High-precision map rendering method and device, electronic equipment and storage medium

Abstract

The invention discloses a high-precision map rendering method and device, electronic equipment and a storage medium. The high-precision map rendering method comprises the following steps: acquiring roadside sensing data containing traffic participants sent by a far end; self-vehicle positioning data are obtained, an overlapping detection fence is generated according to the self-vehicle positioning data, and the self-vehicle positioning data comprise a self-vehicle positioning result of a current frame and a self-vehicle positioning result of a previous frame; determining a to-be-rendered object which is not overlapped with an own vehicle rendering model from the traffic participants according to the roadside sensing data and the overlapping detection fence; and rendering the to-be-rendered object on a high-precision map. According to the technical scheme, the situation that the rendering model of the traffic participant is overlapped with the rendering model of the vehicle can be reduced as much as possible, and a better rendering effect is achieved.

Description

Technical Field

[0001] This application relates to the field of intelligent transportation technologies, and particularly to a high-precision map rendering method, apparatus, electronic device, and storage medium. Background Art

[0002] Vehicles usually need to display the traffic environment around the vehicle through a display interface such as an in-vehicle screen or the screen of a mobile terminal in the vehicle. Using a high-precision map as the bottom-layer data, vehicle information and pedestrian information are superimposed on the map. Among them, vehicle information and pedestrian information are usually sensed and reported by in-vehicle sensors.

[0003] However, for some non-intelligent driving vehicles, they may not have the ability to perceive the environment by themselves, or the environmental perception ability of the vehicle itself fails. When these vehicles perform high-precision map rendering, they obtain roadside perception data from the cloud or roadside, and render vehicles and pedestrians in the surrounding environment onto the high-precision map of the vehicle through the roadside perception data. However, due to reasons such as low vehicle positioning accuracy and a large difference between the vehicle positioning frequency and the roadside data perception frequency, the rendering models of the vehicle's rendering model and the roadside perception object are likely to overlap. Summary of the Invention

[0004] Embodiments of this application provide a high-precision map rendering method, apparatus, electronic device, and storage medium, which can determine as accurately as possible the perception objects that may overlap with the vehicle's rendering model and hide them to achieve a better rendering effect.

[0005] Embodiments of this application adopt the following technical solutions:

[0006] In a first aspect, an embodiment of this application provides a high-precision map rendering method, including:

[0007] Obtain roadside perception data containing traffic participants sent by a remote end;

[0008] Obtain vehicle positioning data, and generate an overlap detection fence according to the vehicle positioning data, where the vehicle positioning data includes the vehicle positioning result of the current frame and the vehicle positioning result of the previous frame;

[0009] Determine, from the traffic participants, the objects to be rendered that do not overlap with the vehicle's rendering model according to the roadside perception data and the overlap detection fence;

[0010] Render the objects to be rendered on the high-precision map.

[0011] In a second aspect, an embodiment of this application further provides a high-precision map rendering apparatus, including:

[0012] A data acquisition unit, configured to obtain roadside perception data containing traffic participants sent by a remote end;

[0013] A fence generation unit, configured to obtain the ego-vehicle positioning data and generate an overlap detection fence according to the ego-vehicle positioning data, where the ego-vehicle positioning data includes the ego-vehicle positioning result of the current frame and the ego-vehicle positioning result of the previous frame;

[0014] An object screening unit, configured to determine, from the traffic participants, a to-be-rendered object that does not overlap with the ego-vehicle rendering model according to the roadside perception data and the overlap detection fence;

[0015] An object rendering unit, configured to render the to-be-rendered object on the high-precision map.

[0016] In a third aspect, an embodiment of the present application further provides an electronic device, including:

[0017] A processor; and

[0018] A memory arranged to store computer-executable instructions, where the executable instructions, when executed, cause the processor to execute the high-precision map rendering method.

[0019] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, where the computer-readable storage medium stores one or more programs, and when the one or more programs are executed by an electronic device including a plurality of application programs, the electronic device is caused to execute the high-precision map rendering method.

[0020] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects:

[0021] In the embodiments of the present application, an overlap detection fence is constructed according to the ego-vehicle positioning result of the current frame and the ego-vehicle positioning result of the previous frame, so that the range of the overlap detection fence is related to the vehicle speed. In this way, the influence of the vehicle speed on the model overlap detection can be reduced to a certain extent. Through the overlap detection fence, roadside perception objects that overlap with the ego-vehicle rendering model can be screened out as much as possible, ensuring that when rendering traffic participants around the ego-vehicle on the high-precision map, the situation where the rendering models of traffic participants overlap with the ego-vehicle rendering model occurs as little as possible, achieving a better rendering effect. Description of the Drawings

[0022] The drawings described herein are used to provide a further understanding of the present application, and constitute a part of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application, and do not constitute an improper limitation to the present application. In the drawings:

[0023] Figure 1 is a schematic flowchart of a high-precision map rendering method in an embodiment of the present application;

[0024] Figure 2 is a schematic diagram of the rectangular form of an overlap detection fence in an embodiment of the present application;

[0025] Figure 3 This is a schematic flow diagram of a process for detecting overlapping objects in an embodiment of the present application;

[0026] Figure 4 This is a structural block diagram of a high-precision map rendering device in an embodiment of the present application;

[0027] Figure 5 This is a schematic structural diagram of an electronic device in an embodiment of the present application. Detailed implementation manners

[0028] To make the objectives, technical solutions, and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below in conjunction with specific embodiments of the present application and the corresponding drawings. Apparently, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0029] Currently, in the solution for processing roadside perception data for vehicle and pedestrian rendering on a high-precision map, due to the following reasons, there is a situation where the rendering models of the ego vehicle rendering model and the roadside perception objects overlap:

[0030] First, the positioning accuracy of the in-vehicle system is relatively low, generally only at the meter level. This may cause the rendering position of the ego vehicle on the high-precision map to deviate from the actual position of the ego vehicle, resulting in an overlap with the rendering model of the roadside perception object;

[0031] Second, the positioning frequency of the in-vehicle system is generally 1 time per second, while the refresh frequency of the roadside perception data is 10 times per second. The frequency difference between the two may also cause an overlap of the rendering models;

[0032] Third, due to the low positioning frequency of the in-vehicle system, when rendering a vehicle on a high-precision map, the transition animation may cause the distance between the actual position and the rendering position of the ego vehicle to reach several meters to more than ten meters. The ego vehicle rendering model will overlap with the rendering models of the roadside perception vehicles within this distance difference range.

[0033] In response to the above problems, the existing technical solution is to traverse the roadside perception data based on the ego vehicle positioning result of the current frame and judge the distance between the roadside perception vehicle and the ego vehicle to filter out the roadside perception vehicles that may overlap with the ego vehicle rendering model. It is found that this solution cannot solve the problem of model overlap caused by a large gap between the map rendering position and the actual position, and the distance threshold is highly dependent on the vehicle speed. When the threshold is too small, it cannot effectively solve the model overlap problem, and when the threshold is too large, it will hide the roadside perception vehicles that do not have an overlap problem, resulting in an unsatisfactory rendering effect.

[0034] Based on this, the present application provides a technical solution for effectively hiding (or filtering) roadside perception objects that overlap with the vehicle's rendering model. The following will combine the accompanying drawings to detail the technical solutions provided by each embodiment of the present application.

[0035] As Figure 1 shown, a flowchart of a high-precision map rendering method in an embodiment of the present application is provided. The method at least includes the following steps S110 to S140:

[0036] Step S110, obtain roadside perception data including traffic participants sent from a remote end.

[0037] The execution subject of the embodiment of the present application is the in-vehicle system. The in-vehicle system in this embodiment can communicate with remote ends such as roadside devices and the cloud. For example, in a V2R (Vehicle to Roadside) scenario, the in-vehicle system can obtain roadside perception data through a Road Side Unit (RSU). The traffic participants in this embodiment refer to movable roadside perception objects such as pedestrians and vehicles, and the roadside perception data refers to traffic data collected by various roadside sensors. These data include the identification, status (such as position, speed, etc.), type (referring to the type of traffic participants, such as pedestrians, vehicles, etc.) of traffic participants, as well as road conditions and environmental conditions data.

[0038] It should be understood that in some application scenarios, the remote end can send down roadside perception data according to the vehicle's position. For example, the roadside perception data of traffic participants within 200 meters of the vehicle itself can be sent down to the in-vehicle system of the vehicle itself, so as to save communication resources and improve rendering efficiency without affecting high-precision map rendering.

[0039] Step S120, obtain the vehicle's own positioning data, and generate an overlap detection fence according to the vehicle's own positioning data. The vehicle's own positioning data includes the vehicle's own positioning result of the current frame and the vehicle's own positioning result of the previous frame.

[0040] In this embodiment, an overlap detection fence is constructed based on the vehicle's own positioning result of the current frame and the vehicle's own positioning result of the previous frame. When the vehicle speed is relatively fast, the vehicle's own positioning result of the current frame and the vehicle's own positioning result of the previous frame are far apart, and the range of the constructed overlap detection fence is large. When the vehicle speed is relatively slow, the vehicle's own positioning result of the current frame and the vehicle's own positioning result of the previous frame are close, and the range of the constructed overlap detection fence is small. In this way, an overlap detection fence with a corresponding range can be constructed according to different vehicle speeds, so that in this embodiment, the overlap detection fence can identify as many roadside perception objects that may overlap with the vehicle's rendering model as possible.

[0041] Step S130: Determine, based on the roadside perception data and the overlapping detection fence, the objects to be rendered that do not overlap with the ego-vehicle rendering model from the traffic participants.

[0042] Step S140: Render the objects to be rendered on the high-precision map.

[0043] After determining the objects to be rendered, the objects to be rendered can be rendered on the high-precision map according to the roadside perception data (such as type and position) of the objects to be rendered. Those skilled in the art can refer to the existing solutions for the specific rendering process, and this embodiment will not elaborate here.

[0044] As Figure 1 shown in the high-precision map rendering method, in the embodiment of the present application, an overlapping detection fence is constructed based on the ego-vehicle positioning result of the current frame and the ego-vehicle positioning result of the previous frame, and the range of the overlapping detection fence is related to the vehicle speed. In this way, the influence of the vehicle speed on the model overlapping detection can be reduced to a certain extent, so that the roadside perception objects overlapping with the ego-vehicle rendering model can be screened out as much as possible through the overlapping detection fence, ensuring that when the in-vehicle system renders the traffic participants around the ego-vehicle on the high-precision map, the situation where the rendering models of the traffic participants overlap with the ego-vehicle rendering model can occur as little as possible, achieving a better rendering effect.

[0045] In some embodiments of the present application, in the above step S120, obtaining the ego-vehicle positioning data and generating an overlapping detection fence based on the ego-vehicle positioning data specifically includes:

[0046] Obtain a distance parameter, where the distance parameter is used to form a closed area based on the ego-vehicle positioning data;

[0047] Generate the overlapping detection fence according to the distance parameter and the ego-vehicle positioning data.

[0048] In some possible implementation manners of this embodiment, the overlapping detection fence is a rectangular fence, and the distance parameter includes a forward distance parameter, a backward distance parameter, a left-side distance parameter, and a right-side distance parameter. Generating the overlapping detection fence according to the distance parameter and the ego-vehicle positioning data specifically includes:

[0049] Generate the rear border of the overlapping detection fence according to the backward distance parameter and the ego-vehicle positioning result of the previous frame;

[0050] Generate the front border of the overlapping detection fence according to the forward distance parameter and the ego-vehicle positioning result of the current frame;

[0051] Generate the left border of the overlapping detection fence according to the left-side distance parameter and the ego-vehicle positioning result of the current frame (it can also be the ego-vehicle positioning result of the previous frame, or the straight line segment determined by the ego-vehicle positioning results of two frames).

[0052] Generate the right border of the overlapping detection fence based on the right distance parameter and the ego-vehicle positioning result of the current frame.

[0053] The rectangular overlapping detection fence constructed based on the above implementation is as Figure 2 shown. The distance between the ego-vehicle positioning result L' of the previous frame and the rear border Line1 is b, the distance between the ego-vehicle positioning result L of the current frame and the front border Line2 is t, the distance between the ego-vehicle positioning result L of the current frame and the left border Line3 is l, and the distance between the ego-vehicle positioning result L of the current frame and the right border Line4 is r.

[0054] In practical applications, the minimum values of the distance parameters b and t are half of the ego-vehicle length, and the maximum values of the distance parameters l and r are half of the lane width. The specific values of these four distance parameters can be set under the above constraints.

[0055] In some possible implementation manners of this embodiment, the overlapping detection fence may also be of other shapes, such as a runway-shaped fence. Generate the left border of the overlapping detection fence according to the left distance parameter and the ego-vehicle positioning result of the current frame, generate the right border of the overlapping detection fence according to the right distance parameter and the ego-vehicle positioning result of the current frame, use the ego-vehicle positioning result of the previous frame as the center point and the rearward distance parameter as the radius to form the rear border as a circle, and use the ego-vehicle positioning result of the current frame as the center point and the forward distance parameter as the radius to form the front border as a circle.

[0056] In some embodiments of the present application, Figure 1 the method in

[0057] further includes:

[0058] Determine, from the traffic participants, a rendering object to be rendered that does not overlap with the ego-vehicle rendering model and a target traffic participant suspected of overlapping with the ego-vehicle rendering model according to the roadside perception data.

[0058] Correspondingly, the step of determining, from the traffic participants, a rendering object to be rendered that does not overlap with the ego-vehicle rendering model according to the roadside perception data and the overlapping detection fence in the above step S130 specifically includes:

[0059] Determine, from the target traffic participants, a rendering object to be rendered that does not overlap with the ego-vehicle rendering model according to the roadside perception data and the overlapping detection fence.

[0060] In practical applications, the positional relationship between the traffic participants sent from the far end and the ego-vehicle includes three categories. The first category is those traffic participants that are far from the ego-vehicle and whose rendering models can be quickly determined not to overlap with the ego-vehicle rendering model without the overlapping detection fence; the second category is those traffic participants whose rendering models have been determined to overlap with the ego-vehicle rendering model at a previous moment; the third category is those traffic participants that need to use the overlapping detection fence for auxiliary judgment.

[0061] Based on this, in this embodiment, the roadside perception data can be used to quickly screen out each type of traffic participant, and only the overlapping detection fence is used to perform overlapping detection on the third type of traffic participant to improve the detection efficiency.

[0062] Specifically, in some embodiments, determining a rendering object that does not overlap with the ego vehicle rendering model and a target traffic participant that is suspected of overlapping with the ego vehicle rendering model from the traffic participants according to the roadside perception data specifically includes:

[0063] Obtaining a preset policy, where the preset policy refers to a traffic participant classification and screening policy that does not rely on the overlapping detection fence;

[0064] Determining a rendering object that does not overlap with the ego vehicle rendering model and a target traffic participant that is suspected of overlapping with the ego vehicle rendering model from the traffic participants according to the preset policy and the roadside perception data.

[0065] In some possible implementation manners of this embodiment, the preset policy includes a blacklist policy and a distance threshold policy, and the roadside perception data includes the object identifier and the perceived position of the traffic participant.

[0066] Determining a rendering object that does not overlap with the ego vehicle rendering model and a target traffic participant that is suspected of overlapping with the ego vehicle rendering model from the traffic participants according to the preset policy and the roadside perception data specifically includes:

[0067] Determining whether the traffic participant belongs to the blacklist according to the object identifier. If it belongs, determining that the traffic participant is an overlapping object that overlaps with the ego vehicle rendering model and not rendering it;

[0068] If it does not belong, determining the distance between the traffic participant and the ego vehicle according to the perceived position and the ego vehicle positioning result of the current frame. If the distance is greater than the preset distance threshold, determining that the traffic participant is a rendering object that does not overlap with the ego vehicle rendering model; if the distance is not greater than the preset distance threshold, determining that the traffic participant is a target traffic participant that is suspected of overlapping with the ego vehicle rendering model. The preset distance threshold here can be set according to experience, for example, it is 30 meters.

[0069] Taking the surrounding vehicle CarA as an example, if the surrounding vehicle CarA is determined to be likely to overlap with the self-vehicle rendering model, then within the next period of time, the surrounding vehicle CarA may continuously overlap with the self-vehicle rendering model. To improve the overlap detection efficiency, the surrounding vehicle CarA is added to the blacklist. Each traffic participant in the blacklist is deleted from the blacklist after a set time (such as 5 minutes or other times set according to experience) of being added to the blacklist. On the one hand, it can avoid the excessive amount of blacklist data, and on the other hand, it can also avoid mis-filtering (after a certain period of time, the perceived vehicles in the blacklist may no longer overlap with the self-vehicle rendering model).

[0070] It can be understood that in other possible implementation schemes of this embodiment, the preset policy may also include one of the blacklist policy and the distance threshold policy, and those skilled in the art can reasonably design the preset policy.

[0071] In some embodiments of the present application, in the above step S130, determining the objects to be rendered that do not overlap with the self-vehicle rendering model from the traffic participants according to the roadside perception data and the overlap detection fence specifically includes:[[]]

[0072] Determining whether the traffic participant is located within the overlap detection fence according to the roadside perception data of the traffic participant;

[0073] If it is located within the overlap detection fence, determining the traffic participant as an overlapping object that overlaps with the self-vehicle rendering model and not rendering it;

[0074] If it is not located within the overlap detection fence, determining the traffic participant as an object to be rendered that does not overlap with the self-vehicle rendering model.

[0075] This embodiment can determine whether a traffic participant is located within the overlap detection fence according to the longitude and latitude information of the traffic participant and the longitude and latitude information of the overlap detection fence. When a certain traffic participant is located within the overlap detection fence, it can be determined that the traffic participant is an overlapping object that overlaps with the self-vehicle rendering model. At this time, the traffic participant should also be added to the blacklist.

[0076] The following combines Figure 3 to introduce in detail the process of obtaining the objects to be rendered in this embodiment.

[0077] Such as Figure 3As shown in the figure, the in-vehicle infotainment (IVI) system obtains the objects to be rendered through the main thread, and maintains the overlapping detection fence through a subordinate thread. The main thread receives the roadside perception data containing traffic participants and performs a primary filter on the traffic participants through a blacklist. Then, based on a preset distance threshold D, a secondary filter is performed on the traffic participants not in the blacklist. If the distance between traffic participant A and the host vehicle is not greater than the preset distance threshold D, the latest overlapping detection fence in the cache is read to determine whether traffic participant A is within the overlapping detection fence. When traffic participant A is outside the overlapping detection fence, traffic participant A is added to the list of objects to be rendered.

[0078] As can be seen from the above embodiments of the present application, the vehicle rendering method of the embodiments of the present application has at least the following advantages:

[0079] Compared with the existing solution that only filters the traffic participants that may overlap with the rendering model of the host vehicle according to the distance between the current positioning position of the host vehicle and the traffic participants, the technical solution of this embodiment constructs an overlapping detection fence through the positioning result of the host vehicle in the current frame and the positioning result of the host vehicle in the previous frame, making the range of the overlapping detection fence related to the vehicle speed. In this way, the influence of the vehicle speed on the model overlapping detection can be reduced to a certain extent. By using the overlapping detection fence, the roadside perception objects that overlap with the rendering model of the host vehicle can be filtered out as much as possible, so that when the IVI system renders the traffic participants around the host vehicle on the high-precision map, the situation where the rendering models of the traffic participants overlap with the rendering model of the host vehicle can be minimized, achieving a better rendering effect.

[0080] The embodiments of the present application also provide a high-precision map rendering device 400, as Figure 4 shown, which provides a structural schematic diagram of a high-precision map rendering device in the embodiments of the present application. The high-precision map rendering device 400 includes: a data acquisition unit 410, a fence generation unit 420, an object screening unit 430, and an object rendering unit 440, where:

[0081] The data acquisition unit 410 is configured to acquire roadside perception data containing traffic participants sent from a remote end;

[0082] The fence generation unit 420 is configured to acquire the host vehicle positioning data and generate an overlapping detection fence according to the host vehicle positioning data, where the host vehicle positioning data includes the positioning result of the host vehicle in the current frame and the positioning result of the host vehicle in the previous frame;

[0083] The object screening unit 430 is configured to determine the objects to be rendered that do not overlap with the rendering model of the host vehicle from the traffic participants according to the roadside perception data and the overlapping detection fence;

[0084] The object rendering unit 440 is configured to render the objects to be rendered on the high-precision map.

[0085] In some embodiments of the present application, the fence generation unit 420 is specifically configured to obtain a distance parameter, where the distance parameter is used to form a closed area based on the self-vehicle positioning data; and generate the overlapping detection fence according to the distance parameter and the self-vehicle positioning data.

[0086] In some embodiments of the present application, the overlapping detection fence is a rectangular fence, and the distance parameter includes a forward distance parameter, a backward distance parameter, a left-side distance parameter, and a right-side distance parameter. The fence generation unit 420 is specifically configured to generate the rear border of the overlapping detection fence according to the backward distance parameter and the self-vehicle positioning result of the previous frame; generate the front border of the overlapping detection fence according to the forward distance parameter and the self-vehicle positioning result of the current frame; generate the left border of the overlapping detection fence according to the left-side distance parameter and the self-vehicle positioning result of the current frame; and generate the right border of the overlapping detection fence according to the right-side distance parameter and the self-vehicle positioning result of the current frame.

[0087] In some embodiments of the present application, the object screening unit 430 is further configured to determine, from the traffic participants, a to-be-rendered object that does not overlap with the self-vehicle rendering model and a target traffic participant that is suspected of overlapping with the self-vehicle rendering model according to the roadside perception data; and determine, from the target traffic participants, a to-be-rendered object that does not overlap with the self-vehicle rendering model according to the roadside perception data and the overlapping detection fence.

[0088] In some embodiments of the present application, the object screening unit 430 is specifically configured to obtain a preset policy, where the preset policy refers to a traffic participant classification and screening policy without using the overlapping detection fence; and determine, from the traffic participants, a to-be-rendered object that does not overlap with the self-vehicle rendering model and a target traffic participant that is suspected of overlapping with the self-vehicle rendering model according to the preset policy and the roadside perception data.

[0089] In some embodiments of the present application, the preset policy includes a blacklist policy and a distance threshold policy. The roadside perception data includes the object identifier and the perceived position of the traffic participant. The object screening unit 430 is specifically configured to determine whether the traffic participant belongs to the blacklist according to the object identifier. If it belongs, determine that the traffic participant is an overlapping object that overlaps with the self-vehicle rendering model and is not rendered; if it does not belong, determine the distance between the traffic participant and the self-vehicle according to the perceived position and the self-vehicle positioning result of the current frame. If the distance is greater than the preset distance threshold, determine that the traffic participant is a to-be-rendered object that does not overlap with the self-vehicle rendering model; if the distance is not greater than the preset distance threshold, determine that the traffic participant is a target traffic participant that is suspected of overlapping with the self-vehicle rendering model.

[0090] In some embodiments of the present application, the object screening unit 430 is specifically configured to determine whether the traffic participant is located within the overlapping detection fence based on the roadside perception data of the traffic participant; if it is located within the overlapping detection fence, it is determined that the traffic participant is an overlapping object overlapping with the ego-vehicle rendering model and is not rendered; if it is not located within the overlapping detection fence, it is determined that the traffic participant is a to-be-rendered object that does not overlap with the ego-vehicle rendering model.

[0091] It can be understood that the above high-precision map rendering device can implement each step of the high-precision map rendering method provided in the foregoing embodiments. The relevant explanations regarding the high-precision map rendering method are applicable to the high-precision map rendering device and will not be elaborated here.

[0092] Figure 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application. Please refer to Figure 5 , at the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. Among them, the memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory, etc. Of course, the electronic device may also include other hardware required for other services.

[0093] The processor, network interface, and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, Figure 5 only a two-way arrow is used in [the figure] to represent it, but it does not mean that there is only one bus or one type of bus.

[0094] The memory is used to store programs. Specifically, the program may include program code, and the program code includes computer operation instructions. The memory may include a memory and a non-volatile memory, and provide instructions and data to the processor.

[0095] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a high-precision map rendering device logically. The processor executes the program stored in the memory and is specifically configured to perform the following operations:

[0096] Obtain roadside perception data including traffic participants sent from a remote end;

[0097] Obtain self-vehicle positioning data, and generate an overlapping detection fence according to the self-vehicle positioning data, where the self-vehicle positioning data includes the self-vehicle positioning result of the current frame and the self-vehicle positioning result of the previous frame;

[0098] Determine, from the traffic participants, a to-be-rendered object that does not overlap with the self-vehicle rendering model according to the roadside perception data and the overlapping detection fence;

[0099] Render the to-be-rendered object on a high-precision map.

[0100] The method executed by the high-precision map rendering device disclosed in the foregoing embodiments of the present application Figure 1 can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. During implementation, the steps of the foregoing method may be completed by the integrated logic circuit in the hardware of the processor or by instructions in the form of software. The foregoing processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application may be directly embodied as being executed and completed by a hardware decoding processor, or by a combination of hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory, and the processor reads the information in the memory and combines its hardware to complete the steps of the foregoing high-precision map rendering method.

[0101] The electronic device can also execute Figure 1 the method executed by the high-precision map rendering device in Figure 1 and implement the functions of the high-precision map rendering device in the

[0102] An embodiment of the present application also provides a computer-readable storage medium storing one or more programs including instructions that, when executed by an electronic device including a plurality of application programs, enable the electronic device to execute Figure 1 the method for online calibration execution of roadside sensors in the illustrated embodiment, and specifically used to execute:

[0103] Obtain roadside perception data containing traffic participants sent from a remote end;

[0104] Obtain the ego vehicle positioning data, and generate an overlapping detection fence according to the ego vehicle positioning data, where the ego vehicle positioning data includes the ego vehicle positioning result of the current frame and the ego vehicle positioning result of the previous frame;

[0105] Determine, from the traffic participants, a to-be-rendered object that does not overlap with the ego vehicle rendering model according to the roadside perception data and the overlapping detection fence;

[0106] Render the to-be-rendered object on a high-precision map.

[0107] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of an all-hardware embodiment, an all-software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0108] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, and the combination of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0109] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in the process Figure 1one or more processes and / or blocks Figure 1 the functions specified in one or more blocks.

[0110] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one or more processes and / or blocks Figure 1 the functions specified in one or more blocks.

[0111] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0112] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

[0113] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can store information by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0114] It should also be noted that the term "comprising", "including" or any other variation thereof is intended to cover non-exclusive inclusion, so that a process, method, commodity or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "comprising one..." does not exclude the presence of additional identical elements in the process, method, commodity or device comprising the element.

[0115] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0116] The above are only the embodiments of the present application and are not intended to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A high-precision map rendering method, characterized in that: The high-precision map rendering method comprises: Obtain roadside perception data including traffic participants sent by the remote end; Acquire self-vehicle positioning data, and generate an overlapping detection fence according to the self-vehicle positioning data, wherein the self-vehicle positioning data includes the self-vehicle positioning result of the current frame and the self-vehicle positioning result of the previous frame; Determine, from the traffic participants, objects to be rendered that do not overlap with the vehicle rendering model according to the roadside perception data and the overlap detection fence; Render the object to be rendered on the high-precision map.

2. The high-precision map rendering method according to claim 1, characterized in that: The obtaining of the vehicle positioning data and generating an overlapping detection fence according to the vehicle positioning data includes: Acquire a distance parameter, wherein the distance parameter is used to form a closed area based on the vehicle positioning data; The overlapping detection fence is generated according to the distance parameter and the self-vehicle positioning data.

3. The high-precision map rendering method according to claim 2, characterized in that: The overlapping detection fence is a rectangular fence, the distance parameters include a forward distance parameter, a backward distance parameter, a left distance parameter, and a right distance parameter, and the overlapping detection fence is generated according to the distance parameters and the self-vehicle positioning data, including: Generate a rear frame of the overlapping detection fence according to the backward distance parameter and the vehicle positioning result of the previous frame; Generate a front frame of the overlapping detection fence according to the forward distance parameter and the self-vehicle positioning result of the current frame; Generate a left frame of the overlapping detection fence according to the left distance parameter and the vehicle positioning result of the current frame; A right frame of the overlapping detection fence is generated according to the right distance parameter and the vehicle positioning result of the current frame.

4. The high-precision map rendering method according to claim 1, characterized in that: The method further comprises: Determine, from the traffic participants, objects to be rendered that do not overlap with the vehicle rendering model and target traffic participants that are suspected to overlap with the vehicle rendering model according to the roadside perception data; The determining, from the traffic participants, objects to be rendered that do not overlap with the vehicle rendering model according to the roadside perception data and the overlap detection fence, comprises: According to the roadside perception data and the overlap detection fence, objects to be rendered that do not overlap with the own-vehicle rendering model are determined from the target traffic participants.

5. The high-precision map rendering method according to claim 4, characterized in that: The determining, from the traffic participants, objects to be rendered that do not overlap with the vehicle rendering model and target traffic participants suspected of overlapping with the vehicle rendering model according to the roadside perception data, includes: Acquire a preset strategy, where the preset strategy refers to a traffic participant classification and screening strategy without the use of the overlapping detection fence; According to the preset strategy and the roadside perception data, objects to be rendered that do not overlap with the vehicle rendering model and target traffic participants suspected of overlapping with the vehicle rendering model are determined from the traffic participants.

6. The high-precision map rendering method according to claim 5, characterized in that: The preset strategy includes a blacklist strategy and a distance threshold strategy, the roadside perception data includes an object identifier and a perception position of a traffic participant, and determining, from the traffic participants, objects to be rendered that do not overlap with the vehicle rendering model and target traffic participants suspected of overlapping with the vehicle rendering model according to the preset strategy and the roadside perception data, including: Determining whether the traffic participant belongs to the blacklist according to the object identifier, and if so, determining that the traffic participant is an overlapping object that overlaps with the self-vehicle rendering model and not rendering it; If it does not, the distance between the traffic participant and the self-vehicle is determined according to the perceived position and the self-vehicle positioning result of the current frame. If the distance is greater than a preset distance threshold, the traffic participant is determined to be an object to be rendered that does not overlap with the self-vehicle rendering model; if the distance is not greater than the preset distance threshold, the traffic participant is determined to be a target traffic participant suspected of overlapping with the self-vehicle rendering model.

7. The high-precision map rendering method according to claim 1, characterized in that: The determining, from the traffic participants, objects to be rendered that do not overlap with the vehicle rendering model according to the roadside perception data and the overlap detection fence, comprises: determining whether the traffic participant is located within the overlap detection fence according to the roadside perception data of the traffic participant; If the vehicle is located within the overlap detection fence, the traffic participant is determined to be an overlapping object that overlaps with the vehicle rendering model and is not rendered; If the traffic participant is not located within the overlap detection fence, it is determined that the traffic participant is an object to be rendered that does not overlap with the vehicle rendering model.

8. A high-precision map rendering device, characterized in that: The high-precision map rendering device comprises: A data acquisition unit, used to acquire roadside sensing data including traffic participants sent from a remote end; A fence generation unit, used to obtain self-vehicle positioning data and generate an overlap detection fence according to the self-vehicle positioning data, wherein the self-vehicle positioning data includes the self-vehicle positioning result of the current frame and the self-vehicle positioning result of the previous frame; An object screening unit, configured to determine objects to be rendered that do not overlap with a self-vehicle rendering model from among the traffic participants according to the roadside perception data and the overlap detection fence; The object rendering unit is used to render the object to be rendered on the high-precision map.

9. An electronic device, comprising: processor; as well as A memory arranged to store computer executable instructions, which, when executed, cause the processor to execute the high-precision map rendering method described in any one of claims 1 to 7.

10. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including multiple application programs, enables the electronic device to execute the high-precision map rendering method described in any one of claims 1 to 7.

Images