Map identifier change detection method and device, equipment and storage medium

Abstract

The invention discloses a map identifier change detection method, device and equipment and a storage medium, relates to the technical field of map identifier detection, and discloses a map identifier change detection method comprising the following steps: obtaining a perception identifier according to sensor data, and obtaining a map identifier according to map information; according to the map identifier and the perception identifier, obtaining a geometric expression form of the map identifier and a geometric expression form of the perception identifier; calculating the position of the map identifier according to the geometric expression form of the map identifier, and calculating the position of the perceptual identifier according to the geometric expression form of the perceptual identifier; performing identifier matching according to the map identifier position, the perception identifier position, the geometric expression form of the map identifier and the geometric expression form of the perception identifier to obtain an identifier matching result; and carrying out map identifier change detection according to an identifier matching result. By integrating the perception data and the map data and using position matching and geometric expression form comparison, the real-time updating of the map identifier in the dynamic environment is realized.

Description

Technical Field

[0001] The present application relates to the field of map marker detection technology, and in particular to a map marker change detection method, device, equipment and storage medium. Background Art

[0002] With the rapid development of autonomous driving technology, achieving real-time and accurate environmental recognition is essential to ensure the safety of autonomous vehicles. The environmental model provides a detailed view of the surrounding environment, including roads, traffic signs, and other objects that may affect driving decisions. In a dynamic road environment, changes are everywhere. For example, road signs may change due to construction, policy updates, or wear and tear; obstacles, such as construction equipment, temporary signs, and obstacles caused by traffic accidents, may suddenly appear on the road. In order to achieve safe driving, it is necessary to be able to reflect any changes in the environment in real time and perform accurate map sign change detection so that the autonomous driving system can respond quickly and accurately.

[0003] Traditional environmental map marker change detection technology is mainly based on laser radar to scan and analyze the environment around the self-driving car to generate a real-time environmental model. However, traditional map marker change detection relies on laser radar, which often contains noise and errors when processing laser radar data, and requires complex algorithms for data cleaning and analysis, resulting in high computing costs and poor real-time performance. When faced with frequent changes in the environment, it is difficult to adapt quickly, thus affecting the reliability and safety of decision-making.

[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of this application is to provide a map sign change detection method, device, equipment and storage medium, aiming to solve the technical problem that traditional map sign change detection technology is difficult to quickly detect and update dynamically changing road signs.

[0006] To achieve the above objectives, the present application proposes a map marker change detection method, the method comprising:

[0007] Obtaining a perception identifier based on the sensor data and obtaining a map identifier based on the map information;

[0008] According to the map identifier and the perception identifier, a geometric expression form of the map identifier and a geometric expression form of the perception identifier are obtained;

[0009] Calculating a map marker position according to a geometric expression of the map marker, and calculating a perceived marker position according to a geometric expression of the perceived marker;

[0010] Performing identification matching according to the map identification position, the perception identification position, the geometric expression form of the map identification, and the geometric expression form of the perception identification to obtain an identification matching result;

[0011] A map marker change is detected according to the marker matching result.

[0012] In one embodiment, the step of performing identifier matching according to the map identifier position, the perception identifier position, the geometric expression form of the map identifier, and the geometric expression form of the perception identifier to obtain the identifier matching result includes:

[0013] Performing a position comparison based on the perception mark position and the map mark position to obtain a position comparison result;

[0014] According to the position comparison result, an unmatched map marker position is obtained, and according to the unmatched map marker position, a marker matching result is recorded as deletion;

[0015] When the position comparison result is less than or equal to the preset association distance, comparing the geometric expression form of the map mark and the geometric expression form of the perception mark to obtain a first comparison result;

[0016] When the first comparison result is a preset matching result, the matching result of the record identification is modified;

[0017] When the position comparison result is greater than the preset association distance, the record identification matching result is newly added.

[0018] In one embodiment, the step of obtaining an unmatched map marker location according to the location comparison result, and recording the marker matching result as deleted according to the unmatched map marker location includes:

[0019] Obtaining the current vehicle position, a preset longitudinal threshold, and a preset lateral threshold;

[0020] According to the position comparison result, identifying the map identifier that is not associated with the perception identifier, and obtaining the position of the unmatched position identifier;

[0021] Obtaining an unmatched distance according to the unmatched position identification position and the current vehicle position;

[0022] When the unmatched distance is smaller than the preset longitudinal threshold or the preset lateral threshold, the identification matching result is deleted according to the unmatched map identification position record.

[0023] In one embodiment, the step of detecting a map marker change according to the marker matching result includes:

[0024] When the identification matching result is deletion, deleting the map identification corresponding to the identification matching result according to the map information, and obtaining a first update result;

[0025] When the identification matching result is modification, modifying the map identification position according to the map information and the perceived identification position corresponding to the identification matching result to obtain a second update result;

[0026] When the identification matching result is newly added, according to the perceived identification position and the geometric expression form of the perceived identification corresponding to the identification matching result, a map identification is added to the map information to obtain a third update result;

[0027] A map mark change is detected according to any one of the first update result, the second update result, and the third update result.

[0028] In one embodiment, the step of calculating the map marker position according to the geometric expression form of the map marker and calculating the perceived marker position according to the geometric expression form of the perceived marker comprises:

[0029] When the geometric expression form of the map mark or the geometric expression form of the perception mark is a ground mark, the center point of the map mark or the center point of the perception mark is calculated according to the first frame of the map mark or the perception mark;

[0030] When the geometric expression form of the map mark or the geometric expression form of the perception mark is an aerial mark, projecting according to the map mark or the perception mark to obtain a second frame, and calculating the center point of the map mark or the perception mark according to the second frame;

[0031] When the geometric expression form of the map mark or the geometric expression form of the perception mark is a cylindrical mark, obtaining the center point of the map mark or the perception mark according to the grounding point of the map mark or the perception mark;

[0032] A coordinate system conversion is performed according to the map mark center point or the perception mark center point to obtain the map mark position or the perception mark position.

[0033] In one embodiment, the step of obtaining a geometric expression form of the map identifier and a geometric expression form of the perception identifier according to the map identifier and the perception identifier comprises:

[0034] Identify the location features and image features of the map mark or the sensory mark;

[0035] When the location feature is a ground element, identifying the geometric expression form of the map identifier or the geometric expression form of the perception identifier as a ground identifier;

[0036] When the location feature is an aerial element, identifying the geometric expression form of the map identifier or the geometric expression form of the perception identifier as an aerial identifier;

[0037] When the image feature is a cylindrical element, it is recognized that the geometric expression form of the map mark or the geometric expression form of the perception mark is a cylindrical mark.

[0038] In one embodiment, the step of acquiring the perception identifier according to the sensor data and acquiring the map identifier according to the map information includes:

[0039] Acquire a first preset detection range and a second preset detection range, wherein the first preset detection range is larger than the second preset detection range;

[0040] Obtaining a map identifier according to the current position of the vehicle, the first preset detection range, and the map information;

[0041] A perception identifier is obtained according to the second preset detection range and the sensor data.

[0042] In addition, to achieve the above-mentioned purpose, the present application also proposes a map mark change detection device, the map mark change detection device comprising:

[0043] A perception identification acquisition module, used to acquire a perception identification according to sensor data, and to acquire a map identification according to map information;

[0044] The perception identifier acquisition module is further used to obtain a geometric expression form of the map identifier and a geometric expression form of the perception identifier according to the map identifier and the perception identifier;

[0045] A marker position calculation module, used to calculate the map marker position according to the geometric expression form of the map marker, and calculate the perceived marker position according to the geometric expression form of the perceived marker;

[0046] A logo matching module, used to perform logo matching according to the map logo position, the perception logo position, the geometric expression form of the map logo and the geometric expression form of the perception logo, to obtain a logo matching result;

[0047] The identification change detection module is used to detect map identification changes according to the identification matching results.

[0048] In addition, to achieve the above-mentioned purpose, the present application also proposes a map marker change detection device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and the computer program is configured to implement the steps of the map marker change detection method as described above.

[0049] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the map identification change detection method described above are implemented.

[0050] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the map identification change detection method described above are implemented.

[0051] One or more technical solutions proposed in this application have at least the following technical effects:

[0052] By using sensors to capture changes in the real-time environment and comparing them with the markers in the initial map, calculating the positions of map markers and perception markers, and matching their geometric expressions and positions, it is possible to identify the marker elements that need to be updated. Compared with existing technologies, by directly comparing perception data and map data, the update process of the environmental model is simplified, and the reliance on complex algorithms is reduced, thereby improving processing speed and reducing computing costs. It not only speeds up the update of map markers, but also improves the accuracy of the reconstructed environmental model, allowing the autonomous driving system to navigate and make decisions more reliably. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0054] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0055] Figure 1 A flowchart of the first embodiment of the map marker change detection method of the present application is provided;

[0056] Figure 2 A flowchart diagram of the second embodiment of the map marker change detection method of the present application is provided;

[0057] Figure 3 This is a schematic diagram of the module structure of the map marker change detection device according to an embodiment of the present application;

[0058] Figure 4 Schematic diagram of the device structure of the hardware operating environment involved in the map marker change detection method in the embodiment of the present application.

[0059] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0060] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0061] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0062] The main solution of the embodiment of the present application is: obtaining a perception identifier based on sensor data, and obtaining a map identifier based on map information; obtaining a geometric expression of the map identifier and a geometric expression of the perception identifier based on the map identifier and the perception identifier; calculating a map identifier position based on the geometric expression of the map identifier, and calculating a perception identifier position based on the geometric expression of the perception identifier; performing identifier matching based on the map identifier position, the perception identifier position, the geometric expression of the map identifier, and the geometric expression of the perception identifier to obtain an identifier matching result; and detecting map identifier changes based on the identifier matching result.

[0063] In this embodiment, for the convenience of description, the following description is made by taking the map marker change detection device as the execution subject.

[0064] Since the conventional map sign change detection technology in the prior art is difficult to quickly detect and update dynamically changing road signs, the present application provides a solution that uses sensors to capture changes in the real-time environment and compares them with the signs in the initial map, calculates the positions of map signs and perception signs, and matches their geometric expressions and positions, so as to identify the sign elements that need to be updated. Compared with the prior art, by directly comparing perception data and map data, the updating process of the environmental model is simplified, and the dependence on complex algorithms is reduced, thereby improving the processing speed and reducing the computing cost. It not only speeds up the update of map signs, but also improves the accuracy of the reconstructed environmental model, so that the autonomous driving system can navigate and make decisions more reliably.

[0065] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device, a vehicle side, a cloud, a map mark change detection device, etc. that can realize the above functions. The following takes the map mark change detection device as an example to illustrate this embodiment and the following embodiments.

[0066] Based on this, the present application embodiment provides a map mark change detection method, referring to Figure 1 , Figure 1 This is a flowchart of the first embodiment of the map marker change detection method of the present application.

[0067] In this embodiment, the map mark change detection method includes steps S10 to S50:

[0068] Step S10, obtaining a perception identifier according to the sensor data, and obtaining a map identifier according to the map information;

[0069] It should be noted that sensor data is information collected by various sensors on autonomous vehicles, including but not limited to cameras, radars, lidars, etc. Sensor data provides real-time information about the environment around the vehicle, including but not limited to road conditions, traffic signs and road markings. Map information refers to the data in the detailed map database used by the vehicle navigation system, which includes preset identification information such as road layout, traffic signs, geographic markers, etc. This information is usually pre-entered and updated regularly to provide a basic framework of the environment and assist in positioning.

[0070] In addition, it should be noted that perception signs refer to various road and traffic-related visual signs identified by analyzing sensor data, such as arrows, stop lines, crosswalks, traffic lights, etc. on the ground. Perception signs are used to assist navigation and ensure driving safety in autonomous driving technology. Map signs are marks in the map information database that indicate specific geographic features or road information. These signs include but are not limited to road names, traffic lights, intersection signs, etc.

[0071] It is understood that environmental data is collected through the sensor system of the autonomous vehicle, and perception identifiers are extracted from this data through image recognition and data analysis technology. For example, traffic lights and road markings captured by the vehicle's camera are identified and classified. At the same time, the map database stored in the vehicle's navigation system is accessed to extract relevant map identifier information, such as the location of preset traffic signs in the area. This process enables the vehicle to compare perception identifiers and map identifiers to verify the accuracy of environmental data and make necessary navigation adjustments.

[0072] Step S20, obtaining a geometric expression form of the map identifier and a geometric expression form of the perception identifier according to the map identifier and the perception identifier;

[0073] It should be noted that the geometric expression of map signs refers to the geometric expression of various signs in the map, which are mainly divided into ground signs, aerial signs and cylindrical signs. Ground signs usually include road lines, parking lines, etc., aerial signs are such as traffic lights, and cylindrical signs usually refer to various poles on the roadside, such as traffic signal poles or street light poles. The geometric expression of perceived signs is based on the geometric expression of road or environmental signs perceived by the vehicle in real time through sensors. This also includes ground signs, aerial signs and cylindrical signs. For example, the camera may capture a newly installed roadside parking sign pole.

[0074] It is understood that the vehicle first needs to identify and classify the signs in the built-in map database and the signs in the actual environment perceived by the sensors. By comparing the data in the map and the real-time sensor data, the system can identify the geometric expression of the signs preset in the map and the geometric expression of the signs perceived by the sensors. For example, the map database may have recorded a street light pole at a specific location, and the vehicle sensor identifies in real time whether there is a street light pole at that location, and whether an aerial sign such as a traffic light has been added or replaced.

[0075] In a feasible implementation, step S20 may include steps S21 to S24:

[0076] Step S21, identifying the location features and image features of the map mark or the perception mark;

[0077] It should be noted that the location feature describes the placement of the sign in the physical environment, helping the system determine whether the sign is located on the ground, in the air, or elsewhere. This feature is critical to correctly interpreting and responding to environmental signs because it directly affects the visibility and functionality of the sign. Image features involve the appearance attributes of the sign, such as shape, color, and physical structure.

[0078] It is understood that the location characteristics and image characteristics of the sign are identified by analyzing map data and real-time perception data. This includes determining whether the sign is located on the ground, in the air, or fixed to a specific structure, as well as the shape, color, and size of the sign. This information helps to correctly classify the sign for more accurate processing and response.

[0079] Step S22, when the location feature is a ground element, identifying the geometric expression form of the map mark or the geometric expression form of the perception mark as a ground mark;

[0080] It should be noted that ground elements refer to signs placed or painted directly on the road surface, such as pedestrian crossings, stop lines, etc. Such signs are usually used to guide ground traffic and pedestrian behavior.

[0081] It is understandable that when the location feature indicates that the sign is located on the ground, the sign is classified as a ground sign, which mainly includes but is not limited to road markings, parking space signs and other ground traffic management symbols.

[0082] Step S23, when the location feature is an aerial element, identifying the geometric expression form of the map mark or the geometric expression form of the perception mark as an aerial mark;

[0083] It should be noted that aerial elements refer to signs hung or fixed in the air, such as traffic lights and signs, which provide visual guidance to traffic participants from a high altitude.

[0084] It is understood that for the case where the position feature shows that the sign is in the air, it is classified as an aerial sign. This includes various hanging signs and traffic lights, which are usually above the road surface to guide or control traffic.

[0085] Step S24, when the image feature is a cylindrical element, identifying that the geometric expression form of the map mark or the geometric expression form of the perception mark is a cylindrical mark.

[0086] It should be noted that cylindrical elements refer to cylindrical physical structures, such as street light poles, traffic signal poles, etc. These structures are usually used to support traffic signs or equipment, such as street lights.

[0087] It is understandable that if the image characteristics of the sign indicate that it is fixed to a cylindrical structure, such as a street light pole or a traffic signal pole, the system will classify such a sign as a cylindrical sign.

[0088] Step S30, calculating the map marker position according to the geometric expression form of the map marker, and calculating the perception marker position according to the geometric expression form of the perception marker;

[0089] It should be noted that the map marker position refers to the specific location coordinates of these map markers in the digital map. These locations are preset in the map data and are defined based on the geographic coordinate system to ensure that the navigation system can use these data for accurate navigation. The perceived marker position is the position of the road or environmental marker determined in real time by the vehicle sensor, including the precise location information of the marker drawn by these sensor systems to update and correct the navigation map in real time.

[0090] It is understood that the location of each sign needs to be determined based on the geometric representation of the sign in the map. This involves extracting the location information about each geometric representation of the sign from the map data, such as the precise coordinates of a street light pole. At the same time, the vehicle's sensor system performs real-time position determination based on the geometric representation of the perceived sign. For example, if a new traffic light is detected that is not recorded in the map data, its position will be calculated and compared with the map data. This process enables the vehicle to update its location information library in real time and adjust its navigation strategy according to the actual environment.

[0091] In a feasible implementation, step S30 may include steps S31 to S34:

[0092] Step S31, when the geometric expression form of the map mark or the geometric expression form of the perception mark is a ground mark, calculate the center point of the map mark or the center point of the perception mark according to the first frame of the map mark or the perception mark;

[0093] It should be noted that the center point of a map marker is the geometric center obtained by calculating the bounding box or shape of the marker based on the map data. The center point of a perceived marker is the center position of the marker calculated after the vehicle sensor system captures and analyzes the marker in the actual environment. The first bounding box is the visible outer boundary directly surrounding the ground marker. This bounding box is used to assist in determining the center point of the ground marker, especially for those markers painted directly on the road, such as stop signs or pedestrian crossings.

[0094] It is understandable that when the geometric expression form of the map mark or the geometric expression form of the perception mark is a ground mark, the center point of the map mark or the perception mark is calculated by analyzing the first frame in the map data or the perception data. Ground arrows, ground text, and pedestrian crossings generally exist in the form of rectangular frames, and stop lines exist in the form of lines or rectangular frames. For ground marks, the geometric center point is obtained by directly averaging the point set.

[0095] Step S32, when the geometric expression form of the map mark or the geometric expression form of the perception mark is an aerial mark, projecting according to the map mark or the perception mark to obtain a second frame, and calculating the center point of the map mark or the perception mark according to the second frame;

[0096] It should be noted that the second frame is the boundary obtained by visually projecting the aerial sign onto a two-dimensional plane. This projected frame helps determine the two-dimensional center point of a hanging sign, such as a traffic light.

[0097] It is understandable that for aerial signs, projection is first performed to form a second bounding box, and then the center point of the map sign or perceived sign is calculated based on this bounding box. This step is mainly used to process high-hanging signs such as traffic lights to ensure that their positions in the two-dimensional map are accurate. In the aerial signs of maps and perceptions, traffic lights and traffic signs generally exist in the form of three-dimensional bounding boxes, which are projected onto the ground into a two-dimensional rectangular box, and then the geometric center is calculated in the same way as the ground.

[0098] Step S33, when the geometric expression form of the map mark or the geometric expression form of the perception mark is a cylindrical mark, obtaining the center point of the map mark or the perception mark according to the grounding point of the map mark or the perception mark;

[0099] It should be noted that the grounding point is the location where the bottom of the cylindrical sign touches the ground. For signs fixed to cylindrical structures, such as street lights or traffic signal poles.

[0100] It is understood that when the marker is fixed on a cylindrical structure such as a street light pole, the ground point is used as the calculation basis to determine the center point of the map marker or perception marker. This step ensures that the cylindrical marker is accurately positioned in the navigation system, which facilitates the vehicle to correctly identify and respond. In the map, the pole is generally a point on the ground, which is the center point. In perception, it is generally a line segment with two endpoints, the lower endpoint is on the ground, and the lower endpoint is taken as the center point.

[0101] Step S34, performing coordinate system conversion according to the map mark center point or the perception mark center point to obtain the map mark position or the perception mark position.

[0102] It should be noted that coordinate system transformation involves converting the center point of a map marker or a sensory marker from one coordinate system to another, usually in order to convert local or relative coordinates to global coordinates used by the Global Positioning System.

[0103] It is understandable that the coordinate system is transformed using the calculated center point to obtain the final position of the map mark or the perceived mark. The geometric center point of the perceived mark is transformed into the map coordinate system using the positioning pose, and then the distance from the geometric center point of the perceived mark to the geometric center point of the map mark is calculated. This includes transforming the center point from the vehicle's local coordinate system or other relative coordinate system to the global coordinate system to ensure global consistency and accuracy of the mark position.

[0104] Step S40, performing identifier matching according to the map identifier position, the perception identifier position, the geometric expression form of the map identifier, and the geometric expression form of the perception identifier to obtain an identifier matching result;

[0105] It should be noted that logo matching refers to comparing the logo data in the map with the logo data perceived by the vehicle sensors to confirm their consistency or difference in position and geometric expression. The logo matching result refers to the conclusion obtained after completing the logo matching, indicating which logos are consistent and which logos do not conform to the map data due to environmental changes or other factors. The matching result is used to guide whether it is necessary to update the map information or adjust the vehicle driving strategy.

[0106] It is understood that the sign positions and geometric expressions recorded in the map are compared in detail with the sign positions and geometric expressions perceived in real time by the vehicle sensors. This includes confirming whether the position and geometric expression of a stop sign on the map are consistent with the stop sign perceived in real time. If there is a difference, such as the perceived sign position or geometric expression does not match that on the map, the sign matching result classifies this information as a mismatch. The matching and mismatching results help the vehicle decide whether a map data update or other navigation adjustment measures are needed to ensure the safety and accuracy of vehicle driving.

[0107] In a feasible implementation, step S40 may include steps S41 to S45:

[0108] Step S41, performing a position comparison based on the perception mark position and the map mark position to obtain a position comparison result;

[0109] It should be noted that the position comparison result is obtained by comparing the perceived marker position with the map marker position, and is used to display the relative position relationship between the two, such as complete match, close or mismatch.

[0110] It is understood that the perceived marker position is directly compared with the map marker position, and the distance or position difference between the two is calculated to obtain a position comparison result. This result is used to preliminarily determine whether the marker may need to be updated or revised.

[0111] Step S42, obtaining an unmatched map marker position according to the position comparison result, and recording a marker matching result as deletion according to the unmatched map marker position;

[0112] It should be noted that the unmatched map marker position refers to the position of the map marker that is found in the position comparison and does not correspond to the perception marker.

[0113] It is understandable that, based on the position comparison result, if a map identifier does not match any perception identifier, the position of the map identifier is recorded as unmatched, and the identifier matching result is marked as requiring deletion.

[0114] In a feasible implementation, step S42 may include steps S421 to S424:

[0115] Step S421, obtaining the current vehicle position, a preset longitudinal threshold, and a preset lateral threshold;

[0116] It should be noted that the current vehicle position refers to the geographic location of the vehicle at a specific point in time determined by its global positioning system (GPS) or other positioning technology. The preset longitudinal threshold is a pre-set maximum acceptable distance error in the longitudinal direction, that is, the vehicle's forward direction, and is used to determine whether two logos are within a reasonable update or matching range. The preset lateral threshold is a system-set maximum acceptable distance error in the lateral direction, that is, the left and right directions of the vehicle, and is also used to evaluate the matching of the logo position or the need for adjustment.

[0117] In this embodiment, the preset longitudinal threshold may be 15 m, and the preset lateral threshold may be 3 m.

[0118] Step S422, identifying the map identifier that is not associated with the perception identifier according to the position comparison result, and obtaining the position of the unmatched position identifier;

[0119] It should be noted that the map marker without associated perception marker refers to a map marker that is found to have no corresponding perception marker during the position comparison process, that is, a marker that is not detected by the sensor in the actual environment but exists on the map.

[0120] It is understood that based on the position comparison result, those marks that exist on the map but are not detected by the perception system of the current vehicle are identified. These marks are recorded as map marks that are not associated with perception marks for further processing.

[0121] Step S423, obtaining an unmatched distance according to the unmatched position identification position and the current vehicle position;

[0122] It should be noted that the unmatched distance refers to the actual physical distance between the current vehicle position and the unmatched position marker position. This distance is used to further determine whether the map marker needs to be updated or deleted.

[0123] It can be understood that the actual distance between the current vehicle position and the position of the unmatched position identifier is calculated, that is, the unmatched distance.

[0124] Step S424: when the unmatched distance is less than the preset longitudinal threshold or the preset lateral threshold, the identification matching result is recorded as deletion according to the unmatched map identification position.

[0125] It is understood that if the calculated unmatched distance is less than the preset longitudinal or lateral threshold, the matching result of the unmatched position marker is recorded as needing to be deleted. Indicates that the actual position of the map marker is close to the current position of the vehicle, but is not confirmed by the perception system, which may indicate that the map marker no longer exists or is wrong and needs to be deleted from the map, thereby ensuring that the vehicle's navigation map is kept up to date and reflects the actual road conditions, thereby improving navigation accuracy and driving safety.

[0126] For example, if an identification element in the map is not associated with any perceived identification element, and this identification element is within the longitudinal threshold and lateral threshold from the vehicle's position, the longitudinal direction of the vehicle is within 15 meters from the front and rear of the vehicle, and the left and right direction of the vehicle is within 3 meters, then it is considered that the map has an extra identification element and needs to be deleted, and the ID of this map identification element is recorded.

[0127] Step S43, when the position comparison result is less than or equal to the preset association distance, compare the geometric expression form of the map mark and the geometric expression form of the perception mark to obtain a first comparison result;

[0128] It should be noted that the preset association distance is the maximum acceptable distance limit between two identifiers set by the system, which is used to determine whether the two identifiers are close enough to be considered a match. In this embodiment, the preset association distance is 2 meters. The first comparison result is the result obtained by further comparing the geometric expressions of the identifiers based on the proximity of the positions, and is used to determine whether the two identifiers also match in terms of geometric expression.

[0129] It is understood that if the position comparison result shows that the distance between the two marks is less than or equal to the preset correlation distance, the system will further compare their geometric expressions. This step is to confirm whether the functions or geometric expressions of the marks are consistent in addition to the positions.

[0130] Step S44, when the first comparison result is a preset matching result, recording the matching result of the identification as modification;

[0131] It should be noted that the preset matching result is a preset standard, indicating that the geometric expression form is inconsistent.

[0132] It is understandable that if the first comparison result shows that the geometric expression does not match consistently, the identification matching result is recorded as modified, indicating that the identification position or details on the map need to be updated based on the perception data.

[0133] In addition, when the position comparison result is less than or equal to the preset association distance, the geometric expression of the map identifier and the geometric expression of the perception identifier are compared to obtain a second comparison result; when the second comparison result is a second preset matching result, the identifier matching result is recorded as a successful match.

[0134] In addition, it should be noted that the second comparison result is the result obtained by further comparing the geometric expressions of the marks based on the proximity of the positions, and is also used to determine whether the two marks also match in terms of geometric expressions. The second preset matching result indicates a successful match. That is, if the positions are close and the geometric expressions match successfully, this map mark does not need to be modified.

[0135] For example, if the position of a perceived identification element can be matched, but the type cannot be matched, it is considered that the type of the map identification element has changed and needs to be modified, and the ID of this map identification element is recorded.

[0136] Step S45: when the position comparison result is greater than the preset association distance, the record identification matching result is newly added.

[0137] It is understandable that if the position comparison result shows that the distance between two markers is greater than the preset association distance, it indicates that the perceived marker has no corresponding position on the map. This situation is recorded as a new addition, indicating that a new marker needs to be added to the map to reflect changes in the actual environment.

[0138] For example, if the position of a perceived identification element does not match, it is considered that the map is missing this identification element and needs to be added, and the ID of this perceived identification element is recorded.

[0139] Step S50: detecting map marker changes according to the marker matching result.

[0140] It should be noted that detecting map marker changes refers to the process of updating the navigation map based on the marker matching results to reflect changes in the actual environment. This involves modifying the marker positions in the map database, adding new markers, or deleting markers that no longer exist, ensuring the accuracy and up-to-dateness of the map information.

[0141] It is understood that if the geometric expression and position of the perceived mark do not match any mark in the map data, the new mark will be added to the map. If the perceived mark partially matches the mark in the map, but there are minor position or geometric expression differences, the details of the corresponding mark in the map will be updated. If a mark in the map no longer exists in the actual environment, it will be deleted from the map.

[0142] In addition, obtain the multi-frame change threshold and the unique identifier of the map identifier corresponding to the current identifier matching result; count whether there are multi-frame changes based on the unique identifier to obtain a multi-frame change statistical result; when the multi-frame change statistical result is greater than the multi-frame change threshold, send the current identifier matching result to the cloud.

[0143] The change of the identification element is recorded based on the unique identifier, i.e., ID. If the change of an identification element exceeds five consecutive frames, it is considered that the identification element has changed significantly, and the change information is reported accordingly. After reporting, possible measures include adding, modifying, or deleting the changed identification element, or remodeling the changed area. If the number of consecutive change frames does not reach the threshold, no change report is performed.

[0144] In addition, it should be noted that if this embodiment is used on the vehicle side, it is necessary to upload sensor data within a period of time before and after the change point. In this embodiment, the period of time before and after the change point can be 1 minute. This embodiment can also be directly used in the cloud. If this embodiment is used in the cloud, it is directly necessary to add, modify or delete the change identification element, or remodel the change area.

[0145] In a feasible implementation, step S50 may include steps S51 to S54:

[0146] Step S51, when the identification matching result is deletion, deleting the map identification corresponding to the identification matching result according to the map information, and obtaining a first update result;

[0147] It should be noted that the first update result is the update status obtained after executing the deletion operation when the mark matching result is "delete", which shows which marks in the map have been successfully removed.

[0148] It is understandable that, when it is determined that a mark needs to be deleted, a deletion operation will be performed based on the map data to remove the map marks that are no longer accurate or no longer exist. After this operation is completed, the first update result is obtained, which reflects the latest status of which marks in the map have been deleted.

[0149] Step S52, when the identification matching result is modification, modifying the map identification position according to the map information and the perceived identification position corresponding to the identification matching result, to obtain a second update result;

[0150] It should be noted that the second update result is the result obtained after adjusting the map marker position according to the actual perception data when the marker matching result indicates "modify", and displays the modified map status.

[0151] It is understood that if a marker needs to be repositioned, the corresponding marker position in the map will be updated based on the perceived marker position. This usually occurs when there is a deviation between the actual position of the existing map marker and the position perceived by the vehicle. After the modification operation is completed, the second update result will show all the markers with adjusted positions.

[0152] Step S53, when the identification matching result is newly added, according to the perceived identification position and the geometric expression form of the perceived identification corresponding to the identification matching result, a map identification is added to the map information to obtain a third update result;

[0153] It should be noted that the third update result is the result obtained after adding a new identifier to the map information when the identifier matching result indicates "newly added", which reflects the situation of the newly added identifier in the map.

[0154] It is understood that for newly added signs, new signs will be added to the map based on the location and geometric expression of the perceived signs. This is usually because new signs or signs that were not previously recorded in the map data are discovered during actual driving. After adding new signs, the third update result will include the details of all new signs added to the map.

[0155] Step S54: detecting a map mark change according to any one of the first update result, the second update result, and the third update result.

[0156] It can be understood that rebuilding the map environment based on any one or all of the first, second and third update results can ensure the overall consistency and accuracy of the map data and provide accurate navigation support for the vehicle.

[0157] This embodiment provides a map marker change detection method, which integrates the sensor data and map information of the autonomous driving vehicle, uses image recognition and data analysis technology to match and update the perception markers in the vehicle's surrounding environment and the map markers in the map database. This process solves the problem that map data in traditional navigation systems lags behind changes in actual road conditions, ensuring the accuracy and timeliness of navigation data. By updating map information in real time, the navigation accuracy of autonomous driving vehicles can be effectively improved, driving safety can be enhanced, and more reliable data support can be provided for driving decisions, thereby achieving the technical effect of keeping the navigation system information up to date and most accurate in a dynamically changing road environment.

[0158] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 2 The step S10 of the map marker change detection method includes steps S11 to S13:

[0159] Step S11, obtaining a first preset detection range and a second preset detection range, wherein the first preset detection range is larger than the second preset detection range;

[0160] It should be noted that the first preset detection range is a larger detection area set according to the current position of the vehicle to obtain map markers, which is used to retrieve markers from map information. The first preset detection range usually covers a wider area of ​​the current position of the vehicle to ensure that all markers on the map that may affect driving decisions are captured. The second preset detection range: a relatively small detection area, which is the range that the sensor can detect, is used to identify and confirm the actual existence of markers in the vehicle's surrounding environment.

[0161] Step S12, obtaining a map identifier according to the current position of the vehicle, the first preset detection range and the map information;

[0162] It is understandable that using map information to retrieve corresponding map identifiers based on the vehicle's current position and the first preset detection range can ensure that the vehicle can obtain necessary navigation information from the map data and predict identifier information on possible driving paths.

[0163] Step S13: obtaining a perception identifier according to the second preset detection range and sensor data.

[0164] It can be understood that by identifying the perception signs in the direct surrounding environment of the vehicle through the second preset detection range and the vehicle's sensor data, more accurate environmental information that affects immediate driving decisions can be captured.

[0165] This embodiment provides a map mark change detection method, which retrieves marks from map information by setting a larger first preset detection range, and accurately identifies the actual environmental marks around the vehicle by combining a smaller second preset detection range with sensor data. This method solves the problem of insufficient fusion of map data and real-time environmental data in autonomous driving vehicles in complex or dynamically changing traffic environments. The implementation of this technical means enables the autonomous driving system to more accurately identify and respond to instant road condition changes, improves navigation accuracy and vehicle driving safety, and achieves rapid adaptation to environmental changes and more accurate driving decision support.

[0166] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the map identification change detection method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.

[0167] This application also provides a map mark change detection device, please refer to Figure 3 , the map mark change detection device comprises:

[0168] A perception identification acquisition module 10, used to acquire a perception identification according to sensor data, and to acquire a map identification according to map information;

[0169] The perception identification acquisition module 10 is further used to obtain a geometric expression form of the map identification and a geometric expression form of the perception identification according to the map identification and the perception identification;

[0170] A marker position calculation module 20, used to calculate the map marker position according to the geometric expression form of the map marker, and calculate the perceived marker position according to the geometric expression form of the perceived marker;

[0171] The identification matching module 30 is used to perform identification matching according to the map identification position, the perception identification position, the geometric expression form of the map identification and the geometric expression form of the perception identification to obtain an identification matching result;

[0172] The marker change detection module 40 is used to detect map marker changes according to the marker matching result.

[0173] The map marker change detection device provided by the present application adopts the map marker change detection method in the above embodiment, which can solve the technical problem that the traditional map marker change detection technology is difficult to quickly detect and update dynamically changing road signs. Compared with the prior art, the beneficial effects of the map marker change detection device provided by the present application are the same as the beneficial effects of the map marker change detection method provided by the above embodiment, and the other technical features of the map marker change detection device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0174] In one embodiment, the identifier matching module 30 is further used to perform a position comparison based on the perceived identifier position and the map identifier position to obtain a position comparison result; based on the position comparison result, an unmatched map identifier position is obtained, and according to the unmatched map identifier position, the identifier matching result is recorded as deletion; when the position comparison result is less than or equal to a preset association distance, the geometric expression form of the map identifier and the geometric expression form of the perceived identifier are compared to obtain a first comparison result; when the first comparison result is a preset matching result, the identifier matching result is recorded as modification; when the position comparison result is greater than the preset association distance, the identifier matching result is recorded as addition.

[0175] In one embodiment, the identification matching module 30 is also used to obtain the current vehicle position, a preset longitudinal threshold and a preset lateral threshold; based on the position comparison result, identify the map identification of the unassociated perception identification to obtain the unmatched position identification position; obtain the unmatched distance based on the unmatched position identification position and the current vehicle position; when the unmatched distance is less than the preset longitudinal threshold or the preset lateral threshold, record the identification matching result as deleted according to the unmatched map identification position.

[0176] In one embodiment, the identification change detection module 40 is also used to, when the identification matching result is deletion, delete the map identification corresponding to the identification matching result according to the map information, and obtain a first update result; when the identification matching result is modification, modify the map identification position according to the map information and the perceived identification position corresponding to the identification matching result, and obtain a second update result; when the identification matching result is addition, add the map identification to the map information according to the perceived identification position corresponding to the identification matching result and the geometric expression of the perceived identification, and obtain a third update result; detect the map identification change according to any one of the first update result, the second update result and the third update result.

[0177] In one embodiment, the marker position calculation module 20 is also used to calculate the center point of the map marker or the center point of the perception marker according to the first border of the map marker or the perception marker when the geometric expression form of the map marker or the perception marker is a ground marker; when the geometric expression form of the map marker or the perception marker is an aerial marker, project the map marker or the perception marker to obtain a second border, and calculate the center point of the map marker or the perception marker according to the second border; when the geometric expression form of the map marker or the perception marker is a cylindrical marker, obtain the center point of the map marker or the perception marker according to the ground point of the map marker or the perception marker; perform coordinate system conversion according to the center point of the map marker or the perception marker to obtain the map marker position or the perception marker position.

[0178] In one embodiment, the perception identification acquisition module 10 is also used to identify the location characteristics and image characteristics of the map identification or the perception identification; when the location characteristic is a ground element, the geometric expression form of the map identification or the geometric expression form of the perception identification is identified as a ground identification; when the location characteristic is an aerial element, the geometric expression form of the map identification or the geometric expression form of the perception identification is identified as an aerial identification; when the image characteristic is a cylindrical element, the geometric expression form of the map identification or the geometric expression form of the perception identification is identified as a cylindrical identification.

[0179] In one embodiment, the perception identification acquisition module 10 is also used to obtain a first preset detection range and a second preset detection range, wherein the first preset detection range is larger than the second preset detection range; a map identification is obtained according to the current position of the vehicle, the first preset detection range and map information; and a perception identification is obtained according to the second preset detection range and sensor data.

[0180] The present application provides a map marker change detection device, which includes: 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 so that the at least one processor can execute the map marker change detection method in the above-mentioned embodiment one.

[0181] Reference below Figure 4 , which shows a schematic diagram of the structure of a map mark change detection device suitable for implementing the embodiment of the present application. The map mark change detection device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 4 The map marker change detection device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0182] like Figure 4As shown, the map mark change detection device may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the map mark change detection device are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the map marker change detection device to communicate wirelessly or wired with other devices to exchange data. Although the map marker change detection device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0183] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0184] The map marker change detection device provided by the present application adopts the map marker change detection method in the above embodiment, which can solve the technical problem that the traditional map marker change detection technology is difficult to quickly detect and update dynamically changing road signs. Compared with the prior art, the beneficial effects of the map marker change detection device provided by the present application are the same as the beneficial effects of the map marker change detection method provided by the above embodiment, and the other technical features of the map marker change detection device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0185] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0186] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0187] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the map marker change detection method in the above-mentioned embodiment.

[0188] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0189] The computer-readable storage medium may be included in the map marker change detection device; or may exist independently without being assembled into the map marker change detection device.

[0190] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the map identification change detection device, the map identification change detection device is enabled to: obtain the perception identification according to the sensor data, and obtain the map identification according to the map information; obtain the geometric expression form of the map identification and the geometric expression form of the perception identification according to the map identification and the perception identification; calculate the map identification position according to the geometric expression form of the map identification, and calculate the perception identification position according to the geometric expression form of the perception identification; perform identification matching according to the map identification position, the perception identification position, the geometric expression form of the map identification and the geometric expression form of the perception identification to obtain an identification matching result; and detect the map identification change according to the identification matching result.

[0191] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0192] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0193] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0194] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned map mark change detection method, and can solve the technical problem that the traditional map mark change detection technology is difficult to quickly detect and update dynamically changing road marks. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the map mark change detection method provided by the above-mentioned embodiment, and will not be repeated here.

[0195] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned map marker change detection method when executed by a processor.

[0196] The computer program product provided by the present application can solve the technical problem that the traditional map mark change detection technology is difficult to quickly detect and update the dynamically changing road marks. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the map mark change detection method provided by the above embodiment, and will not be repeated here.

[0197] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A map marker change detection method, characterized in that: The method comprises: Obtaining a perception identifier based on the sensor data and obtaining a map identifier based on the map information; According to the map identifier and the perception identifier, a geometric expression form of the map identifier and a geometric expression form of the perception identifier are obtained; Calculating a map marker position according to a geometric expression of the map marker, and calculating a perceived marker position according to a geometric expression of the perceived marker; Performing identification matching according to the map identification position, the perception identification position, the geometric expression form of the map identification, and the geometric expression form of the perception identification to obtain an identification matching result; A map marker change is detected according to the marker matching result.

2. The method according to claim 1, characterized in that The step of performing identifier matching according to the map identifier position, the perception identifier position, the geometric expression form of the map identifier, and the geometric expression form of the perception identifier to obtain the identifier matching result comprises: Performing a position comparison based on the perception mark position and the map mark position to obtain a position comparison result; According to the position comparison result, an unmatched map marker position is obtained, and according to the unmatched map marker position, a marker matching result is recorded as deletion; When the position comparison result is less than or equal to the preset association distance, comparing the geometric expression form of the map mark and the geometric expression form of the perception mark to obtain a first comparison result; When the first comparison result is a preset matching result, the matching result of the record identification is modified; When the position comparison result is greater than the preset association distance, the record identification matching result is newly added.

3. The method according to claim 2, characterized in that The step of obtaining the unmatched map marker position according to the position comparison result, and recording the marker matching result as deletion according to the unmatched map marker position comprises: Obtaining the current vehicle position, a preset longitudinal threshold, and a preset lateral threshold; According to the position comparison result, identifying the map identifier that is not associated with the perception identifier, and obtaining the position of the unmatched position identifier; Obtaining an unmatched distance according to the unmatched position identification position and the current vehicle position; When the unmatched distance is smaller than the preset longitudinal threshold or the preset lateral threshold, the identification matching result is deleted according to the unmatched map identification position record.

4. The method according to claim 1, characterized in that The step of detecting a map identifier change according to the identifier matching result comprises: When the identification matching result is deletion, deleting the map identification corresponding to the identification matching result according to the map information, and obtaining a first update result; When the identification matching result is modification, modifying the map identification position according to the map information and the perceived identification position corresponding to the identification matching result to obtain a second update result; When the identification matching result is newly added, according to the perceived identification position and the geometric expression form of the perceived identification corresponding to the identification matching result, a map identification is added to the map information to obtain a third update result; A map mark change is detected according to any one of the first update result, the second update result, and the third update result.

5. The method according to claim 1, characterized in that The step of calculating the map marker position according to the geometric expression form of the map marker and calculating the perceived marker position according to the geometric expression form of the perceived marker comprises: When the geometric expression form of the map mark or the geometric expression form of the perception mark is a ground mark, the center point of the map mark or the center point of the perception mark is calculated according to the first frame of the map mark or the perception mark; When the geometric expression form of the map mark or the geometric expression form of the perception mark is an aerial mark, projecting according to the map mark or the perception mark to obtain a second frame, and calculating the center point of the map mark or the perception mark according to the second frame; When the geometric expression form of the map mark or the geometric expression form of the perception mark is a cylindrical mark, obtaining the center point of the map mark or the perception mark according to the grounding point of the map mark or the perception mark; A coordinate system conversion is performed according to the map mark center point or the perception mark center point to obtain the map mark position or the perception mark position.

6. The method according to claim 1, characterized in that The step of obtaining the geometric expression form of the map identifier and the geometric expression form of the perception identifier according to the map identifier and the perception identifier comprises: Identify the location features and image features of the map mark or the sensory mark; When the location feature is a ground element, identifying the geometric expression form of the map identifier or the geometric expression form of the perception identifier as a ground identifier; When the location feature is an aerial element, identifying the geometric expression form of the map identifier or the geometric expression form of the perception identifier as an aerial identifier; When the image feature is a cylindrical element, it is recognized that the geometric expression form of the map mark or the geometric expression form of the perception mark is a cylindrical mark.

7. The method according to claim 1, characterized in that The step of acquiring the perception identifier according to the sensor data and acquiring the map identifier according to the map information includes: Acquire a first preset detection range and a second preset detection range, wherein the first preset detection range is larger than the second preset detection range; Obtaining a map identifier according to the current position of the vehicle, the first preset detection range, and the map information; A perception identifier is obtained according to the second preset detection range and the sensor data.

8. A map mark change detection device, characterized in that: The device comprises: A perception identification acquisition module, used to acquire a perception identification according to sensor data, and to acquire a map identification according to map information; The perception identifier acquisition module is further used to obtain a geometric expression form of the map identifier and a geometric expression form of the perception identifier according to the map identifier and the perception identifier; A marker position calculation module, used to calculate the map marker position according to the geometric expression form of the map marker, and calculate the perceived marker position according to the geometric expression form of the perceived marker; A logo matching module, used to perform logo matching according to the map logo position, the perception logo position, the geometric expression form of the map logo and the geometric expression form of the perception logo, to obtain a logo matching result; The identification change detection module is used to detect map identification changes according to the identification matching results.

9. A map mark change detection device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the map marker change detection method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the map marker change detection method according to any one of claims 1 to 7 are implemented.

Images