CN115876183A

CN115876183A - Electronic map updating method and device and automatic driving vehicle

Info

Publication number: CN115876183A
Application number: CN202211336357.8A
Authority: CN
Inventors: 古新才; 谢佳林; 白宇; 黄杰
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2022-10-28
Filing date: 2022-10-28
Publication date: 2023-03-31

Abstract

The disclosure provides an updating method and equipment of an electronic map and an automatic driving vehicle, and relates to the field of artificial intelligence, in particular to the field of automatic driving and high-precision maps. The specific implementation scheme is as follows: the electronic device acquires image data of a target road including a plurality of elements. When the electronic device determines that the scene change is present on the target road, the electronic device inputs the image data of the target road into the plurality of element change determination models to obtain a plurality of recognition results. Wherein, one element change determination model is used for determining whether one element is changed, and the corresponding recognition result of the element change determination model is used for indicating whether the corresponding element in the target road is changed. The electronic device determines a changed element in the target road based on the plurality of recognition results, and updates the electronic map based on image data of the changed element.

Description

Electronic map updating method and device and automatic driving vehicle

Technical Field

The disclosure relates to the technical field of artificial intelligence, in particular to the field of automatic driving and high-precision maps, and specifically relates to an electronic map updating method and device and an automatic driving vehicle.

Background

With the continuous development of automatic driving, as an important component of automatic driving technology, the function of electronic maps (such as high-precision maps) is more and more important. For example, autonomous vehicles require navigation through high-precision maps during travel.

Generally, in order to ensure the accuracy of the electronic map. When the elements of the road are changed (for example, the road is added with an intersection, a traffic light, a road sign, etc.), the specific changed elements of the road need to be determined as soon as possible, and then the electronic map needs to be updated.

Disclosure of Invention

The disclosure provides an updating method and equipment of an electronic map and an automatic driving vehicle.

According to a first aspect of the present disclosure, there is provided a method for determining an electronic map, including:

the electronic device acquires image data of a target road including a plurality of elements. When it is determined that the scene change occurs in the target road, the electronic device inputs the image data of the target road into the plurality of element change determination models, and obtains a plurality of recognition results. Wherein, one element change determining model is used for determining whether one element is changed, and the corresponding recognition result of the element change determining model is used for indicating whether the corresponding element in the target road is changed. The electronic device determines a changed element in the target road based on the plurality of recognition results, and updates the electronic map based on image data of the changed element.

According to a second aspect of the present disclosure, there is provided an updating apparatus of an electronic map, including: an acquisition unit acquires image data of a target road including a plurality of elements. And a processing unit for inputting the image data of the target road into the plurality of element change determination models to obtain a plurality of recognition results when determining that the scene change exists on the target road. Wherein, one element change determination model is used for determining whether one element is changed, and the corresponding recognition result of the element change determination model is used for indicating whether the corresponding element in the target road is changed. And a determination unit configured to determine the modified element in the target road based on the plurality of recognition results. And the processing unit is also used for updating the electronic map according to the image data of the changed elements.

According to a third aspect of the present disclosure, there is provided an electronic device comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform any one of the methods of the first aspect.

According to a fourth aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions, comprising:

the computer instructions are for causing a computer to perform any one of the methods of the first aspect.

According to a fourth aspect of the present disclosure, there is provided a computer program product comprising:

a computer program which, when executed by a processor, performs any of the methods of the first aspect.

According to a fifth aspect of the present disclosure, there is provided an autonomous vehicle comprising an electronic device for performing any of the methods of the first aspect.

According to the technical scheme of the disclosure, under the condition that the scene change of the target road is determined, the changed elements in the target road are rapidly determined through the plurality of element change determination models, and the electronic map is updated according to the image data of the changed elements. The updating efficiency of the electronic map is improved.

It should be understood that the statements in this section are not intended to identify key or critical 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 apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

FIG. 1 is a schematic diagram of the architecture of a system of an embodiment of the present disclosure;

fig. 2 is a schematic diagram of an updating method of an electronic map according to an embodiment of the present disclosure;

FIG. 3 is a schematic diagram of a solution flow of an embodiment of the present disclosure;

fig. 4 is a schematic diagram of another electronic map updating method according to an embodiment of the present disclosure;

FIG. 5 is a schematic diagram of a default transport protocol according to an embodiment of the present disclosure;

fig. 6 is a schematic diagram of another electronic map updating method according to an embodiment of the present disclosure;

FIG. 7 is a schematic illustration of a charting flow of an embodiment of the present disclosure;

fig. 8 is a schematic diagram of a data transmission manner provided by an embodiment of the present disclosure;

fig. 9 is a schematic diagram of an updating apparatus of an electronic map according to an embodiment of the present disclosure;

fig. 10 is a block diagram of an electronic device of a method for determining a point of interest provided by an embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of embodiments of the present disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

Before describing the updating method of the electronic map in the embodiment of the present disclosure in detail, the application elements in the embodiment of the present disclosure are explained.

When a user drives a vehicle or the vehicle is in automatic driving, the user needs to realize safe driving through a navigation function of an electronic map (such as a high-precision map). If the changed elements appear on the road where the vehicle runs, but the elements are not updated in time on the electronic map, the use of the user or the driving safety may be affected. For example, if an intersection is newly added to a certain road, but the electronic map displays no intersection on the road, the vehicle in automatic driving will not detect whether a vehicle passes through the intersection of the road when the vehicle is driven according to the electronic map. However, if a vehicle appears at the intersection, the vehicle in automatic driving may not have time to avoid or decelerate, thereby causing a traffic accident.

In order to avoid traffic accidents, the electronic map needs to be updated in time when the road elements are changed, so that the timeliness of the electronic map configured by vehicles is guaranteed.

In general, in order to update an electronic map, the electronic map may be updated in a batch process. The batch processing is to update the electronic map according to the plurality of road data after the plurality of road data are acquired. However, this method is inferior in terms of time efficiency.

It should be noted that the updating process of the electronic map may include a middle business stage and a back business stage. The middle-business stage refers to a stage of processing road data. The post-operation stage is a stage of drawing according to the processed road data.

In order to guarantee timeliness of the electronic map, the map can be updated in a way of service and real-time calculation. The following describes the servitization and real-time computation, respectively.

1. And (5) serving. The service may refer to a manner of converting a batch job into a request, that is, after one piece of road data is acquired, the update of the electronic map is performed by a server/device for updating the electronic map in a request manner.

In one example, a server/device may be provided with multiple modules, one of which may have one or more interfaces. The interface of the module may be used to receive or transmit data. For example, the plurality of modules may include a preprocessing module, a fusion module, a mapping module, and the like.

In a possible implementation manner, after acquiring a plurality of road data (which may also be referred to as multi-pass data, where one-pass data is road data acquired by the acquisition device at one time), the server may call the plurality of modules through the interface to perform mapping.

For example, the server may call the preprocessing module to perform preprocessing operations (such as data filtering, etc.) on the road data, and transmit the processed road data to the fusion module through the interface calling the preprocessing module. After receiving the processed road data, the fusion module may perform fusion (e.g., merge the road data of the same element) on the processed road data. The server can call the interface of the fusion module to transmit the fused road data to the mapping module. Therefore, the mapping module can map according to the fused road data.

Specifically, the servitization has the following characteristics:

1-1, transformation process: if Flink supports containerization, then Flink may be used directly; if Flink supports streams, the spark batching part can be applied to Flink.

1-2, expandability: and the expansion flow, the expansion operator and the flow processing frame are unchanged.

1-3, code multiplexing: data distribution, data input/output (input/output).

1-4, delay: the data processing delay from the beginning of the process to the intermediate stage can be in the order of milliseconds.

1-5, fault tolerance: transaction support is provided with a perfect fault-tolerant mechanism (checkpoint), exact once (instance) consistency and pulsar.

1-6, data throughput: with high throughput, high throughput (up to 10 million/sec) provided by the pulsar message queue.

2. And (4) calculating in real time. Real-time computing may refer to a way to turn batch processing out of stream, achieving high throughput and low latency.

For example, the server may implement real-time computing based on Flink or spark streaming. Flink is a framework and distributed processing engine for computing unthrottled data and bounded flow data streams. An unbounded flow refers to an end point that has a start point but not. A bounded flow has a start and an end. spark streaming is a streaming framework that supports scalable, high-throughput, fault-tolerant real-time data stream processing. Specifically, the Flink and spark streaming may refer to the description of the prior art, and are not described in detail.

Specifically, real-time computation has the following characteristics:

2-1, transformation process: a layer of service framework needs to be nested on the algorithmic engineering framework, and the data distribution logic needs to be determined.

2-2, expandability: interfaces and interface logic may be added.

2-3, delay: mainly refers to the delay generated by the calling module, which is about millisecond.

2-4, fault tolerance: if the service is abnormal or interrupted in the processing flow, the whole processing flow is interrupted; the flow of recovering the exception needs to manually initiate a request, restart the execution flow or start the execution flow with a certain request in the middle.

2-5, data throughput: data throughput relies on requesting internal bone access to external storage.

As can be seen from the above, since the updating of the electronic map involves processing of point cloud data and the like, the complexity is high, and the real-time calculation (such as Flink and spark streaming) has no way of being directly applied to the updating process of the high-precision map. In addition, the servitization cannot realize a data distribution process in data processing. In the data processing process, if a certain request is abnormal, there is no way to continue executing the processing flow.

In view of this, the embodiment of the present application provides an updating method for an electronic map, which implements a real-time computing process of the electronic map (such as a high-precision map) based on Flink. In particular, reference may be made to the following description of embodiments. Therefore, the received road data can be efficiently processed in a stream processing mode based on the character of code multiplexing of the Flink, so that the updating efficiency of the electronic map is improved.

Fig. 1 is a system architecture provided in an embodiment of the present application. The system may include one or more acquisition devices and a server. The one or more acquisition devices may be communicatively coupled to a server.

The collection device may be used to collect road data of a road. For example, the acquisition device may be a vehicle terminal, an electronic device, or the like. The vehicle terminal may be provided with means for collecting road data, such as radar equipment, cameras, video cameras, and the like.

The server is not limited in the embodiments of the present disclosure. The server in the embodiments of the present disclosure may be a single server, or may be a server cluster formed by a plurality of servers. In some embodiments, the server cluster may also be a distributed cluster. The present disclosure is also not limited to a specific implementation of the server.

In yet another example, as shown in fig. 1, the system may further include a terminal configured with an electronic map. The terminal can be a vehicle-mounted terminal or an electronic device. The terminal may be an autonomous vehicle or may be a device in an autonomous vehicle, etc.

The embodiment of the present disclosure does not limit the electronic device. The electronic device in the embodiments of the present disclosure may be a tablet computer, a mobile phone, a desktop computer, a laptop computer, a handheld computer, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a cellular phone, a Personal Digital Assistant (PDA), an automatic guided vehicle, and the like, and the specific form of the electronic device is not particularly limited in the embodiments of the present disclosure.

The execution subject of the updating method of the electronic map provided by the disclosure can be an updating device, and the updating device can be the server. For example, the updating device may also be a Central Processing Unit (CPU) of the server, or a control module in the server for updating the electronic map.

The following describes in detail an update method of an electronic map provided in an embodiment of the present disclosure with reference to the accompanying drawings.

As shown in fig. 2, an updating method of an electronic map provided by the embodiment of the present disclosure may include: s201 to S204.

S201, acquiring image data of the target road.

Wherein the target road includes a plurality of elements. For example, the target road may include traffic lights, lane lines, road signs, barriers, and the like. The image data of the target link may include image data of a plurality of elements.

In a possible implementation manner, after receiving the road data collected by the collection device, the server may divide the received road data into multiple types of data according to a resolving process. The multiple types of data may include image data, point cloud data, video data, and the like. Therefore, the server can quickly classify the road data to obtain a plurality of types of road data.

Wherein, the resolving process may include: data consolidation (or ex-senones) and multiple data processing (or data splitting). The data integration may refer to converting the road data of different coordinates into the road data of the same coordinate. The data processing may be to divide the road data into multiple types of data according to the device type, and analyze the multiple types of data to obtain the road data corresponding to each type. The coordinates may refer to the distribution of the road data in the coordinate system configured by the acquisition device. For example, when acquiring the road data, the acquiring device may map the acquired road data into a configured coordinate system, and obtain coordinates corresponding to each piece of data in the road data.

In one example, as shown in FIG. 3, a server may implement a solution flow by calling multiple modules. The plurality of models may include a data integration module (or an extrinsic normalization module) and a plurality of data processing modules. One data module may be used to process one type of road data. For example, the plurality of data processing modules may include a point cloud data processing module, an image data processing module, a video data processing module, and the like. The point cloud data processing module can be used for processing the point cloud data to obtain a plurality of point cloud data. The image data processing module may be configured to process the image data to obtain a plurality of image data. The video data processing module may be configured to process the video data to obtain a plurality of image data,

specifically, after acquiring road data acquired by a plurality of acquisition devices (such as radar devices, cameras, video cameras, and the like), the server may call a data integration module to integrate the road data acquired by the plurality of acquisition devices. For example, the coordinate systems corresponding to the road data collected by different collection devices are different. The data integration module can integrate the road data of different coordinate systems into the same coordinate system. After the server integrates the road data, the road data can be classified according to the equipment types of the acquisition equipment to obtain multiple types of data, and the different types of data are distributed to the corresponding data processing modules to obtain corresponding data processing results. For example, the server may transmit point cloud data in the road data to the point cloud data processing module, and the point cloud data processing module may classify the point cloud data to obtain point cloud data corresponding to each element. For another example, the server may transmit the image data to the image data processing module, and the image data processing module may classify the image data to obtain image data corresponding to each element. For another example, the server may transmit the data processing module to the video data processing module, and the video data processing module may perform image extraction processing on the video data to obtain image data of a plurality of elements.

Further, after the road data is split according to the device type of the acquisition device, the split data of multiple types may be stored.

S202, when it is determined that the scene change is present on the target road, the image data of the target road is input to the plurality of element change determination modules, and a plurality of recognition results are obtained.

The target road presence scene change may include element change of the target road (for example, building change on both sides of the target road, and lane line change from a dotted line to a solid line), element increase (for example, traffic lights, barriers, intersections, etc. are added), and element decrease (for example, barriers, signs, etc. are decreased).

In one example, the server may accurately determine that the target road has the scene change according to the indication information indicating the scene change. For example, the terminal may transmit instruction information for instructing a scene change to the server in response to a trigger operation by the user. Accordingly, the server may receive the indication information from the terminal. The terminal can be a vehicle terminal, a mobile phone and the like configured with an electronic map. The indication information may include a first indicator, which may be used to indicate a scene change. The first indicator may be a number, a character, or a combination of numbers and characters, etc. Of course, the indication information may also include other information, such as an indicator of the road on which the scene change occurred and location information. The location information may refer to location information, such as longitude and latitude, of a target road where a scene change occurs.

In one application scenario, when a user navigates using a terminal equipped with an electronic map, the electronic map displays that a target road has no element (such as a traffic light), and the target road actually has an element. In this way, the terminal may transmit indication information indicating a scene change to the server in response to a trigger operation (such as an upload error) by the user. The server can accurately determine that the target road has the scene change after receiving the indication information for indicating the scene change from the terminal.

In another application scenario, when the vehicle in automatic driving travels using the electronic map, the electronic map displays that there is a barrier in the target road, and the vehicle detects that there is no barrier, the vehicle may actively send instruction information for instructing a scene change to the server. The server can accurately determine that the target road has a scene change after receiving the instruction information for instructing the scene change from the vehicle.

In one possible implementation, the server may be configured with a plurality of element change specification models in advance, and when a scene change is specified for a target road, the server may input a plurality of image data of the target road to each of the plurality of element change specification models to obtain a plurality of recognition results.

Wherein one element change determination model is used to determine whether one element is changed. The input of the element change determination model may be image data of a road, and the output recognition result may be used to indicate whether or not the corresponding element is changed. For example, the recognition result may include a second indicator, which may be used to indicate whether to change. The second indicator may be a number, a character, or a combination of numbers and characters. For example, when the recognition result is Y, it indicates that the element change corresponding to the element change determination model is changed; and if the identification result is N, indicating that the element corresponding to the element change determination model is not changed.

In one example, the server may be configured with a plurality of element change determination models in advance. In this way, when the server specifies that the target road has a scene change, the server can input the image data of the target road to the plurality of element change specifying models to obtain a plurality of recognition results.

For example, the plurality of element change determination models may include a traffic light change determination model, a road sign change determination model, a lane line change determination model, and the like. The traffic light change determination model may be used to determine whether a traffic light of a road is changed, the road sign change determination model may be used to determine whether a road sign is changed, and the lane line change determination model may be used to determine whether a lane line is changed.

It should be noted that, in the embodiment of the present disclosure, the element change determining model may be obtained by training the original image data of the target road according to a preset algorithm. The raw image data may be image data of a target road in an electronic map, or the raw image data may also be used to construct the electronic map. The preset algorithm may be a neural network algorithm, a deep learning algorithm, and the like, and is not limited. In this way, the element change determination model can detect whether or not the image data of the input target road matches the data of the corresponding element in the original image data. If the two elements are consistent, the corresponding elements are not changed; if not, the corresponding element is changed.

S203, according to the plurality of recognition results, the changed elements in the target road are determined.

The changed element of the target road may be one or more of the plurality of elements of the target road.

And S204, updating the electronic map according to the image data of the changed elements in the target road.

In one example, the server may determine image data of the changed element from the image data of the target road after determining the changed element from the plurality of recognition results, and update the electronic map from the image data of the changed element.

For example, if the server determines the traffic light change of the target road according to the traffic light change determination model, the server may determine the position where the traffic light change occurs in the electronic map and the change information of the traffic light corresponding to the position according to the image data of the target road and the data of the target road in the electronic map. The change information may include addition of a new traffic light, reduction of traffic lights, or a change in the model of the traffic light. Therefore, the server can change the data of the traffic lights in the electronic map according to the position information to obtain the updated electronic map.

In the embodiment of the present disclosure, the data of the electronic map may be three-dimensional model data or image data, which is not limited.

For another example, if the server determines a barrier change of a target road based on the barrier change determination model, the server may determine a position where the barrier change occurs in the electronic map and barrier change information corresponding to the position based on the image data of the target road and the data of the target road in the electronic map. The change information may include the addition of a new fence, the reduction of fences, and the change in the type of fence. In this way, the server can change the data of the isolation bar of the position information in the electronic map to obtain the updated electronic map.

For another example, if the server determines a lane change of the target road based on the lane change determination model, the server may determine the type of the lane change and the position information in the electronic map based on the image data of the target road and the data of the target road in the electronic map. In this way, the server can update the electronic map based on the position information and the type of the lane line after the change. The lane line corresponding to the position information in the updated electronic map is the type of the changed lane line.

In still another example, if the instruction information received by the server includes position information of the changed element, the server may determine the position of the changed element in the image data of the target road based on the position information of the changed element after determining the changed element based on the plurality of recognition results. Based on the position, the server may determine image data of the changed elements. Thus, the server can accurately determine the image data of the changed elements and quickly update the electronic map according to the image data of the changed elements.

For example, the indication information is used to indicate that traffic lights are added to certain position information. The server may specify the image data of the changed element in the image data of the target road based on the position information, and thus, the server may update the electronic map based on the image data of the changed element.

Based on the technical solution of fig. 2, in the embodiment of the present disclosure, when it is determined that there is a changed element in the target road, the image data of the target road may be input to the multiple element change determination models to obtain multiple recognition results. Since one recognition result can be used to indicate whether or not one element of the target road is changed, the changed element in the target road can be quickly determined. In this way, the electronic map can be updated based on the image data of the changed elements, and the updating efficiency of the electronic map is improved.

In some embodiments, in S204, when the number of the changed elements of the target road is large, the server may update the electronic map based on the road data in order to avoid updating the electronic map many times. For example, the server may update the data of the target road in the electronic map according to the point cloud data in the road data. In this way, the server can comprehensively update the road data of the electronic map (for example, all the data of a plurality of scenes of the target road in the electronic map are updated), and obtain the electronic map matched with the actual elements of the target road. Meanwhile, the updating times of the electronic map are reduced.

In some embodiments, in order to obtain an electronic map of a timely terminal configuration, as shown in fig. 4, after S204, the method provided in the embodiments of the present disclosure may further include:

s401, updating information is sent to a terminal configured with the electronic map. Accordingly, the terminal receives the update information.

Wherein the update information can be used to update the electronic map. For example, the update information may include data of the changed elements, which may be used for the terminal to update the configured electronic map. The terminal may be an autonomous vehicle or may be a device in an autonomous vehicle (e.g., an in-vehicle terminal, etc.).

S402, the terminal updates the electronic map according to the updating information.

The updating of the electronic map by the terminal may include the terminal actively updating the electronic map or the terminal updating the electronic map in response to a determination operation.

In one example, the terminal may update the configured electronic map according to the data of the changed elements in the update information after receiving the update information.

In yet another example, the terminal may output a message prompting an update of the electronic map after receiving the update information. In response to the determination operation by the user, the terminal may update the configured electronic map according to the data of the changed elements in the update information.

Based on the technical scheme, the terminal can update the configured electronic map in time after receiving the updating information of the electronic map, so that the safety of automatic driving is improved.

In still other embodiments, in S201, the receiving road data of the target road collected by the multiple collection devices may include: and receiving road data transmitted by a plurality of acquisition devices according to a preset transmission protocol.

The preset transmission protocol may be used to specify a data format for the acquisition device to transmit the acquired road data.

In one example, as shown in fig. 5, the data format includes a data format used for receiving road data, a data format used for transmitting road data, and a data format used for transmitting the last road data. The data format used for receiving the road data and the data format used for transmitting the road data may be the same. To facilitate the server determining that all data has been received. The data format used by the last piece of data may be provided with a flag bit (e.g.,/1). The flag bit may be used to identify the piece of data as the last piece of data to be transmitted. Thus, when the server receives data including the flag bit, it can be determined that all the data has been received.

The data format may include a Key-Value pair (Key-Value), a Unique identity (Unique ID), and a Tag (Tag). Key-Value can be referred to the prior art. The Unique ID may be used to identify a piece of data. Tag may be used to represent the sending end of the data (i.e., the upstream operator).

For example, when the collection device transmits a plurality of pieces of road data to the server, each piece of road data may use the data format shown in b of fig. 5, and each piece of data may have a Unique ID. Accordingly, the data format in which the server receives the road data may be the data format shown in a of fig. 5. The last piece of data sent by the acquisition device to the server may use the data format shown in c of fig. 5.

For another example, when a plurality of collection devices respectively transmit a plurality of pieces of road data to the server, the road data transmitted by different collection devices may have different tags.

For another example, after the collection device collects road data of a target road a plurality of times, data of the same road in the road data collected a plurality of times may have a Unique ID.

Further, when the server sends the data of the changed elements to the terminal, the preset transmission protocol may also be used, and specifically, the description of sending the road data to the server by using the collection device may be referred to, which is not described in detail.

Based on the technical scheme, the acquisition equipment can send the acquired road data to the server by using a preset transmission protocol. Thus, normal data transmission between the acquisition device and the server can be ensured. In addition, the server rapidly analyzes the road data after receiving the road data from the acquisition equipment, and the processing efficiency of the road data is improved.

In still other embodiments, as shown in fig. 6, before inputting the road data of the target road into the plurality of element change determination models in S202, the method may further include:

s601, merging the image data of the same element in the image data of the target road to obtain merged image data.

The same element may mean an element having the same positional information.

In one example, the server may merge the road data by invoking multiple modules, as shown in FIG. 7. For example, the plurality of modules may include a mapping module and a merging module. The mapping module may be configured to divide the road data of the target road into data of a plurality of elements. For example, each element in the target road has corresponding coordinate data in the same coordinate system. The mapping module may divide each piece of road data into data of a plurality of elements according to the coordinate data of the elements. The merging module may be configured to merge data of the same element in the plurality of pieces of road data. For example, the merging model may merge data of elements having the same Unique ID from the Unique ID of the elements.

Specifically, after receiving the plurality of pieces of road data, the server may invoke the mapping module to process each piece of road data, respectively, to obtain data of a plurality of elements corresponding to each piece of road data. The server may invoke a merging model to merge the data of the plurality of elements of each of the plurality of pieces of road data, so as to obtain merged road data.

In another example, in order to improve the efficiency of data processing, the server may also divide the road data in an asynchronous 1/O manner when receiving the road data collected by the multiple collection devices, so as to obtain multiple types of data corresponding to the road data. For example, the server may process the road data by a plurality of modules and distribute the data to the plurality of modules in an asynchronous input/output (I/O) manner.

For example, as shown in fig. 8, the server may synchronously send a plurality of pieces of road data to the mapping module, and after receiving the plurality of pieces of road data, the mapping module may synchronously process the plurality of pieces of road data to obtain respective corresponding processing results. For example, the plurality of pieces of road data may include road data 1, road data 2, road data 3, and road data 4. The server can synchronously input the road data 1-4 into the mapping module to respectively obtain the processing results corresponding to the road data. For example, the processing result 1 corresponding to the road data 1, the processing result 2 corresponding to the road data 2, the processing result 3 corresponding to the road data 3, and the processing result 4 corresponding to the road data 4 are shown.

As can be seen from fig. 8, compared to the synchronous I/0, the asynchronous I/O method can reduce the latency of data processing and improve the processing efficiency. In the embodiment of the disclosure, the server processes the road data in an asynchronous I/O mode, so that the processing efficiency of the road data can be improved. Furthermore, the updating efficiency of the electronic map can be improved.

It should be noted that, in the embodiment of the present disclosure, the server may be provided with a message queue. After the collection device collects the road data, the road data can be written into a message queue. In response to the operation of writing the road data into the message queue, the server can be triggered to execute the resolving process and the drawing process.

Further, the server may also be provided with a plurality of interfaces (or called callback interfaces). The interface may be used to receive status information (e.g., processing success or processing failure) of the module's processing of the road data. That is, after the module finishes processing the road data, the data processing result can be returned through the interface. For example, after the plurality of element recognition determination models obtain the recognition results, the recognition results may be input through the interface individually.

S202 may be specifically implemented by S602.

S602, the merged image data is input to the plurality of element change specifying models, and a plurality of recognition results are obtained.

For example, as shown in fig. 7, after acquiring the merged image data, the server may input the merged image data to the plurality of element change specification models in synchronization to obtain a plurality of recognition results.

Based on the technical scheme, the road data of the same element in the road data of the target road are merged. In this way, the number of image data to be detected can be reduced, providing processing efficiency.

In the technical scheme of the disclosure, the collection, storage, use, processing, transmission, provision, disclosure and other processing of the personal information of the related user are all in accordance with the regulations of related laws and regulations and do not violate the good customs of the public order.

The foregoing describes the solution provided by embodiments of the present disclosure, primarily from the perspective of a computer device. It will be appreciated that the computer device, in order to implement the above-described functions, comprises corresponding hardware structures and/or software modules for performing the respective functions. Those of skill in the art will readily appreciate that the exemplary form recognition method steps described in connection with the embodiments disclosed herein may be implemented as hardware or a combination of hardware and computer software. Whether a function is performed as hardware or computer software drives hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

The method for determining the information point according to the embodiments of the present disclosure may be implemented by dividing functional modules or functional units according to the above method examples, for example, each functional module or functional unit may be divided according to each function, or two or more functions may be integrated into one processing module. The integrated module may be implemented in a form of hardware, or may be implemented in a form of a software functional module or a functional unit. The division of the modules or units in the embodiments of the present disclosure is schematic, and is only a logic function division, and there may be another division manner in actual implementation.

Fig. 9 is a schematic structural diagram of an updating apparatus of an electronic map according to an embodiment of the present disclosure. The updating device of the electronic map can comprise: an acquisition unit 901, a processing unit 902 and a determination unit 903.

An acquisition unit 901 for acquiring image data of a target road including a plurality of elements.

When specifying that there is a scene change on the target road, the processing section 902 inputs the image data of the target road to the plurality of element change specifying models to obtain a plurality of recognition results. Wherein, one element change determining model is used for determining whether one element is changed, and the corresponding recognition result of the element change determining model is used for indicating whether the corresponding element in the target road is changed.

A determination unit 903 for determining a modified element in the target road based on the plurality of recognition results.

The processing unit 902 is further configured to update the electronic map according to the image data of the changed elements.

Optionally, the obtaining unit 901 is specifically configured to: receiving road data of the target road collected by a plurality of collecting devices; the road data is divided into a plurality of types of data according to device types of the plurality of acquisition devices, and the plurality of types of data include image data.

Optionally, the obtaining unit 901 is specifically configured to: before the image data of the target road is input into the plurality of element change determination models, the image data of the same element in the image data of the target road are merged to obtain merged image data.

Optionally, the obtaining unit 901 is specifically configured to receive the road data transmitted by the multiple acquiring devices according to a preset transmission protocol, where the preset transmission protocol is used to specify a data format of the road data transmitted and acquired by the acquiring devices.

The data format used for receiving the road data is consistent with the data format used for sending the road data, and the data format used for sending the last road data comprises a flag bit which is used for indicating that the road data is the last data to be sent.

Optionally, the determining unit 903 is specifically configured to: receiving indication information, wherein the indication information is used for indicating that the target road has element change; and determining the target road existence element change according to the indication information.

Optionally, the apparatus further comprises a sending unit 904. A sending unit 904, configured to send first update information to a terminal configured with an electronic map, where the first update information is used to instruct to update the electronic map configured by the terminal.

Optionally, the processing unit 902 is specifically configured to divide the road data acquired by the multiple acquisition devices in an asynchronous I/O manner to obtain multiple types of data corresponding to the road data.

The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.

FIG. 10 shows a schematic block diagram of an example electronic device 1000 that can be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 10, the apparatus 1000 includes a computing unit 1001 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 1002 or a computer program loaded from a storage unit 1008 into a Random Access Memory (RAM) 1003. In the RAM 1003, various programs and data necessary for the operation of the device 1000 can be stored. The calculation unit 1001, the ROM1002, and the RAM 1003 are connected to each other by a bus 1004. An input/output (I/O) interface 1005 is also connected to bus 1004.

A number of components in device 1000 are connected to I/O interface 1005, including: an input unit 1006 such as a keyboard, a mouse, and the like; an output unit 1007 such as various types of displays, speakers, and the like; a storage unit 1008 such as a magnetic disk, an optical disk, or the like; and a communication unit 1009 such as a network card, a modem, a wireless communication transceiver, or the like. The communication unit 1009 allows the device 1000 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.

Computing unit 1001 may be a variety of general and/or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. Computing unit 1001 performs the various methods and examples described above, such as method XXX. For example, in some embodiments, method XXX may be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 1008. In some embodiments, part or all of a computer program may be loaded onto and/or installed onto device 1000 via ROM1002 and/or communications unit 1009. When the computer program is loaded into RAM 1003 and executed by computing unit 1001, one or more steps of method XXX described above may be performed. Alternatively, in other embodiments, computing unit 1001 may be configured to perform method XXX in any other suitable manner (e.g., by way of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

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

To provide for interaction with a user, the systems and techniques described here 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 a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user may provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, 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 may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server with a combined blockchain.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solutions of the present disclosure can be achieved.

The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made, depending on design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the protection scope of the present disclosure.

Claims

1. An updating method of an electronic map comprises the following steps:

acquiring image data of a target road, wherein the target road comprises a plurality of elements;

in the case that the scene change of the target road is determined, inputting the image data of the target road into a plurality of element change determination models to obtain a plurality of identification results, wherein one element change determination model is used for determining whether one element is changed, and the identification result corresponding to the element change determination model is used for indicating whether the corresponding element in the target road is changed;

determining a changed element in the target road according to the plurality of recognition results, wherein the plurality of elements comprise the changed element;

and updating the electronic map according to the image data of the changed elements.

2. The method of claim 1, wherein said obtaining image data of a target roadway comprises:

receiving road data of the target road collected by a plurality of collecting devices;

dividing the road data into a plurality of types of data according to device types of the plurality of acquisition devices, wherein the plurality of types of data comprise the image data.

3. The method according to claim 1 or 2, wherein before inputting the image data of the target road into a plurality of element change determination models, the method further comprises:

and merging the image data of the same element in the image data of the target road to obtain merged image data.

4. The method of claim 2, wherein the receiving road data of the target road collected from a plurality of collection devices comprises:

receiving road data transmitted by the plurality of acquisition devices according to a preset transmission protocol, wherein the preset transmission protocol is used for stipulating a data format of the road data transmitted and acquired by the acquisition devices;

the data format comprises a data format used for receiving road data, a data format used for sending the road data and a data format used for sending the last road data, wherein the data format used for receiving the road data is consistent with the data format used for sending the road data, the data format used for sending the last road data comprises a flag bit, and the flag bit is used for indicating that the road data is the last data to be sent.

5. The method of any of claims 1-4, wherein the determining the target road presence element change comprises:

receiving indication information, wherein the indication information is used for indicating that the target road has element change;

and determining that the target road has scene change according to the indication information.

6. The method of any of claims 1-5, wherein after updating the electronic map, the method further comprises:

and sending update information to a terminal configured with the electronic map, wherein the update information is used for indicating to update the electronic map configured by the terminal.

7. The method of claim 2, wherein the partitioning the road data into a plurality of types of data comprises:

and dividing the road data acquired by the plurality of acquisition devices by adopting an asynchronous input/output (I/O) mode to obtain a plurality of types of data corresponding to the road data.

8. An updating device of an electronic map comprises:

an acquisition unit configured to acquire image data of a target road, the target road including a plurality of elements;

a processing unit, configured to, when it is determined that there is a scene change in the target road, input image data of the target road into a plurality of element change determination models to obtain a plurality of recognition results, wherein one element change determination model is used to determine whether or not an element is changed, and the recognition result corresponding to the element change determination model is used to indicate whether or not a corresponding element in the target road is changed;

a determination unit configured to determine a changed element in the target road according to the plurality of recognition results, the plurality of elements including the changed element;

and the processing unit is further used for updating the electronic map according to the image data of the changed elements.

9. The apparatus according to claim 8, wherein the obtaining unit is specifically configured to:

10. The apparatus according to claim 8 or 9, wherein the obtaining unit is specifically configured to:

and merging the image data of the same element in the image data of the target road to obtain merged image data before inputting the image data of the target road into a plurality of element change determination models.

11. The apparatus according to claim 9, wherein the obtaining unit is specifically configured to:

12. The apparatus according to any one of claims 8 to 11, wherein the determining unit is specifically configured to:

and determining the change of the target road existence element according to the indication information.

13. The apparatus of any one of claims 8-12, wherein the apparatus further comprises:

and the sending unit is used for sending update information to a terminal configured with the electronic map, and the update information is used for indicating the update of the electronic map configured by the terminal.

14. The apparatus according to claim 9, wherein the processing unit is specifically configured to:

and dividing the road data acquired by the plurality of acquisition devices in an asynchronous I/O mode to obtain a plurality of types corresponding to the road data.

15. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein, the first and the second end of the pipe are connected with each other,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.

16. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-7.

17. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1-7.

18. An autonomous vehicle comprising the electronic device of claim 15.