Map precision control method, high-precision map generation method, device and equipment

Abstract

This disclosure relates to a method for controlling map accuracy, a method for generating high-precision maps, an apparatus, and equipment. This disclosure obtains multiple trajectories within the same road surface area and a standard trajectory corresponding to that road surface area. The standard trajectory is used to align different trajectories within the road surface area, obtaining the alignment accuracy of different trajectories. Then, target trajectories that meet the alignment accuracy requirements are selected, thus controlling the trajectory alignment accuracy. A first vector of the map elements associated with the target trajectory and a second vector obtained after adjusting the first vector are obtained. Vector matching is used to obtain the vector adjustment accuracy of the second vector. Finally, the accuracy of the second vector that does not meet the preset vector adjustment accuracy requirements is controlled, thus controlling the vector adjustment accuracy. Therefore, this disclosure, through the control of trajectory alignment accuracy and vector adjustment accuracy, allows the accuracy of the second vector used to generate the map to be controlled, thereby achieving map accuracy control.

Description

Technical Field

[0001] This disclosure relates to the field of map technology, specifically to a method for controlling map accuracy, a method for generating high-precision maps, an apparatus, a device, and a computer program product. Background Technology

[0002] High-precision maps are the infrastructure for navigation in intelligent driving vehicles. Accuracy is a crucial factor affecting the quality of high-precision maps; therefore, it is necessary to control their accuracy. Currently, target points are mainly used for accuracy control. However, target points are obtained manually by marking points on-site using laser total stations, which can output the actual coordinates of the target points. Therefore, increasing the number of target points would increase labor costs; furthermore, some scenarios are not suitable for marking points, such as highways, where safety risks exist, and the coverage area for map accuracy control using only target points is limited. Summary of the Invention

[0003] At least one embodiment of this disclosure provides a method for controlling map accuracy, a method for generating high-precision maps, an apparatus, a device, a medium, and a computer program product.

[0004] In a first aspect, embodiments of this disclosure propose a method for controlling map accuracy, the method comprising:

[0005] Obtain multiple trajectories within the same road surface area and the standard trajectory corresponding to the road surface area;

[0006] Align at least one trajectory within the road surface area to a standard trajectory, determine the alignment accuracy corresponding to at least one trajectory, and identify the target trajectory in at least one trajectory whose alignment accuracy is greater than or equal to a preset alignment accuracy threshold.

[0007] Obtain a first vector of at least one map element associated with the target trajectory and a second vector obtained after adjusting the first vector, and perform vector matching on the first and second vectors to determine the vector adjustment accuracy of the second vector;

[0008] Precision control is applied to the second vector whose vector adjustment precision is greater than the preset vector adjustment precision threshold.

[0009] In some embodiments, before obtaining multiple trajectories encompassing the same road surface area, the method further includes:

[0010] Obtain the trajectories corresponding to multiple data collection operations targeting the target area;

[0011] Based on the road boundaries and start and end points included in the target area, at least one road surface range is determined.

[0012] In some embodiments, aligning at least one track within the road surface area to a standard track includes:

[0013] Obtain the original accuracy of each trajectory within the road surface area;

[0014] Align trajectories with original accuracy greater than or equal to a preset original accuracy threshold to the standard trajectory.

[0015] In some embodiments, aligning at least one trajectory within the road surface area to a standard trajectory, and determining the alignment accuracy corresponding to the at least one trajectory, includes:

[0016] Align at least one trajectory within the road surface area with the standard trajectory to obtain the positional difference between each trajectory point on the at least one trajectory and the corresponding point on the standard trajectory, as well as the variation range of adjacent positional differences.

[0017] Based on the position difference and the magnitude of change, determine the alignment accuracy corresponding to at least one trajectory included in the road surface range.

[0018] In some embodiments, obtaining a first vector of at least one map element associated with the target trajectory and a second vector obtained by adjusting the first vector includes:

[0019] Acquire the collected data corresponding to the target trajectory, and determine the first vector of at least one map element associated with the target trajectory based on the collected data;

[0020] Obtain the second vector obtained by adjusting the first vector of at least one map element.

[0021] In some embodiments, vector matching is performed on the first vector and the second vector to determine the vector adjustment accuracy of the second vector, including:

[0022] Perform vector matching on the first and second vectors to obtain the vector position difference and the magnitude of change of the vector position difference for each map element associated with the target trajectory.

[0023] The vector adjustment accuracy is determined based on the vector position difference and the magnitude of its change.

[0024] Secondly, this disclosure also proposes a high-precision map generation method, comprising: using the map precision control method described in any embodiment of the first aspect to determine a second vector whose vector adjustment precision is greater than or equal to a preset vector adjustment precision threshold; and generating a high-precision map based on the second vector whose vector adjustment precision is greater than or equal to the preset vector adjustment precision threshold.

[0025] Thirdly, embodiments of this disclosure also propose a map accuracy control device, which includes:

[0026] The acquisition unit is used to acquire multiple trajectories within the same road surface area and the standard trajectory corresponding to the road surface area.

[0027] The alignment unit is used to align at least one trajectory within the road surface area to a standard trajectory, determine the alignment accuracy corresponding to at least one trajectory, and determine the target trajectory in the at least one trajectory whose alignment accuracy is greater than or equal to a preset alignment accuracy threshold.

[0028] The vector matching unit is used to acquire a first vector of at least one map element associated with the target trajectory and a second vector obtained by adjusting the first vector, and to perform vector matching on the first vector and the second vector to determine the vector adjustment accuracy of the second vector.

[0029] The control unit is used to control the accuracy of a second vector whose vector adjustment accuracy is less than a preset vector adjustment accuracy threshold.

[0030] Fourthly, this disclosure also proposes a high-precision map generation device, which is used to: determine a second vector with a vector adjustment precision greater than or equal to a preset vector adjustment precision threshold using the map precision control method described in any embodiment of the first aspect; and generate a high-precision map based on the second vector with a vector adjustment precision greater than or equal to the preset vector adjustment precision threshold.

[0031] Fifthly, embodiments of this disclosure also provide an electronic device, which includes a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the map accuracy control method as described in any embodiment of the first aspect or the steps of the high-precision map generation method as described in the second aspect.

[0032] In a sixth aspect, embodiments of this disclosure also provide a computer-readable storage medium, wherein the computer-readable storage medium stores a program or instructions that cause a computer to perform steps of the map accuracy control method as described in any embodiment of the first aspect or the high-precision map generation method as described in the second aspect.

[0033] In a seventh aspect, embodiments of this disclosure also provide a computer program product comprising computer instructions, wherein, when executed by a processor, the computer instructions implement the steps of the map accuracy control method as described in any embodiment of the first aspect or the steps of the high-precision map generation method as described in the second aspect.

[0034] As can be seen, in at least one embodiment of this disclosure, by acquiring multiple trajectories within the same road surface area and a standard trajectory corresponding to the road surface area, the standard trajectory is used to align different trajectories within the road surface area, thereby obtaining the alignment accuracy of different trajectories; then, target trajectories that meet the alignment accuracy requirements are selected, thus controlling the trajectory alignment accuracy; thereby, a first vector of the map element associated with the target trajectory and a second vector obtained after adjusting the first vector are acquired, and the vector adjustment accuracy of the second vector is obtained through vector matching; finally, the accuracy of the second vector that does not meet the preset vector adjustment accuracy requirements is controlled, thereby controlling the vector adjustment accuracy. It is evident that this disclosure, through the control of trajectory alignment accuracy and vector adjustment accuracy, enables the control of the accuracy of the second vector used to generate the map, thereby achieving map accuracy control. Attached Figure Description

[0035] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings.

[0036] Figure 1 A flowchart illustrating one embodiment of the map accuracy control method provided in this disclosure;

[0037] Figure 2 A schematic flowchart of another embodiment of the map accuracy control method provided in this disclosure;

[0038] Figure 3 A schematic diagram of a map accuracy control device provided in an embodiment of this disclosure;

[0039] Figure 4 This is an exemplary block diagram of an electronic device provided in an embodiment of the present disclosure. Detailed Implementation

[0040] To better understand the above-described objectives, features, and advantages of this disclosure, the present disclosure will be further described in detail below with reference to the accompanying drawings and embodiments. It is to be understood that the described embodiments are only some, not all, of the embodiments of this disclosure. The specific embodiments described herein are merely for explaining this disclosure and are not intended to limit it. All other embodiments obtained by those skilled in the art based on the described embodiments of this disclosure are within the scope of protection of this disclosure.

[0041] It should be noted that in this article, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0042] In related technologies, high-precision maps are mainly obtained by extracting and editing map features from point clouds and images collected by mobile measurement systems (such as vehicles equipped with lidar and image acquisition devices). Lidar equipment, for example, is a laser scanning device (Lidar). The laser pulses emitted by the Lidar at preset intervals are reflected from the ground surface and objects on the ground (forming laser points), and a large number of points are combined to form a point cloud. Image acquisition equipment, for example, is a visible light camera.

[0043] In related technologies, target points are mainly used to control the accuracy of high-precision maps. Specifically, by acquiring the real coordinates of multiple target points and their map coordinates in the high-precision map, the real and map coordinates of each target point are compared to obtain the coordinate differences of each target point. The accuracy of the high-precision map is then determined using these coordinate differences. Various metrics can be used to measure accuracy, including but not limited to the acceptable percentage, standard deviation, and variance of the coordinate differences of each target point. Target points can be abrupt change points (e.g., vertices) at the boundaries of map elements. Map elements are the features used to construct high-precision maps. Types of map elements include, but are not limited to, ground elements such as directional arrows, lane lines, stop lines, and ground text, as well as ground elements such as signs and speedometers. For example, each vertex of a directional arrow can be a target point. However, since target points are obtained manually using a laser total station in the field, increasing the number of target points increases labor costs. Furthermore, some scenarios are not suitable for manual point marking, such as highways where safety risks exist, and the coverage area for map accuracy control using only target points is relatively small.

[0044] To reduce manual costs and improve the coverage of map accuracy control, at least one embodiment of this disclosure provides a method for controlling map accuracy, a method for generating high-precision maps, an apparatus, device, medium, or computer program product. This method involves acquiring multiple trajectories within the same road surface area and a standard trajectory corresponding to that area. The standard trajectory is then used to align different trajectories within the road surface area, obtaining the alignment accuracy of each trajectory. Target trajectories that meet the alignment accuracy requirements are then selected, thus controlling the trajectory alignment accuracy. A first vector of the map elements associated with the target trajectory and a second vector obtained after adjusting the first vector are then acquired. Vector matching is used to obtain the vector adjustment accuracy of the second vector. Finally, the accuracy of the second vector that does not meet the preset vector adjustment accuracy requirements is controlled, thus controlling the vector adjustment accuracy. Therefore, this disclosure controls the accuracy of the second vector used to generate the map by controlling the trajectory alignment accuracy and the vector adjustment accuracy, thereby achieving map accuracy control.

[0045] It should be noted that in some embodiments, the scheme of using target points to control map accuracy can be used together with the map accuracy control scheme provided in this disclosure to complement each other and further improve the control effect of map accuracy.

[0046] Figure 1 This is a flowchart illustrating a map accuracy control method provided in an embodiment of this disclosure. The method is executed by an electronic device. The electronic device includes, but is not limited to, smartphones, PDAs, tablets, wearable devices with displays, desktop computers, laptops, all-in-one computers, smart home devices, in-vehicle devices, and servers. The server can be a standalone server or a cluster of multiple servers, and can include locally located servers and cloud-based servers.

[0047] like Figure 1 As shown, the method for controlling the map accuracy may include, but is not limited to, steps 101 to 104:

[0048] In step 101, multiple trajectories within the same road surface range and the standard trajectory corresponding to the road surface range are obtained.

[0049] For the target area (which can be understood as the area where a map is to be created or updated, and can be a manually defined area), a mobile measurement system (such as a vehicle equipped with lidar equipment and image acquisition equipment) collects point clouds and images within the target area, and records the trajectory of the mobile measurement system during this acquisition operation through the positioning system (such as an inertial navigation system). The trajectory consists of multiple trajectory points (which can be understood as coordinate points).

[0050] Since the data collected in a single data acquisition operation (including point cloud and image) is insufficient to generate a map, in some embodiments, multiple data acquisition operations are performed on the target. Accordingly, each data acquisition operation yields data and the trajectory of the moving measurement system.

[0051] For a target area, different road surface ranges can be pre-determined based on road network information. For example, uphill and downhill roads have different road surface ranges, and main roads and auxiliary roads have different road surface ranges. A road surface range can be understood as the area formed by the starting and ending points of the road and the road boundaries (e.g., polygons such as rectangles, parallelograms, etc.). The road boundaries include, for example, road curbs, fences, and boundary lane lines.

[0052] After determining the different road surface ranges included in the target area, the trajectory corresponding to multiple data collection operations of the mobile measurement system for the same road surface range can be obtained. The standard trajectory corresponding to the road surface range can be obtained. The standard trajectory can be understood as the expected travel trajectory of the mobile measurement system when carrying out data collection operations on the road surface range.

[0053] In step 102, at least one trajectory within the road surface area is aligned with a standard trajectory, the alignment accuracy corresponding to at least one trajectory is determined, and a target trajectory with an alignment accuracy greater than or equal to a preset alignment accuracy threshold is identified within the at least one trajectory.

[0054] For the same road surface area, considering that the trajectory points collected by the positioning system in the mobile measurement system cannot all be points on the standard trajectory during each data collection operation, and there is a certain distance deviation, in this disclosure example, at least one trajectory included in the road surface area is aligned with the standard trajectory. Alignment can be understood as assigning a certain correction amount to the collected trajectory points so that the corrected trajectory points are located on the standard trajectory.

[0055] By aligning at least one trajectory within the road surface area with the standard trajectory, the positional difference (i.e., correction amount) between each trajectory point on the at least one trajectory and the corresponding point on the standard trajectory can be obtained, and the variation range of adjacent positional differences (i.e., the difference between adjacent positional differences) can be determined.

[0056] For a trajectory encompassed by the road surface, the alignment accuracy of that trajectory can be determined based on the variation range of the correction values ​​at each trajectory point and adjacent correction values. Alignment accuracy can be considered a statistical result of the variation range of the correction values ​​and adjacent correction values. For example, alignment accuracy includes absolute alignment accuracy and relative alignment accuracy. Absolute alignment accuracy is inversely proportional to the standard deviation or variance of the correction values ​​at each trajectory point; that is, the smaller the standard deviation of the correction values, the greater the absolute alignment accuracy. Similarly, relative alignment accuracy is inversely proportional to the standard deviation or variance of the variation range of adjacent correction values; that is, the smaller the standard deviation of the variation range of adjacent correction values, the greater the relative alignment accuracy. In some embodiments, the absolute alignment accuracy is the proportion of trajectory points whose correction amount is less than or equal to a preset correction amount threshold. For example, if there are 10 correction amounts and 3 of them are greater than or equal to the preset correction amount threshold, the absolute alignment accuracy is 0.7. The relative alignment accuracy is the proportion of adjacent correction amounts whose change amplitude is less than or equal to a preset change amplitude threshold. For example, if there are 10 correction amounts and the change amplitude of adjacent correction amounts is calculated, there are a total of 9 change amplitudes. If 3 of them are greater than or equal to the preset change amplitude threshold, the relative alignment accuracy is 2 / 3.

[0057] After determining the alignment accuracy of at least one trajectory within the road surface area, a target trajectory with an alignment accuracy greater than or equal to a preset alignment accuracy threshold can be identified from among the at least one trajectory. This means that target trajectories meeting the alignment accuracy requirements are selected, indicating that the target trajectory is of good quality, thus achieving control over trajectory alignment accuracy. For example, for a trajectory within the road surface area, the alignment accuracy corresponding to this trajectory includes absolute alignment accuracy and relative alignment accuracy. If the absolute alignment accuracy is greater than or equal to a preset absolute alignment accuracy threshold and the relative alignment accuracy is greater than or equal to a preset relative alignment accuracy threshold, then this trajectory is determined to be the target trajectory.

[0058] In step 103, a first vector of at least one map element associated with the target trajectory and a second vector obtained after adjusting the first vector are obtained, and vector matching is performed on the first vector and the second vector to determine the vector adjustment accuracy of the second vector.

[0059] After determining the target trajectory, the first vector of at least one map element associated with the target trajectory can be obtained. For example, the collected data corresponding to the target trajectory can be obtained, which consists of point clouds and images collected by the mobile surveying system during the data collection operation. Then, based on the collected data, at least one map element associated with the target trajectory can be determined. Determining map elements from collected data is a mature technology in the field of mapping and will not be elaborated further. Then, the first vector of the map element can be obtained through map element vectorization recognition technology. The first vector can be understood as the edge shape of the map element. For example, the map element of a road sign can be vectorized to obtain the vector of the road sign shape. Map element vectorization is a routine operation in the field of mapping and will not be elaborated further.

[0060] After obtaining a first vector of at least one map element, a second vector can be obtained by adjusting the first vector. For example, the first vector can be provided to a professional technician, who can then adjust the first vector to obtain the second vector.

[0061] After obtaining the first and second vectors of the same map element, vector matching is performed on the first and second vectors. Vector matching can not only determine whether the first and second vectors belong to the same map element, but also determine the vector position difference between the first and second vectors. This allows us to obtain the vector position difference corresponding to each map element associated with the target trajectory, and also determine the variation range of the vector position difference between different map elements (e.g., the difference between adjacent vector position differences).

[0062] Based on the vector position difference and the magnitude of change of each map element associated with the target trajectory, the vector adjustment accuracy can be determined. Vector adjustment accuracy can be considered as the statistical result of the vector position difference and the magnitude of change of the vector position difference. For example, vector adjustment accuracy includes absolute vector adjustment accuracy and relative vector adjustment accuracy. The absolute vector adjustment accuracy is inversely proportional to the standard deviation or variance of the vector position difference associated with each map element associated with the target trajectory. That is, the smaller the standard deviation of the vector position difference, the greater the absolute vector adjustment accuracy. The relative vector adjustment accuracy is inversely proportional to the standard deviation or variance of the magnitude of change of the vector position difference. That is, the smaller the standard deviation of the magnitude of change of the vector position difference, the greater the relative alignment accuracy. In some embodiments, the absolute vector adjustment accuracy is the proportion of vector position differences that are less than or equal to a preset vector position difference threshold. For example, if there are 10 vector position differences and 3 of them are greater than or equal to the preset vector position difference threshold, then the absolute vector adjustment accuracy is 0.7. The relative vector adjustment accuracy is the proportion of vector position difference changes that are less than or equal to a preset change range threshold. For example, if there are 10 vector position differences and the change range of adjacent vector position differences is calculated, there are a total of 9 change ranges. If 3 of them are greater than or equal to the preset change range threshold, then the relative vector adjustment accuracy is 2 / 3.

[0063] In step 104, precision control is performed on the second vector whose vector adjustment precision is less than the preset vector adjustment precision threshold.

[0064] Among them, the second vector whose vector adjustment accuracy is less than the preset vector adjustment accuracy threshold, that is, the second vector whose vector adjustment accuracy does not meet the vector adjustment accuracy requirements and is of poor quality, is subject to accuracy control. In some embodiments, accuracy control of the second vector whose vector adjustment accuracy is less than the preset vector adjustment accuracy threshold is, for example, by outputting the second vector for manual verification and visual viewing, thereby achieving control of vector adjustment accuracy.

[0065] As can be seen, this disclosure controls the accuracy of the second vector used to generate the map by controlling the trajectory alignment accuracy and the vector adjustment accuracy, thereby achieving map accuracy control.

[0066] Based on the above embodiments, Figure 2 Another embodiment of the map accuracy control method provided in this disclosure may include, but is not limited to, the following steps 201 to 211:

[0067] In step 201, the trajectories corresponding to multiple data collection operations targeting the target area are obtained.

[0068] For the target area (which can be understood as the area where a map is to be created or updated, and can be a manually defined area), a mobile measurement system (such as a vehicle equipped with lidar equipment and image acquisition equipment) collects point clouds and images within the target area, and records the trajectory of the mobile measurement system during this acquisition operation through the positioning system (such as an inertial navigation system). The trajectory consists of multiple trajectory points (which can be understood as coordinate points).

[0069] Since the data collected in a single data acquisition operation (including point cloud and image) is insufficient to generate a map, multiple data acquisition operations are performed on the target. Accordingly, each data acquisition operation will yield the acquired data and the trajectory of the mobile measurement system.

[0070] In step 202, at least one road surface range is determined based on the road boundaries and road start and end locations included in the target area.

[0071] For a target area, different road surface ranges are determined based on road network information. For example, uphill and downhill roads are different road surface ranges, as are main roads and auxiliary roads. A road surface range can be understood as the area formed by the start and end points of the road and its boundaries (e.g., polygons such as rectangles or parallelograms). The road boundaries include, for example, curbs, fences, and lane markings.

[0072] In step 203, multiple trajectories within the same road surface range and the standard trajectory corresponding to the road surface range are obtained.

[0073] After determining the different road surface ranges included in the target area, the trajectory corresponding to multiple data collection operations of the mobile measurement system for the same road surface range can be obtained. The standard trajectory corresponding to the road surface range can be obtained. The standard trajectory can be understood as the expected travel trajectory of the mobile measurement system when carrying out data collection operations on the road surface range.

[0074] In step 204, the original accuracy of each trajectory within the same road surface range is obtained.

[0075] The positioning system in a mobile measurement system has a certain acquisition accuracy. While outputting the trajectory of the mobile measurement system, the positioning system can also output the original accuracy of the trajectory. The higher the value of the original accuracy, the better the quality of the trajectory.

[0076] In some embodiments, the original accuracy of the trajectory is determined based on the trajectory calculation error and the number of satellites associated with the trajectory. The trajectory calculation process is a conventional method in the field of positioning technology. For example, the positioning system records the heading, wheel speed, and other driving status information of the motion measurement system. In scenarios with weak satellite signals, such as caves, the positioning system combines the driving status information to calculate the position (i.e., coordinates) of the trajectory points. The trajectory calculation itself has a certain error, such as the standard deviation of each collected trajectory point. The positioning system outputs the trajectory calculation error and the number of satellites associated with the trajectory along with the trajectory output.

[0077] For example, the trajectory's state level is determined based on the duration of orientation stability, the trajectory's calculation error, and the number of satellites associated with the trajectory. The trajectory's state level can be divided into, for example, five levels, each corresponding to a different level of accuracy (i.e., raw accuracy). Each state level has thresholds for orientation stability duration, trajectory calculation error, and the number of satellites. Furthermore, the raw accuracy of the trajectory is determined based on its state level. A higher trajectory state level indicates better trajectory quality.

[0078] In step 205, the trajectory with original accuracy greater than or equal to the preset original accuracy threshold is aligned with the standard trajectory to obtain the position difference between each trajectory point on the trajectory and the corresponding point on the standard trajectory, as well as the change range of the adjacent position difference.

[0079] Trajectories with an original accuracy greater than or equal to a preset original accuracy threshold can be understood as trajectories of good quality that meet the original accuracy requirements. Aligning these trajectories with standard trajectories can improve the accuracy of subsequent processing.

[0080] For the same road surface area, considering that the trajectory points collected by the positioning system in the mobile measurement system cannot all be points on the standard trajectory during each data collection operation, and there is a certain distance deviation, in this disclosure example, the trajectory with original accuracy greater than or equal to the preset original accuracy threshold is aligned with the standard trajectory. Alignment can be understood as assigning a certain correction amount to the collected trajectory points so that the corrected trajectory points are located on the standard trajectory.

[0081] Aligning a trajectory with an original accuracy greater than or equal to a preset original accuracy threshold with a standard trajectory can yield the position difference (i.e., correction amount) between each trajectory point and the corresponding point on the standard trajectory, and can also determine the variation range of adjacent position differences (i.e., the difference between adjacent position differences).

[0082] In step 206, the alignment accuracy is determined based on the variation range of the position difference and the adjacent position difference.

[0083] Alignment accuracy can be considered as a statistical result of the variation range of the correction amount and adjacent correction amounts. For example, alignment accuracy includes absolute alignment accuracy and relative alignment accuracy. Absolute alignment accuracy is inversely proportional to the standard deviation or variance of the correction amounts of each trajectory point on the trajectory; that is, the smaller the standard deviation of the correction amount, the greater the absolute alignment accuracy. Relative alignment accuracy is inversely proportional to the standard deviation or variance of the variation range of adjacent correction amounts; that is, the smaller the standard deviation of the variation range of adjacent correction amounts, the greater the relative alignment accuracy. In some embodiments, absolute alignment accuracy is the proportion of trajectory points whose correction amounts are less than or equal to a preset correction amount threshold. For example, if there are 10 correction amounts, and 3 of them are greater than or equal to the preset correction amount threshold, then the absolute alignment accuracy is 0.7. Relative alignment accuracy is the proportion of adjacent correction amounts whose variation range is less than or equal to a preset variation range threshold. For example, if there are 10 correction amounts, and the variation range of adjacent correction amounts is calculated (9 variation ranges in total), and 3 of them are greater than or equal to the preset variation range threshold, then the relative alignment accuracy is 2 / 3.

[0084] In step 207, a target trajectory with an alignment accuracy greater than or equal to a preset alignment accuracy threshold is determined.

[0085] After determining the alignment accuracy of at least one trajectory within the road surface area, a target trajectory with an alignment accuracy greater than or equal to a preset alignment accuracy threshold can be identified from among the at least one trajectory. This means that target trajectories meeting the alignment accuracy requirements are selected, indicating that the target trajectory is of good quality, thus achieving control over trajectory alignment accuracy. For example, for a trajectory within the road surface area, the alignment accuracy corresponding to this trajectory includes absolute alignment accuracy and relative alignment accuracy. If the absolute alignment accuracy is greater than or equal to a preset absolute alignment accuracy threshold and the relative alignment accuracy is greater than or equal to a preset relative alignment accuracy threshold, then this trajectory is determined to be the target trajectory.

[0086] In step 208, the collected data corresponding to the target trajectory is obtained, and the first vector of at least one map element associated with the target trajectory is determined based on the collected data.

[0087] The collected data consists of point clouds and images acquired by the mobile surveying system during data collection operations. Based on the collected data, at least one map element associated with the target trajectory is determined. Determining map elements from collected data is a mature technology in the field of mapping and will not be elaborated further. The first vector of the map element is obtained by vectorizing the map element. The first vector can be understood as the edge shape of the map element. For example, the map element of a road sign can be vectorized to obtain the vector of the road sign shape. The vectorization of map elements is a routine operation in the field of mapping and will not be elaborated further.

[0088] In step 209, a second vector is obtained by adjusting the first vector of at least one map element.

[0089] In this embodiment of the disclosure, the first vector is provided to a person skilled in the art, who then adjusts the first vector to obtain the second vector.

[0090] In step 210, vector matching is performed on the first vector and the second vector to obtain the vector position difference and the change range of the vector position difference for each map element associated with the target trajectory.

[0091] After obtaining the first and second vectors of the same map element, vector matching is performed on the first and second vectors. Vector matching can not only determine whether the first and second vectors belong to the same map element, but also determine the vector position difference between the first and second vectors. This allows us to obtain the vector position difference corresponding to each map element associated with the target trajectory, and also determine the variation range of the vector position difference between different map elements (e.g., the difference between adjacent vector position differences).

[0092] In step 211, the vector adjustment accuracy of the second vector is determined based on the vector position difference and the magnitude of the change in the vector position difference.

[0093] Vector adjustment accuracy can be considered as a statistical result of vector position differences and the magnitude of their changes. For example, vector adjustment accuracy includes absolute vector adjustment accuracy and relative vector adjustment accuracy. Absolute vector adjustment accuracy is inversely proportional to the standard deviation or variance of the vector position differences corresponding to each map element associated with the target trajectory; that is, the smaller the standard deviation of the vector position differences, the greater the absolute vector adjustment accuracy. Relative vector adjustment accuracy is inversely proportional to the standard deviation or variance of the magnitude of the vector position differences; that is, the smaller the standard deviation of the magnitude of the vector position differences, the greater the relative alignment accuracy. In some embodiments, absolute vector adjustment accuracy is the proportion of vector position differences less than or equal to a preset vector position difference threshold. For example, if there are 10 vector position differences, and 3 of them are greater than or equal to the preset vector position difference threshold, then the absolute vector adjustment accuracy is 0.7. Relative vector adjustment accuracy is the proportion of vector position difference magnitudes less than or equal to a preset magnitude threshold. For example, if there are 10 vector position differences, and the magnitudes of changes in adjacent vector position differences are calculated (9 magnitudes in total), and 3 of these magnitudes are greater than or equal to the preset magnitude threshold, then the relative vector adjustment accuracy is 2 / 3.

[0094] In step 212, precision control is performed on the second vector whose vector adjustment precision is less than the preset vector adjustment precision threshold.

[0095] Among them, the second vector whose vector adjustment accuracy is less than the preset vector adjustment accuracy threshold, that is, the second vector whose vector adjustment accuracy does not meet the vector adjustment accuracy requirements and is of poor quality, is subject to accuracy control. In some embodiments, accuracy control of the second vector whose vector adjustment accuracy is less than the preset vector adjustment accuracy threshold is, for example, by outputting the second vector for manual verification and visual viewing, thereby achieving control of vector adjustment accuracy.

[0096] As can be seen, this disclosure controls the accuracy of the second vector used to generate the map by controlling the trajectory alignment accuracy and the vector adjustment accuracy, thereby achieving map accuracy control.

[0097] In some embodiments, this disclosure also provides a high-precision map generation method, the method comprising: determining a second vector with a vector adjustment precision greater than or equal to a preset vector adjustment precision threshold using the map precision control method disclosed in any of the foregoing embodiments; and generating a high-precision map based on the second vector with a vector adjustment precision greater than or equal to the preset vector adjustment precision threshold. The second vector is a vector of a map element, and generating a high-precision map from the vectors of map elements is a mature technology in the field of map technology, and will not be elaborated further.

[0098] In some embodiments, this disclosure also provides a high-precision map generation apparatus, used to determine a second vector with a vector adjustment precision greater than or equal to a preset vector adjustment precision threshold using the map precision control method disclosed in any of the foregoing embodiments; and to generate a high-precision map based on the second vector with a vector adjustment precision greater than or equal to the preset vector adjustment precision threshold.

[0099] Figure 3 This is a schematic diagram of a map accuracy control device provided in an embodiment of the present disclosure. The map accuracy control device can execute the processing flow provided in the embodiment of the map accuracy control method. Figure 3 As shown, the map accuracy control device includes: acquisition unit 31, alignment unit 32, vector matching unit 33 and control unit 34.

[0100] Acquisition unit 31 is used to acquire multiple trajectories included in the same road surface range and the standard trajectory corresponding to the road surface range;

[0101] Alignment unit 32 is used to align at least one trajectory included in the road surface range to a standard trajectory, determine the alignment accuracy corresponding to at least one trajectory, and determine the target trajectory in at least one trajectory whose alignment accuracy is greater than or equal to a preset alignment accuracy threshold.

[0102] Vector matching unit 33 is used to acquire a first vector of at least one map element associated with the target trajectory and a second vector obtained after adjusting the first vector, and to perform vector matching on the first vector and the second vector to determine the vector adjustment accuracy of the second vector;

[0103] The control unit 34 is used to perform precision control on a second vector whose vector adjustment accuracy is less than a preset vector adjustment accuracy threshold.

[0104] In some embodiments, the acquisition unit 31 is used to acquire trajectories corresponding to multiple data collection operations for a target area; determine at least one road surface range based on the road boundaries and road start and end positions included in the target area; and acquire multiple trajectories included in the same road surface range and the standard trajectory corresponding to the road surface range.

[0105] In some embodiments, the alignment unit 32 aligns at least one trajectory included in the road surface range to a standard trajectory, including obtaining the original accuracy of each trajectory included in the road surface range; and aligning trajectories with original accuracy greater than or equal to a preset original accuracy threshold to the standard trajectory.

[0106] In some embodiments, the alignment unit 32 aligns at least one trajectory included in the road surface area to a standard trajectory and determines the alignment accuracy corresponding to the at least one trajectory, including: aligning at least one trajectory included in the road surface area to a standard trajectory to obtain the position difference between each trajectory point on the at least one trajectory and the corresponding point on the standard trajectory, as well as the variation range of adjacent position differences; and determining the alignment accuracy corresponding to the at least one trajectory included in the road surface area based on the position difference and the variation range.

[0107] In some embodiments, the vector matching unit 33 acquires a first vector of at least one map element associated with the target trajectory and a second vector obtained by adjusting the first vector, including: acquiring collected data corresponding to the target trajectory, and determining a first vector of at least one map element associated with the target trajectory based on the collected data; and acquiring a second vector obtained by adjusting the first vector of at least one map element.

[0108] In some embodiments, the vector matching unit 33 performs vector matching on the first vector and the second vector to determine the vector adjustment accuracy of the second vector, including: performing vector matching on the first vector and the second vector to obtain the vector position difference and the change range of the vector position difference corresponding to each map element associated with the target trajectory; and determining the vector adjustment accuracy based on the vector position difference and the change range of the vector position difference.

[0109] For details of the embodiments of the map accuracy control device disclosed above, please refer to the details of the embodiments of the map accuracy control method described above. To avoid repetition, they will not be repeated.

[0110] Figure 4 This is an exemplary block diagram of an electronic device provided in an embodiment of this disclosure. Figure 4 As shown, the electronic device includes a memory 41, a processor 42, and a computer program stored on the memory 41. It is understood that the memory 41 in this embodiment may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory.

[0111] In some implementations, memory 41 stores elements such as executable modules or data structures, or subsets thereof, or extended sets thereof: operating systems and applications.

[0112] The operating system includes various system programs, such as the framework layer, core library layer, and driver layer, used to implement various basic tasks and handle hardware-based tasks. The application programs include various applications, such as media players and browsers, used to implement various application tasks. The program implementing the map accuracy control method or high-precision map generation method provided in the embodiments of this disclosure can be included in the application programs.

[0113] In this embodiment of the disclosure, at least one processor 42 executes the steps of the map accuracy control method or high-precision map generation method embodiments provided in this disclosure by calling a program or instruction stored in at least one memory 41, specifically, a program or instruction stored in an application.

[0114] The map accuracy control method or high-precision map generation method provided in this disclosure can be applied to or implemented by the processor 42. The processor 42 can be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method can be completed by integrated logic circuits in the hardware of the processor 42 or by instructions in software form. The processor 42 can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor or any conventional processor.

[0115] The steps of the map accuracy control method or high-precision map generation method provided in this disclosure can be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software modules can be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory 41, and the processor 42 reads the information in memory 41 and combines it with hardware to complete the steps of the method.

[0116] This disclosure also proposes a computer-readable storage medium that stores a program or instructions that cause a computer to perform steps, such as those in embodiments of a map accuracy control method or a high-precision map generation method. To avoid repetition, these steps will not be described again here. The computer-readable storage medium can be a non-transitory computer-readable storage medium.

[0117] This disclosure also proposes a computer program product, wherein the computer program product includes a computer program stored in a non-transitory computer-readable storage medium, and at least one processor of the computer reads from the storage medium and executes the computer program, causing the computer to perform the steps of embodiments such as the map accuracy control method or the high-precision map generation method, which will not be repeated here to avoid repetition.

[0118] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0119] Those skilled in the art will understand that although some embodiments described herein include certain features included in other embodiments but not others, combinations of features from different embodiments are meant to be within the scope of this disclosure and form different embodiments.

[0120] Those skilled in the art will understand that the descriptions of the various embodiments have different focuses, and for parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0121] Although embodiments of the present disclosure have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for controlling map accuracy, the method comprising: Obtain multiple trajectories within the same road surface area and the standard trajectory corresponding to the road surface area; Align at least one trajectory within the road surface area to the standard trajectory, determine the alignment accuracy corresponding to the at least one trajectory, and determine the target trajectory in the at least one trajectory whose alignment accuracy is greater than or equal to a preset alignment accuracy threshold. A first vector of at least one map element associated with the target trajectory and a second vector obtained by adjusting the first vector are obtained. Vector matching is performed on the first vector and the second vector to obtain the vector position difference and the change range of the vector position difference for each map element associated with the target trajectory. Based on the vector position difference and the change range of the vector position difference, the vector adjustment accuracy of the second vector is determined. Precision control is applied to the second vector whose vector adjustment precision is less than the preset vector adjustment precision threshold.

2. The method according to claim 1, wherein, Before obtaining multiple trajectories within the same road surface area, the method further includes: Obtain the trajectories corresponding to multiple data collection operations targeting a specific area; Based on the road boundaries and road start and end locations included in the target area, at least one road surface range is determined.

3. The method according to claim 1, wherein, Aligning at least one trajectory encompassed by the road surface area to the standard trajectory includes: Obtain the original accuracy of each trajectory within the road surface area; Align trajectories with original accuracy greater than or equal to a preset original accuracy threshold to the standard trajectory.

4. The method according to claim 1, wherein, Aligning at least one trajectory within the road surface area to the standard trajectory, and determining the alignment accuracy corresponding to the at least one trajectory, includes: Align at least one trajectory within the road surface area with the standard trajectory to obtain the positional difference between each trajectory point on the at least one trajectory and the corresponding point on the standard trajectory, as well as the variation range of adjacent positional differences. Based on the position difference and the change amplitude, the alignment accuracy corresponding to at least one trajectory included in the road surface range is determined.

5. A method for generating high-precision maps, the method comprising: Using the map accuracy control method according to any one of claims 1 to 4, a second vector with a vector adjustment accuracy greater than or equal to a preset vector adjustment accuracy threshold is determined; A high-precision map is generated based on a second vector whose vector adjustment accuracy is greater than or equal to a preset vector adjustment accuracy threshold.

6. A map accuracy control device, the device comprising: The acquisition unit is used to acquire multiple trajectories within the same road surface range and the standard trajectory corresponding to the road surface range; An alignment unit is used to align at least one trajectory included in the road surface range to the standard trajectory, determine the alignment accuracy corresponding to the at least one trajectory, and determine the target trajectory in the at least one trajectory whose alignment accuracy is greater than or equal to a preset alignment accuracy threshold. The vector matching unit is used to acquire a first vector of at least one map element associated with the target trajectory and a second vector obtained by adjusting the first vector, and to perform vector matching on the first vector and the second vector to obtain the vector position difference and the change range of the vector position difference for each map element associated with the target trajectory; and to determine the vector adjustment accuracy of the second vector based on the vector position difference and the change range of the vector position difference. The control unit is used to control the accuracy of a second vector whose vector adjustment accuracy is less than a preset vector adjustment accuracy threshold.

7. A high-precision map generation apparatus, the apparatus being used to: determine a second vector whose vector adjustment precision is greater than or equal to a preset vector adjustment precision threshold using the map precision control method according to any one of claims 1 to 4; and generate a high-precision map based on the second vector whose vector adjustment precision is greater than or equal to the preset vector adjustment precision threshold.

8. An electronic device, wherein, The system includes a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the map accuracy control method as claimed in any one of claims 1 to 4 or the steps of the high-precision map generation method as claimed in claim 5.

9. A computer program product comprising computer instructions, wherein, When executed by a processor, the computer instruction implements the steps of the map accuracy control method as described in any one of claims 1 to 4 or the steps of the high-precision map generation method as described in claim 5.

Images