A Method and Device for Calibrating the Coordinates of Road Administration Facilities Based on High-Precision Vehicle Positioning

Abstract

The present invention discloses a method for calibrating the coordinates of road administration facilities based on high-precision vehicle positioning. Road administration facilities are set beside the road, and the road administration facilities include a feature part and the area of the feature part. A high-precision positioning device and a first imaging unit are set on a first vehicle. The first coordinate of the first vehicle is obtained according to the high-precision positioning device, the feature part is obtained through the first imaging unit, and the area of the feature part is obtained through the server. The coordinates of the road administration facilities are calibrated according to the first imaging position of the feature part in the first imaging unit, the area of the first imaging feature part, and the first coordinate. A device for calibrating the coordinates of road administration facilities based on high-precision vehicle positioning is also disclosed. On the one hand, it reduces the coordinate measurement when a large number of road administration facilities are set on the road; on the other hand, it can also provide a more accurate and reliable coordinate basis for autonomous driving technology; at the same time, it can also perform high-precision positioning on vehicles without high-precision positioning.

Description

Technical Field

[0001] The present invention relates to the technical field of coordinate calibration of road administration facilities, and particularly relates to a method and device for coordinate calibration of road administration facilities based on high-precision vehicle positioning. Background Art

[0002] In vehicle positioning technology, it is a very common means to adopt a fusion positioning system composed of inertial navigation, satellite navigation and wheel speed sensors, and relatively satisfactory positioning performance can be obtained in many scenarios. Compared with using a single navigation device, it has the advantages of full autonomy, all-weather, and being free from external information interference. However, the development of autonomous driving technology has put forward higher requirements for the performance of the fusion positioning system. The fusion positioning device needs to achieve real-time and uninterrupted centimeter-level positioning in all scenarios. It is very difficult for the fusion positioning device composed of inertial navigation, satellite navigation and wheel speed sensors to meet the above requirements. In the case of long-term loss of satellite signals, especially in places such as tunnels or viaducts, the positioning error of inertial / wheel speed sensor fusion positioning will accumulate with the increase of the vehicle driving mileage, causing the positioning result to gradually deviate from the true position of the vehicle, thus leading to the inability to continue autonomous driving.

[0003] To solve this problem, the commonly adopted technical solutions usually include technical means such as adding map matching, adding lidar positioning, adding visual navigation, or the superposition of several means. However, continuous high-precision positioning by map matching requires obvious geometric features on the driving route, and it is difficult to ensure the feature requirements for the actual driving route of the vehicle; laying out a large number of geometric feature graphics on the driving route will incur huge labor costs only for the positioning and calibration of each feature graphic. Summary of the Invention

[0004] Based on the above situation, the present invention proposes a method for coordinate calibration of road administration facilities based on high-precision vehicle positioning, which utilizes high-precision vehicle positioning equipment to calibrate the coordinates of road administration facilities set beside the road by a server during vehicle driving. In this way, on the one hand, it reduces the coordinate measurement when a large number of road administration facilities are set on the road; on the other hand, it can also provide a more accurate and reliable coordinate basis for autonomous driving technology.

[0005] The present invention provides a method for coordinate calibration of road administration facilities based on high-precision vehicle positioning. Road administration facilities are set beside the road, and the road administration facilities include a feature part and the area of the feature part; a high-precision positioning device and a first camera unit are set on a first vehicle; the first coordinate of the first vehicle is obtained according to the high-precision positioning device, the feature part is obtained through the first camera unit, and the area of the feature part is obtained through the server; the coordinates of the road administration facilities are calibrated according to the first imaging position of the feature part in the first camera unit, the area of the first imaging feature part, and the first coordinate.

[0006] The steps for calibrating the coordinates of road administration facilities include: obtaining the first distance between the first vehicle and the road administration facilities based on the area of the road administration facilities and the area of the first imaged road administration facilities; obtaining the first angle between the first vehicle and the road administration facilities based on the position of the imaging of the road administration facilities in the first imaging unit; calculating and generating the coordinates of the road administration facilities using the first distance, the first angle, and the first coordinates.

[0007] When the area of the first imaged feature part is less than the preset threshold, the vehicle can set a second imaging unit; set the spacing between the first imaging unit and the second imaging unit; obtain the first angle of the included angle between the first imaging unit and the road administration facilities and obtain the second angle of the included angle between the second imaging unit and the road administration facilities, calculate and obtain the relative position information between the vehicle and the road administration facilities based on the spacing, the first angle, and the second angle, and calculate the coordinates of the road administration facilities based on the first coordinates and the relative position information.

[0008] The first vehicle obtains the first imaging position and the area of the first imaged road administration facilities of the road administration facilities in the first imaging unit at the first moment; obtains the second imaging position and the area of the second imaged road administration facilities of the road administration facilities in the imaging unit at the second moment; calculates the offset angle of the vehicle based on the first imaging position and the second imaging position, and calculates the offset distance of the vehicle based on the area of the first imaged road administration facilities and the area of the second imaged road administration facilities; calculates the time difference between the first moment and the second moment; calculates and obtains the angular acceleration and linear acceleration of the first vehicle; corrects the IMU data of the first vehicle.

[0009] The road administration facilities may further include a feature line segment and the length of the feature line segment; when the vehicle obtains the feature part through the first imaging unit and obtains the feature line segment and the length of the feature line segment through the server; use the feature line segment to replace the feature part and use the length of the feature line segment to replace the area of the feature part.

[0010] The coordinates of the road administration facilities, the feature part, and the area of the feature part are uploaded to the cloud server.

[0011] Meanwhile, the present invention also provides a device for calibrating the coordinates of road administration facilities based on high-precision vehicle positioning, which is characterized in that it includes: a first vehicle imaging module, a high-precision positioning module, and a module for calibrating the coordinates of road administration facilities, and the data of each module is connected;

[0012] The first vehicle camera module includes at least a first camera unit and is installed on the first vehicle; it is used to capture the road administration facilities set beside the road through the first camera unit and obtain the characteristic parts of the road administration facilities; the road administration facilities include characteristic parts and the area of the characteristic parts; the high-precision positioning module is used to obtain the first coordinate of the first vehicle according to the high-precision positioning device; the road administration facility coordinate calibration module is used to calibrate the coordinates of the road administration facilities according to the first imaging position of the characteristic parts of the road administration facilities in the first camera unit, the area of the first imaging characteristic parts, and the first coordinate.

[0013] Some technical effects of the present disclosure are as follows: By using the vehicle high-precision positioning device, during the vehicle's driving, the high-precision coordinate calibration of the road administration facilities set beside the road is carried out through the cloud server. In this way, on the one hand, it reduces the coordinate measurement when a large number of road administration facilities are set on the road; on the other hand, it can also provide a more accurate and reliable coordinate basis for the autonomous driving technology. At the same time, it can also perform high-precision positioning on vehicles without high-precision positioning and correct the IMU data. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] For a better understanding of the technical solutions of the present disclosure, the following drawings can be referred to, which are used to assist in explaining the prior art or embodiments. These drawings will selectively show the products or methods involved in the prior art or some embodiments of the present disclosure. The basic information of these drawings is as follows:

[0015] Figure 1 It is a flowchart of an embodiment of a method for calibrating the coordinates of road administration facilities based on vehicle high-precision positioning of the present invention.

[0016] Figure 2 It is a schematic diagram of the characteristic parts corresponding to the conventional road administration facilities in an embodiment of the present invention.

[0017] Figure 3 It is a schematic diagram of the first angle in an embodiment of the present invention.

[0018] Figure 4 It is a flowchart of an embodiment of a device for calibrating the coordinates of road administration facilities based on vehicle high-precision positioning of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] The technical means or technical effects involved in the present disclosure will be further described in detail below. Obviously, the provided embodiments are only part of the implementation manners of the present disclosure, rather than all. Based on the embodiments and the explicit or implicit content in the drawings in the present disclosure, all other embodiments that those skilled in the art can obtain without creative labor will fall within the protection scope of the present disclosure.

[0020] Such as Figure 1As shown in the figure, the method in this embodiment includes the following steps:

[0021] S1: Set road administration facilities beside the road. The road administration facilities include a feature part and the area of the feature part.

[0022] Currently, some road administration facilities are set around ordinary roads and highways (including both sides of the road or above the road. In some cases, for better distinction, they are set on the road, such as printed fonts or road signs). According to the functions played by the road administration facilities and the conventional graphics used, the feature part of the road administration facility and the corresponding area of the feature part can be known during layout. Upload the feature part of the road administration facility, the corresponding area of the feature part, and the corresponding first coordinate to the server. In this way, each road administration facility will have a feature part and the area of the feature part. For example Figure 2 As described above, road administration facilities generally include traffic signs, street lights, and traffic lights. Conventional road administration facilities have obvious features, and the feature part and the corresponding area of the feature part can be identified through image recognition technology. When the road administration facility is a traffic sign set by the roadside, the conventional feature part includes conventional graphics such as circles, triangles, quadrilaterals, or trapezoids (of course, equilateral triangles, squares, or isosceles trapezoids are better). The area of the feature part can be measured before layout, or the manufacturer can provide the corresponding marked area after production. In addition, the feature part recognition of some road administration facilities cannot be easily converted into conventional graphics. Then, the outermost points of the recognized feature part can be used as feature points to virtually construct a new conventional graphic (such as a triangle, square, or trapezoid), and the area of the virtually constructed graphic is given during layout. And store and mark the virtual area data in the server. That is, the user can recognize the road administration facility without a conventional graphic through the feature part, and use the virtual constructed area comparison for calculation when calculating the distance. When performing feature recognition, since there is a certain angle between the vehicle and the graphic, the graphic may be distorted. Through the imaging position of the graphic in the camera unit, the shooting angle between the graphic and the vehicle can be known. The graphic can be corrected for distortion and compensated for distortion correction through the shooting angle. Since this technology is relatively mature, it will not be described in detail in this embodiment.

[0023] S2: Set a high-precision positioning device and a first camera unit on the first vehicle; obtain the first coordinate of the first vehicle according to the high-precision positioning device, and the first camera unit obtains the feature part and obtains the area of the feature part through the server.

[0024] When the satellite signal is very good, a dedicated high-precision positioning device is set in the first vehicle, and continuous high-precision positioning (centimeter level) can be obtained. The accuracy and credibility of this positioning are relatively high; the first vehicle travels on the road, continuously obtains the first coordinates of high-precision positioning and takes pictures of the road ahead through the first camera unit; when detecting road administration facilities, identify special parts of the road administration facilities.

[0025] As a special case, a characteristic part of a road administration facility only corresponds to one characteristic part area. In this case, only a set of data of the road administration facility needs to be stored in the server.

[0026] In the case of large-scale use, it is inevitable that many road administration facilities use the same characteristic parts but have different corresponding first coordinates. At this time, there are two ways for the first camera unit to obtain the characteristic parts and obtain the characteristic part area through the server: The first is to upload the current first coordinates of the vehicle, obtain the characteristic parts of the road administration facilities within the preset range of the first coordinates, and through the data pre-stored in the server, it is possible to accurately know which road administration facility in the server the currently photographed road administration facility is, and then determine the characteristic part area corresponding to the obtained road administration facility. This method is suitable for the case where there are a large number of road administration facilities for positioning, which can greatly reduce the data burden on the server. The second is to obtain all the road administration facilities corresponding to the characteristic parts obtained by all the first camera units, and obtain the corresponding characteristic part area according to this characteristic; then, through the first coordinates uploaded by the vehicle, judge whether it is within the preset range of the first coordinates. If so, screen out the road administration facilities photographed by the current first camera unit; and obtain the corresponding characteristic part area. This method generally transmits the result to the vehicle after big data cloud computing. The camera unit mentioned in this embodiment can use a high-definition camera device or generally refers to all devices that can take pictures.

[0027] S3: Calibrate the coordinates of the road administration facility according to the first imaging position of the characteristic part of the road administration facility in the first camera unit, the first imaging of the characteristic part area, and the first coordinates.

[0028] After the first vehicle captures the characteristic part of the road administration facility, there is a first imaging position and a first imaging characteristic part area of the characteristic part of the road administration facility in the first imaging unit. Generally, the first imaging of the road administration facility obtained by the imaging unit will be in the currently captured picture. The closer the vehicle is to the road administration facility, the larger its area in the imaging unit will be. By using the change in area during the driving process of the first vehicle when it captures the characteristic part of the road administration facility as an empirical value, the first distance between the first vehicle and the road administration facility can be calculated; through such an empirical value, a reference list can be listed, and there is a reference relationship between the characteristic part area and the area of the first imaged road administration facility. Specifically, on the test section, by taking pictures 1000 times (the more test times, the more accurate) of the area change situation and the first imaging position situation when the first vehicle is 1 - 200 meters away from the road administration facility, record the current area. When the same area and the same first imaging position are extracted, the distance between the first vehicle and the road administration facility can be known. By repeatedly recording the angles formed by the vehicle in different lanes and the captured areas, a series of corresponding values can be obtained. The server records these values, and then the accurate positioning of the road administration facility can be achieved through the high-precision positioning of the first vehicle. The first imaging characteristic part area refers to the area of the first imaging of the characteristic part of the road administration facility in the imaging unit, and its change can also be calculated through relevant algorithms defining area change. There are relevant records in the prior art (Visual SLAM, PnP technology), which will not be elaborated here. When shooting and identifying, the intersection point of the diagonal of the road administration facility image can be used as the point collected by the imaging unit. According to the position of the road administration facility in the captured picture to form the first imaging position of the road administration facility, the first angle formed by the road administration facility and the first vehicle can be obtained. As Figure 2 shown, the included angle formed by the plane extension line of the imaging unit and the straight line connecting the imaging unit to the road administration facility is defined as the first angle. Then, the coordinates of the road administration facility are calculated and generated by using the first distance, the first angle, and the first coordinate. Since the first coordinate is a high-precision positioning value and the distance between the road administration facility and the vehicle is an empirical or calculated conversion value, both have relatively high data reliability. Based on the first distance, the first angle, and the first coordinate, a simple coordinate system can be established, and the corresponding coordinates of the road administration facility can be calculated through coordinate conversion. In addition, regarding the first distance and the first angle, there are relatively many ways to define and calculate them based on the area and the corresponding imaging area. There can be different definitions and different calculation methods (Visual SLAM, PnP technology), but it should be understood that the methods for calculating the corresponding numerical values and coordinate relationships are all changed or modified on this basis. This embodiment will not elaborate on this here.

[0029] Since the vehicle can roughly identify road administration facilities at a relatively far distance by using an ordinary navigation map in cooperation with the first camera unit during driving, but the area of the characteristic part of the road administration facilities is too small, and it is shown as a small point on the graph. If it is greater than the preset threshold, the first camera unit can be directly used. When the area of the first imaging characteristic part is less than the preset threshold, the characteristic part of the road administration facilities can be regarded as a point at this time, and a second camera unit can be set on the first vehicle; the setting distance between the first camera unit and the second camera unit. Obtain the first angle between the first camera unit and the characteristic part of the road administration facilities and the second angle between the second camera unit and the characteristic part of the road administration facilities. According to the distance, the first angle and the second angle, the relative position information between the first vehicle and the characteristic part of the road administration facilities can be calculated by using the cosine theorem-related method (some simple angle conversions are required and will not be described in detail here); and the coordinates of the road administration facilities can be calculated according to the first coordinate and the relative position information.

[0030] When the first vehicle calculates and obtains the coordinate information of the road administration facilities through the high-precision positioning device and the above method, this coordinate information is relatively accurate. Upload this coordinate information to the server; it can enable subsequent vehicles without high-precision positioning to identify the characteristic part of the road administration facilities and obtain the corresponding coordinate information of the road administration facilities and the area information of the characteristic part; through this information, the second vehicle without high-precision positioning can also obtain the coordinates of high-precision positioning, thereby achieving the same high-precision positioning effect as the vehicle with high-precision positioning equipment.

[0031] Specifically, the second vehicle uploads the rough coordinates and obtains the road administration facilities information within a preset distance range. The second vehicle itself can find the road administration facilities within the preset range (about 0 - 2000 meters) through the rough positioning information and the positioning information of the cloud server. Obtain the corresponding coordinate of the road administration facilities and the area of the characteristic part from the cloud server; when the second vehicle obtains the characteristic part of this road administration facility through the third camera unit, the second vehicle is positioned according to the third imaging position of the characteristic part in the third camera unit and the area of the third imaging road administration facility (this positioning method can adopt the empirical value method or the PnP calculation method); the steps of positioning the vehicle include: obtaining the second distance between the second vehicle and the road administration facility according to the area of the road administration facility and the area of the third imaging road administration facility; obtaining the third angle between the second vehicle and the road administration facility according to the imaging position of the road administration facility in the third camera unit; calculating and generating the position coordinates of the second vehicle by using the second distance, the third angle and the coordinates of the road administration facility.

[0032] Meanwhile, a fourth camera unit is provided on the second vehicle; a second spacing is provided between the third camera unit and the fourth camera unit; if the second vehicle fails to parse and obtain the area of the road administration facility, the third angle formed by the third camera unit and the road administration facility and the fourth angle formed by the fourth camera unit and the road administration facility are obtained, and the relative position information between the second vehicle and the road administration facility is calculated based on the second spacing, the third angle, and the fourth angle; and the high-precision positioning coordinates of the second vehicle are calculated based on the coordinates of the road administration facility and the relative position information.

[0033] Since the positioning error of the inertial / wheel speedometer integrated positioning will accumulate as the driving mileage of the first vehicle increases, causing the positioning result to gradually deviate from the true position of the vehicle. At this time, it is necessary to periodically correct the data of the inertial / wheel speedometer integrated positioning. In order to further provide more accurate correction data for the IMU data of the vehicle. The first vehicle obtains the first imaging position and the area of the first imaging feature part of the road administration facility in the first camera unit at the first moment; obtains the second imaging position and the area of the second imaging feature part of the road administration facility in the first camera unit at the second moment; calculates the deviation angle of the vehicle according to the first imaging position and the second imaging position, and calculates the deviation distance of the vehicle according to the area of the first imaging feature part and the area of the second imaging feature part; according to the time difference between the first moment and the second moment; calculates the angular acceleration and linear acceleration of the first vehicle; and corrects the IMU data of the first vehicle. In the field of integrated positioning technology, technicians can use existing integrated positioning technologies (such as particle filtering, Kalman filtering technology, etc.) to fuse these three position information (inertial navigation, satellite, and vision), collect data through multiple vehicles, perform big data statistics and correction (that is, obtain the average value that most vehicles are relatively close to), and finally obtain the corrected position information and output the positioning result.

[0034] As another example, the information uploaded by the road administration facility may also include the feature line segment and the length of the feature line segment; when the vehicle obtains the feature part through the first camera unit and obtains the feature line segment and the length of the feature line segment through the server; the feature line segment is used to replace the feature part of the road administration facility in the above example, and the length of the feature line segment is used to replace the area of the feature part of the road administration facility in the above example. As long as the relevant information reserved by the server is matched with the information required by the vehicle, a good positioning effect can be achieved similarly.

[0035] As another example, when the vehicle obtains the feature part through the first camera unit and obtains the feature line segment and the length information of the feature line segment of the road administration facilities through the server. After the camera unit captures and recognizes the feature part, it can extract its feature points. Here, the feature points can be the corner points of the road administration facilities or the midpoint of a certain line segment. Select two of the feature points and connect them to form a feature connection line segment to obtain the corresponding feature line segment. After the first camera unit captures the feature line segment of the road administration facilities, a first imaging feature line segment and the length of the first imaging feature line segment are formed in the camera unit (here, the more regular the figure, the easier it is to recognize the extracted feature line segment; for example, for triangles, squares, and trapezoids, the imaging position and length of one side length can be directly known; for irregular ones, the corner points and connections can be recognized, and the corresponding data can be obtained through actual measurement, and the graphic data can be obtained through the graphic ratio). Then, the first distance between the vehicle and the two-dimensional code is obtained according to the length of the feature line segment and the length of the first imaging feature line segment; the first angle between the vehicle and the road administration facilities is obtained according to the imaging position of the feature line segment in the first camera unit (i.e., the first imaging feature line segment); finally, the vehicle position coordinates are calculated and generated using the first distance, the first angle, and the first coordinates of the two-dimensional code. Here, the calculation can be performed based on the relevant knowledge of the camera imaging principle, or the empirical value method mentioned in the above example can be used for multiple records, which will not be elaborated here.

[0036] As Figure 3 shown, this embodiment further includes a coordinate calibration device for road administration facilities based on high-precision vehicle positioning, including: a first vehicle camera module, a high-precision positioning module, and a coordinate calibration module for road administration facilities, and the data of each module is connected.

[0037] The first vehicle camera module includes at least a first camera unit installed on the first vehicle; it is used to obtain the road administration facilities set beside the road through the first camera unit; the road administration facilities include the area of the road administration facilities; the high-precision positioning module is used to obtain the first coordinates of the first vehicle according to the high-precision positioning device; the coordinate calibration module for road administration facilities is used to calibrate the coordinates of the road administration facilities according to the first imaging position, the first imaging area of the road administration facilities, and the first coordinates in the first camera unit; the steps of calibrating the coordinates of the road administration facilities include: obtaining the first distance between the first vehicle and the road administration facilities according to the parameter relationship between the area of the road administration facilities and the first imaging area of the road administration facilities; obtaining the first angle between the first vehicle and the road administration facilities according to the imaging position of the road administration facilities in the first camera unit; calculating and generating the coordinates of the road administration facilities using the first distance, the first angle, and the first coordinates.

[0038] It is consistent with the description of the method embodiment. Since when the vehicle is in motion, it is impossible to scan and analyze the information of road administration facilities in a relatively far place (through high-precision map data matching, the approximate position of road administration facilities on the map can be known). If the first vehicle fails to parse and obtain the area of the road administration facilities, a second camera unit can be set on the first vehicle; the first camera unit and the second camera unit are set at a certain distance. Then, obtain the first angle between the first camera unit and the road administration facilities and the second angle between the second camera unit and the road administration facilities. According to the distance, the first angle and the second angle, using the relevant method of the cosine theorem, the relative position information between the first vehicle and the road administration facilities can be calculated; and the coordinates of the road administration facilities can be calculated according to the first coordinate and the relative position information. The first vehicle obtains the first imaging position and the area of the first imaging feature part of the road administration facilities in the first camera unit at the first moment; obtains the second imaging position and the area of the second imaging road administration facilities of the road administration facilities in the camera unit at the second moment; calculates the offset angle of the vehicle according to the first imaging position and the second imaging position, and calculates the offset distance of the vehicle according to the area of the first imaging feature part and the area of the second imaging feature part; according to the time difference between the first moment and the second moment; calculates the angular acceleration and linear acceleration of the first vehicle; and corrects the IMU data of the first vehicle. The coordinates of the road administration facilities and the area of the characteristic part of the road administration facilities are uploaded to the cloud server, and the link to the cloud server address is set in the road administration facilities information. Through this device, a vehicle fusion positioning device based on road administration facilities can also be obtained.

[0039] Those skilled in the art can understand that all or part of the steps in the embodiment can be implemented by instructing relevant hardware through a computer program, and this program can be stored in a computer-readable medium. The readable medium can include various media that can store program codes, such as a flash drive, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk or an optical disc. In one embodiment, the present disclosure provides a computer-readable medium, in which a computer program is stored, and the computer program is loaded and executed by a processing module to implement the calibration of the coordinates of road administration facilities.

[0040] Within the scope of the knowledge and ability level of those skilled in the art, various embodiments or technical features mentioned in this article can be combined with each other as other optional embodiments without conflict. These optional embodiments formed by combining a limited number of technical features that are not listed one by one still fall within the technical scope disclosed in the present disclosure, and can also be understood or inferred by those skilled in the art in combination with the drawings and the above text.

[0041] In addition, the descriptions of most embodiments are based on different focuses. For the parts not detailed, reference can be made to the content of the prior art or other relevant descriptions in this article for understanding.

[0042] Once again, it is emphasized that the embodiments listed above are relatively typical and preferred embodiments of the present disclosure, and are only used for detailed description and explanation of the technical solutions of the present disclosure for the convenience of readers to understand, and are not used to limit the protection scope or application of the present disclosure. Any technical solutions obtained by making any modifications, equivalent replacements, improvements, etc. within the spirit and principle of the present disclosure should be covered within the protection scope of the present disclosure.

Claims

1. A method for calibrating the coordinates of road administration facilities based on high-precision vehicle positioning, characterized in that: Set road administration facilities beside the road, the road administration facilities include a feature part and the area of the feature part; set a high-precision positioning device and a first camera unit on the first vehicle; obtain the first coordinate of the first vehicle according to the high-precision positioning device, obtain the feature part through the first camera unit and obtain the area of the feature part through the server; calibrate the coordinates of the road administration facilities according to the first imaging position of the feature part in the first camera unit, the first imaging feature part area and the first coordinate; The vehicle is provided with a second camera unit, and the first camera unit and the second camera unit are set at a distance; when the first imaging feature part area is less than a preset threshold; obtain the first angle of the included angle formed by the first camera unit and the road administration facilities and obtain the second angle of the included angle formed by the second camera unit and the road administration facilities, calculate and obtain the relative position information between the vehicle and the road administration facilities according to the distance, the first angle and the second angle, and calculate the coordinates of the road administration facilities according to the first coordinate and the relative position information.

2. The method for calibrating the coordinates of road administration facilities according to claim 1, characterized in that: The steps of calibrating the coordinates of the road administration facilities include: obtaining the first distance between the first vehicle and the road administration facilities according to the area of the feature part and the first imaging feature part area; obtaining the first angle between the first vehicle and the road administration facilities according to the first imaging position of the road administration facilities in the first camera unit; calculating and generating the coordinates of the road administration facilities by using the first distance, the first angle and the first coordinate.

3. The method for calibrating the coordinates of road administration facilities according to claim 1, characterized in that: The first vehicle obtains the first imaging position and the first imaging feature part area of the road administration facilities in the first camera unit at the first moment; obtains the second imaging position and the second imaging feature part area of the road administration facilities in the camera unit at the second moment; calculates the offset angle of the vehicle according to the first imaging position and the second imaging position, and calculates the offset distance of the vehicle according to the first imaging feature part area and the second imaging feature part area; according to the time difference between the first moment and the second moment; calculate and obtain the angular acceleration and linear acceleration of the first vehicle; correct the IMU data of the first vehicle.

4. The method for calibrating the coordinates of road administration facilities according to any one of claims 1-3, characterized in that: The road administration facilities further include a feature line segment and the length of the feature line segment; when the vehicle obtains the feature part through the first camera unit and obtains the feature line segment and the length of the feature line segment through the server; use the feature line segment to replace the feature part and use the length of the feature line segment to replace the area of the feature part.

5. The method for calibrating the coordinates of road administration facilities according to any one of claims 1-3, characterized in that: The coordinates of the road administration facilities, the feature part and the area of the feature part are uploaded to the server. ​ 6. A vehicle fusion positioning method based on road administration facility recognition, characterized in that: The second vehicle uploads rough coordinates and obtains road administration facility information within a preset distance range of the road administration facility coordinates; the road administration facility information obtains the corresponding road administration facility coordinates, the feature part and the area of the feature part from the method described in claim 5; When the third camera unit of the second vehicle acquires the road administration facility, the second vehicle is positioned according to the third imaging position and the third imaging feature part area of the road administration facility in the third camera unit; The steps of positioning the second vehicle include: obtaining a second distance between the second vehicle and the road administration facility according to the area of the feature part and the third imaging feature part area; Obtaining a third angle between the second vehicle and the road administration facility according to the imaging position of the road administration facility in the third camera unit; calculating and generating the position coordinates of the second vehicle by using the second distance, the third angle and the road administration facility coordinates.

7. A road administration facility coordinate calibration device based on high-precision vehicle positioning, characterized in that: It includes: A first vehicle camera module, a high-precision positioning module and a road administration facility coordinate calibration module, with data connections among the modules; the first vehicle camera module includes at least a first camera unit, which is installed on the first vehicle; it is used to capture the road administration facilities set beside the road through the first camera unit and obtain the feature parts of the road administration facilities and obtain the area of the feature parts through the server; the road administration facilities include feature parts and the area of the feature parts; the high-precision positioning module is used to obtain the first coordinates of the first vehicle according to the high-precision positioning device; the road administration facility coordinate calibration module is used to calibrate the coordinates of the road administration facility according to the first imaging position, the first imaging feature part area of the road administration facility in the first camera unit and the first coordinates; The vehicle is provided with a second camera unit; there is a set distance between the first camera unit and the second camera unit. When the area of the first imaging feature part is less than a preset threshold; obtaining a first angle of the included angle formed by the first camera unit and the road administration facility and obtaining a second angle of the included angle formed by the second camera unit and the road administration facility, calculating and obtaining the relative position information between the vehicle and the road administration facility according to the distance, the first angle and the second angle, and calculating the road administration facility coordinates according to the first coordinates and the relative position information.

8. The road administration facility coordinate calibration device according to claim 7, characterized in that: Calibrating the coordinates of the road administration facility includes: obtaining a first distance between the first vehicle and the road administration facility according to the area of the road administration facility and the first imaging feature part area; obtaining a first angle between the first vehicle and the road administration facility according to the imaging position of the road administration facility in the first camera unit; calculating and generating the coordinates of the road administration facility by using the first distance, the first angle and the first coordinates.

9. The road administration facility coordinate calibration device according to any one of claims 7-8, characterized in that: The road administration facilities further include a feature line segment and the length of the feature line segment; when the vehicle acquires the feature part through the first camera unit and acquires the feature line segment and the length of the feature line segment through the server; the feature line segment is used to replace the feature part and the length of the feature line segment is used to replace the area of the feature part.

Images