binding operation in autonomous driving scenarios, thereby avoiding unnecessary calculation processes and ensuring that the traffic lights selected in the final process do indeed have practical value in the application scenario. In other words, it ensures that the selected traffic lights are usable and reliable, thus improving the reliability and accuracy of the final binding result.

[0109] For example, if the attribute information of a traffic light corresponds to any of the following conditions, it will be determined not to bind it: (1) it indicates an abnormal state, such as being out of service; (2) it indicates "for non-motorized vehicle lanes"; (3) its installation location is not "suspended light"; (4) its light frame type is not "regular light"; among which, (3) and (4) are used to exclude similar conditions. Figure 2 The traffic lights shown are of this type; this filters out all traffic lights that are normally used in the motor vehicle lanes and are either hanging lights or conventional lights, such as... Figure 3 As shown. Of course, other conditions can also be included, as long as the selected traffic lights meet the binding requirements, which will not be elaborated here.

[0110] In one feasible solution, the target road information acquisition module 2 includes:

[0111] The location information acquisition unit 8 is used to acquire the location information of the target traffic light in the horizontal direction;

[0112] The first judgment unit 9 is used to determine whether there is a situation where the outer contour of the road includes the location range of the location information. If so, the target road determination unit 10 is called to determine the corresponding road as the target road and obtain the corresponding target road information.

[0113] In this solution, the road's outer geometry is determined by projecting the traffic light's location onto the ground. If the projection includes the traffic light's location, the corresponding road is identified as the target road, and its information is obtained. If the projection does not include the traffic light, the search stops, the binding fails, and the binding operation is terminated.

[0114] In one feasible solution, the target traffic light acquisition module 1 includes:

[0115] The attribute information acquisition unit 6 is used to acquire the attribute information corresponding to each traffic light in the preset map;

[0116] The target traffic light acquisition unit 7 is used to acquire multiple target traffic lights that are in the same row and in the same direction based on attribute information and a preset search method.

[0117] Among them, multiple target traffic lights are arranged in sequence according to their spatial location;

[0118] Target road information acquisition module 2 includes:

[0119] The location information acquisition unit 8 is used to acquire the horizontal location information of each target traffic light;

[0120] The second judgment unit 11 is used to determine, based on the sorting rules, whether there is a case where the outer contour of a road includes the location range of any target traffic light. If so, the target road determination unit 10 is called to use the existing road as the target road for matching multiple target traffic lights and obtain the corresponding target road information.

[0121] In one feasible solution, the binding system also includes:

[0122] The stop binding determination module 12 is used to determine that the binding has failed and stop the binding operation if it is determined that there is no road outline that includes the location range of any target traffic light location information.

[0123] In this solution, the preset search methods include, but are not limited to: within a 15m distance, normal attribute status, for motor vehicle lanes, and in the same direction (the vertical angle between the traffic lights is less than 5 degrees, defined as in the same direction), to search for multiple traffic lights in the same row and in the same direction, such as... Figure 4 As shown, the searched traffic lights are sorted from closest to farthest from one side of the road (e.g., for...). Figure 4 The three traffic lights in the row are ordered from right to left as A, B, and C. If any traffic light finds a road with a value greater than 0, the search stops, and that road becomes the target road for matching the remaining three traffic lights. If none of the three traffic lights find a matching road, the binding operation fails and stops. The entire road matching process is automated and requires no human intervention, ensuring the feasibility and efficiency of subsequent binding operations.

[0124] In one feasible solution, the target lane determination module 4 includes:

[0125] The first judgment module 13 is used to determine whether the target lane belongs to the front-wheel drive lane based on the lane association information. If it does, the second judgment module 14 is called to determine whether the front-wheel drive lane exists on the front-wheel drive road. If it does, the target lane determination unit 10 is called to determine that the current lane is the target lane that meets the preset binding conditions. Each lane in the target road is traversed to obtain all target lanes that meet the preset binding conditions.

[0126] In this solution, by determining the presence of front-wheel drive lanes and roads with front-wheel drive, unnecessary lane binding operations are avoided. This ensures that all lanes bound to traffic lights have driving guidance value, effectively guaranteeing the rationality of the binding process and ensuring the accuracy and reliability of the final binding result.

[0127] In one feasible solution, the first judgment module 13 is further used to determine whether the outer contour of the corresponding lane contains a stop line and is a straight lane based on the lane association information. If so, the corresponding lane is determined to be a front-wheel drive lane; otherwise, the corresponding lane is determined not to be a front-wheel drive lane.

[0128] For each lane, the system can search multiple times to ensure the reliability of front-wheel drive lane determination; at the same time, setting an upper limit for the search (no more than 5 times) also ensures the efficiency and rationality of the entire process.

[0129] In one feasible solution, the stop binding determination module 12 is also used to determine the binding failure and stop the binding operation if each lane in the traversed target road does not belong to the front drive lane; otherwise, the second judgment module 14 is called.

[0130] This solution promptly identifies lanes that do not need to be bound, avoiding unnecessary processing operations, skipping the binding process, simplifying the binding process, and ensuring its efficiency.

[0131] In one feasible solution, the stop binding determination module 12 is also used to determine the next front-wheel drive lane after determining that there is no front-wheel drive road in the front-wheel drive lane. If there is no front-wheel drive road after traversing all front-wheel drive lanes, the binding is determined to have failed and the binding operation is stopped.

[0132] This solution promptly identifies lanes that do not need to be bound, avoiding unnecessary processing operations, skipping the binding process, simplifying the binding process, and ensuring its efficiency.

[0133] In one feasible solution, the binding system also includes:

[0134] The third judgment module 15 is used to determine whether there is a stop line in the subsequent lane of each lane in the target road. If there is, the target lane determination module 4 is called; if there is not, the stop binding determination module 12 is called to determine that the binding has failed and the binding operation is stopped; the next lane is judged until all lanes in the target road have been traversed.

[0135] In this solution, the system checks whether there is a stop line in the next lane of each lane. If there is no stop line, it cannot effectively distinguish between the next lane and the current lane. To avoid binding the traffic lights of the next lane and the current lane, the system does not bind the current lane to the straight-ahead operation, thus deduplicating all lanes and further ensuring the accuracy and reliability of the binding operation.

[0136] In one feasible solution, the binding control module 5 includes:

[0137] The stop line information acquisition unit 16 is used to associate the direction association information corresponding to each target lane with the corresponding target stop line to obtain the target stop line information;

[0138] The binding control unit 17 is used to bind the target traffic light to the target stop line in the target lane based on the target attribute information of the target traffic light and the target stop line information of each target stop line.

[0139] In one feasible solution, the binding control unit is used to bind the target traffic light to the target stop line in the target lane if there is an intersection between the traffic light control direction information in the target attribute information and the direction association information in the target stop line information.

[0140] In this scheme, the directional information associated with the target lane includes one or more combinations of left turn, right turn, straight, and U-turn information. This information for each target lane is associated with the stop line in the corresponding lane. Then, when there is an intersection with the control direction of the traffic light, the target traffic light is automatically bound to the corresponding target stop line, without the need for manual intervention throughout the process.

[0141] Example 3

[0142] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0143] Figure 13 A schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0144] like Figure 13 As shown, device 800 includes a computing unit 801, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 802 or a computer program loaded from storage unit 808 into random access memory (RAM) 803. RAM 803 may also store various programs and data required for the operation of device 800. The computing unit 801, ROM 802, and RAM 803 are interconnected via bus 804. Input / output (I / O) interface 805 is also connected to bus 804.

[0145] Multiple components in device 800 are connected to I / O interface 805, including: input unit 806, such as keyboard, mouse, etc.; output unit 807, such as various types of monitors, speakers, etc.; storage unit 808, such as disk, optical disk, etc.; and communication unit 809, such as network card, modem, wireless transceiver, etc. Communication unit 809 allows device 800 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0146] The computing unit 801 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as method XXX. For example, in some embodiments, method XXX may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of method XXX described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform method XXX by any other suitable means (e.g., by means of firmware).

[0147] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0148] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0149] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0150] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0151] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0152] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0153] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0154] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for binding traffic lights and stop lines, comprising: Filter out target traffic lights in the preset map that meet the set filtering criteria; Obtain the target road that matches the target traffic light and the corresponding target road information; Based on the target road information, obtain the lane association information corresponding to each lane in the target road; Based on the lane association information, a target lane that meets the preset binding conditions is determined, and the target traffic light is bound to the target stop line within the target lane; The step of obtaining the target road that matches the target traffic light and the corresponding target road information includes: Obtain the horizontal position information of the target traffic light; Determine if there is a case where the outer contour of a road encompasses the location range of the location information. If so, determine the corresponding road as the target road and obtain the corresponding target road information. or, The step of obtaining the target road that matches the target traffic light and the corresponding target road information includes: Obtain the attribute information corresponding to each traffic light in the preset map; Based on the attribute information and the preset search method, obtain multiple target traffic lights that are in the same row and in the same direction; Among them, the multiple target traffic lights are arranged sequentially according to their spatial location; Obtain the horizontal position information of each of the target traffic lights; Based on the sorting rules, it is determined whether there is a case where the outer contour of a road includes the location range of the location information of any of the target traffic lights. If so, the existing road is used as the target road for matching multiple target traffic lights and the corresponding target road information is obtained.

2. The method according to claim 1, wherein, The step of filtering out target traffic lights in the preset map that meet the set filtering conditions includes: Obtain the attribute information corresponding to each traffic light in the preset map; Filter out the target traffic lights whose attribute information satisfies the first set filtering conditions; The first set filtering condition indicates that the traffic light can perform a binding operation; Alternatively, the target traffic light can be obtained by removing traffic lights whose attribute information meets the second set filtering conditions from all traffic lights in the preset map. The second set filtering condition indicates that the traffic light cannot perform binding operations.

3. The method according to claim 1, further comprising: If it is determined that there is no road outline that includes the location range of the location information of any of the target traffic lights, then the binding is determined to have failed and the binding operation is stopped.

4. The method according to claim 3, wherein, The step of determining the target lane that meets the preset binding conditions based on the lane association information includes: Based on the lane association information, it is determined whether the target lane is a front-wheel drive lane. If it is, it is determined whether the front-wheel drive lane has a front-wheel drive road. If it does, the current lane is determined to be the target lane that meets the preset binding conditions. Traverse each lane in the target road to obtain all target lanes that satisfy the preset binding conditions.

5. The method according to claim 4, wherein, The step of determining whether a corresponding lane belongs to a front-wheel drive lane based on the lane association information includes: Based on the lane association information, it is determined whether the outer contour of the corresponding lane contains a stop line and is a straight-ahead lane. If so, the corresponding lane is determined to be a front-wheel drive lane; otherwise, the corresponding lane is determined not to be a front-wheel drive lane.

6. The method according to claim 5, further comprising: If none of the lanes in the target road being traversed is a front-wheel drive lane, then the binding is determined to have failed and the binding operation is stopped. Otherwise, proceed with the step of determining whether a front-wheel drive road exists in the front-wheel drive lane.

7. The method according to claim 4, further comprising: After determining that there is no front-wheel drive road in the front-wheel drive lane, the system continues to determine the next front-wheel drive lane. If there is no front-wheel drive road after traversing all the front-wheel drive lanes, the binding is determined to have failed and the binding operation is stopped.

8. The method according to any one of claims 3-7, further comprising: Determine whether there is a stop line in the subsequent lane of each lane in the target road. If there is, then execute the step of determining the target lane that meets the preset binding conditions based on the lane association information. If it does not exist, the binding is determined to have failed and the binding operation is stopped. The process continues to check the next lane until all lanes of the target road have been traversed.

9. The method according to claim 1, wherein, The step of binding the target traffic light to the target stop line in the target lane includes: The direction association information corresponding to each target lane is associated with the corresponding target stop line to obtain the target stop line information; Based on the target attribute information of the target traffic light and the target stop line information of each target stop line, the target traffic light is bound to the target stop line in the target lane.

10. The method according to claim 9, wherein, The step of binding the target traffic light to the target stop line in the target lane based on the target attribute information of the target traffic light and the target stop line information of each target stop line includes: If there is an intersection between the traffic light control direction information in the target attribute information and the direction association information in the target stop line information, then the target traffic light will be bound to the target stop line in the target lane.

11. A device for binding traffic lights and stop lines, comprising: The target traffic light acquisition module is used to filter out target traffic lights in the preset map that meet the set filtering conditions; The target road information acquisition module is used to acquire the target road that matches the target traffic light and the corresponding road information; The lane association information acquisition module is used to acquire lane association information corresponding to each lane in the target road based on the target road information; The target lane determination module is used to determine the target lane that meets the preset binding conditions based on the lane association information; A binding control module is used to bind the target traffic light to the target stop line in the target lane; The target road information acquisition module includes: A location information acquisition unit is used to acquire the location information of the target traffic light in the horizontal direction; The first judgment unit is used to determine whether there is a situation where the outer contour of a road includes the location range of the location information. If so, the target road determination unit is called to determine the corresponding road as the target road and obtain the corresponding target road information. or, The target traffic light acquisition module includes: An attribute information acquisition unit is used to acquire attribute information corresponding to each traffic light in the preset map; The target traffic light acquisition unit is used to acquire multiple target traffic lights that are in the same row and in the same direction based on the attribute information and a preset search method. Among them, the multiple target traffic lights are arranged sequentially according to their spatial location; The target road information acquisition module includes: A location information acquisition unit is used to acquire the location information of each of the target traffic lights in the horizontal direction; The second judgment unit is used to determine, based on the sorting rules, whether there is a case where the outer contour of a road includes the location range of the location information of any of the target traffic lights. If so, the target road determination unit is called to use the existing road as the target road for matching multiple target traffic lights and obtain the corresponding target road information.

12. The apparatus of claim 11, wherein the target traffic light acquisition module comprises: An attribute information acquisition unit is used to acquire attribute information corresponding to each traffic light in the preset map; A target traffic light acquisition unit is used to filter out the target traffic lights whose attribute information satisfies a first set filtering condition. The first set filtering condition indicates that the traffic light can perform a binding operation; Alternatively, the target traffic light can be obtained by removing traffic lights whose attribute information meets the second set filtering conditions from all traffic lights in the preset map. The second set filtering condition indicates that the traffic light cannot perform binding operations.

13. The apparatus of claim 11, wherein the binding device further comprises: The stop binding determination module is used to determine that binding has failed and stop the binding operation if it is determined that there is no road outline that includes the location range of the location information of any of the target traffic lights.

14. The apparatus of claim 13, wherein the target lane determination module comprises: The first judgment module is used to determine whether the target lane belongs to the front-wheel drive lane based on the lane association information. If it does, the second judgment module is called to determine whether the front-wheel drive lane exists on a front-wheel drive road. If it does, the target lane determination unit is called to determine that the current lane is the target lane that meets the preset binding conditions. Each lane in the target road is traversed to obtain all the target lanes that meet the preset binding conditions.

15. The apparatus of claim 14, wherein the first determining module is further configured to determine, based on the lane association information, whether the outer contour of the corresponding lane contains a stop line and is a straight-ahead lane; if so, determine that the corresponding lane is a front-wheel drive lane; otherwise, determine that the corresponding lane is not a front-wheel drive lane.

16. The apparatus of claim 14, wherein the stop binding determination module is further configured to determine binding failure and stop binding operation if each lane in the traversal of the target road does not belong to the front drive lane; otherwise, call the second determination module.

17. The apparatus of claim 14, wherein the stop binding determination module is further configured to, after determining that there is no front-drive road in the front-drive lane, continue to determine the next front-drive lane, and if there is no front-drive road in all the front-drive lanes, determine that the binding has failed and stop the binding operation.

18. The apparatus of any one of claims 13-17, wherein the binding device further comprises: The third judgment module is used to determine whether there is a stop line in the subsequent lane of each lane in the target road. If there is, the target lane determination module is called. If it does not exist, the stop binding determination module is invoked to determine that the binding has failed and to stop the binding operation; Continue to determine the next lane until all lanes of the target road have been traversed.

19. The apparatus of claim 11, wherein the binding control module comprises: The stop line information acquisition unit is used to associate the direction association information corresponding to each target lane with the corresponding target stop line to obtain the target stop line information; A binding control unit is used to bind the target traffic light to the target stop line in the target lane based on the target attribute information of the target traffic light and the target stop line information of each target stop line.

20. The apparatus of claim 19, wherein the binding control unit is configured to bind the target traffic light to the target stop line in the target lane if there is an intersection between the traffic light control direction information in the target attribute information and the direction association information in the target stop line information.

21. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the method of any one of claims 1-10.

22. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-10.

23. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-10.

Images