A map data updating method, device, apparatus, and storage medium

Abstract

The disclosure provides a map data updating method and device, equipment and storage medium, relates to the technical field of data processing, and particularly relates to the technical field of intelligent transportation. The specific implementation scheme is: a road element in a road image is identified, first road data of the road element in a target road region to which the road image is directed is obtained; second road data of the road element in the target road region in existing map data is obtained; the geographical position of the road element in the second road data is used to adjust the geographical position of the road element in the first road data; based on the first road data after the geographical position is adjusted and the second road data, change road data is determined, wherein the change road data indicates a sub-region in which a road condition in the target road region changes; and based on the change road data, the map data is updated. The scheme provided in the embodiment of the disclosure can improve the accuracy of map data updating.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, and more particularly to the field of intelligent transportation technology. Background Technology

[0002] With the development of technology, electronic maps have greatly facilitated people's travel. Electronic map data contains detailed road information for road areas. While driving, users can obtain detailed road information about their current driving environment through electronic maps. Furthermore, electronic map data is also fundamental to the safe driving of autonomous vehicles; therefore, ensuring the timeliness of map data is crucial. In view of the above, it is necessary to update existing map data. Summary of the Invention

[0003] This disclosure provides a map data updating method, apparatus, device, and storage medium.

[0004] According to one aspect of this disclosure, a map data updating method is provided, comprising:

[0005] Identify road elements in a road image to obtain first road data for the road elements within the target road area represented by the road image;

[0006] Obtain second road data for road elements within the target road area from existing map data;

[0007] Use the geographical location of the road elements in the second road data to adjust the geographical location of the road elements in the first road data;

[0008] Based on the first road data and the second road data after adjusting the geographical location, changed road data is determined, wherein the changed road data indicates the sub-regions within the target road area where the road conditions have changed;

[0009] The existing map data is updated based on the changed road data.

[0010] According to another aspect of this disclosure, a data updating apparatus is provided, comprising:

[0011] An element recognition module is used to identify road elements in a road image and obtain first road data of the road elements within the target road area targeted by the road image.

[0012] The first data acquisition module is used to acquire the second road data of road elements within the target road area in the existing map data;

[0013] The location adjustment module is used to adjust the geographical location of road elements in the first road data using the geographical location of road elements in the second road data;

[0014] The data determination module is used to determine changed road data based on the first road data after adjusting the geographical location and the second road data, wherein the changed road data indicates the sub-regions within the target road area where the road conditions have changed;

[0015] The data update module is used to update the map data based on the changed road data.

[0016] According to another aspect of this disclosure, an electronic device is provided, comprising:

[0017] At least one processor; and

[0018] A memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the map data update method described above.

[0020] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the computer to perform the above-described map data update method.

[0021] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the above-described map data update method.

[0022] The solution provided by the embodiments of this disclosure improves the accuracy of map data updates.

[0023] It should be understood that the description in this section is not intended to identify key or essential elements of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other elements of this disclosure will become readily apparent from the following description. Attached Figure Description

[0024] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0025] Figure 1 A flowchart illustrating the first map data update method provided in this embodiment of the disclosure;

[0026] Figure 2 A flowchart illustrating the second map data update method provided in this embodiment of the disclosure;

[0027] Figure 3a A flowchart illustrating the third map data update method provided in this embodiment of the disclosure;

[0028] Figure 3b A road image provided for an embodiment of this disclosure;

[0029] Figure 4 A flowchart illustrating the fourth map data update method provided in this embodiment of the disclosure;

[0030] Figure 5 A flowchart illustrating the fifth map data update method provided in this embodiment of the disclosure;

[0031] Figure 6 A flowchart illustrating the sixth map data update method provided in this embodiment of the disclosure;

[0032] Figure 7 This is a schematic diagram of the structure of a map data updating device provided in an embodiment of the present disclosure;

[0033] Figure 8 This is a block diagram of an electronic device used to implement the map data update method of the embodiments of this disclosure. Detailed Implementation

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

[0035] When updating map data, road images are typically captured by specialized road image acquisition equipment. These images are then integrated to obtain a complete road image reflecting the overall road conditions. This complete road image is then matched with existing map data, and the existing map data is updated based on the matching results. This process is costly and inefficient due to the need for specialized road image acquisition equipment, and the integration of multiple road images is complex and time-consuming. Therefore, this disclosure provides a map data updating method.

[0036] Before describing the map data update method provided in the embodiments of this disclosure, the application scenarios of the embodiments of this disclosure will first be described.

[0037] The application scenario of this disclosure is: updating existing map data. The aforementioned existing map data can be high-precision map data for autonomous vehicles or navigation map data for users.

[0038] High-precision map data, compared to navigation map data, is accurate to the centimeter level and contains more dimensions of road information. When applied to autonomous driving scenarios, high-precision map data is fundamental to the safe operation of autonomous vehicles; therefore, ensuring the freshness of high-precision map data is crucial.

[0039] Next, the implementing entity of the embodiments of this disclosure will be described.

[0040] The execution subject of this embodiment is an electronic device with map data update function, such as a server.

[0041] See Figure 1 , Figure 1 This is a flowchart illustrating the first map data update method provided in this embodiment of the present disclosure. The method includes the following steps S101-S105.

[0042] Step S101: Identify road elements in the road image to obtain the first road data of the road elements within the target road area of ​​the road image.

[0043] Road images can be acquired by road image acquisition devices. These devices can be specialized road image acquisition equipment or image acquisition devices mounted on vehicles, drones, or other transportation vehicles. Image acquisition devices mounted on vehicles, drones, or other transportation vehicles can also be called crowdsourced devices. Compared to specialized road image acquisition equipment, crowdsourced devices are less expensive, and using crowdsourced devices to acquire road images can reduce image acquisition costs.

[0044] Taking a road image acquisition device operating in a vehicle as an example, while the vehicle is in motion, the road image acquisition device can continuously acquire road images of the road area, and then send the acquired road images to electronic devices via a network.

[0045] Road elements represent road signs that appear on a road. For example, road elements may include lane dividers, edge lines, stop lines, signs, medians, road signs, lampposts, guardrails, and shoulders.

[0046] The aforementioned first road data may include data such as the element type and location information of road elements within the target road area of ​​the road image.

[0047] In one implementation, a road image can be input into a pre-trained road element recognition model to obtain the element type of the road element output by the road element recognition model. Based on the preset mapping relationship between the image coordinate system and the GIS (Geographic Information System) coordinate system, the mapping elements of each road element in the road image under the GIS coordinate system are determined. The position of each mapping element under the GIS coordinate system is the geographical location of each road element in the road image. The obtained element type and geographical location are determined as the first road data.

[0048] The road element recognition model described above is used to identify road elements in road images and obtain road data containing road elements in the road images.

[0049] Since road images are images captured for a target road area, the road data of road elements in the road image can reflect the actual road conditions of the target road area. The road data of road elements can also be called the image semantic features of the road image, and when the road data is represented by vector data, the road data of the aforementioned road elements can also be called a vector semantic map.

[0050] Step S102: Obtain the second road data of road elements within the target road area from the existing map data.

[0051] In one implementation, the geographical location range of the target road area is obtained, and based on the geographical location range, road data of road elements within the aforementioned geographical location range in existing map data is obtained as second road data.

[0052] The geographical location range of the target road area can be calculated based on the geographical location of the road elements in the first road data.

[0053] The aforementioned existing map data can be high-precision map data for autonomous vehicles or navigation map data for users.

[0054] The existing map data contains the location range of each road area and the road data of the road elements within each road area. Based on the correspondence between the location range and the road data contained in the existing map data, an index relationship corresponding to the map data can be established in advance. The index relationship includes the correspondence between the index value and the road data of the road elements in the map data. In view of this, the geographical location range of the target road area can be converted into the target index value. From the pre-built index relationship, the road data corresponding to the target index value can be determined as the second road data.

[0055] Step S103: Use the geographical location of the road elements in the second road data to adjust the geographical location of the road elements in the first road data.

[0056] Because of errors in the image acquisition equipment, the geographical locations of road elements in the first road data corresponding to the obtained road image are inaccurate. Since map data requires high accuracy, it is necessary to adjust the geographical locations of road elements in the first road data.

[0057] Furthermore, since the second road data is road data from existing map data, and the accuracy of existing map data is relatively high compared to the accuracy of the first road data, the geographical location of road elements in the second road data can be accurately adjusted.

[0058] For adjustments to the geographic location of road elements in the first road data, please refer to the following sections. Figure 2 The embodiments shown are not described in detail here.

[0059] Step S104: Based on the first road data and the second road data after adjusting the geographical location, determine the changed road data.

[0060] The aforementioned road change data indicates sub-regions within the target road area where road conditions have changed.

[0061] For ease of explanation, the "first road data after position adjustment" will be referred to as "third road data" in the following content.

[0062] When there is a difference between the third road data and the second road data, it means that the current road conditions in the target road area have changed compared to the historical road conditions, and the existing map data cannot accurately reflect the current road conditions. In this case, it is necessary to determine the road data of the sub-areas in the target road area where the road conditions have changed, i.e., the changed road data, and update the existing map data based on the changed roads.

[0063] In one implementation, it is determined whether there is any inconsistency between the third road data and the second road data in terms of element type, number of elements of the same element type, or geographical location of road elements of the same element type. If so, it indicates that there is a sub-region within the target road area where the road conditions have changed, and the road data of the road elements in the third road data that differ from the second road data are identified as changed road data.

[0064] Road data for road elements that differ may originate from either the third or second road data set. The following explanation addresses three scenarios:

[0065] In the first case, if the road data of road element Q1 exists in the third road data but not in the second road data, then the road data of road element Q1 is variable road data.

[0066] In the second scenario, if the road data for road element Q2 exists in the second road data but not in the third road data, then the road data for road element Q2 is variable road data.

[0067] In the third scenario, the road data of the third road data changes from the road data of the same type of road element Q3 in the second road data. In this case, the road data of the road element Q3 that has changed is the changed road data.

[0068] Step S105: Update map data based on changed road data.

[0069] Since the changed road data may be from the third road data or the second road data, the way to update the map data is also different. The following three situations will be explained.

[0070] In the first scenario, if the road data of road element Q1 exists in the third road data but not in the second road data, then the road data of road element Q1 is the road data of the first road element that has differences, i.e., it is the variable road data.

[0071] This situation indicates that the current road conditions have added road element Q1 compared to the historical road conditions. Therefore, when updating existing map data, road data with the aforementioned road element Q1 can be added to the existing map data.

[0072] In the second scenario, if the second road data contains road data of a second road element that is not present in the third road data, then the road data of the second road element is the road data of the road element that has differed, which is the changed road data.

[0073] This situation indicates that the current road conditions have reduced road element Q2 compared to the historical road conditions. Therefore, when updating existing map data, the road data containing the aforementioned road element Q2 can be deleted from the existing map data.

[0074] In the third scenario, the third road data contains the same road elements as the second road data, but the road data of the third road element in the third road data has changed compared to the road data of the third road element in the second road data. In this case, the road data of the third road element in the third road data is the road data of the road element that has changed, i.e., the changed road data.

[0075] This situation indicates that the current road conditions have changed compared to the historical road conditions for road element Q3. Therefore, when updating high-precision map data, the road data for road element Q3 in the existing map data can be replaced with the road data for road element Q3 in the second road data.

[0076] As can be seen from the above, when updating data using the solution provided in this embodiment, since the geographical location of road elements in the first road data corresponding to the road image has errors, and the second road data is road data in existing map data, the accuracy of the existing map data is relatively high compared to the accuracy of the first road data. Therefore, when adjusting the geographical location of road elements in the first road data, the geographical location of road elements in the second road data is used, thereby making the accuracy of the adjusted geographical location higher than the accuracy of the geographical location before adjustment. Therefore, based on the first road data and the second road data after adjusting the geographical location, the changed road data can be accurately determined, thereby improving the accuracy of updating map data.

[0077] Furthermore, in this embodiment, multiple road images are not integrated to obtain a road image reflecting the complete road area. Integrating road images would be extremely time-consuming, taking approximately one week, and to ensure the freshness of map data, it would require at least daily updates. Therefore, since this embodiment does not require integrating road images to obtain a road image reflecting the complete road area, it updates the map data using each road image individually. Furthermore, it adjusts the corresponding road data for each road image using existing map data, thereby improving the efficiency of map data updates while maintaining accuracy.

[0078] The foregoing Figure 1 In the illustrated embodiment, adjusting the geographical location of road elements in the first road data in step S103 can be done as follows: Figure 2 The implementation method for calculating the offset component in the illustrated embodiment adjusts the geographical location; therefore, see [link to relevant documentation]. Figure 2 , Figure 2 This is a flowchart illustrating the second map data update method provided in this disclosure embodiment, which is consistent with the foregoing Figure 1 Compared to the illustrated embodiments, the aforementioned Figure 1 Step S103 in the illustrated embodiment can be performed as follows: Figure 2 Steps S203-S205 of the illustrated embodiment are implemented.

[0079] Specifically, Figure 2 The illustrated embodiment includes the following steps S201-S207.

[0080] Step S201: Identify road elements in the road image to obtain the first road data of the road elements within the target road area of ​​the road image.

[0081] Step S202: Obtain the second road data of road elements within the target road area from the existing map data.

[0082] The steps S201-S202 described above are respectively related to the aforementioned Figure 1 Steps S101-S102 in the illustrated embodiment are the same and will not be described again here.

[0083] Step S203: Calculate the first location difference value between the geographical locations of road elements of the same type in the first road data and the second road data.

[0084] In one implementation, the distance between the geographical locations of road elements of the same type in the first road data and the second road data can be calculated as a first location difference value.

[0085] Step S204: If there is a position difference value within a preset error range in the calculated first position difference value, determine the target offset component of the geographical location of the road element in the first road data in each preset offset direction according to the geographical location of the target type road element in the first road data and the second road data.

[0086] The target type mentioned above refers to the type of road element corresponding to the first position difference value within the preset error range. For example, if there are road elements corresponding to the first position difference value within the preset error range, including road element 1, road element 2, and road element 3, where road element 1 is of type lane line, road element 2 is of type stop line, and road element 3 is of type street light, the target type can be one of the types of road elements mentioned above, such as lane line.

[0087] When the first position difference value is within the preset error range, it can be assumed that the geographical location of the road element corresponding to the first position difference value in the first road data and the geographical location of the road element in the second road data should coincide. However, due to the error in the road image acquisition device when acquiring road images, the geographical location of the road element in the first road data is deviated. Therefore, it is necessary to correct the geographical location of the road element in the first road data.

[0088] In one implementation, when calculating the target offset component, the offset distance and offset direction of the first geographical location of the road element of the target type relative to the second geographical location in each preset offset direction can be calculated in parallel, and these can be used as the target offset component. Here, the first geographical location refers to the geographical location of the road element of the target type in the first road data, and the second geographical location refers to the geographical location of the road element of the target type in the second road data.

[0089] Other implementations for calculating the target offset components can be found in the following sections. Figure 3a The embodiments shown are not described in detail here.

[0090] Step S205: Based on each target offset component calculated, adjust the geographical location of the road elements in the first road data.

[0091] Since the target offset component is the offset component in each preset offset direction, the geographical location can be adjusted from each preset offset direction based on the offset component in each preset offset direction, thereby achieving precise adjustment of the geographical location. Therefore, based on each target offset component calculated, the accuracy of the adjusted geographical location can be high.

[0092] In one implementation, when the target offset includes offset distance and offset direction, the location of the first geographical location can be taken as the starting point, and the starting point can be moved along the offset direction by the offset distance to obtain the offset point. The location of the offset point is then determined as the geographical location of the road element in the adjusted first road data.

[0093] Step S206: Based on the first road data and the second road data after adjusting the geographical location, determine the changed road data.

[0094] The aforementioned changed road data indicates sub-regions within the target road area where road conditions have changed.

[0095] Step S207: Update map data based on changed road data.

[0096] The steps S206-S207 described above are respectively related to the aforementioned Figure 1 Steps S104-S105 in the illustrated embodiment are the same and will not be described again here.

[0097] As can be seen from the above, when the first position difference value is within the preset error range, it indicates that the geographical location of the road element in the first road data has deviated. In this case, the offset component of the geographical location of the road element in the first road data in each preset offset direction is calculated, and based on the offset component in each preset offset direction, the geographical location can be adjusted from each preset offset direction, thereby achieving precise adjustment of the geographical location. Therefore, based on each target offset component calculated, the accuracy of the adjusted geographical location can be improved.

[0098] The foregoing Figure 2 In the illustrated embodiment, the target offset component of the geographical location of the road element in the first road data in each preset offset direction in step S204 can be calculated serially, in addition to the parallel calculation of the offset distance and offset direction of the first geographical location of the target type road element relative to the second geographical location in each preset offset direction in some implementations. The preset offset direction includes the first direction and the second direction.

[0099] In view of the above, see Figure 3a , Figure 3a This is a flowchart illustrating the third map data update method provided in this embodiment of the disclosure, which is consistent with the foregoing Figure 2 Compared to the illustrated embodiments, the aforementioned Figure 2 Step S204 in the illustrated embodiment can be performed as follows: Figure 3a Steps S304-S307 of the illustrated embodiment are implemented.

[0100] Specifically, Figure 3a The illustrated embodiment includes the following steps S301-S310.

[0101] Step S301: Identify road elements in the road image to obtain the first road data of the road elements within the target road area of ​​the road image.

[0102] Step S302: Obtain the second road data of road elements within the target road area from the existing map data.

[0103] Step S303: Calculate the first location difference value between the geographical locations of road elements of the same type in the first road data and the second road data.

[0104] The steps S301-S303 described above are respectively related to the aforementioned Figure 2 Steps S201-S203 of the illustrated embodiment are the same and will not be described again here.

[0105] Step S304: If there is a position difference value within a preset error range in the calculated first position difference value, calculate the first translation vector and the first rotation vector of the geographical location of the road element of the target type in the first road data in the first direction according to the geographical location of the road element of the target type in the first road data and the second road data.

[0106] The above target type is a type of road element corresponding to the first position difference value within the preset error range.

[0107] The first direction mentioned above can be the transverse direction of the road, which refers to the direction perpendicular to the road direction on the horizontal plane within the target road area.

[0108] by Figure 3b For example, Figure 3b A road image is shown, in which the black solid lines represent lane lines. The road direction corresponding to the target road area in the road image is the direction of the line "y". The direction perpendicular to the road direction on the horizontal plane is the direction of the line "x". That is, the first direction is the direction of the line "x".

[0109] The first rotation vector contains the direction and angle of rotation of the geographic location in the first road data around a preset center. The first translation vector contains the offset distance and direction of offset of the geographic location in the first road data.

[0110] Specifically, the first translation vector and the first rotation vector can be calculated using the following two methods.

[0111] In the first embodiment, when calculating the first rotation vector, the offset angle and offset direction between the geographical location of the target type road element in the first road data and the geographical location of the target type road element in the second road data can be calculated, and the offset angle and offset direction can be determined as the first rotation vector of the geographical location of the road element in the first road data in the first direction.

[0112] When calculating the first translation vector, the geographical location of the road element of the target type in the first road data, the first component position in the first direction, and the geographical location of the road element of the target type in the second road data, the second component position in the first direction, are calculated. The offset distance and offset direction of the first component position relative to the second component position are calculated, and the offset distance and offset direction are determined as the first translation vector of the geographical location of the road element in the first road data in the first direction.

[0113] In the second implementation method, the first translation vector T can be calculated according to the following expression. l and the first rotation vector R l :

[0114]

[0115] Where P1 represents the geographical location of the target type road element in the first road data, P CS R represents the geographic location of road elements of the target type in the second road data. l T represents the first rotation vector in the first direction representing the geographical location of a road element in the first road data. l This represents the first translation vector in the first direction, indicating the geographical location of the road element in the first road data. ||()|| indicates calculating the absolute value of the value within the parentheses. This indicates that T is the minimum value on the right side of the equation. l The values ​​of R1.

[0116] Step S305: Based on the first translation vector and the first rotation vector, adjust the geographical location of the target type road element in the first road data to obtain the adjusted position.

[0117] In one embodiment, when the first rotation vector includes the rotation direction and rotation angle of the geographical location in the first road data around the preset center, and the first translation vector includes the offset distance and offset direction of the geographical location in the first road data, the geographical location of the target type road element in the first road data can be taken as the starting point, the starting point can be rotated along the rotation direction by the rotation angle, and the offset distance can be moved along the offset direction in the first direction, and the position of the point obtained after the offset can be determined as the adjustment position.

[0118] Step S306: Based on the adjusted position of the road element of the target type in the first road data and the geographical location of the road element of the target type in the second road data, calculate the second translation vector and the second rotation vector of the adjusted position of the road element in the first road data in the second direction.

[0119] The second direction mentioned above can be a direction perpendicular to the first direction on a horizontal plane. For example, when the first direction is the transverse direction of the road, the second direction can be the road direction.

[0120] Specifically, the second translation vector and the second rotation vector can be calculated using the following two methods.

[0121] In the first embodiment, when calculating the second rotation vector, the offset angle and offset direction between the adjusted position of the target type road element in the first road data and the geographical location of the target type road element in the second road data can be calculated, and the offset angle and offset direction can be determined as the second rotation vector of the geographical location of the road element in the first road data in the second direction.

[0122] When calculating the second translation vector, the third component position of the adjusted position of the road element of the target type in the first road data in the second direction and the fourth component position of the geographical location of the road element of the target type in the second road data in the second direction can be calculated. The offset distance and offset direction of the third component position relative to the fourth component position are calculated, and the above offset distance and offset direction are determined as the second translation vector of the adjusted position of the road element in the first road data in the second direction.

[0123] In the second implementation, the second translation vector T2 and the second rotation vector R2 can be calculated according to the following expressions:

[0124]

[0125] Where P2 represents the adjusted position of the road element of the target type in the first road data, P CS R2 represents the geographic location of the target type road element in the second road data, R2 represents the second rotation vector of the adjusted position of the road element in the first road data in the second direction, and T2 represents the second translation vector of the adjusted position of the road element in the first road data in the second direction.

[0126] Step S307: The calculated first translation vector, second translation vector, first rotation vector, and second rotation vector are determined as the target offset components of the geographical location of the road element in the first road data in each preset offset direction.

[0127] Step S308: Based on each target offset component calculated, adjust the geographical location of the road elements in the first road data.

[0128] Step S309: Based on the first road data and the second road data after adjusting the geographical location, determine the changed road data.

[0129] The aforementioned changed road data indicates sub-regions within the target road area where road conditions have changed.

[0130] Step S310: Update map data based on changed road data.

[0131] The steps S308-S310 described above are respectively related to the aforementioned Figure 2 Steps S205-S207 of the illustrated embodiment are the same and will not be described again here.

[0132] Since the first rotation vector and first translation vector of the geographical location in the first road data in the first direction are calculated first, and then the geographical location in the first road data is adjusted using the calculated first rotation vector and first translation vector to obtain the adjusted position, and finally the second rotation vector and second translation vector of the adjusted position in the first road data in the second direction are calculated, it can be seen that when calculating the second rotation vector and second translation vector in the second direction, the already adjusted position is used for calculation. The accuracy of the above-mentioned adjusted position has been improved. Based on the highly accurate adjusted position, the second rotation vector and second translation vector can be accurately calculated, thereby making the accuracy of the obtained target offset component higher.

[0133] In calculating the target offset component of the geographic location contained in the first road data corresponding to the road image, the accuracy of the calculated target offset component is low due to the presence of noise. Therefore, the calculated target offset component can be corrected.

[0134] In view of the above, in one embodiment of this disclosure, see [link to relevant documentation]. Figure 4 It provides a flowchart of the fourth data update method, compared to Figure 2 The illustrated embodiment, in Figure 2 Before step S205 of the illustrated embodiment, the calculated target offset component can also be corrected.

[0135] Specifically, Figure 4 The illustrated embodiment includes the following steps S401-S409.

[0136] Step S401: Identify road elements in the road image to obtain the first road data of the road elements within the target road area of ​​the road image.

[0137] Step S402: Obtain the second road data of road elements within the target road area from the existing map data.

[0138] Step S403: Calculate the first location difference value between the geographical locations of road elements of the same type in the first road data and the second road data.

[0139] Step S404: If there is a position difference value within a preset error range in the calculated first position difference value, determine the target offset component of the geographical location of the road element in the first road data in each preset offset direction based on the geographical location of the target type road element in the first road data and the second road data.

[0140] The above target type is a type of road element corresponding to the location difference value within the preset error range.

[0141] The steps S401-S404 described above are respectively related to the aforementioned Figure 2 Steps S201-S204 of the illustrated embodiment are the same and will not be described again here.

[0142] Step S405: Obtain the reference offset component of the geographical location of the road element in the reference image in each preset offset direction.

[0143] The road area corresponding to the aforementioned reference image is adjacent to the target road area. The aforementioned reference image can be multiple road images, such as 5 images, 10 images, etc.

[0144] The electronic device can pre-store the correspondence between each acquired road image and the offset component. Based on this, in one embodiment, a reference image of the road image can be determined from each acquired road image contained in the above correspondence, and the offset component corresponding to the reference image can be determined as the reference offset component.

[0145] Since the image acquisition device can acquire road images while the vehicle is in motion, the acquired road images have acquisition time information, and the road areas corresponding to images acquired at adjacent acquisition times are also adjacent. Based on this, the target acquisition time of the road image can be obtained, and the acquired road images whose acquisition time is less than the target acquisition time are determined from each acquired road image included in the correspondence, and used as reference images of the road image.

[0146] Step S406: Based on the obtained reference offset components, adjust the target offset components of the geographical location of the road elements in the first road data in each preset offset direction.

[0147] Since the road region corresponding to the reference image is adjacent to the target road region, the offset component of the geographical location in the road data corresponding to the reference image is correlated with the offset component corresponding to the road image. Therefore, the target offset component corresponding to the first road data can be adjusted according to the offset component corresponding to the reference image.

[0148] In one embodiment, when adjusting the target offset component, for each preset offset direction, a second offset component other than the maximum and minimum offset components in the first offset component in that preset offset direction can be determined. Statistical analysis is performed on the second offset component corresponding to each preset direction to obtain a third offset component corresponding to each preset direction. Based on the third offset component corresponding to each preset direction, the target offset component of the geographical location of the road element in the first road in each preset direction is adjusted.

[0149] The first offset component mentioned above includes the reference offset component and the target offset component.

[0150] The above statistical analysis may include calculating the mean, calculating the median, etc.

[0151] The third offset component corresponding to each preset direction can be replaced with the target offset component in each preset direction to achieve adjustment of the target offset component.

[0152] Since the maximum and minimum offset components are relatively extreme offsets, they are not considered in the statistical analysis. This avoids the impact of these extreme offset components on the statistical analysis results, resulting in higher accuracy of the statistical analysis results and thus improving the accuracy of adjusting the target offset components.

[0153] Based on the above steps S405-S406, the aforementioned Figure 2 Step S205 shown can be implemented according to step S407 below.

[0154] Step S407: Based on each adjusted target offset component, adjust the geographical location of the road elements in the first road data.

[0155] Step S408: Based on the first road data and the second road data after adjusting the geographical location, determine the changed road data.

[0156] The aforementioned changed road data indicates sub-regions within the target road area where road conditions have changed.

[0157] Step S409: Update map data based on changed road data.

[0158] The steps S408-S409 described above are respectively related to the aforementioned Figure 2 Steps S206-S207 in the illustrated embodiment are the same and will not be described again here.

[0159] Since the road region corresponding to the reference image is adjacent to the target road region, the offset component of the geographical location in the road data corresponding to the reference image is correlated with the offset component corresponding to the road image. Therefore, the target offset component corresponding to the first road data can be accurately adjusted based on the offset component corresponding to the reference image.

[0160] In the foregoing Figure 1 In step S101 of the illustrated embodiment, first road data corresponding to the road image is obtained. Due to some interference factors that occur during the acquisition process of the image acquisition device, the first road data corresponding to the road image may become abnormal. If abnormal first road data is used to update the map data, the accuracy of the data update will be reduced. Therefore, it can be determined whether the road image currently in use is abnormal.

[0161] In view of the above, see Figure 5 , Figure 5 This is a flowchart illustrating the fifth data update method provided in the embodiments of this disclosure, as described above. Figure 1 After step S101 of the illustrated embodiment, it is also possible to detect whether there are any anomalies in the road image.

[0162] Specifically, Figure 5 The illustrated embodiment includes the following steps S501-S507.

[0163] Step S501: Identify road elements in the road image to obtain the first road data of the road elements within the target road area of ​​the road image.

[0164] The above step S501 is the same as the aforementioned Figure 1 Step S101 in the illustrated embodiment is the same and will not be described again here.

[0165] Step S502: Obtain reference road data for road elements in the reference image.

[0166] The road area corresponding to the aforementioned reference image is adjacent to the target road area. The aforementioned reference image can be multiple road images, such as 5 images, 10 images, etc.

[0167] The electronic device can pre-store the correspondence between each acquired road image and road data. Based on this, in one embodiment, a reference image of a road image can be determined from the acquired road images included in the pre-stored correspondence, and the road data corresponding to the reference image can be determined as reference road data. For a specific implementation of obtaining the reference image, please refer to the implementation of obtaining the reference image in step S405 above, which will not be repeated here.

[0168] Step S503: Based on the geographical location of the road elements in the reference road data, determine whether the geographical location of the road elements in the first road data is abnormal. If not, proceed to step S504.

[0169] Since the road region corresponding to the reference image is adjacent to the road region corresponding to the road image, the geographical location of the road element in the reference road data corresponding to the reference image is related to the geographical location of the road element in the first road data. Therefore, it is possible to determine whether the geographical location of the road element in the first road data is abnormal based on the geographical location of the road element in the reference road data corresponding to the reference image.

[0170] In one embodiment, the average geographical location of road elements of a preset type in the reference road data and the first road data can be calculated, and the difference between the geographical location of the road elements of the preset type in the first road data and the above average value can be calculated. If the difference is greater than a preset difference threshold, it indicates that the geographical location of the road elements in the first road data is abnormal.

[0171] Other implementation methods for determining whether the geographical location of road elements in the first road data is abnormal can be found in subsequent embodiments, and will not be described in detail here.

[0172] When an anomaly is detected in the geographical location of road elements in the first road data, it indicates a very high probability that the first road data is abnormal. In this case, the high-precision map data will not be updated using the first road data, and the process will end. The high-precision map data will only continue to be updated using the first road data if it is determined that the geographical location of road elements in the first road data is not abnormal.

[0173] Step S504: Obtain the second road data of road elements within the target road area from the existing map data.

[0174] Step S505: Use the geographical location of the road elements in the second road data to adjust the geographical location of the road elements in the first road data.

[0175] Step S506: Based on the first road data and the second road data after adjusting the geographical location, determine the changed road data.

[0176] The aforementioned road change data indicates sub-regions within the target road area where road conditions have changed.

[0177] Step S507: Update map data based on changed road data.

[0178] The steps S504-S507 described above are respectively related to the aforementioned Figure 1 Steps S102-S105 in the illustrated embodiment are the same and will not be described again here.

[0179] Since the road region corresponding to the reference image is adjacent to the road region corresponding to the road image, the geographical location of the road element in the reference road data corresponding to the reference image is related to the geographical location of the road element in the first road data. Therefore, based on the geographical location of the road element in the reference road data corresponding to the reference image, it is possible to accurately determine whether the geographical location of the road element in the first road data is abnormal.

[0180] The foregoing Figure 5 In step S503 of the illustrated embodiment, in addition to determining whether the geographical location corresponding to the first road data is abnormal based on the difference between geographical locations, the following two different implementation methods can also be used to determine whether the geographical location corresponding to the first road data is abnormal.

[0181] The first implementation method is carried out according to the following steps A1-A4.

[0182] Step A1: Based on the geographical location of the lane line elements in the reference road data, calculate the first width value of the lane width of the road area corresponding to the reference image.

[0183] It can calculate the distance between the geographical locations of every two lane line elements in the reference road data and determine the farthest distance as the first width value.

[0184] Step A2: Based on the geographical location of the lane line elements in the first road data, calculate the second width value of the lane width within the target road area.

[0185] The distance between the geographical locations of every two lane line elements in the first road data can be calculated, and the farthest distance is determined as the second width value.

[0186] Step A3: When there are multiple reference images, calculate the average width value of the first width value and the second width value.

[0187] Step A4: Based on the second width value and the average width value, determine whether the geographical location of the road elements in the first road data is abnormal.

[0188] Based on the second width value and the average width value, the first RMSE (Root Mean Squared Error) of the lane width in the target road area can be calculated. It can be determined whether the first RMSE is less than the preset first RMSE. If it is, it means that the geographical location of the road element in the first road data is abnormal; if it is not, it means that the geographical location of the road element in the first road data is not abnormal.

[0189] The first RMSE is calculated using the following expression:

[0190]

[0191] Where Rmse1 represents the first RMSE, n is the total number of reference images and road images, i represents the sequence number of the road image, and w i This represents the second width value. This represents the average width value.

[0192] Since the average width value represents the average width level of the lanes within the road area corresponding to the road image and the reference image, the second width value and the average width value can accurately determine whether the lane width meets the average width level, thereby accurately determining whether the geographical location of the road elements in the first road data is abnormal.

[0193] The second implementation method is carried out according to the following steps B1-B3.

[0194] Step B1: When there are multiple reference images, for each target image, calculate the positional difference of the lane line elements in the third direction between the target image and the adjacent images, and use it as the second positional difference value of the lane lines in the road area corresponding to the target image.

[0195] The target image mentioned above is either a reference image or a road image.

[0196] The aforementioned adjacent images are those acquired at times adjacent to the target image in the reference image and the road image.

[0197] The third direction can be a pre-defined direction, for example, the third direction can be the transverse direction of the road.

[0198] It can calculate the geographical location differences of lane line elements in the target image and neighboring images in the third direction, and select the smallest geographical difference as the second geographical difference value.

[0199] Step B2: Calculate the average of the difference values ​​at the second position to obtain the average difference value.

[0200] Step B3: Based on the second location difference value and the average difference value corresponding to the geographical location of the lane line element in the first road data, determine whether the geographical location of the road element in the first road data is abnormal.

[0201] Based on the second location difference value and the average difference value corresponding to the geographical location of the lane line element in the first road data, the second RMSE of the second location difference value corresponding to the lane line in the target road area can be calculated. It can be determined whether the second RMSE is less than the preset second RMSE. If it is, it means that the geographical location of the road element in the first road data is abnormal; if it is not, it means that the geographical location of the road element in the first road data is not abnormal.

[0202] The second RMSE is calculated using the following expression:

[0203]

[0204] Where Rmse2 represents the second RMSE, n is the total number of reference images and road images, i represents the sequence number of the road image, and w p This indicates the difference value at the second position. This represents the average difference value.

[0205] Since the average difference value represents the average level of difference between lane elements in the road area corresponding to two images acquired at adjacent times, by comparing the second location difference value with the average difference value, it is possible to accurately determine whether the second location difference value meets the average difference level, thereby accurately determining whether the geographical location of the road elements in the first road data has become abnormal.

[0206] The following combination Figure 6 The data update scheme provided in the embodiments of this disclosure will be described in detail. Figure 6 The illustrated embodiment includes the following steps S601-S607.

[0207] Step S601: Identify road elements in the road image to obtain the first road data of the road elements within the target road area of ​​the road image.

[0208] Step S602: Obtain reference road data of road elements in the reference image of the road image. Based on the geographical location of the road elements in the reference road data, determine whether the geographical location of the road elements in the first road data is abnormal. If not, proceed to step S603. If yes, end the process.

[0209] Step S603: Determine the second road data of the road elements within the target road area corresponding to the road image in the existing map data from the index relationship of the existing map data.

[0210] Step S604: Using the geographical location of the road elements in the second road data, determine the target offset component of the geographical location of the road elements in the first road data in each preset offset direction.

[0211] Step S605: Based on each target offset component calculated, adjust the geographical location of the road elements in the first road data.

[0212] Step S606: Based on the first road data and the second road data after adjusting the geographical location, determine the changed road data.

[0213] Step S607: Update existing map data based on the changed road data.

[0214] Corresponding to the above-described map data update method, this disclosure also provides a schematic diagram of the structure of a map data update device.

[0215] See Figure 7 , Figure 7 This is a schematic diagram of a map data update device provided in an embodiment of the present disclosure. The device includes the following modules 701-705.

[0216] The element recognition module 701 is used to recognize road elements in a road image and obtain first road data of road elements in the target road area targeted by the road image.

[0217] The first data acquisition module 702 is used to acquire the second road data of road elements in the target road area from the existing map data;

[0218] The location adjustment module 703 is used to adjust the geographical location of the road elements in the first road data using the geographical location of the road elements in the second road data;

[0219] The data determination module 704 is used to determine changed road data based on the first road data after adjusting the geographical location and the second road data, wherein the changed road data indicates the sub-regions in the target road area where the road conditions have changed;

[0220] The data update module 705 is used to update the map data based on the changed road data.

[0221] As can be seen from the above, when updating data using the solution provided in this embodiment, since the geographical location of road elements in the first road data corresponding to the road image has errors, and the second road data is road data in existing map data, the accuracy of the existing map data is relatively high compared to the accuracy of the first road data. Therefore, when adjusting the geographical location of road elements in the first road data, the geographical location of road elements in the second road data is used, thereby making the accuracy of the adjusted geographical location higher than the accuracy of the geographical location before adjustment. Therefore, based on the first road data and the second road data after adjusting the geographical location, the changed road data can be accurately determined, thereby improving the accuracy of updating map data.

[0222] Furthermore, in this embodiment, multiple road images are not integrated to obtain a road image reflecting the complete road area. Integrating road images would be extremely time-consuming, taking approximately one week, and to ensure the freshness of map data, it would require at least daily updates. Therefore, since this embodiment does not require integrating road images to obtain a road image reflecting the complete road area, it updates the map data using each road image individually. Furthermore, it adjusts the corresponding road data for each road image using existing map data, thereby improving the efficiency of map data updates while maintaining accuracy.

[0223] In one embodiment of this disclosure, the position adjustment module 703 includes:

[0224] The difference value calculation submodule is used to calculate the first location difference value between the geographical locations of the same type of road elements in the first road data and the second road data;

[0225] The offset component determination submodule is used to determine the target offset component of the geographical location of the road element in the first road data in each preset offset direction if there is a position difference value within a preset error range in the calculated first position difference value, based on the geographical location of the target type road element in the first road data and the second road data. The target type is a type of road element corresponding to the first position difference value within the preset error range.

[0226] The location adjustment submodule is used to adjust the geographical location of road elements in the first road data based on each calculated target offset component.

[0227] As can be seen from the above, when the first position difference value is within the preset error range, it indicates that the geographical location of the road element in the first road data has deviated. In this case, the offset component of the geographical location of the road element in the first road data in each preset offset direction is calculated, and based on the offset component in each preset offset direction, the geographical location can be adjusted from each preset offset direction, thereby achieving precise adjustment of the geographical location. Therefore, based on each target offset component calculated, the accuracy of the adjusted geographical location can be improved.

[0228] In one embodiment of this disclosure, the preset offset direction includes a first direction and a second direction;

[0229] The offset component determination submodule includes:

[0230] The first vector calculation unit is used to calculate, based on the geographical location of the road element of the target type in the first road data, the first translation vector and the first rotation vector in the first direction.

[0231] The position adjustment unit is used to adjust the geographical location of the target type road element in the first road data based on the first translation vector and the first rotation vector to obtain the adjusted position;

[0232] The second vector calculation unit is used to calculate the second translation vector and the second rotation vector of the adjusted position of the road element in the first road data in the second direction based on the adjusted position of the road element of the target type in the first road data and the geographical location of the road element of the target type in the second road data.

[0233] The offset component determination unit is used to determine the calculated first translation vector, second translation vector, first rotation vector, and second rotation vector as the target offset component of the geographical location of the road element in the first road data in each preset offset direction.

[0234] Since the calculation process involves first calculating the first rotation vector and first translation vector of the geographical location in the first road data in the first direction, then adjusting the geographical location in the first road data using the calculated first rotation vector and first translation vector to obtain the adjusted position, and finally calculating the second rotation vector and second translation vector of the adjusted position in the first road data in the second direction, it can be seen that the calculation of the second rotation vector and second translation vector in the second direction uses the already adjusted position. The accuracy of the above-mentioned adjusted position has been improved. Based on the highly accurate adjusted position, the second rotation vector and second translation vector can be accurately calculated, thereby making the accuracy of the obtained target offset component higher.

[0235] In one embodiment of this disclosure, the first vector calculation unit is specifically used to calculate the first translation vector T according to the following expression. l and the first rotation vector R l :

[0236]

[0237] Where P1 represents the geographical location of the target type road element in the first road data, P CS R represents the geographic location of road elements of the target type in the second road data. l T represents the first rotation vector of the geographical location of a road element in the first road data in the first direction. l This represents the first translation vector of the geographical location of a road element in the first road data in the first direction.

[0238] In one embodiment of this disclosure, the second vector calculation unit is specifically used to calculate the second translation vector T2 and the second rotation vector R2 according to the following expressions:

[0239]

[0240] Where P2 represents the adjusted position of the road element of the target type in the first road data, P CS R2 represents the geographic location of the target type road element in the second road data, R2 represents the second rotation vector of the adjusted position of the road element in the first road data in the second direction, and T2 represents the second translation vector of the adjusted position of the road element in the first road data in the second direction.

[0241] In one embodiment of this disclosure, the position adjustment module further includes:

[0242] The offset component acquisition submodule is used to obtain the reference offset component of the geographical location of the road element in the reference image in each preset offset direction before adjusting the geographical location of the road element in the first road data based on each calculated target offset component in the position adjustment submodule, wherein the road area corresponding to the reference image is adjacent to the target road area.

[0243] The offset component adjustment submodule is used to adjust the target offset component of the geographical location of the road element in the first road data in each preset offset direction based on the obtained reference offset component.

[0244] The location adjustment submodule is specifically used to adjust the geographical location of road elements in the first road data based on each adjusted target offset component.

[0245] Since the road region corresponding to the reference image is adjacent to the target road region, the offset component of the geographical location in the road data corresponding to the reference image is correlated with the offset component corresponding to the road image. Therefore, the target offset component corresponding to the first road data can be accurately adjusted based on the offset component corresponding to the reference image.

[0246] In one embodiment of this disclosure, the aforementioned offset component adjustment submodule is specifically configured to, for each preset offset direction, determine a second offset component in the first offset component of the preset direction, excluding the maximum and minimum offset components, wherein the first offset component includes a reference offset component and a target offset component; perform statistical analysis on the second offset component corresponding to each preset offset direction to obtain a third offset component corresponding to each preset offset direction; and adjust the target offset component of the geographical location of the road element in the first road in each preset offset direction based on the third offset component corresponding to each preset offset direction.

[0247] Since the maximum and minimum offset components are relatively extreme offsets, they are not considered in the statistical analysis. This avoids the impact of these extreme offset components on the statistical analysis results, resulting in higher accuracy of the statistical analysis results and thus improving the accuracy of adjusting the target offset components.

[0248] In one embodiment of this disclosure, the apparatus further includes:

[0249] The second data acquisition module is used to obtain reference road data of road elements in a reference image before obtaining the second road data of road elements in the target road area in the existing map data in the first data acquisition module, wherein the road area corresponding to the reference image is adjacent to the target road area.

[0250] The anomaly detection module is used to determine whether the geographical location of the road element in the first road data is abnormal based on the geographical location of the road element in the reference road data. If not, the first data acquisition module is triggered.

[0251] Since the road region corresponding to the reference image is adjacent to the road region corresponding to the road image, the geographical location of the road element in the reference road data corresponding to the reference image is related to the geographical location of the road element in the first road data. Therefore, based on the geographical location of the road element in the reference road data corresponding to the reference image, it is possible to accurately determine whether the geographical location of the road element in the first road data is abnormal.

[0252] In one embodiment of this disclosure, the above-mentioned anomaly judgment module is specifically used to calculate a first width value of the lane width of the road area corresponding to the reference image based on the geographical location of the lane line elements in the reference road data; calculate a second width value of the lane width in the target road area based on the geographical location of the lane line elements in the first road data; calculate the average width value of the first width value and the second width value when the reference image is multiple images; and determine whether the geographical location of the road elements in the first road data is abnormal based on the second width value and the average width value.

[0253] Since the average width value represents the average width level of the lanes within the road area corresponding to the road image and the reference image, the second width value and the average width value can accurately determine whether the lane width meets the average width level, thereby accurately determining whether the geographical location of the road elements in the first road data is abnormal.

[0254] In one embodiment of this disclosure, the above-mentioned anomaly judgment module is specifically used to, when there are multiple reference images, calculate the positional difference in the geographical location of lane line elements in the third direction between the target image and adjacent images for each target image, as the second positional difference value of lane lines in the road area corresponding to the target image, wherein the target image is: a reference image or a road image, and the adjacent images are: images in the reference image and the road image that are adjacent to the acquisition time of the target image; calculate the average value of the second positional difference value to obtain the average difference value; and determine whether the geographical location of road elements in the first road data is abnormal based on the second positional difference value of lane lines in the target road area corresponding to the road image and the average difference value.

[0255] Since the average difference value represents the average level of difference between lane elements in the road area corresponding to two images acquired at adjacent times, by comparing the second location difference value with the average difference value, it is possible to accurately determine whether the second location difference value meets the average difference level, thereby accurately determining whether the geographical location of the road elements in the first road data has become abnormal.

[0256] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0257] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0258] In one embodiment of this disclosure, an electronic device is provided, comprising:

[0259] At least one processor; and

[0260] A memory communicatively connected to the at least one processor; wherein,

[0261] The memory stores instructions that can be executed by the at least one processor, which, when executed by the at least one processor, enables the at least one processor to perform the map data update method described above.

[0262] In one embodiment of this disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause the computer to perform the above-described map data update method.

[0263] In one embodiment of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the above-described map data update method.

[0264] Figure 8 A schematic block diagram of an example electronic device 800 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0265] like Figure 8As shown, device 800 includes a computing unit 801, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 802 or a computer program loaded from storage unit 808 into random access memory (RAM) 803. RAM 803 may also store various programs and data required for the operation of device 800. The computing unit 801, ROM 802, and RAM 803 are interconnected via bus 804. Input / output (I / O) interface 805 is also connected to bus 804.

[0266] Multiple components in device 800 are connected to I / O interface 805, including: input unit 806, such as keyboard, mouse, etc.; output unit 807, such as various types of monitors, speakers, etc.; storage unit 808, such as disk, optical disk, etc.; and communication unit 809, such as network card, modem, wireless transceiver, etc. Communication unit 809 allows device 800 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0267] The computing unit 801 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as the map data update method. For example, in some embodiments, the map data update method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 808. In some embodiments, part or all of the computer program may be loaded and / or installed on device 800 via ROM 802 and / or communication unit 809. When the computer program is loaded into RAM 803 and executed by the computing unit 801, one or more steps of the map data update method described above may be performed. Alternatively, in other embodiments, the computing unit 801 may be configured to perform the map data update method by any other suitable means (e.g., by means of firmware).

[0268] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0269] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0270] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0271] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the 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 can be received in any form (including sound input, voice input, or tactile input).

[0272] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0273] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0274] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0275] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for updating map data, comprising: identifying road elements in a road image to obtain first road data of road elements in a target road region to which the road image is directed; obtaining second road data of road elements in the target road region in existing map data; calculating first position difference values between geographical positions of road elements of a same type in the first road data and the second road data; if there is a position difference value within a preset error range in the calculated first position difference values, determining target offset components of the geographical positions of road elements in the first road data in each preset offset direction according to the geographical positions of road elements of a target type in the first road data and the second road data, wherein the target type is a type of road elements corresponding to the first position difference value within the preset error range; adjusting the geographical positions of road elements in the first road data based on each calculated target offset component; determining changed road data based on the first road data after the adjustment of the geographical positions and the second road data, wherein the changed road data indicates a sub-region in which road conditions in the target road region have changed; and updating the existing map data based on the changed road data. The preset offset directions include a first direction and a second direction. The determining of the target offset components of the geographical positions of road elements in the first road data in each preset offset direction according to the geographical positions of road elements of the target type in the first road data and the second road data comprises: calculating a first translation vector and a first rotation vector of the geographical positions of road elements in the first road data in the first direction according to the geographical positions of road elements of the target type in the first road data and the second road data; adjusting the geographical positions of road elements of the target type in the first road data based on the first translation vector and the first rotation vector to obtain adjusted positions; calculating a second translation vector and a second rotation vector of the adjusted positions of road elements in the first road data in the second direction according to the adjusted positions of road elements of the target type in the first road data and the geographical positions of road elements of the target type in the second road data; and determining the calculated first translation vector, the second translation vector, the first rotation vector and the second rotation vector as the target offset components of the geographical positions of road elements in the first road data in each preset offset direction. The calculating of the first translation vector and the first rotation vector of the geographical positions of road elements in the first road data in the first direction according to the geographical positions of road elements of the target type in the first road data and the second road data comprises: The calculating of the second translation vector and the second rotation vector of the adjusted positions of road elements in the first road data in the second direction according to the adjusted positions of road elements of the target type in the first road data and the geographical positions of road elements of the target type in the second road data comprises: ​ ​ ​ 2. The method of claim 1, wherein, ​ ​ ​ ​ ​ ​ 3. The method of claim 2, wherein, ​ The first translation vector is calculated according to the following expression and the first rotation vector is calculated according to the following expression : ; wherein represents a geographical position of a road element of the target type in the first road data, represents a geographical position of a road element of the target type in the second road data, represents a first rotation vector of the geographical position of the road element in the first road data in the first direction, represents a first translation vector of the geographical position of the road element in the first road data in the first direction.

4. The method of claim 2, wherein, ​ The second translation vector is calculated according to the following expression and the second rotation vector is calculated according to the following expression : ; wherein represents an adjusted position of a road element of the target type in the first road data, represents a geographical position of a road element of the target type in the second road data, represents a second rotation vector of the adjusted position of the road element in the first road data in the second direction, represents a second translation vector of the adjusted position of the road element in the first road data in the second direction.

5. The method of any one of claims 1-4, before the adjusting the geographical positions of the road elements in the first road data based on the calculated target offset component in each offset direction, further comprising: obtaining a reference offset component of the geographical positions of the road elements in a reference image in each preset offset direction, wherein the road region corresponding to the reference image is adjacent to the target road region; adjusting the target offset component of the geographical positions of the road elements in the first road data in each preset offset direction based on the obtained reference offset component; and the adjusting the geographical positions of the road elements in the first road data based on the calculated target offset component in each offset direction comprises: adjusting the geographical positions of the road elements in the first road data based on the adjusted target offset component in each offset direction.

7. The method of any one of claims 1-4, before the obtaining the second road data of the road elements in the target road region in the existing map data, further comprising: obtaining reference road data of the road elements in a reference image, wherein the road region corresponding to the reference image is adjacent to the target road region; and determining whether the geographical positions of the road elements in the first road data are abnormal based on the geographical positions of the road elements in the reference road data, and if not, performing the obtaining the second road data of the road elements in the target road region in the existing map data.

7. The method of any one of claims 1-4, before the obtaining the second road data of the road elements in the target road region in the existing map data, further comprising: obtaining reference road data of the road elements in a reference image, wherein the road region corresponding to the reference image is adjacent to the target road region; and determining whether the geographical positions of the road elements in the first road data are abnormal based on the geographical positions of the road elements in the reference road data, and if not, performing the obtaining the second road data of the road elements in the target road region in the existing map data.

7. The method of any one of claims 1-4, before the obtaining the second road data of the road elements in the target road region in the existing map data, further comprising: obtaining reference road data of the road elements in a reference image, wherein the road region corresponding to the reference image is adjacent to the target road region; and determining whether the geographical positions of the road elements in the first road data are abnormal based on the geographical positions of the road elements in the reference road data, and if not, performing the obtaining the second road data of the road elements in the target road region in the existing map data.

7. The method of any one of claims 1-4, before the obtaining the second road data of the road elements in the target road region in the existing map data, further comprising: obtaining reference road data of the road elements in a reference image, wherein the road region corresponding to the reference image is adjacent to the target road region; and determining whether the geographical positions of the road elements in the first road data are abnormal based on the geographical positions of the road elements in the reference road data, and if not, performing the obtaining the second road data of the road elements in the target road region in the existing map data.

6. The method of claim 5, wherein, 7. The method of any one of claims 1-4, before the obtaining the second road data of the road elements in the target road region in the existing map data, further comprising: obtaining reference road data of the road elements in a reference image, wherein the road region corresponding to the reference image is adjacent to the target road region; and determining whether the geographical positions of the road elements in the first road data are abnormal based on the geographical positions of the road elements in the reference road data, and if not, performing the obtaining the second road data of the road elements in the target road region in the existing map data. ​ ​ ​ ​ ​ ​ 8. The method of claim 7, wherein, ​ ​ ​ ​ ​ 9. The method of claim 7, wherein, ​ In a case where the reference images are multiple images, for each target image, a position difference of a geographical position of a lane line element in the target image and a geographical position of the lane line element in a neighboring image in a third direction is calculated as a second position difference value of a lane line in a road region corresponding to the target image, wherein the target image is a reference image or a road image, and the neighboring image is an image adjacent in time to the target image among the reference images and the road images; An average value of the second position difference values is calculated to obtain an average difference value; Based on the second position difference value of the lane line in the target road region corresponding to the road image and the average difference value, it is determined whether the geographical position of the road element in the first road data is abnormal.

10. A map data updating apparatus, comprising: an element identification module configured to identify road elements in a road image to obtain first road data of road elements in a target road region corresponding to the road image; a first data obtaining module configured to obtain second road data of road elements in the target road region in existing map data; a difference value calculation submodule configured to calculate a first position difference value between geographical positions of road elements of a same type in the first road data and the second road data; an offset component determination submodule configured to, if there is a position difference value within a preset error range in the calculated first position difference value, determine a target offset component of the geographical position of the road element in the first road data in each preset offset direction according to the geographical positions of road elements of a target type in the first road data and the second road data, wherein the target type is a type of road element corresponding to the first position difference value within the preset error range; a position adjustment submodule configured to adjust the geographical position of the road element in the first road data based on each target offset component calculated; a data determination module configured to determine changed road data based on the first road data after the geographical position is adjusted and the second road data, wherein the changed road data indicates a sub-region in which a road condition in the target road region has changed; a data updating module configured to update the map data based on the changed road data.

11. The apparatus of claim 10, wherein, The preset offset directions include a first direction and a second direction; the offset component determination submodule includes: a first vector calculation unit configured to calculate a first translation vector and a first rotation vector of the geographical position of the road element in the first road data in the first direction according to the geographical positions of road elements of the target type in the first road data and the second road data; a position adjustment unit configured to adjust the geographical position of the road element of the target type in the first road data based on the first translation vector and the first rotation vector to obtain an adjusted position; a second vector calculation unit configured to calculate a second translation vector and a second rotation vector of the adjusted position of the road element in the first road data in the second direction according to the adjusted position of the road element of the target type in the first road data and the geographical position of the road element of the target type in the second road data; The offset component determination unit is configured to determine the calculated first translation vector, the second translation vector, the first rotation vector and the second rotation vector as target offset components of the geographical positions of the road elements in the first road data in each preset offset direction.

12. The apparatus of claim 11, wherein, The first vector calculation unit is specifically configured to calculate a first translation vector according to the following expression and a first rotation vector : ; wherein represents a geographical position of a road element of the target type in the first road data, represents a geographical position of a road element of the target type in the second road data, represents a first rotation vector of the geographical position of the road element in the first road data in the first direction, represents a first translation vector of the geographical position of the road element in the first road data in the first direction.

13. The apparatus of claim 11, wherein, The second vector calculation unit is specifically configured to calculate a second translation vector according to the following expression and a second rotation vector : ; wherein represents an adjusted position of a road element of the target type in the first road data, represents a geographical position of a road element of the target type in the second road data, represents a second rotation vector of the adjusted position of the road element in the first road data in the second direction, represents a second translation vector of the adjusted position of the road element in the first road data in the second direction.

14. The apparatus of any one of claims 10-13, the position adjustment module further comprising: an offset component obtaining sub-module configured to, before adjusting the geographical positions of the road elements in the first road data based on each calculated target offset component in the position adjustment sub-module, obtain reference offset components of the geographical positions of the road elements in a reference image in each preset offset direction, wherein the reference image corresponds to a road region adjacent to the target road region; an offset component adjustment sub-module configured to adjust the target offset components of the geographical positions of the road elements in the first road data in each preset offset direction based on the obtained reference offset components; the position adjustment sub-module is specifically configured to adjust the geographical positions of the road elements in the first road data based on each adjusted target offset component.

15. The apparatus of claim 14, wherein, The offset component adjustment sub-module is specifically configured to, for each preset offset direction, determine second offset components in the first offset components in the preset offset direction other than the maximum offset component and the minimum offset component, wherein the first offset components include the reference offset components and the target offset components; statistically analyze the second offset components corresponding to each preset offset direction to obtain third offset components corresponding to each preset direction; and adjust the target offset components of the geographical positions of the road elements in the first road in each preset offset direction based on the third offset components corresponding to each preset offset direction.

16. An electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-9.

17. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to enable the computer to perform the method of any one of claims 1-9.

18. A computer program product comprising a computer program which, when executed by a processor, implements the method of any one of claims 1-9. The computer program product comprises a computer program which, when executed by a processor, implements the method of any one of claims 1-9.

Images