Navigation guidance method, road shape data generation method, device, equipment and medium

Abstract

The disclosed embodiments relate to a navigation guidance method, a method, device, equipment and medium for generating road shape data, wherein the method comprises: when judging that a vehicle is approaching an intersection, obtaining road shape data corresponding to the navigation guidance action of the intersection; when the vehicle passes through the intersection, requesting the absolute posture of the camera device based on the road image captured by the camera device carried by the vehicle and the positioning position information of the vehicle when the road image is captured; determining the real-time external parameters of the camera device according to the absolute posture of the camera device, the vehicle direction change data detected by the gyroscope carried by the vehicle and the driving speed of the vehicle; determining the projection position of the road shape data on the road image captured by the camera device when the vehicle passes through the intersection based on the internal parameters and real-time external parameters of the camera device; rendering the road shape on the road image according to the projection position to form a navigation guide line. The scheme provided by the disclosed embodiments can improve the accuracy of navigation guidance at intersections.

Description

Technical Field

[0001] The embodiments of the present disclosure relate to the field of navigation technology, and more particularly to a navigation guidance method, a method for generating road shape data, an apparatus, a device, and a medium. Background Art

[0002] In the related art, augmented reality (AR) navigation can obtain the image of the road in front of the vehicle through a camera, and realize AR navigation guidance by rendering navigation guidance information on the image. The inventor of the present application found that the accuracy of navigation guidance at the intersection in the AR navigation scene has a great impact on the driving user experience, and the related art currently generally has the problem of insufficient accuracy. Therefore, how to improve the accuracy of navigation guidance at the intersection in the AR navigation scene is a problem that technicians in this field need to solve. Summary of the invention

[0003] In order to solve the above technical problems or at least partially solve the above technical problems, the embodiments of the present disclosure provide a navigation guidance method, a method, an apparatus, a device and a medium for generating road shape data.

[0004] A first aspect of an embodiment of the present disclosure provides a navigation guidance method, which includes: obtaining a vehicle's positioning position information; determining whether the vehicle is approaching an intersection based on the vehicle's positioning position information and the obtained navigation path information; when the vehicle approaches the intersection, obtaining road shape data corresponding to the navigation guidance action of the intersection; and when the vehicle passes through the intersection, requesting the absolute posture of the camera device based on the road image captured by the camera device carried by the vehicle and the positioning position information of the vehicle when the road image is captured; then determining the real-time external parameters of the camera device based on the absolute posture of the camera device, the vehicle direction change data detected by the gyroscope carried by the vehicle, and the vehicle's driving speed; based on the internal parameters and real-time external parameters of the camera device, determining the projection position of the road shape data on the road image captured by the camera device when the vehicle passes through the intersection; and then rendering the road shape on the road image according to the projection position to form a navigation guidance line.

[0005] The second aspect of the disclosed embodiment provides a method for generating road shape data, the method comprising: obtaining a through path of an intersection based on accurate map data, the through path including an entry section into the intersection and an exit section out of the intersection; obtaining trajectory data matching the entry section and the exit section from pre-collected trajectory data with positioning accuracy meeting preset accuracy requirements; processing the trajectory data into road shape data corresponding to the through path of the intersection. .

[0006] A third aspect of an embodiment of the present disclosure provides a navigation guidance device, the device comprising:

[0007] The first acquisition module is used to acquire the positioning position information of the vehicle.

[0008] The first determination module is used to determine whether the vehicle is approaching an intersection based on the positioning position information of the vehicle and the obtained navigation path information.

[0009] The second acquisition module is used to acquire road shape data corresponding to the navigation guidance action of the intersection when the vehicle approaches the intersection.

[0010] The request module is used to request the absolute position of the camera device when the vehicle passes through the intersection based on the road image captured by the camera device carried by the vehicle and the positioning position information of the vehicle when the road image is taken.

[0011] The second determination module is used to determine the real-time external parameters of the camera device according to the absolute position and posture of the camera device, the vehicle direction change data detected by the gyroscope carried by the vehicle, and the vehicle's driving speed.

[0012] The third determination module is used to determine the projection position of the road shape data on the road image collected by the camera device when the vehicle passes through the intersection based on the internal parameters and real-time external parameters of the camera device.

[0013] The rendering module is used to render the road shape on the road image according to the projection position of the road shape data on the road image to form a navigation guide line.

[0014] A fourth aspect of the embodiments of the present disclosure provides a device for generating road shape data, the device comprising:

[0015] A first acquisition module is used to obtain a passing path of the intersection based on the precise map data, wherein the passing path includes an entrance section into the intersection and an exit section out of the intersection;

[0016] The second acquisition module is used to acquire trajectory data matching the entry section and the exit section from the pre-collected trajectory data whose positioning accuracy meets the preset accuracy requirement;

[0017] The processing module is used to process the trajectory data into road shape data corresponding to the passing path of the intersection.

[0018] A fifth aspect of an embodiment of the present disclosure provides a navigation device, the navigation device comprising:

[0019] A memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor can execute the method of the first aspect mentioned above.

[0020] A sixth aspect of an embodiment of the present disclosure provides a computing device, the computing device comprising:

[0021] A memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor can execute the method of the second aspect mentioned above.

[0022] A seventh aspect of an embodiment of the present disclosure provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by a processor, the processor can execute the method of the first aspect or the second aspect mentioned above.

[0023] An eighth aspect of an embodiment of the present disclosure provides a computer program product, which includes: a computer program, which is stored in a computer-readable storage medium, and when the computer program is read and executed by a processor, the processor executes the method of the first aspect or the second aspect above.

[0024] Compared with the prior art, the technical solution provided by the embodiments of the present disclosure has the following advantages:

[0025] The disclosed embodiment acquires the positioning position information of the vehicle, predicts the shape of the road that the vehicle is about to pass through according to the positioning position of the vehicle and the obtained navigation path information, and can promptly acquire the road shape data corresponding to the navigation guidance action at the intersection when the vehicle is about to pass through the intersection. Since the road conditions at the intersection are relatively complicated, the road shape data of the intersection is acquired in advance, and the driving direction of the user at the intersection is guided based on the road shape data, so that the user can obtain the guidance information in advance, avoid the guidance being too hasty and causing the user to be unable to drive to the correct road in time, and improve the timeliness of the navigation guidance. By requesting the absolute position of the camera device when the vehicle passes through the intersection based on the road image captured by the camera device carried by the vehicle and the positioning position information of the vehicle when the road image is taken, the absolute position of the camera device when the vehicle is traveling at the intersection can be obtained in time. On this basis, the real-time external parameters of the camera device are determined according to the absolute position of the camera device, the direction change data of the vehicle and the driving speed. The real-time projection position of the road shape data on the road image can be accurately obtained according to the internal parameters and real-time external parameters of the camera device, so that the projection position of the road shape on the road image can always be consistent with the road on the road image, thereby improving the accuracy of intersection navigation guidance and improving the user's navigation guidance experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0028] Figure 1 is a schematic diagram of an exemplary navigation guidance scenario provided by an embodiment of the present disclosure;

[0029] Figure 2 is a flow chart of a navigation guidance method provided by an embodiment of the present disclosure;

[0030] Figure 3A and Figure 3B is a schematic diagram of a method for determining whether a vehicle is approaching an intersection provided by an embodiment of the present disclosure;

[0031] Figure 4A is a road image of an actual road provided by an embodiment of the present disclosure;

[0032] Figure 4B It is used to depict the Figure 4A a schematic diagram of the road shape of the road shown;

[0033] Figure 4C is based on Figure 4A A schematic diagram of a road shape line drawn by actual road shape data of the road shown;

[0034] Figure 4D Yes Figure 4B The road lines shown are rendered to Figure 4A A schematic diagram of the navigation guidance lines obtained on the road image shown;

[0035] Figure 4E Yes Figure 4C The road lines shown are rendered to Figure 4A A schematic diagram of the navigation guidance lines obtained on the road image shown;

[0036] Figure 5 is a flow chart of a method for generating road shape data provided by an embodiment of the present disclosure;

[0037] Figure 6 is a schematic diagram of a method for generating intersection road shape data provided by an embodiment of the present disclosure;

[0038] Fig. 7A It is a road shape diagram of an intersection;

[0039] Figure 7B yes Fig. 7A Schematic diagram of the extended trajectory gh;

[0040] Figure 8 is a structural schematic diagram of a navigation device provided by an embodiment of the present disclosure;

[0041] Fig. 9 It is a structural schematic diagram of a road shape data generating device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0042] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0043] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0044] In view of the problem of insufficient intersection navigation accuracy in related technologies, the embodiments of the present disclosure provide a navigation guidance solution. For example, Figure 1 is a schematic diagram of an exemplary navigation guidance scenario provided by an embodiment of the present disclosure, such as Figure 1 As shown, the navigation guidance scene includes a positioning satellite 10, a navigation device 11 and a server 12. Among them, the positioning satellite 10 can be a positioning satellite in the Global Navigation Satellite System (GNSS), and the GNSS positioning satellite can be a positioning satellite of the Global Positioning System (GPS), or a Beidou navigation satellite. The navigation device 11 can determine the positioning position information of the vehicle based on the signal of the positioning satellite. The navigation device 11 can be a device with positioning and navigation functions such as a mobile phone, a car machine, and a smart car box. The navigation device 11 is equipped with a computer program product with AR navigation function (such as a map navigation application or a shared travel application, etc.). Such products can plan the driving route according to the starting position and the end position set by the user, and guide the user to travel according to the planned driving route. The server 12 stores at least the following information: one or more road images collected near the intersection, information on the absolute position of the acquisition device when collecting these road images, and road shape data of the intersection. Among them, the road shape data can be road shape data collected from actual roads through measurement or mapping methods, with a positioning accuracy that meets preset accuracy requirements. For example, in the embodiment of the present disclosure, road shape data with an absolute positioning error within 1 meter and a relative positioning error within 20 centimeters can be exemplarily understood as high-precision road shape data that meets the accuracy requirements.

[0045] See also Figure 1 ,exist Figure 1 In the scene shown, the navigation device 11 obtains the positioning position information of the vehicle, and determines whether the vehicle is approaching the intersection according to the positioning position of the vehicle and the navigation path information obtained. When the vehicle approaches the intersection, the road shape data corresponding to the navigation action of the intersection is obtained from the server 12. When the vehicle passes through the intersection, the positioning position of the vehicle and the road image captured by the camera device on the vehicle at the positioning position are sent to the server 12, so that the server 12 calculates the absolute position and posture of the camera device when capturing the road image based on the preset algorithm and / or model, and feeds back the calculation result to the navigation device 11. After receiving the absolute position and posture fed back by the server 12, the navigation device 11 determines the real-time external parameters of the camera device according to the absolute position and posture of the camera device, the speed and driving direction of the vehicle, and determines the projection position of the road shape data of the intersection on the road image captured by the camera device when the vehicle passes through the intersection based on the internal parameters and real-time external parameters of the camera device, so as to render the road shape onto the road image according to the projection position to form a navigation guide line.

[0046] exist Figure 1 In the scenario shown, the navigation device 11 can predict the road shape that the vehicle is about to pass, and can promptly obtain road shape data corresponding to the navigation guidance action at the intersection when the vehicle is about to pass through the intersection. Since the road conditions at the intersection are relatively complicated, by obtaining the road shape data of the intersection in advance and guiding the user's driving direction at the intersection based on the road shape data, the user can obtain guidance information in advance, avoiding the situation where the guidance is too hasty and the user is unable to drive to the correct road in time, thereby improving the timeliness of the navigation guidance.

[0047] In addition, when the vehicle passes through the intersection, the absolute position of the camera device is requested based on the road image captured by the camera device carried by the vehicle and the positioning position information of the vehicle when the road image is taken, the real-time external parameters of the camera device are determined according to the absolute position of the camera device, the direction change data of the vehicle and the driving speed, the real-time projection position of the road shape data on the road image is determined according to the internal parameters and real-time external parameters of the camera device, and the road shape is rendered on the road image according to the projection position, so that the guide line on the road image can always fit the actual road on the road image, thereby improving the accuracy of road shape rendering and the accuracy of intersection navigation guidance.

[0048] The scheme of the embodiment of the present disclosure is described in detail below with reference to exemplary embodiments.

[0049] Figure 2is a flow chart of a navigation guidance method provided by an embodiment of the present disclosure. The method can be executed by a navigation device mounted on a vehicle, and the navigation device can be exemplified as a device equipped with a computer program product with AR navigation function (such as a map navigation application or a shared travel application, etc.), such as a mobile phone, a car computer, a smart car box, but not limited to these devices. Among them, the AR navigation function refers to a navigation method that uses a camera device, such as a mobile phone camera, a camera mounted on a vehicle, a driving recorder, etc., to obtain the image of the road ahead in real time, and combines the vehicle positioning position and navigation data to generate a virtual navigation guidance on the actual road image. As Figure 2 As shown, Figure 2 The navigation guidance method provided in the embodiment includes the following steps:

[0050] Step 201: Obtain the vehicle's location information.

[0051] In an exemplary implementation scenario, the positioning position information of the vehicle includes the coordinate position of the vehicle in the world coordinate system. The coordinate position can be obtained from the positioning system carried by the navigation device itself, or from the positioning system carried by the vehicle. Among them, the positioning system referred to in this embodiment may include but is not limited to at least one of the following systems: GPS, Beidou navigation system.

[0052] In another implementation scenario, the positioning position information of the vehicle may also include information about the road section where the vehicle is located and the position of the vehicle in the road section. The information about the road section where the vehicle is located may include, but is not limited to, at least one of the following information: the name of the road section, the road section number, the position of the road section, and the information about the road section near the road section connected to the road section. The information about the road section where the vehicle is located and the position of the vehicle in the road section may be obtained in a variety of ways. For example, in a feasible acquisition method, the road section where the coordinate position is located may be obtained from the pre-acquired map data according to the coordinate position of the vehicle in the world coordinate system, and then the relative position of the vehicle in the road section may be determined according to the coordinate range of the road section. For another example, in another feasible method, after obtaining the coordinate position of the vehicle in the world coordinate system, the road section where the coordinate position is located on the navigation path may be determined according to the pre-acquired navigation path information, and then the relative position of the vehicle in the road section may be determined according to the coordinate range of the road section in the world coordinate system.

[0053] Of course, the above two implementation scenarios are only examples. In practice, the vehicle positioning information can be obtained in different ways as needed, without being limited to one or several specific ways.

[0054] Step 202: Determine whether the vehicle is approaching an intersection based on the vehicle's positioning position information and the obtained navigation path information.

[0055] In this embodiment, the navigation path information includes the planned route from the starting position to the end position, as well as the road sections and road shape information that the planned route passes through. Intersections, as a common road shape, are an important navigation guidance scenario. In order to achieve effective navigation guidance at the intersection, it is necessary to determine whether the vehicle is approaching the intersection based on the vehicle's positioning position information and the obtained navigation path information, so as to obtain the road shape data corresponding to the navigation guidance action of the intersection in time when the vehicle approaches the intersection. Among them, there are many methods for judging whether the vehicle is approaching the intersection. For example, in a feasible implementation, according to a preset distance range, the information of the road shape in the path ahead of the vehicle within a preset distance range from the current positioning position can be obtained from the navigation path information for judgment. When it is determined that the preset distance range ahead of the vehicle includes an intersection, it is determined that the vehicle is approaching the intersection, otherwise it is determined that the vehicle is not approaching the intersection. For example, Figure 3A and Figure 3B It is a schematic diagram of a method for determining whether a vehicle is approaching an intersection provided by an embodiment of the present disclosure. Figure 3A and Figure 3B The curve e in the figure is a part of the navigation path, and the arrow on the curve e indicates the driving direction. Position a on the curve e is the position of the projection point of the vehicle's positioning position on the navigation path. Position b and position c are two positions on the path in front of the vehicle. Figure 3A In an embodiment, the preset distance range may be specifically the length range of the navigation path. Assuming that the actual path length corresponding to the curve between position a and position b on the navigation path (hereinafter referred to as curve ab) is n, and the value of n is the maximum path length specified in the preset distance range, then, in an exemplary embodiment, the road shape information corresponding to curve ab may be extracted from the navigation path information, and when curve ab passes through the intersection, it is determined that the vehicle is approaching the intersection. Figure 3B In the implementation of the preset distance range, the above-mentioned preset distance range can also be specifically the straight-line distance range between the position on the navigation path and the vehicle positioning position. Assuming that the straight-line distance between position c and position a is m, and the value of m is the maximum straight-line distance specified in the preset distance range, then, in another exemplary implementation, the road shape information corresponding to the curve ac can be extracted from the navigation path information, and when the curve ac passes through the intersection, it is determined that the vehicle is approaching the intersection. Of course, this is only an example and is not the only limitation of the embodiments of the present disclosure.

[0056] Step 203: When the vehicle approaches an intersection, obtain road shape data corresponding to the navigation guidance action of the intersection.

[0057] The road shape data in this embodiment can be used to describe the shape, curvature, coordinates (position in the world coordinate system) and other information of each position on the road shape. The road shape of a real road can be simulated by the road shape data. The coordinates of each point in the road shape data are expressed in the coordinates of the world coordinate system.

[0058] For example, the road shape data of this embodiment can be pre-produced based on the trajectory data whose positioning accuracy meets the preset accuracy requirements. In this embodiment, the trajectory data whose positioning accuracy meets the preset accuracy requirements can be exemplarily understood as high-precision trajectory data with an absolute positioning error within 1 meter and a relative positioning error within 20 centimeters, but in other embodiments, the preset accuracy can also be set as needed.

[0059] In this embodiment, there may be multiple methods for producing the road shape data. For example, in this exemplary implementation, based on the accurate map data, an action path corresponding to the navigation guidance action of the intersection may be obtained, and the action path includes: an entry section for entering the intersection and an exit section for exiting the intersection; then, in the pre-collected trajectory data whose positioning accuracy meets the preset accuracy requirements, trajectory data matching the entry section and the exit section of the intersection are obtained, and the trajectory data is processed into the road shape data corresponding to the navigation guidance action. Among them, in the process of processing the trajectory data into the road shape data corresponding to the navigation guidance action, the trajectory data may be directly used as the road shape data corresponding to the navigation guidance action, or the trajectory data may be processed in a preset manner to obtain the road shape data corresponding to the navigation guidance action. For example, in an exemplary preset processing method, the trajectory length of the entrance section and the trajectory length of the exit section of the intersection can be obtained respectively according to the trajectory data, and then the trajectory length of the entrance section and the trajectory length of the exit section are judged. If the trajectory length of the entrance section is less than the first preset length, and there are no other intersections within the first preset range before entering the intersection, the trajectory of the entrance section of the intersection is extended in the opposite direction of the direction of entering the intersection to obtain road shape data corresponding to the entrance section of the intersection; and / or, if the trajectory length of the exit section is less than the second preset length, and there are no other intersections within the second preset range after exiting the intersection, the trajectory of the exit section is extended in the direction of exiting the intersection to obtain road shape data corresponding to the exit section of the intersection.

[0060] In this embodiment, the road shape data obtained by the above method can be pre-stored in the navigation device or remote server. When the vehicle approaches the intersection, the navigation device can obtain the road shape data corresponding to the navigation guidance action of the intersection from the local or remote server according to the positioning position of the vehicle. For example, in an exemplary embodiment, after obtaining the positioning position of the vehicle, the road section information where the vehicle is currently located can be obtained according to the positioning position of the vehicle and the pre-obtained map data or navigation path information, and then the information of the intersection that the vehicle is about to pass is determined according to the road section where the vehicle is located and the navigation path information, and then the corresponding road shape data is obtained from the local or remote server according to the information of the intersection. For another example, in another exemplary embodiment, the information of the first road section entering the intersection and the information of the second road section exiting the intersection can also be obtained according to the pre-obtained navigation guidance action, and then the road shape data of the first road section entering the intersection and the second road section exiting the intersection in the collected road shape data can be obtained from the local or remote server as the road shape data of the intersection. Of course, this is only one implementation of the embodiment of the present disclosure and not all implementations. In fact, the method for obtaining road shape data can be set as needed and does not have to be limited to a specific method.

[0061] In related technologies, AR navigation technology generally renders the lines used to depict the road shape on a two-dimensional map onto a road image to generate virtual navigation guide lines. However, the lines on the two-dimensional map can only roughly reflect the style of the road shape, such as straight lines, forks, intersections, etc., and cannot accurately reflect the true shape of the road shape, such as arcs, shapes, etc. Therefore, the navigation guide lines generated based on the lines on the two-dimensional map cannot perfectly blend with the actual roads on the road image, resulting in reduced accuracy of navigation guidance. The road shape data of this embodiment is obtained through field collection and can truly reflect the true shape of the road shape, so that the navigation guide lines generated based on the road shape data can perfectly blend with the actual road shape on the road image. For example, Figure 4A is a road image of an actual road provided by an embodiment of the present disclosure, Figure 4B It is used to depict the Figure 4A A schematic diagram of the road shape lines of the road shown, Figure 4C is based on Figure 4A The schematic diagram of the road shape lines drawn by the actual road shape data of the road shown, Figure 4D Yes Figure 4B The road lines shown are rendered to Figure 4A A schematic diagram of the navigation guidance lines obtained on the road image shown in FIG. Figure 4E Yes Figure 4C The road lines shown are rendered to Figure 4A Schematic diagram of the navigation guidance lines obtained on the road image shown in FIG. Figure 4BAs shown in the figure, in general two-dimensional maps, for cartographic and aesthetic considerations, the same road shape, such as forks and intersections, is generally represented by lines of the same shape. However, these lines cannot truly reflect the actual shape and curvature of the road. Therefore, in Figure 4D In Figure 4B The road lines are rendered to Figure 4A The navigation guide line obtained after the road image is shown cannot perfectly coincide with the actual road on the road image, the guidance accuracy is low, and the user experience is poor. Figure 4C In the example, since the road shape line is obtained based on the real road shape data of the road, the line can truly reflect the actual shape and curvature of the road. Figure 4E In Figure 4C The road lines are rendered to Figure 4A The navigation guide line obtained on the road image can perfectly coincide with the actual road on the road image, with high guidance accuracy and good user experience. Figure 4A-4E It is not difficult to see that the solution of the embodiment of the present disclosure can effectively improve the accuracy of navigation guidance and improve the user experience.

[0062] Step 204: When the vehicle passes through the intersection, based on the road image captured by the camera device carried by the vehicle and the positioning position information of the vehicle when the road image is captured, the absolute position of the camera device is requested.

[0063] Among them, in this embodiment, the camera device can be specifically but not limited to one of the following mobile devices: a camera on a mobile phone, a camera device mounted on a car computer, a camera mounted on a vehicle, and a driving recorder. However, in other embodiments, it is not limited to the devices listed in this embodiment. In fact, any device with a shooting function can be applied as the camera device in this embodiment. In this embodiment, the absolute position and posture of the camera device can be understood as the position and posture of the camera device in the world coordinate system.

[0064] For example, in some embodiments, the requested device may be a server, that is, the navigation device may be configured to request the absolute position of the camera device from a preset server, and the server may be configured to determine and return the absolute position of the camera device based on the vehicle positioning information and the collected road image carried in the request of the navigation device. The method by which the server determines the absolute position of the camera device based on the vehicle positioning information and the collected road image carried in the request of the navigation device may include at least the following:

[0065] For example, in the following method, the server at least stores road images collected near the intersection and the absolute position of the collection device when collecting these road images. The server has image processing capabilities and computing capabilities.

[0066] For example, in an exemplary method, if the road image includes objects such as road signs that contain road information such as road names and road numbers, the server identifies the road information from the image, and then obtains an image that also contains the road information collected at that position from locally stored images based on the positioning position of the vehicle as a reference image, and then based on the reference image and the received road image, a preset model is used to obtain the relative pose between the camera device and the acquisition device of the reference image, and then based on the acquired relative pose and the absolute pose of the acquisition device when taking the reference image, the absolute pose of the camera device when taking the road image is calculated.

[0067] In another exemplary method, after receiving the road image and the positioning position information, the server can also first select multiple road images of the road near the positioning position from the pre-collected road images based on the positioning position information, and determine the image with the highest similarity to the received road image from these road images as a reference image, and then input the received road image and the determined reference image into a preset deep neural network model, and obtain the relative posture between the camera device and the acquisition device of the reference image through the output of the preset deep neural network model. Then, according to the absolute posture of the acquisition device of the reference image when acquiring the reference image, the absolute posture of the camera device can be obtained. That is to say, in this embodiment, this method can be exemplarily described as obtaining a reference image of the road near the positioning position from the pre-collected road images based on the positioning position information carried in the request of the navigation device, and the reference image refers to the road image with the highest similarity to the road image collected by the camera device at the positioning position; calculating the relative posture between the acquisition device of the reference image and the camera device according to the reference image and the road image; calculating the absolute posture of the camera device according to the relative posture between the acquisition device and the camera device and the absolute posture of the acquisition device when acquiring the reference image.

[0068] Step 205 : Determine the real-time external parameters of the camera device according to the absolute position and posture of the camera device, the vehicle direction change data detected by the gyroscope carried by the vehicle, and the driving speed of the vehicle.

[0069] The external parameters of the camera device refer to the parameters of the camera device in the world coordinate system, such as position and rotation direction.

[0070] The camera device and the gyroscope can be integrated into the same device or exist independently. Whether they are integrated together or set independently can be set as needed. For example, when the navigation device referred to in this embodiment is specifically a mobile phone or a car computer, the camera device and the gyroscope can be integrated into the mobile phone or the car computer at the same time. For another example, when the navigation device referred to in this embodiment is specifically a smart car box, the camera device can be integrated into the vehicle's driving recorder, and the gyroscope can be integrated into the smart car box. Of course, this is only an example. In fact, in different navigation scenarios, the integration method of the camera device and the gyroscope can be set as needed.

[0071] In practice, in order to obtain the accurate projection position of the road shape data on the road image, the real-time external parameters of the camera device must be obtained. In practice, the real-time external parameters of the camera device are associated with the real-time position and posture of the camera device, and the relative posture between the camera device and the vehicle is fixed, so the real-time position and posture of the camera device depend on the real-time position and posture of the vehicle. Since parameters such as the position and driving direction of the vehicle change in real time during driving, the real-time external parameters of the camera device after a certain moment can be calculated based on the absolute posture of the camera device at that moment and the driving direction and speed of the vehicle at that moment. The calculation method can be similar to that of the related technology, which will not be repeated here.

[0072] Step 206: Based on the intrinsic parameters and real-time extrinsic parameters of the camera device, determine the projection position of the road shape data on the road image captured by the camera device when the vehicle passes through the intersection.

[0073] The intrinsic parameters of the camera device refer to parameters related to the characteristics of the camera device itself, such as focal length, pixel size, etc.

[0074] In practice, the coordinate system corresponding to the real-time external parameters of the camera device is the world coordinate system, and the coordinate system corresponding to the internal parameters is the coordinate system of the camera device itself. The road shape data in this embodiment is a kind of data obtained in the world coordinate system. If the road shape data is to be projected onto the road image, it is necessary to convert the road shape data from the world coordinate system to the coordinate system of the camera device itself. Therefore, in one implementation of this embodiment, after obtaining the real-time external parameters of the camera device, the rotation and translation matrix and the camera projection matrix of the camera device can be first calculated according to the real-time external parameters and internal parameters of the camera device (the internal parameters of the camera device are fixed). Among them, the rotation and translation matrix is ​​used to describe the conversion relationship between the world coordinate system and the coordinate system of the camera device, and the camera projection matrix is ​​used to describe how to project a point in three-dimensional space into a two-dimensional image. Then, according to the rotation and translation matrix and the camera projection matrix, the projection position of the road shape data on the road image collected by the camera device is determined. The calculation method of the rotation and translation matrix and the camera projection matrix in this embodiment can adopt a method similar to the related art, which is not repeated here.

[0075] Step 207: Render the road shape on the road image according to the projection position of the road shape data on the road image to form a navigation guide line.

[0076] The disclosed embodiment acquires the positioning position information of the vehicle, predicts the shape of the road that the vehicle is about to pass through according to the positioning position of the vehicle and the obtained navigation path information, and can promptly acquire the road shape data corresponding to the navigation guidance action at the intersection when the vehicle is about to pass through the intersection. Since the road conditions at the intersection are relatively complicated, the road shape data of the intersection is acquired in advance, and the driving direction of the user at the intersection is guided based on the road shape data, so that the user can obtain the guidance information in advance, avoid the guidance being too hasty and causing the user to be unable to drive to the correct road in time, and improve the timeliness of the navigation guidance. By requesting the absolute position of the camera device when the vehicle passes through the intersection based on the road image captured by the camera device carried by the vehicle and the positioning position information of the vehicle when the road image is taken, the absolute position of the camera device when the vehicle is traveling at the intersection can be obtained in time. On this basis, the real-time external parameters of the camera device are determined according to the absolute position of the camera device, the direction change data of the vehicle and the driving speed. The real-time projection position of the road shape data on the road image can be accurately obtained according to the internal parameters and real-time external parameters of the camera device, so that the projection position of the road shape on the road image can always be consistent with the road on the road image, thereby improving the accuracy of intersection navigation guidance and improving the user's navigation guidance experience.

[0077] The above is an implementation method for when the vehicle is in a navigation guidance state. When the vehicle is in a cruising state, the solution provided by the embodiment of the present disclosure can also be combined with a solution for predicting the driving direction of the vehicle at an intersection. Specifically: the road shape data corresponding to the predicted high probability driving direction of the vehicle (equivalent to the navigation guidance action) is rendered in one way, for example, with a solid line, and the route data corresponding to other driving directions are rendered in other ways, for example, fading, becoming a dotted line or not displaying.

[0078] Figure 5 is a flow chart of a method for generating road shape data provided by an embodiment of the present disclosure, such as Figure 5 As shown, in an exemplary embodiment, the road shape data of the intersection can be obtained by the following method:

[0079] Step 501: Based on the precise map data, obtain a path through the intersection, where the path includes an entrance section into the intersection and an exit section out of the intersection.

[0080] Among them, the standard precision is an expression of positioning accuracy relative to high precision. Its absolute positioning error is generally greater than 1 meter, such as 5 meters or 10 meters, and the relative positioning error exceeds 20 centimeters, such as 1 meter or 2 meters.

[0081] Step 502: From the pre-collected trajectory data whose positioning accuracy meets the preset accuracy requirement, obtain trajectory data that matches the entry section and exit section of the intersection.

[0082] Step 503: Process the trajectory data into road shape data corresponding to the path through the intersection.

[0083] The trajectory data referred to in this embodiment can be exemplarily understood as high-precision trajectory data with an absolute positioning error within 1 meter and a relative positioning error within 20 centimeters. The trajectory data can be collected by a collection vehicle equipped with a high-precision GPS and an Advanced Driving Assistance System (ADAS).

[0084] Considering the issue of collection efficiency, in practice, a collection vehicle may collect trajectory data of one or more areas at the same time in one collection task, and these trajectory data may include trajectory data collected by the collection vehicle at multiple intersections. So how to determine the correspondence between these trajectory data and intersections is also one of the technical problems solved by the embodiments of the present disclosure. Since an intersection is usually located at the junction of two sections, that is, the section entering the intersection and the section exiting the intersection are usually two different sections, and different sections have different GPS information, therefore, in one implementation of this embodiment, the information of the entry section and the exit section of a certain intersection can be first obtained according to the precise map data, and the information includes the GPS information corresponding to each point in the entry section and the exit section. Then, according to the GPS information of each point in the entry section and the exit section, all the trajectory data collected by the collection vehicle are traversed. When the entry section corresponding to the trajectory data is the same as the entry section of the intersection, and the exit section is the same as the exit section of the intersection, then this trajectory data is processed into the road shape data of the intersection. For example, Figure 6 is a schematic diagram of a method for generating intersection road shape data provided by an embodiment of the present disclosure, such as Figure 6 As shown, assuming that the intersection includes section a, section b and section c, driving trajectory d and driving trajectory e are driving trajectories obtained based on two different trajectory data. Among them, section a is the section entering the intersection, and section b and section c are exit sections corresponding to different exits. The GPS coordinates of the entry trajectory 61 in trajectory d are the same as the GPS coordinates of section a, and the GPS coordinates of the exit trajectory 62 are the same as the GPS coordinates of section b. The GPS coordinates of the entry trajectory 63 in trajectory e are the same as the GPS coordinates of section a, and the GPS coordinates of the exit trajectory 64 are the same as the GPS coordinates of section c. Assuming that according to the navigation path indication, the vehicle needs to enter from section a and exit from section b, then it is necessary to obtain the road shape data from section a to section b. After the section matching, it is found that the entry section of trajectory d is section a, and the exit section is section b. Then the trajectory data corresponding to trajectory d can be used as the road shape data from section a to section b, and trajectory d is rendered on the road image of the intersection to obtain the navigation guide line. Of course, this is only an example and not a limitation.

[0085] Furthermore, in order to increase the guidance distance of the intersection, the user can clearly know the path at the intersection even if he is far away from the intersection, and prepare in advance. In an exemplary implementation of the present embodiment, after obtaining the trajectory data matching the entry section and the exit section of the intersection, the trajectory length of the entry section and the trajectory length of the exit section of the intersection can also be obtained according to the trajectory data. When the trajectory length of the entry section is less than the first preset length, and there are no other intersections within the first preset range before entering the intersection, the trajectory of the entry section is extended in the opposite direction of the direction of entering the intersection to obtain the road shape data corresponding to the entry section of the intersection, and / or, when the trajectory length of the exit section is less than the second preset length, and there are no other intersections within the second preset range after exiting the intersection, the trajectory of the exit section is extended in the opposite direction of the direction of exiting the intersection to obtain the road shape data corresponding to the exit section of the intersection. For example, Fig. 7A It is a schematic diagram of the road shape of an intersection. Fig. 7A In , the trajectory gh is the trajectory obtained based on the trajectory data collected at the intersection, such as Fig. 7A As shown in the figure, there is no other intersection before entering the intersection, and there is no other road opening after exiting the intersection. Then, the g end of the trajectory gh can be extended in the opposite direction of the entry direction, and the h end of the trajectory gh can be extended in the exit direction, and the Figure 7B The track shown, wherein the extension length of the track can be set as required, is not specifically limited in this embodiment.

[0086] Since the road shape data of the embodiment of the present disclosure is obtained based on high-precision trajectory data, the road shape obtained according to the road shape data is more accurate than the road shape in the precision map. Therefore, after the road shape is rendered onto the road image, the road shape can fit the road on the road image, thereby improving the accuracy of intersection guidance and user experience.

[0087] Figure 8 is a structural diagram of a navigation device provided by an embodiment of the present disclosure, and the navigation device can be understood as the navigation device or a part of the functional modules of the navigation device in the above embodiment. Figure 8 As shown, the navigation device 80 includes:

[0088] The first acquisition module 81 is used to acquire the positioning position information of the vehicle.

[0089] The first determination module 82 is used to determine whether the vehicle is approaching an intersection based on the vehicle's positioning position information and the obtained navigation path information.

[0090] The second acquisition module 83 is used to acquire road shape data corresponding to the navigation guidance action of the intersection when the vehicle approaches the intersection.

[0091] The request module 84 is used to request the absolute position of the camera device when the vehicle passes through the intersection based on the road image captured by the camera device carried by the vehicle and the positioning position information of the vehicle when the road image is captured.

[0092] The second determination module 85 is used to determine the real-time external parameters of the camera device according to the absolute position and posture of the camera device, the vehicle direction change data detected by the gyroscope carried by the vehicle, and the driving speed of the vehicle.

[0093] The third determination module 86 is used to determine the projection position of the road shape data on the road image captured by the camera device when the vehicle passes through the intersection based on the intrinsic parameters and real-time extrinsic parameters of the camera device.

[0094] The rendering module 87 is used to render the road shape on the road image according to the projection position to form a navigation guide line.

[0095] In one implementation, the second acquisition module 83 is used to:

[0096] According to the navigation guidance action of the intersection, the information of the first road section entering the intersection and the information of the second road section exiting the intersection are obtained; the road shape data of the first road section as the entry section and the second road section as the exit section in the collected road shape data are obtained as the road shape data of the intersection.

[0097] In one embodiment, the road shape data is pre-made based on the trajectory data, and the device 80 further includes:

[0098] A first acquisition module is used to obtain an action path corresponding to the navigation guidance action of the intersection based on the precise map data, and the action path includes: an entry section into the intersection and an exit section out of the intersection;

[0099] A first acquisition module is used to acquire trajectory data matching the entry section and the exit section from the pre-collected trajectory data whose positioning accuracy meets the preset accuracy requirement;

[0100] The processing module is used to process the trajectory data into road shape data corresponding to the navigation guidance action.

[0101] In one embodiment, the processing module,

[0102] Used to obtain the trajectory length of the entry section and the trajectory length of the exit section respectively according to the trajectory data;

[0103] If the length of the trajectory of the entry section is less than the first preset length, and there is no other intersection within the first preset range before the entry intersection, the trajectory of the entry section is extended in the opposite direction of the direction of the entry intersection to obtain the road shape data corresponding to the entry section;

[0104] and / or

[0105] If the trajectory length of the exit section is less than the second preset length and there is no other intersection within the second preset range after the exit intersection, the trajectory of the exit section is extended along the direction of the exit intersection to obtain road shape data corresponding to the exit section.

[0106] In one embodiment, the request module 84 requests the absolute posture of the camera device based on the road image captured by the camera device mounted on the vehicle and the positioning position information of the vehicle when taking the road image, so that the requested device determines and returns the absolute posture of the camera device based on the positioning position information of the vehicle carried in the request and the captured road image.

[0107] In one implementation, based on the vehicle positioning information carried in the request and the collected road image, determining and returning the absolute position of the camera device specifically includes:

[0108] Based on the positioning position information of the vehicle carried in the request, a reference image of the road near the positioning position is obtained from the pre-collected road images, where the reference image refers to a road image that has the highest similarity to the road image collected by the camera device at the positioning position; the relative pose between the acquisition device of the reference image and the camera device is calculated based on the reference image and the received road image; the absolute pose of the camera device is calculated based on the calculated relative pose and the absolute pose of the acquisition device when collecting the reference image.

[0109] In one implementation, the third determination module 86 is configured to:

[0110] Based on the intrinsic parameters and real-time extrinsic parameters of the camera device, the rotation and translation matrix and the camera projection matrix of the camera device are calculated; based on the rotation and translation matrix and the camera projection matrix, the projection position of the road shape data on the road image collected by the camera device when the vehicle passes through the intersection is determined.

[0111] The device provided in this embodiment can perform the above Figure 1 -The method of any embodiment in Figure 7 has similar execution methods and beneficial effects, which will not be repeated here.

[0112] Fig. 9 is a schematic diagram of the structure of a road shape data generating device provided by an embodiment of the present disclosure, such as Fig. 9 As shown, the road shape data generating device 90 includes:

[0113] A first acquisition module 91 is used to obtain a path through the intersection based on the precise map data, wherein the path through the intersection includes an entry section into the intersection and an exit section out of the intersection;

[0114] A second acquisition module 92 is used to acquire trajectory data matching the entry section and the exit section from the pre-collected trajectory data whose positioning accuracy meets the preset accuracy requirement;

[0115] The processing module 93 is used to process the trajectory data into road shape data corresponding to the passing path of the intersection.

[0116] In one embodiment, the processing module 93 is used to:

[0117] According to the trajectory data, respectively obtaining the trajectory length of the entry section and the trajectory length of the exit section;

[0118] If the trajectory length corresponding to the entry section is less than a first preset length and there is no other intersection within a first preset range before entering the intersection, the trajectory of the entry section is extended in the opposite direction of the direction of entering the intersection to obtain the road shape data of the entry section corresponding to the passing path;

[0119] and / or

[0120] If the trajectory length corresponding to the exit section is less than the second preset length, and there is no other intersection within the second preset range after exiting the intersection, the trajectory of the exit section is extended along the direction of exiting the intersection to obtain the road shape data of the exit section corresponding to the passing path.

[0121] The device provided in this embodiment can perform the above Figure 5 The method of the embodiment has similar execution mode and beneficial effects, which will not be described in detail here.

[0122] The present disclosure also provides a navigation device, which includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor can perform the above Figure 1 - The method of any embodiment in Figure 7. Wherein, the navigation device includes at least one of the following: a mobile phone, a car machine, and a smart car box.

[0123] The present disclosure also provides a computing device, which includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor can perform the above Figure 5 Method of embodiment.

[0124] The present disclosure also provides a computer-readable storage medium in which a computer program is stored. When the computer program is executed by a processor, the processor can perform the above Figure 1 - The method of any one of the embodiments in FIG. 7 .

[0125] The present disclosure also provides a computer program product, which includes: a computer program stored in a computer-readable storage medium, and when the computer program is read and executed by a processor, the processor executes the above Figure 1 - The method of any one of the embodiments in FIG. 7 .

[0126] Wherein, the computer-readable storage medium can be a tangible medium, which can contain or store a program for use by an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. The computer-readable storage medium can be a machine-readable signal medium or a machine-readable storage medium. The computer-readable storage medium can include but is not limited to electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the above. A more specific example of computer-readable can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0127] The computer program stored in the computer-readable storage medium may be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The computer program may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server.

[0128] The method, device or product provided in the embodiments of the present disclosure can be implemented together with other technical solutions for realizing AR navigation in actual application. In this case, the navigation device can determine which technical solution to enable at the corresponding intersection. For example, if the intersection is in a normal traffic state, the solution provided in the embodiments of the present disclosure can be enabled. If there are special events such as road closures and accidents at the intersection, the AR navigation technical solution based on visual recognition can be enabled. The present disclosure does not impose any restrictions on this. The method, device or product provided in the embodiments of the present disclosure can be applied to scenarios requiring AR navigation, such as logistics, shared travel, and autonomous driving.

[0129] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0130] The above description is only a specific embodiment of the present disclosure, so that those skilled in the art can understand or implement the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A navigation guidance method, comprising: Obtaining the vehicle's location information; Determining whether the vehicle is approaching an intersection based on the positioning position information and the obtained navigation path information; When the vehicle approaches an intersection, obtaining road shape data corresponding to the navigation guidance action of the intersection from pre-made road shape data; When the vehicle passes through the intersection, based on a road image captured by a camera mounted on the vehicle and the positioning position information of the vehicle when the road image is captured, requesting the absolute position of the camera; Determine the real-time external parameters of the camera device according to the absolute position and posture of the camera device, the vehicle direction change data detected by the gyroscope carried by the vehicle, and the driving speed of the vehicle; Based on the intrinsic parameters and real-time extrinsic parameters of the camera device, determining the projection position of the road shape data on the road image captured by the camera device when the vehicle passes through the intersection; Rendering the road shape on the road image according to the projection position to form a navigation guide line; The road shape data is pre-made based on the trajectory data, and specifically includes: Based on the precise map data, an action path corresponding to the navigation guidance action of the intersection is obtained, wherein the action path includes: an entry section for entering the intersection and an exit section for exiting the intersection; Acquire trajectory data matching the entry section and the exit section from pre-collected trajectory data whose positioning accuracy meets preset accuracy requirements; The trajectory data is processed into road shape data corresponding to the navigation guidance action.

2. The method according to claim 1, wherein: The acquiring of the road shape data corresponding to the navigation guidance action at the intersection includes: According to the navigation guidance action of the intersection, obtaining information of a first road section entering the intersection and information of a second road section exiting the intersection; The road shape data of the intersection is obtained by obtaining the road shape data in which the entry section is the first road section and the exit section is the second road section.

3. The method according to claim 1, wherein: The processing of the trajectory data into road shape data corresponding to the navigation guidance action specifically includes: According to the trajectory data, respectively obtaining the trajectory length of the entry section and the trajectory length of the exit section; If the length of the trajectory of the entering road section is less than a first preset length and there is no other intersection within a first preset range before entering the intersection, the trajectory of the entering road section is extended in the opposite direction of the direction of entering the intersection to obtain road shape data corresponding to the entering road section; and / or If the trajectory length of the exit section is less than a second preset length and there is no other intersection within a second preset range after exiting the intersection, the trajectory of the exit section is extended along the direction of exiting the intersection to obtain road shape data corresponding to the exit section.

4. The method according to claim 1, wherein: Based on a road image captured by a camera mounted on a vehicle and the positioning position information of the vehicle when the road image is captured, requesting the absolute position of the camera, specifically comprising: Based on the road image captured by the camera device mounted on the vehicle and the positioning position information of the vehicle when taking the road image, an absolute posture positioning request is sent to the requested device, so that the requested device determines and returns the absolute posture of the camera device based on the positioning position information of the vehicle carried in the request and the captured road image.

5. The method according to claim 4, wherein: Determining and returning the absolute position of the camera device based on the positioning position information of the vehicle carried in the request and the collected road image, specifically including: Based on the positioning position information of the vehicle carried in the request, obtaining a reference image of the road near the positioning position from pre-collected road images, wherein the reference image refers to a road image having the highest similarity to the road image collected by the camera at the positioning position; Calculate the relative position and posture between the acquisition device of the reference image and the camera device according to the reference image and the road image; The absolute posture of the camera device is calculated based on the relative posture and the absolute posture of the acquisition device when acquiring the reference image.

6. The method according to claim 1 or 5, wherein: The step of determining the projection position of the road shape data on the road image captured by the camera device when the vehicle passes through the intersection based on the intrinsic parameters and real-time extrinsic parameters of the camera device comprises: Based on the intrinsic parameters and real-time extrinsic parameters of the camera device, a rotation and translation matrix and a camera projection matrix of the camera device are calculated; Based on the rotation and translation matrix and the camera projection matrix, a projection position of the road shape data on a road image captured by a camera when the vehicle passes through the intersection is determined.

7. A method for generating road shape data, comprising: Based on the precise map data, a path through the intersection is obtained, wherein the path through the intersection includes an entrance section into the intersection and an exit section out of the intersection; Acquire trajectory data matching the entry section and the exit section from pre-collected trajectory data whose positioning accuracy meets preset accuracy requirements; The trajectory data is processed into road shape data corresponding to a passing path of the intersection.

8. The method according to claim 7, wherein: The step of processing the trajectory data into road shape data corresponding to the passing path of the intersection includes: According to the trajectory data, respectively obtaining the trajectory length of the entry section and the trajectory length of the exit section; If the trajectory length corresponding to the entry section is less than a first preset length and there is no other intersection within a first preset range before entering the intersection, the trajectory of the entry section is extended in the opposite direction of the direction of entering the intersection to obtain the road shape data of the entry section corresponding to the passing path; and / or If the trajectory length corresponding to the exit section is less than the second preset length, and there is no other intersection within the second preset range after exiting the intersection, the trajectory of the exit section is extended along the direction of exiting the intersection to obtain the road shape data of the exit section corresponding to the passing path.

9. A navigation guidance device, comprising: A first acquisition module is used to acquire the positioning position information of the vehicle; A first determination module, used to determine whether the vehicle is approaching an intersection based on the positioning position information and the obtained navigation path information; A second acquisition module is used to acquire, when the vehicle approaches an intersection, road shape data corresponding to the navigation guidance action of the intersection from pre-made road shape data; A request module, configured to request the absolute position of the camera device when the vehicle passes through the intersection based on the road image captured by the camera device carried by the vehicle and the positioning position information of the vehicle when the road image is captured; A second determination module is used to determine the real-time external parameters of the camera device according to the absolute position and posture of the camera device, the vehicle direction change data detected by the gyroscope carried by the vehicle, and the driving speed of the vehicle; A third determination module is used to determine the projection position of the road shape data on the road image collected by the camera device when the vehicle passes through the intersection based on the intrinsic parameters and real-time extrinsic parameters of the camera device; A rendering module, used for rendering the road shape on the road image according to the projection position to form a navigation guide line; The road shape data is pre-made based on the trajectory data, and specifically includes: Based on the precise map data, an action path corresponding to the navigation guidance action of the intersection is obtained, wherein the action path includes: an entry section for entering the intersection and an exit section for exiting the intersection; Acquire trajectory data matching the entry section and the exit section from pre-collected trajectory data whose positioning accuracy meets preset accuracy requirements; The trajectory data is processed into road shape data corresponding to the navigation guidance action.

10. A road shape data generating device, comprising: A first acquisition module is used to obtain a path through the intersection based on the precise map data, wherein the path through the intersection includes an entry section into the intersection and an exit section out of the intersection; A second acquisition module is used to acquire trajectory data matching the entry section and the exit section from the pre-collected trajectory data whose positioning accuracy meets the preset accuracy requirement; A processing module is used to process the trajectory data into road shape data corresponding to the passing path of the intersection.

11. A navigation device comprising: A memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the method according to any one of claims 1 to 6.

12. A computing device comprising: A memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the method according to claim 7 or 8.

13. A computer-readable storage medium, wherein a computer program is stored in the storage medium, and when the computer program is executed by a processor, the processor executes the method according to any one of claims 1 to 8.

14. A computer program product, the computer program product comprising: A computer program, wherein the computer program is stored in a computer-readable storage medium, and when the computer program is read and executed by a processor, the processor is caused to execute the method according to any one of claims 1 to 8.

Images