Method, device, equipment and storage medium for detecting base map rendering effect

Abstract

The present application provides a method, device, equipment and storage medium for detecting the rendering effect of a base map. The technical solution of the present application can be applied to various scenarios such as cloud technology, artificial intelligence, smart transportation, and assisted driving. The detection method includes: obtaining the trajectory data between two points; performing image rendering according to the trajectory data between the two points to obtain a target video; obtaining a target base map in the target video; and obtaining the detection result of the rendering effect of the target base map according to the target base map and the target model. On the one hand, this automated detection method can improve the detection efficiency, and on the other hand, this automated detection method does not rely on the detection experience of the tester, thereby improving the detection accuracy.

Description

Technical Field

[0001] The embodiments of the present application relate to image processing technology, and in particular to a method, device, equipment and storage medium for detecting base map rendering effects. Background Art

[0002] With the continuous development of navigation technology, people have higher and higher requirements for the rendering accuracy of navigation images. Since navigation images are usually three-dimensional space images, including images of the sky, the ground and other control spaces, and the ground image, referred to as the base map, is an important part of the navigation image, it is very important to detect the rendering effect of the base map.

[0003] The current method for testing the rendering effect of the base map is that the tester needs to drive a test car to conduct field tests on the routes in the base map to test the rendering effect of the base map. However, on the one hand, this detection method has the problem of low detection efficiency, and on the other hand, this detection method may have the problem of low detection accuracy because it relies on the detection experience of the tester. Summary of the invention

[0004] The present application provides a method, device, equipment and storage medium for detecting base map rendering effects. On the one hand, this automated detection method can improve detection efficiency. On the other hand, this automated detection method does not rely on the detection experience of the tester, thereby improving detection accuracy.

[0005] In a first aspect, a method for detecting a base map rendering effect is provided, comprising: obtaining trajectory data between two points; performing image rendering according to the trajectory data between the two points to obtain a target video; obtaining a target base map in the target video; and obtaining a detection result of the rendering effect of the target base map according to the target base map and a target model.

[0006] In a second aspect, a device for detecting a base map rendering effect is provided, comprising: a first acquisition module, a rendering module, a second acquisition module and a processing module, wherein the first acquisition module is used to acquire trajectory data between two points; the rendering module is used to perform image rendering according to the trajectory data between the two points to obtain a target video; the second acquisition module is used to acquire a target base map in the target video; and the processing module is used to obtain a detection result of the rendering effect of the target base map according to the target base map and the target model.

[0007] According to a third aspect, an electronic device is provided, comprising: a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the method in the first aspect or its various implementations.

[0008] According to a fourth aspect, a computer-readable storage medium is provided for storing a computer program, wherein the computer program enables a computer to execute the method according to the first aspect or its various implementations.

[0009] According to a fifth aspect, a computer program product is provided, comprising computer program instructions, wherein the computer program instructions enable a computer to execute the method according to the first aspect or its various implementations.

[0010] According to a sixth aspect, a computer program is provided, which enables a computer to execute the method according to the first aspect or its various implementations.

[0011] Through the technical solution provided by the present application, the electronic device can obtain the detection result of the rendering effect of the target base map according to the target base map and the target model. In other words, there is no need for the tester to conduct on-site detection, but to use this automated detection method to detect the rendering effect of the base map. On the one hand, this automated detection method can improve the detection efficiency, and on the other hand, this automated detection method does not rely on the tester's detection experience, thereby improving the detection accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0013] Figure 1 Provides schematic diagrams of common basemap rendering problems;

[0014] Figure 2 A flowchart of a method for detecting a base map rendering effect provided in an embodiment of the present application;

[0015] Figure 3 A flow chart of a trajectory data generation method provided in an embodiment of the present application;

[0016] Figure 4 A flowchart of an image rendering method provided in an embodiment of the present application;

[0017] Figure 5 A schematic diagram of the classification of rendering problems provided in an embodiment of the present application;

[0018] Figure 6 A schematic diagram of a target model provided in an embodiment of the present application;

[0019] Figure 7 A flowchart of a method for detecting rendering effects of a target base map provided in an embodiment of the present application;

[0020] Figure 8 A schematic diagram of a method for detecting rendering effects of a target base map provided in an embodiment of the present application;

[0021] Fig. 9 A schematic diagram of creating a rendering problem sheet provided in an embodiment of the present application;

[0022] Fig.10 A flow chart of a method for training a model provided in an embodiment of the present application;

[0023] Fig.11 A schematic diagram of a device for detecting a base map rendering effect provided in an embodiment of the present application;

[0024] Fig.12 It is a schematic block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0027] Before introducing the technical solution of this application, the relevant knowledge of this application will be explained below:

[0028] Base map: A navigation image is usually a three-dimensional space image, including images of the sky, ground, and other control spaces, and the ground image can be called a base map.

[0029] Figure 1 Provides schematic diagrams of common basemap rendering problems, such as Figure 1As shown, common base map rendering problems may include: current lane line data loss, opposite lane line data loss, lane line data loss, uneven intersection connection, bridge pier drawing errors, road cracks, missing zebra crossings, median cracks, missing guide lines, median display of road surface, display of multiple speed limit signs, and misaligned turn arrows.

[0030] It should be noted that Figure 1 It only lists some problems of missing or incorrect base map rendering. In fact, there are other problems of missing or incorrect rendering, such as missing speed limit signs, misplaced zebra crossings, misplaced road joints, etc.

[0031] The following is a description of the technical problems, inventive concepts and application scenarios to be solved by this application:

[0032] As mentioned above, the current method for testing the rendering effect of the base map is that the tester needs to drive a test car to conduct field tests on the routes in the base map to test the rendering effect of the base map. However, on the one hand, this detection method has the problem of low detection efficiency, and on the other hand, this detection method may have the problem of low detection accuracy because it relies on the detection experience of the tester.

[0033] In order to solve the above technical problems, the present application provides a method for automatically detecting base map rendering effects.

[0034] The technical solution of this application can be applied to various scenarios such as cloud technology, artificial intelligence, smart transportation, assisted driving, etc., but is not limited to these.

[0035] The technical solution of this application will be described in detail below:

[0036] Figure 2 The present invention provides a flowchart of a method for detecting a base map rendering effect in an embodiment of the present invention. The method can be executed by electronic devices such as desktop computers, laptop computers, PDAs, cloud servers, etc., but is not limited thereto. Figure 2 As shown, the method includes:

[0037] S210: Acquire trajectory data between two points;

[0038] S220: Rendering an image according to the trajectory data between the two points to obtain a target video;

[0039] S230: Acquire a target base map in the target video;

[0040] S240: Obtaining a detection result of a rendering effect of the target base map according to the target base map and the target model.

[0041] It should be understood that there may be one or more routes between two points, and each route may include at least one road.

[0042] Optionally, the route may be a Standard-Definition (SD) route, and accordingly, the roads included in the route may be SD roads. The route may also be a High-Definition (HD) route, and accordingly, the roads included in the route may be HD roads.

[0043] It should be understood that, in the present application, the trajectory data between two points refers to the data on the trajectory between the two points, wherein the electronic device can collect points on the center line of the road between the two points, fit these collected points, and obtain the trajectory between the two points.

[0044] Optionally, the trajectory data between two points includes at least one of the following, but is not limited thereto: the number of satellites, the position of satellites, the status of satellites, the orientation of satellites, the type of satellites, etc.

[0045] Optionally, the number of satellites may be one or more, and this application does not impose any limitation on this.

[0046] It should be understood that the number of satellites refers to the number of satellites at each satellite position, and the number of satellites at different satellite positions may be the same or different.

[0047] It should be understood that the satellite position may also be referred to as satellite coordinates, which may be two-dimensional or three-dimensional coordinates.

[0048] Optionally, the satellite status includes: an available status and an unavailable status, but is not limited thereto. Usually, the satellite status is an available status.

[0049] Optionally, the satellite orientation may be in the opposite direction of the trajectory direction, for example, for a trajectory starting at point A and ending at point B, the trajectory direction of the trajectory points to point B, and of course there may be a certain angle between the trajectory direction and the direction of point B, then the satellite orientation may point to point A, and of course there may be a certain angle between the satellite orientation and the direction of point A. In short, this application does not restrict the satellite orientation.

[0050] Optionally, the satellite type may be any satellite type used to achieve positioning, and this application does not impose any limitation on this.

[0051] Optionally, the trajectory data between the above two points may be trajectory data collected on-site by a tester or trajectory data generated based on SD route planning results, and this application does not impose any restrictions on this.

[0052] Two optional methods for generating trajectory data based on SD route planning results are provided below. The present application is not limited to the methods for generating trajectory data based on SD route planning results:

[0053] Possible implementation method 1: Figure 3 As shown, the methods for generating trajectory data based on SD route planning results include:

[0054] S310: Obtaining a SD route planning result between two points;

[0055] S320: Determine a HD route planning result between two points according to the SD route planning result;

[0056] S330: Determine trajectory data between two points according to the HD route planning result.

[0057] Optionally, the electronic device may use a route planning algorithm, such as an A* algorithm, to calculate the SD route between two points, and obtain a SD route planning result between the two points, and the SD route planning result may include: a road identification of at least one SD road between the two points, but not limited thereto. Further, the electronic device may determine a HD route planning result between the two points based on the SD route planning result, and the HD route planning result may include: a road identification of at least one HD road between the two points and a block identification of each HD road, but not limited thereto. The road identification and block identification of each HD road are used as search conditions to search the data engine for the road centerline of the HD road corresponding to these identifications, wherein the road centerline of each HD road is composed of a series of shape points. Furthermore, the electronic device may obtain trajectory generation parameters, and generate trajectory data between the two points based on the trajectory generation parameters and the road centerline of the at least one HD road mentioned above.

[0058] Optionally, the electronic device can obtain a mapping relationship between the road identification of the at least one SD road and the road identification of the at least one HD road, and obtain the road identification of the at least one HD road based on the mapping relationship and the road identification of the at least one SD road; and then use the road identification of each HD road as a search condition to the data engine to obtain the block identification of each HD road.

[0059] It should be understood that the block identifier of the HD road is an identifier corresponding to each area block when the HD road is divided into multiple area blocks.

[0060] Optionally, the mapping relationship between the road sign of the at least one SD road and the road sign of the at least one HD road is a one-to-one correspondence.

[0061] Exemplarily, Table 1 exemplarily shows the mapping relationship between the road signs of some SD roads and the road signs of some HD roads:

[0062] Table 1

[0063] Road signs on SD roads Road signs on HD roads 123 134 456 467 789 791 …… ……

[0064] Optionally, assuming that the road identification of each HD road and all the block identifications of the HD road constitute a joint identification, the electronic device can obtain the mapping relationship between the road identification of at least one SD road and the joint identification, obtain the joint identification based on the mapping relationship and the road identification of at least one SD road, and further parse the joint identification to obtain the road identification and block identification of the HD road.

[0065] Optionally, the mapping relationship between the road identification of the at least one SD road and the joint identification is a one-to-one correspondence.

[0066] Exemplarily, Table 2 exemplarily shows the mapping relationship between the road identification of some SD roads and some joint identifications:

[0067] Table 2

[0068] Road signs on SD roads Joint identification 123 134012 456 467234 789 791567 …… ……

[0069] Optionally, the electronic device may combine the road identifier and the block identifier of the HD road according to a preset rule. Accordingly, after obtaining the combined identifier, the electronic device may parse the combined identifier according to the preset rule.

[0070] For example, assuming that the preset rule stipulates that the first three digits in the joint identifier are the road identifier of the HD road, and each digit starting from the fourth digit is a block identifier, then assuming that the joint identifier is 134012, the electronic device parses the joint identifier and can obtain that the road identifier of the HD road is 134, and can be parsed into three block identifiers, namely 0, 1, and 2.

[0071] It should be understood that the road identification and block identification of the HD road have a one-to-one correspondence with the road centerline. For example, when the road identification of the HD road is 134, and the three block identifications are 0, 1, and 2 respectively, their corresponding road centerline is the road centerline L1. Here, "L1" is the identification of the road centerline, which can also be called an index.

[0072] Optionally, the trajectory generation parameters include a simulation frame rate, a simulation speed, and a simulation interference amount, but are not limited thereto.

[0073] Optionally, the above-mentioned simulation frame rate can be predefined by the electronic device, or obtained based on experiments, or specified by other devices such as a cloud server. In short, this application does not limit the method for determining the simulation frame rate.

[0074] Optionally, the above simulation speed may be predefined by the electronic device, or obtained based on experiments, or specified by other devices such as a cloud server. In short, this application does not limit the method for determining the simulation speed.

[0075] Optionally, the above-mentioned simulated interference amount can be predefined by the electronic device, or obtained according to experiments, or specified by other devices such as a cloud server. In short, this application does not limit the method for determining the simulated interference amount.

[0076] Optionally, the electronic device can collect points on the center line of each HD road according to the above-mentioned simulation frame rate and simulation speed; correct the collected points according to the collected points and the simulated interference amount to obtain corrected points, and the corrected points constitute the trajectory between the two points; and determine at least one of the number of satellites, satellite positions, satellite states, satellite orientations and satellite types on the trajectory between the two points as the trajectory data between the two points.

[0077] Optionally, the electronic device may determine the time interval for collecting a point based on the simulation frame rate, and further determine the distance interval for collecting a point in combination with the simulation speed, thereby collecting points on the center line of the road at the determined collection frequency.

[0078] Optionally, the electronic device can perform a sum operation on the coordinates of the collected points and the simulated interference amount to obtain the coordinates of the corrected points, or perform a difference operation on the coordinates of the collected points and the simulated interference amount to obtain the coordinates of the corrected points. In short, the present application does not limit the method of correcting the point coordinates.

[0079] Optionally, the electronic device may use a curve fitting method for the corrected points to form a trajectory between the two points, wherein the present application does not limit the curve fitting method.

[0080] Optionally, the electronic device determines each corrected point on the trajectory as a satellite position, and the number of satellites at each position may be one or more, which is not limited in the present application. The satellite state at each position may be an available state, the satellite orientation may be the opposite direction of the trajectory direction, and the satellite type may be any satellite type used to achieve positioning.

[0081] The following example illustrates how to generate trajectory data between two points:

[0082] Exemplarily, assuming that the simulation frame rate is to collect 10 points per second, that is, a point is collected every 0.1 seconds, assuming that the simulation speed is 72km / h, that is, 20m / s, it can be seen that a point is collected every two meters. Further, assuming that the simulated interference amount is (0.5,0.5), the simulated interference amount is a correction to the collected points. For example: assuming that the coordinates of a collected point are (1,1), then the point is corrected to (1.5,1.5). Furthermore, the electronic device can fit these corrected points to obtain the trajectory between the two points. These corrected points are satellite positions, and the number of satellites at each position can be one or more. And the state of each satellite can be an available state, the direction can be the opposite direction of the trajectory direction, and the satellite type of each satellite can be the same or different.

[0083] Optionally, when the electronic device generates trajectory data between two points based on the trajectory generation parameters and the road center line of the at least one HD road, the trajectory data between the two points can also be determined based on a mapping relationship between the trajectory generation parameters and the road center line of the at least one HD road as a whole and the trajectory data between the two points.

[0084] It should be noted that the electronic device may not generate the trajectory data between the two points according to the trajectory generation parameters and the road center line of the at least one HD road, but may directly determine the trajectory data between the two points based on the mapping relationship between the HD route planning result and the trajectory data.

[0085] In a second implementation method, the electronic device may use a route planning algorithm, such as an A* algorithm, to calculate the SD route between two points, and obtain a SD route planning result between the two points. The SD route planning result may include: the identification of at least one SD road between the two points, but is not limited thereto. Furthermore, the electronic device may use the identification of at least one SD road as a search condition to search the data engine for the road centerline of the SD road corresponding to these identifications, wherein the road centerline of each SD road is composed of a series of shape points. Furthermore, the electronic device may obtain trajectory generation parameters, and generate trajectory data between the two points according to the trajectory generation parameters and the road centerline of the at least one SD road.

[0086] It should be understood that the difference between the second implementation method and the first implementation method is that in the second implementation method, there is no need to determine the HD route planning result based on the SD route planning result, but the road center line of the SD road is directly determined based on the SD route planning result. Regarding the generation of trajectory data between two points based on the trajectory generation parameters and the road center line of the above-mentioned at least one SD road, reference can be made to the method of generating trajectory data between two points based on the trajectory generation parameters and the road center line of the above-mentioned at least one HD road in the first implementation method, and this application will not go into details about this.

[0087] Alternatively, if Figure 4 As shown, the electronic device can perform image rendering in the following manner:

[0088] S410: Analyze the trajectory data between the two points to obtain a trajectory analysis result;

[0089] S420: Obtaining positioning data corresponding to the trajectory analysis result;

[0090] S430: Perform image rendering according to the positioning data to obtain a target video.

[0091] Optionally, after the electronic device obtains the trajectory data between two points, the trajectory data can be loaded into a specified directory of the vehicle computer, and the trajectory data can be played back. The playback process of the trajectory data includes: loading the trajectory data, reading the trajectory data, parsing the trajectory data to extract the number of satellites, satellite positions, satellite status, satellite orientations, satellite types, etc., or only the satellite positions and satellite orientations can be extracted, and the extracted information, i.e., the trajectory parsing results are sent to a positioning software development kit (Software Development Kit, SDK), which can process the trajectory parsing results to return the positioning data corresponding to the trajectory parsing results.

[0092] Optionally, the above trajectory analysis result is part or all of the trajectory data, for example, the trajectory analysis result may be the number of satellites, satellite positions, satellite states, satellite orientations, satellite types, etc. For another example, the trajectory analysis result may be satellite positions and satellite orientations.

[0093] Optionally, the positioning SDK can collect positioning signals on these satellites based on the trajectory analysis results, such as real-time kinematic (RTK) signals or global navigation satellite system (GNSS) signals. The positioning SDK can obtain the initial position of the vehicle through the positioning signal, load the local map based on the initial position, and make motion trajectory predictions, and output the vehicle's absolute position, relative position, accuracy radius, confidence and other positioning data through the positioning algorithm.

[0094] It should be understood that this application does not limit the positioning algorithm used by the positioning SDK.

[0095] Optionally, assuming that the electronic device has previously obtained the positioning data corresponding to the trajectory data, the electronic device does not need to replay the above trajectory data again, but can establish a correspondence between the trajectory data and the positioning data, and can directly obtain the positioning data based on the correspondence and the trajectory data.

[0096] Optionally, the electronic device may use a rendering engine to perform image rendering according to the positioning data to obtain a target video.

[0097] It should be understood that the present application does not limit the rendering engine and the rendering algorithm adopted.

[0098] It should be understood that since the above-mentioned positioning data is generated during the simulation of vehicle driving, these positioning data will be rendered as a navigation video, that is, the above-mentioned target video. This video is composed of several frames of images, and each frame of image includes several background map elements, such as: lanes, lane lines, bridge piers, intersections, zebra crossings, isolation belts, guide lines, speed limit signs, turn arrows, etc.

[0099] Optionally, the target base map may be any image frame of the target video whose rendering effect is to be detected.

[0100] Optionally, the target model may be a deep learning model, a support vector machine (SVM) model, or a model using a template matching algorithm, etc., and this application does not impose any restrictions on this.

[0101] Optionally, rendering problems can be divided into two categories: problems with rendering and problems without rendering.

[0102] Optionally, rendering problems can be further subdivided into lane data problems, lane line data problems, intersection problems, viaduct problems, ground sign problems and others.

[0103] Optionally, each major category of rendering problems can be further divided into multiple minor categories of rendering problems, such as Figure 5 As shown, lane data problems may include: missing green belt, missing lane surface, road surface covering green belt, and others. Intersection problems may include: missing guide / divider line, missing zebra crossing, missing intersection surface, and others. Overpass problems may include: bridge piers passing through the road surface, bridge deck covering the road surface, and others. Ground signs may include: missing turn arrows, misaligned turn arrows, and others. Based on this, Figure 6 As shown, the target model may include: a feature extraction layer, a first classification layer and a second classification layer, but not limited thereto, wherein the feature extraction layer is used to extract the features of the input target base map area; the first classification layer is used to obtain the features of the target base map area, and determine the first problem category to which the rendering problem of the target base map area belongs; the second classification layer is used to obtain the first problem category, and determine the second problem category to which the rendering problem of the target base map area belongs; wherein the second problem category is a subcategory of the first problem category, for example: the first classification layer determines that the rendering problem existing in a certain base map area is a lane data problem, and the second classification layer determines that the specific rendering problem existing in the base map area is a missing green belt.

[0104] Optionally, the feature extraction layer can be an embedding layer, which can adopt one-hot encoding, which is also called one-bit effective encoding. It mainly uses an N-bit state register to encode N states. Each state has its own independent register bit, and only one bit is valid at any time.

[0105] Optionally, the target base map area can be any base map area, and this application does not impose any limitation on this.

[0106] Optionally, the electronic device may determine the detection result of the rendering effect of the target base map in the following achievable manner, but is not limited thereto:

[0107] Possible implementation method 1: Figure 7 As shown, the method includes:

[0108] S710: Acquire a specific area in the target base map;

[0109] S720: Divide the specific area into multiple sub-areas;

[0110] S730: Input each sub-region into the target model to obtain a detection result of the rendering effect of each sub-region;

[0111] The detection results of the rendering effects of the multiple sub-areas constitute the detection results of the rendering effect of the target base map.

[0112] Optionally, the specific area may be predefined, or an area designated by the electronic device, or a region of interest (ROI), etc., and the present application does not impose any limitation on this.

[0113] Optionally, the above-mentioned specific area may be the central area of ​​the target base map, which is not limited in this application.

[0114] Optionally, the electronic device may use an ROI determination algorithm to determine the ROI, and this application does not limit the algorithm.

[0115] Optionally, the electronic device may divide the above-mentioned specific area according to a preset block size, or divide the above-mentioned specific area according to lane spacing. In short, the present application does not limit the area division method.

[0116] Optionally, the detection result of the rendering effect of each area may be no rendering problem, or an existing rendering problem. The rendering problem may be the above-mentioned large category rendering problem, such as lane data problem, or the above-mentioned small category rendering problem, such as missing green belt. The specific type of rendering problem is related to the trained target model. For example: when the trained target model only has the above-mentioned first classification layer, the rendering problem determined by the electronic device will be a large category rendering problem. When the trained target model includes the above-mentioned first classification layer and the second classification layer, the rendering problem determined by the electronic device will be a small category rendering problem. Of course, the trained target model can also include more fine-grained classification types, and the categories of rendering problems obtained at this time are more fine-grained.

[0117] For example, Figure 8 As shown, the electronic device can obtain the target base map, determine the ROI in the target base map, and extract the ROI in the target base map. Further, the ROI can be divided into 10 sub-areas according to a preset block size, or the ROI can be divided into 6 sub-areas according to the lane interval, and each sub-area is input into the target model to obtain the detection result of the rendering effect of each sub-area, such as Figure 8 In the bottom figure, the black boxes represent sub-regions with rendering problems, and the striped boxes represent sub-regions without rendering problems.

[0118] A second achievable method is as follows: the electronic device can directly divide the target base map into regions to obtain multiple sub-regions; each sub-region is input into the target model to obtain a detection result of the rendering effect of each sub-region; wherein the detection results of the rendering effects of multiple sub-regions constitute the detection results of the rendering effect of the target base map.

[0119] Optionally, the electronic device may divide the target base map according to a preset block size, or divide the target base map according to lane intervals. In short, the present application does not impose any restrictions on the area division method.

[0120] Optionally, the detection result of the rendering effect of each area may be no rendering problem, or an existing rendering problem. The rendering problem may be the above-mentioned large category rendering problem, such as lane data problem, or the above-mentioned small category rendering problem, such as missing green belt. The specific type of rendering problem is related to the trained target model. For example: when the trained target model only has the above-mentioned first classification layer, the rendering problem determined by the electronic device will be a large category rendering problem. When the trained target model includes the above-mentioned first classification layer and the second classification layer, the rendering problem determined by the electronic device will be a small category rendering problem. Of course, the trained target model can also include more fine-grained classification types, and the categories of rendering problems obtained at this time are more fine-grained.

[0121] In summary, the present application provides a method for detecting a base map rendering effect, wherein the electronic device can obtain a detection result of the rendering effect of the target base map according to the target base map and the target model. In other words, there is no need for the tester to conduct on-site detection, but to use this automated detection method to detect the rendering effect of the base map. On the one hand, this automated detection method can improve the detection efficiency, and on the other hand, this automated detection method does not rely on the tester's detection experience, thereby improving the detection accuracy.

[0122] In addition, in the present application, the electronic device can determine the trajectory data between two points based on the SD route planning results without the need for the tester to drive the vehicle on site to generate trajectory data. That is to say, the present application provides a method for automatically generating trajectory data, and the link for generating trajectory data determines the image rendering link and the entire rendering problem detection process. Therefore, the automation method provided by the present application can also improve the image rendering efficiency and accuracy, and further improve the detection efficiency and detection accuracy.

[0123] Optionally, if there is a rendering problem with the target base map, after obtaining the detection result of the rendering effect of the target base map based on the target base map and the target model, the electronic device can also create a rendering problem ticket corresponding to the target base map; and push the rendering problem ticket to notify the processing personnel to circulate the rendering problem ticket.

[0124] Alternatively, if Fig. 9 As shown, the electronic device can obtain the problem title corresponding to the rendering problem based on the rendering problem existing in the target base map; and can obtain the location of the rendering problem in the target base map, the time of occurrence, a problem screenshot of the rendering problem, at least one piece of information of the navigation version and the base map version, directly fill in at least one piece of information into the problem description field, and combine the problem description and the problem title to obtain a rendering problem ticket corresponding to the target base map, and the rendering problem ticket can be submitted to the background service, and the background service can notify the processing personnel through message reminders and the like, so that the processing personnel can circulate the rendering problem ticket.

[0125] For example, assuming that the electronic device determines that the rendering problem existing in the target base map is the missing intersection surface in the intersection problem, and assuming that the rule begins with "high-precision base map rendering defect", the problem title generated by the electronic device is "high-precision base map rendering defect-intersection problem-missing intersection surface". Further, at least one of the information about the location of the rendering problem in the target base map, the time of occurrence, the problem screenshot of the rendering problem, the navigation version and the base map version can be directly filled in the problem description field without further editing.

[0126] It should be noted that after obtaining at least one of the following information: the location of the rendering problem in the target base map, the time of occurrence, a screenshot of the rendering problem, the navigation version, and the base map version, the electronic device may not fill in at least one of the information into the problem description field, but directly combine this information with the problem title to obtain a rendering problem sheet corresponding to the target base map, and submit the rendering problem sheet to the background service, which may notify the processing personnel through message reminders and other methods, so that the processing personnel can circulate the rendering problem sheet. This application does not limit the method of creating a rendering problem sheet.

[0127] In summary, the automatic bill of lading solution provided by this embodiment can reduce testing costs, reduce manual links, and improve problem flow efficiency.

[0128] Fig.10 A flow chart of the method for training the model provided in the embodiment of the present application, such as Fig.10 As shown, the method includes:

[0129] S1010: Obtain positive samples and negative samples;

[0130] S1020: Train the target model using positive and negative samples.

[0131] Among them, the electronic device can input positive samples and negative samples into the target model to obtain the detection results of the rendering effects of the positive samples and negative samples. It is assumed that the detection result is called the prediction result, and the detection results carried in the positive samples and negative samples themselves are called the actual results. The target model is trained by the prediction result and the actual result.

[0132] Among them, the positive sample includes: the first base map area and the detection result of the rendering effect of the first base map area, and the detection result of the rendering effect of the first base map area is that there is no rendering problem; the negative sample includes: the second base map area and the detection result of the rendering effect of the second base map area, and the detection result of the rendering effect of the second base map area is the problem category to which the rendering problem of the second base map area belongs. The rendering problem of the second map area can be the above-mentioned major rendering problem or minor rendering problem, and this application does not limit this.

[0133] Optionally, the tester can record rendering problems during the actual vehicle test to form positive samples and negative samples. Alternatively, the electronic device can also generate trajectory data according to the above-mentioned trajectory data generation method, obtain positioning data by playing back the trajectory data, and obtain the target video by image rendering based on the positioning data. The tester can record the base map rendering problems in the target video to form positive samples and negative samples. Furthermore, when the positive samples and negative samples reach a certain number, the electronic device can train the target model through these samples. Next, an automated detection method can be used to detect rendering problems in any base map area.

[0134] In summary, the present application provides the above-mentioned model training method to obtain a trained target model, which can be used to automatically detect rendering problems.

[0135] Fig.11 A schematic diagram of a detection device 1100 for a base map rendering effect provided in an embodiment of the present application is shown as follows: Fig.11 As shown, the device 1100 includes: a first acquisition module 1110, a rendering module 1120, a second acquisition module 1130 and a processing module 1140, wherein the first acquisition module 1110 is used to acquire trajectory data between two points; the rendering module 1120 is used to perform image rendering according to the trajectory data between the two points to obtain a target video; the second acquisition module 1130 is used to acquire a target base map in the target video; and the processing module 1140 is used to obtain a detection result of the rendering effect of the target base map according to the target base map and the target model.

[0136] Optionally, the first acquisition module 1110 is specifically used to: acquire a SD route planning result between two points; determine a HD route planning result between the two points according to the SD route planning result; and determine trajectory data between the two points according to the HD route planning result.

[0137] Optionally, the first acquisition module 1110 is specifically used to: obtain the road identification of at least one SD road in the SD route planning result; obtain the mapping relationship between the road identification of at least one SD road and the road identification of at least one HD road; obtain the road identification of at least one HD road according to the mapping relationship and the road identification of at least one SD road; obtain the block identification of each HD road; wherein the HD route planning result of each HD road includes: the road identification and block identification of the HD road.

[0138] Optionally, the first acquisition module 1110 is specifically used to: determine the road center line of at least one HD road according to the HD route planning result; obtain trajectory generation parameters; and generate trajectory data between two points according to the trajectory generation parameters and the road center line of at least one HD road.

[0139] Optionally, the trajectory generation parameters include a simulation frame rate, a simulation speed and a simulation interference amount; the first acquisition module 1110 is specifically used to: collect points on the center line of each HD road according to the simulation frame rate and the simulation speed; correct the collected points according to the collected points and the simulated interference amount to obtain corrected points, and the corrected points constitute the trajectory between the two points; determine at least one of the number of satellites, satellite positions, satellite states, satellite orientations and satellite types on the trajectory between the two points as the trajectory data between the two points.

[0140] Optionally, the rendering module 1120 is used to: parse the trajectory data between two points to obtain a trajectory parsing result; obtain positioning data corresponding to the trajectory parsing result; and perform image rendering according to the positioning data to obtain a target video.

[0141] Optionally, the processing module 1140 is specifically used to: obtain a specific area in the target base map; divide the specific area into multiple sub-areas; input each sub-area into the target model to obtain a detection result of the rendering effect of each sub-area; wherein the detection results of the rendering effects of multiple sub-areas constitute the detection results of the rendering effect of the target base map.

[0142] Optionally, the device 1100 also includes: a third acquisition module 1150 and a training module 1160, wherein the third acquisition module 1150 is used to acquire positive samples and negative samples; the training module 1160 is used to train the target model through positive samples and negative samples; wherein the positive samples include: the first base map area and the detection results of the rendering effect of the first base map area, and the detection result of the rendering effect of the first base map area is that there is no rendering problem; the negative samples include: the second base map area and the detection results of the rendering effect of the second base map area, and the detection result of the rendering effect of the second base map area is the problem category to which the rendering problem of the second base map area belongs.

[0143] Optionally, the target model includes: a feature extraction layer, a first classification layer, and a second classification layer;

[0144] The feature extraction layer is used to extract the features of the input target base map area;

[0145] The first classification layer is used to obtain the characteristics of the target base map area and determine the first problem category to which the rendering problem of the target base map area belongs;

[0146] The second classification layer is used to obtain the first problem category and determine the second problem category to which the rendering problem of the target base map area belongs;

[0147] The second question category is a subcategory of the first question category.

[0148] Optionally, the device 1100 further includes: a creation module 1170 and a push module 1180, wherein the creation module 1170 is used to create a rendering problem sheet corresponding to the target base map, and the push module 1180 is used to push the rendering problem sheet.

[0149] Optionally, creation module 1170 is specifically used to: obtain a problem title corresponding to the rendering problem based on the rendering problem existing in the target base map; obtain at least one piece of information including the location of the rendering problem in the target base map, the time of occurrence, a screenshot of the rendering problem, a navigation version, and a base map version; and combine the problem title and at least one of the above information to obtain a rendering problem ticket corresponding to the target base map.

[0150] Optionally, the target model is a deep learning model.

[0151] It should be understood that the device embodiment and the method embodiment may correspond to each other, and similar descriptions may refer to the method embodiment. To avoid repetition, they will not be described here. Specifically, Fig.11 The device 1100 shown may perform Figure 2 The corresponding method embodiments, and the aforementioned and other operations and / or functions of each module in the device 1100 are respectively to implement Figure 2 For the sake of brevity, the corresponding processes in each method are not repeated here.

[0152] The above describes the device 1100 of the embodiment of the present application from the perspective of the functional module in conjunction with the accompanying drawings. It should be understood that the functional module can be implemented in hardware form, can be implemented by instructions in software form, and can also be implemented by a combination of hardware and software modules. Specifically, the steps of the method embodiment in the embodiment of the present application can be completed by the hardware integrated logic circuit and / or software form instructions in the processor, and the steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to perform, or a combination of hardware and software modules in the decoding processor to perform. Optionally, the software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor reads the information in the memory, and completes the steps in the above method embodiment in conjunction with its hardware.

[0153] Fig.12 It is a schematic block diagram of an electronic device provided in an embodiment of the present application.

[0154] like Fig.12 As shown, the electronic device may include:

[0155] The memory 1210 and the processor 1220, the memory 1210 is used to store the computer program and transmit the program code to the processor 1220. In other words, the processor 1220 can call and run the computer program from the memory 1210 to implement the method in the embodiment of the present application.

[0156] For example, the processor 1220 may be configured to execute the above method embodiments according to instructions in the computer program.

[0157] In some embodiments of the present application, the processor 1220 may include but is not limited to:

[0158] General-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, etc.

[0159] In some embodiments of the present application, the memory 1210 includes but is not limited to:

[0160] Volatile memory and / or non-volatile memory. Among them, the non-volatile memory can be read-only memory (ROM), programmable ROM (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM) or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link DRAM (SLDRAM), and direct RAM bus random access memory (DR RAM).

[0161] In some embodiments of the present application, the computer program may be divided into one or more modules, which are stored in the memory 1210 and executed by the processor 1220 to complete the method provided by the present application. The one or more modules may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in the electronic device.

[0162] like Fig.12 As shown, the electronic device may also include:

[0163] The transceiver 1230 may be connected to the processor 1220 or the memory 1210 .

[0164] The processor 1220 may control the transceiver 1230 to communicate with other devices, specifically, to send information or data to other devices, or to receive information or data sent by other devices. The transceiver 1230 may include a transmitter and a receiver. The transceiver 1230 may further include an antenna, and the number of antennas may be one or more.

[0165] It should be understood that the various components in the electronic device are connected via a bus system, wherein the bus system includes not only a data bus but also a power bus, a control bus and a status signal bus.

[0166] The present application also provides a computer storage medium on which a computer program is stored, and when the computer program is executed by a computer, the computer can perform the method of the above method embodiment. In other words, the present application embodiment also provides a computer program product containing instructions, and when the instructions are executed by a computer, the computer can perform the method of the above method embodiment.

[0167] When software is used for implementation, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integration. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a digital video disc (digital video disc, DVD)), or a semiconductor medium (e.g., a solid state drive (solid state disk, SSD)), etc.

[0168] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0169] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the module is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0170] The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. For example, each functional module in each embodiment of the present application may be integrated into a processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0171] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the 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.

Claims

1. A method for detecting a base map rendering effect, characterized in that: include: Get the SD route planning result between two points; Obtaining a road identification of at least one SD road in the SD route planning result; Acquire a mapping relationship between the road identification of the at least one SD road and the road identification of the at least one HD road; Obtaining a road identification of the at least one HD road according to the mapping relationship and the road identification of the at least one SD road; Obtaining a block identifier of each of the HD roads; wherein the HD route planning result of each of the HD roads includes: a road identifier and a block identifier of the HD road; Determining trajectory data between the two points according to the HD route planning result; Perform image rendering according to the trajectory data between the two points to obtain a target video; Obtaining a target base map in the target video; A detection result of the rendering effect of the target base map is obtained according to the target base map and the target model.

2. The method according to claim 1, characterized in that The determining the trajectory data between the two points according to the HD route planning result includes: Determine a road centerline of each of the at least one HD road according to the HD route planning result; Get trajectory generation parameters; Trajectory data between the two points is generated based on the trajectory generation parameters and the road center line of each of the at least one HD road.

3. The method according to claim 2, characterized in that The trajectory generation parameters include simulation frame rate, simulation speed and simulation interference amount; The step of generating trajectory data between the two points according to the trajectory generation parameter and the road center line of each of the at least one HD road comprises: collecting points on the center line of each of the HD roads according to the simulation frame rate and the simulation speed; According to the collected points and the simulated interference amount, the collected points are corrected to obtain corrected points, and the corrected points constitute a trajectory between the two points; At least one of the number of satellites, satellite positions, satellite states, satellite orientations, and satellite types on the trajectory between the two points is determined as trajectory data between the two points.

4. The method according to any one of claims 1 to 3, characterized in that: The step of performing image rendering according to the trajectory data between the two points to obtain a target video includes: Analyzing the trajectory data between the two points to obtain a trajectory analysis result; Obtaining positioning data corresponding to the trajectory analysis result; Image rendering is performed according to the positioning data to obtain the target video.

5. The method according to any one of claims 1 to 3, characterized in that: The step of obtaining a detection result of a rendering effect of the target base map according to the target base map and the target model includes: Acquire a specific area in the target base map; Dividing the specific area into multiple sub-areas; Inputting each of the sub-regions into the target model to obtain a detection result of the rendering effect of each of the sub-regions; The detection results of the rendering effects of the multiple sub-areas constitute the detection results of the rendering effect of the target base map.

6. The method according to any one of claims 1 to 3, characterized in that: Also includes: Get positive and negative samples; Training the target model by using the positive samples and the negative samples; Among them, the positive sample includes: the first base map area and the detection result of the rendering effect of the first base map area, and the detection result of the rendering effect of the first base map area is that there is no rendering problem; the negative sample includes: the second base map area and the detection result of the rendering effect of the second base map area, and the detection result of the rendering effect of the second base map area is the problem category to which the rendering problem of the second base map area belongs.

7. The method according to claim 6, characterized in that The target model comprises: a feature extraction layer, a first classification layer and a second classification layer; The feature extraction layer is used to extract the features of the input target base map area; The first classification layer is used to obtain the characteristics of the target base map area and determine the first problem category to which the rendering problem of the target base map area belongs; The second classification layer is used to obtain the first problem category and determine the second problem category to which the rendering problem of the target base map area belongs; The second question category is a subcategory of the first question category.

8. The method according to any one of claims 1 to 3, characterized in that: If the target base map has a rendering problem, after obtaining the detection result of the rendering effect of the target base map according to the target base map and the target model, the method further includes: Creating a rendering problem sheet corresponding to the target base map; Push the rendering issue ticket.

9. The method according to claim 8, characterized in that The step of creating a rendering problem sheet corresponding to the target base map includes: According to the rendering problem existing in the target base map, obtaining a problem title corresponding to the rendering problem; Obtain at least one of the following information: the location of the rendering problem in the target base map, the occurrence time, a screenshot of the rendering problem, a navigation version, and a base map version; The question title and the at least one piece of information are combined to obtain a rendering question sheet corresponding to the target base map.

10. The method according to any one of claims 1 to 3, characterized in that: The target model is a deep learning model.

11. A device for detecting a base map rendering effect, characterized in that: include: The first acquisition module is used to: Get the SD route planning result between two points; Obtaining a road identification of at least one SD road in the SD route planning result; Acquire a mapping relationship between the road identification of the at least one SD road and the road identification of the at least one HD road; Obtaining a road identification of the at least one HD road according to the mapping relationship and the road identification of the at least one SD road; Obtaining a block identifier of each of the HD roads; wherein the HD route planning result of each of the HD roads includes: a road identifier and a block identifier of the HD road; Determining trajectory data between the two points according to the HD route planning result; A rendering module, used for performing image rendering according to the trajectory data between the two points to obtain a target video; A second acquisition module is used to acquire a target base map in the target video; The processing module is used to obtain a detection result of the rendering effect of the target base map according to the target base map and the target model.

12. An electronic device, characterized in that: include: A processor and a memory, the memory being used to store a computer program, and the processor being used to call and run the computer program stored in the memory to execute the method according to any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that: Used to store a computer program, wherein the computer program causes a computer to execute the method according to any one of claims 1 to 10.

Images