Expressway accurate positioning method and device, and storage medium

Abstract

The invention discloses an expressway accurate positioning method and device and a storage medium, and relates to the technical field of expressway management, and the method comprises the steps: obtaining a panoramic image of a to-be-positioned road section, carrying out the coarse positioning of the panoramic image, and obtaining a coarse positioning image corresponding to the panoramic image; determining a coarse positioning line corresponding to the acquisition device according to the coarse positioning image; when the acquisition device moves based on the coarse positioning line, acquiring high-precision detection data according to a high-precision sensor arranged on the acquisition device, and determining a high-precision line corresponding to the acquisition device based on the high-precision detection data and the coarse positioning line; and the acquisition device moves along the high-precision line and acquires map data. According to the invention, the acquisition device moves along the high-precision line, so that the obtained positioning of the expressway is high in precision. And accurate positioning of the expressway can be realized only by using the acquisition device along the high-precision route, so that the positioning efficiency of the expressway is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of highway management, and in particular to a method and device for accurately positioning a highway, and a storage medium. Background Art

[0002] With the rapid development of highway construction, it is becoming increasingly important to accurately and real-time locate and manage people and vehicles on highways. This can not only improve traffic management efficiency and reduce the occurrence of traffic accidents, but also provide strong support for intelligent transportation systems.

[0003] When locating a target object on a highway, if only the latitude and longitude information of the target object is available, the positioning information is not rich and intuitive enough. Therefore, the prior art often uses the road section, stake number, direction and other information commonly used by the operating unit to locate the target object. However, the premise of the above positioning method is to have accurate location information of the highway itself or accurate location information of the road stakes on the highway.

[0004] However, accurate positioning of highways cannot be achieved by simply taking a few photos from certain locations. Instead, it requires individual sampling of each detail on the highway and comprehensive analysis. One solution in the prior art is to use a dynamic differential positioning method to determine the coordinates of the mobile station relative to the base station, and then inversely calculate its own instantaneous coordinates based on the coordinates of the base station, but this solution is inefficient. Therefore, it is necessary to propose a new method for accurate positioning of highways, which can efficiently complete the positioning of highways while ensuring positioning accuracy. Summary of the invention

[0005] The present invention provides a method and device for accurately positioning a highway, and a storage medium, which are used to efficiently complete the positioning of the highway while ensuring the positioning accuracy.

[0006] In order to solve the above technical problems, the first aspect of the present invention discloses a method for accurate positioning of a highway, the method comprising: Acquire a panoramic image of the road section to be positioned, perform coarse positioning on the panoramic image, and obtain a coarse positioning image corresponding to the panoramic image; Determining a coarse positioning line corresponding to the acquisition device according to the coarse positioning image; When the acquisition device moves based on the rough positioning route, high-precision detection data is acquired according to the high-precision sensor provided on the acquisition device, and the high-precision route corresponding to the acquisition device is determined based on the high-precision detection data and the rough positioning route; The acquisition device moves along the high-precision route and acquires map data, and the map data is used to accurately locate the road section to be located.

[0007] As an optional implementation, in the first aspect of the present invention, the acquisition device moves along the high-precision route and acquires map data, including: When the acquisition device moves along the high-precision line, it is determined whether there is an obstacle on the high-precision line; If it is determined that there are no obstacles on the high-precision route, the acquisition device moves along the high-precision route and acquires point information of a characteristic area on the high-precision route, where the characteristic area is an area used to represent the main section features of the section to be located; If it is determined that there is an obstacle on the high-precision line, a correction line corresponding to the high-precision line is determined based on the positional relationship between the obstacle and the characteristic area on the high-precision line; the acquisition device moves along the correction line and acquires point information of the characteristic area on the high-precision line.

[0008] As an optional implementation, in the first aspect of the present invention, if it is determined that there is an obstacle on the high-precision line, a correction line corresponding to the high-precision line is determined according to the positional relationship between the obstacle and the characteristic area on the high-precision line; the acquisition device moves along the correction line and acquires point information of the characteristic area on the high-precision line, including: If it is determined that there is an obstacle on the high-precision route, further determining whether the obstacle on the high-precision route is a moving obstacle or a stationary obstacle; If it is determined that the obstacle on the high-precision route is a mobile obstacle, a correction route corresponding to the high-precision route is determined according to the positional relationship between the mobile obstacle and the characteristic area on the high-precision route and the movement of the mobile obstacle; the acquisition device moves along the correction route and acquires point position information of the characteristic area on the high-precision route; If it is determined that the obstacle on the high-precision route is a stationary obstacle, the following steps are performed: Determine a first corrected route and a second corrected route corresponding to the high-precision route according to a positional relationship between the obstacle and a characteristic area on the high-precision route; The collecting device moves along the first corrected route and collects first point information of the characteristic area on the high-precision route; the collecting device moves along the second corrected route and collects second point information of the characteristic area on the high-precision route; wherein the first point information and the second point information are information obtained by collecting the same point; Based on the first point information and the second point information, point information of a characteristic area on the high-precision route is determined.

[0009] As an optional implementation, in the first aspect of the present invention, the first point information and the second point information are image information captured by a camera on the acquisition device; and the step of determining the point information of the characteristic area on the high-precision line based on the first point information and the second point information includes: Acquire a first coordinate when the acquisition device detects the first point information and a second coordinate when the acquisition device detects the second point information; Determine a geometric position relationship of a target camera between the first point information and the second point information according to the first coordinate and the second coordinate; According to the geometric position relationship and the internal parameters, external parameters and distortion coefficient of the target camera, the point coordinates are determined using the first point information and the second point information, and the point coordinates are determined to be the point information of the characteristic area on the high-precision line.

[0010] As an optional implementation, in the first aspect of the present invention, the acquisition device moves along the high-precision line and acquires point information of a characteristic area on the high-precision line, including: Determining, according to the panoramic image, a feature type corresponding to the feature area; Determine, according to the feature type corresponding to the feature area, a point information collection strategy corresponding to the feature area; For the feature areas of different feature types, the acquisition device moves along the high-precision line and uses a corresponding point information acquisition strategy to acquire point information of the feature area on the high-precision line.

[0011] As an optional implementation, in the first aspect of the present invention, the feature type includes a straight line type, a right angle type and a curve type; Wherein, for the feature areas of different feature types, the acquisition device moves along the high-precision line and uses the corresponding point information acquisition strategy to acquire the point information of the feature area on the high-precision line, including: For a straight line feature area, the acquisition device moves along the high-precision line and acquires point information of the straight line feature area on the high-precision line according to a preset point acquisition density; For the right-angle feature area, the acquisition device moves along the high-precision line and adjusts the point acquisition density according to the distance between the current position of the acquisition device and the right-angle vertex, and acquires point information of the right-angle feature area on the high-precision line based on different point acquisition densities; For the curve feature area, the acquisition device moves along the high-precision line and adjusts the point acquisition density according to the curvature radius of the curve line in the curve feature area, and acquires point information of the curve feature area on the high-precision line based on different point acquisition densities.

[0012] As an optional implementation, in the first aspect of the present invention, the acquisition device is provided with a camera and a radar device, and when the acquisition device moves along the high-precision line, determining whether there is an obstacle on the high-precision line includes: When the acquisition device moves along the high-precision route, the acquisition device acquires image data through the camera. If a target obstacle is identified from the image data, the height change of the acquisition device is controlled, and a plurality of radar data are acquired through the radar device when the acquisition device is at different heights; For each radar data, obtaining radar-visual fusion data corresponding to the radar data based on the radar data and the image data based on the radar-visual fusion technology; According to the radar-vision fusion data corresponding to all the radar data, it is determined whether there is an obstacle on the high-precision route and the positional relationship between the target obstacle and the characteristic area on the high-precision route is determined.

[0013] The second aspect of the present invention discloses a highway precise positioning device, the device comprising: A coarse positioning module is used to obtain a panoramic image of the road section to be positioned, perform coarse positioning on the panoramic image, and obtain a coarse positioning image corresponding to the panoramic image; A first line determination module, used to determine the coarse positioning line corresponding to the acquisition device according to the coarse positioning image; A second route determination module is used to obtain high-precision detection data according to a high-precision sensor provided on the acquisition device when the acquisition device moves based on the rough positioning route, and determine the high-precision route corresponding to the acquisition device based on the high-precision detection data and the rough positioning route; A collection device is used to move along the high-precision route and obtain map data, and the map data is used to accurately locate the road section to be located.

[0014] As an optional implementation, in the second aspect of the present invention, the specific manner in which the acquisition device moves along the high-precision route and acquires map data includes: When the acquisition device moves along the high-precision line, it is determined whether there is an obstacle on the high-precision line; If it is determined that there are no obstacles on the high-precision route, the acquisition device moves along the high-precision route and acquires point information of a characteristic area on the high-precision route, where the characteristic area is an area used to represent the main section features of the section to be located; If it is determined that there is an obstacle on the high-precision line, a correction line corresponding to the high-precision line is determined based on the positional relationship between the obstacle and the characteristic area on the high-precision line; the acquisition device moves along the correction line and acquires point information of the characteristic area on the high-precision line.

[0015] As an optional implementation, in the second aspect of the present invention, if the acquisition device determines that there is an obstacle on the high-precision line, the acquisition device determines the correction line corresponding to the high-precision line according to the positional relationship between the obstacle and the characteristic area on the high-precision line; the specific manner in which the acquisition device moves along the correction line and acquires the point information of the characteristic area on the high-precision line includes: If it is determined that there is an obstacle on the high-precision route, further determining whether the obstacle on the high-precision route is a moving obstacle or a stationary obstacle; If it is determined that the obstacle on the high-precision route is a mobile obstacle, a correction route corresponding to the high-precision route is determined according to the positional relationship between the mobile obstacle and the characteristic area on the high-precision route and the movement of the mobile obstacle; the acquisition device moves along the correction route and acquires point position information of the characteristic area on the high-precision route; If it is determined that the obstacle on the high-precision route is a stationary obstacle, the following steps are performed: Determine a first corrected route and a second corrected route corresponding to the high-precision route according to a positional relationship between the obstacle and a characteristic area on the high-precision route; The collecting device moves along the first corrected route and collects first point information of the characteristic area on the high-precision route; the collecting device moves along the second corrected route and collects second point information of the characteristic area on the high-precision route; wherein the first point information and the second point information are information obtained by collecting the same point; Based on the first point information and the second point information, point information of a characteristic area on the high-precision route is determined.

[0016] As an optional implementation, in the second aspect of the present invention, the first point information and the second point information are image information captured by a camera on the acquisition device; and the specific method of determining the point information of the characteristic area on the high-precision line based on the first point information and the second point information includes: Acquire a first coordinate when the acquisition device detects the first point information and a second coordinate when the acquisition device detects the second point information; Determine a geometric position relationship of a target camera between the first point information and the second point information according to the first coordinate and the second coordinate; According to the geometric position relationship and the internal parameters, external parameters and distortion coefficient of the target camera, the point coordinates are determined using the first point information and the second point information, and the point coordinates are determined to be the point information of the characteristic area on the high-precision line.

[0017] As an optional implementation, in the second aspect of the present invention, the specific manner in which the acquisition device moves along the high-precision line and acquires point information of a characteristic area on the high-precision line includes: Determining, according to the panoramic image, a feature type corresponding to the feature area; Determine, according to the feature type corresponding to the feature area, a point information collection strategy corresponding to the feature area; For the feature areas of different feature types, the acquisition device moves along the high-precision line and uses a corresponding point information acquisition strategy to acquire point information of the feature area on the high-precision line.

[0018] As an optional implementation, in the second aspect of the present invention, the feature type includes a straight line type, a right angle type and a curve type; Among them, for the feature areas of different feature types, the specific manner in which the acquisition device moves along the high-precision line and uses the corresponding point information acquisition strategy to acquire the point information of the feature area on the high-precision line includes: For a straight line feature area, the acquisition device moves along the high-precision line and acquires point information of the straight line feature area on the high-precision line according to a preset point acquisition density; For the right-angle feature area, the acquisition device moves along the high-precision line and adjusts the point acquisition density according to the distance between the current position of the acquisition device and the right-angle vertex, and acquires point information of the right-angle feature area on the high-precision line based on different point acquisition densities; For the curve feature area, the acquisition device moves along the high-precision line and adjusts the point acquisition density according to the curvature radius of the curve line in the curve feature area, and acquires point information of the curve feature area on the high-precision line based on different point acquisition densities.

[0019] As an optional implementation, in the second aspect of the present invention, the acquisition device is provided with a camera and a radar device, and when the acquisition device moves along the high-precision line, a specific method for determining whether there is an obstacle on the high-precision line includes: When the acquisition device moves along the high-precision route, the acquisition device acquires image data through the camera. If a target obstacle is identified from the image data, the height change of the acquisition device is controlled, and a plurality of radar data are acquired through the radar device when the acquisition device is at different heights; For each radar data, obtaining radar-visual fusion data corresponding to the radar data based on the radar data and the image data based on the radar-visual fusion technology; According to the radar-vision fusion data corresponding to all the radar data, it is determined whether there is an obstacle on the high-precision route and the positional relationship between the target obstacle and the characteristic area on the high-precision route is determined.

[0020] The third aspect of the present invention discloses another highway precise positioning device, the device comprising: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the highway precise positioning method disclosed in the first aspect of the present invention.

[0021] A fourth aspect of the present invention discloses a computer storage medium, wherein the computer storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the highway precise positioning method disclosed in the first aspect of the present invention.

[0022] Compared with the prior art, the acquisition device of the present invention moves along a high-precision route, so the accuracy of the coordinate information of the acquisition device itself is sufficiently high, and the positioning of the highway obtained thereby is also high-precision. In addition, the accurate positioning of the highway can be achieved by only using the acquisition device along the high-precision route, thereby improving the efficiency of highway positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 It is a flow chart of a method for precise positioning of a highway disclosed in an embodiment of the present invention; Figure 2 It is a structural schematic diagram of a highway precise positioning device disclosed in an embodiment of the present invention; Figure 3 It is a schematic diagram of the structure of another highway precise positioning device disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or end including a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units inherent to these processes, methods, products or ends.

[0027] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0028] Embodiment 1 See also Figure 1 , Figure 1 : is a flow chart of a method for accurate positioning of a highway disclosed in an embodiment of the present invention. Figure 1 The described highway precise positioning method can be applied to a highway precise positioning device, and the highway precise positioning device can be integrated in a cloud server or a local server or a collection device, which is not limited in the embodiments of the present invention. Figure 1 As shown, the highway precise positioning method may include the following operations: Step 101: Acquire a panoramic image of a road section to be positioned, perform coarse positioning on the panoramic image, and obtain a coarse positioning image corresponding to the panoramic image.

[0029] In the embodiment of the present invention, for any road section to be located on the highway that needs to be located, a panoramic image is first obtained, for example, by taking a panoramic image with a handheld camera, a viewfinder, a drone, etc. However, due to various distortions in the panoramic image (for example, objects near are larger and objects far are smaller), it is difficult to determine the location of the road section through the panoramic image. Therefore, it is necessary to determine a positioning route based on the panoramic image, and then use a collection device to perform accurate position collection along the positioning route.

[0030] In the embodiment of the present invention, there are many road section features on the highway, such as road markings, roadside posts, guardrails, etc. The embodiment of the present invention needs to collect the features of the highway to achieve accurate positioning of the highway. Therefore, for the acquired panoramic image, it is necessary to perform coarse positioning on it to determine a coarse positioning image. Optionally, each feature part in the panoramic image can be identified. For example, an image recognition algorithm is used to extract important features such as the road surface, road markings, and road posts in the panoramic image, and then the coordinates of each feature are preliminarily given based on the rough position information, thereby forming a coarse positioning image.

[0031] Step 102: Determine the coarse positioning line corresponding to the acquisition device according to the coarse positioning image.

[0032] In the prior art, there is a solution of using a framing car for framing positioning, but the framing car can only determine the coordinates of a specific road post beside the road by estimation, because the framing car is not based on a precise route when it is moving. In particular, when the framing car is driven by a human driver, its driving process can only be determined in a general direction, and it is difficult to control a more precise route.

[0033] Therefore, in an embodiment of the present invention, it is necessary to determine the coarse positioning route corresponding to the acquisition device in subsequent acquisition operations based on the coarse positioning image. For example, a road post along the right side of the road in the coarse positioning image is selected as a coarse positioning route, and a certain line on the road surface in the coarse positioning image is selected as a coarse positioning route.

[0034] Step 103: When the acquisition device moves based on the coarse positioning route, high-precision detection data is obtained according to the high-precision sensor provided on the acquisition device, and the high-precision route corresponding to the acquisition device is determined based on the high-precision detection data and the coarse positioning route.

[0035] In the embodiment of the present invention, the coarse positioning line can control the acquisition line of the acquisition device within a certain accuracy requirement, but it is still necessary to further improve the accuracy of the acquisition line to achieve more accurate acquisition. Therefore, in the embodiment of the present invention, it is necessary to obtain high-precision detection data based on the high-precision sensor set on the acquisition device to determine the high-precision line, for example, the image data obtained by the image sensor is used to continuously adjust and optimize the coarse positioning line, so as to obtain a high-precision line.

[0036] Step 104: The acquisition device moves along the high-precision route and acquires map data, and the map data is used to accurately locate the road section to be located.

[0037] In the embodiment of the present invention, the acquisition device acquires map data through radar, image sensor and other devices. The map data may be an image or radar data of each road post. Since the acquisition device moves along a high-precision route, the accuracy of the coordinate information of the acquisition device itself is sufficiently high, and the positioning of the highway obtained thereby is also high-precision. Furthermore, since the accurate positioning of the highway can be achieved by only using the acquisition device along the high-precision route, the efficiency of highway positioning is improved.

[0038] In an optional embodiment, due to the complex situation on the highway, there may be various obstacles on the high-precision route. In order to deal with the situation where obstacles exist, the above-mentioned acquisition device moves along the high-precision route and obtains map data, which may include: When the acquisition device moves along the high-precision line, it determines whether there are obstacles on the high-precision line; If it is determined that there are no obstacles on the high-precision line, the acquisition device moves along the high-precision line and acquires point information of the characteristic area on the high-precision line.

[0039] If it is determined that there is an obstacle on the high-precision line, the correction line corresponding to the high-precision line is determined based on the positional relationship between the obstacle and the characteristic area on the high-precision line; the acquisition device moves along the correction line and acquires point information of the characteristic area on the high-precision line.

[0040] In this optional embodiment, the characteristic area is an area used to represent the main road section features in the road section to be located, such as the road posts and road markings mentioned above. Taking a drone as an example, when using a drone as a collection device to collect map information, the best solution is for the drone to directly face the point in the characteristic area. At this time, the position of the drone is the position of the point. However, if the point is blocked by an obstacle, other routes that can obtain the point can only be determined based on the positional relationship between the obstacle and the characteristic area on the high-precision line, that is, the corrected route. At this time, the drone may obtain the point information at a specific angle on the corrected route, and then restore the position information of the point through the positional relationship between the drone position and the point. Thereby achieving the acquisition of map data even when there are obstacles.

[0041] In another optional embodiment, obstacles are divided into static obstacles and mobile obstacles, and there are different coping strategies for the above two situations. Therefore, if it is determined that there is an obstacle on the high-precision line, a correction line corresponding to the high-precision line is determined according to the positional relationship between the obstacle and the characteristic area on the high-precision line; the acquisition device moves along the correction line and acquires point information of the characteristic area on the high-precision line, which may include: If it is determined that there is an obstacle on the high-precision line, it is further determined whether the obstacle on the high-precision line is a moving obstacle or a stationary obstacle; If it is determined that the obstacle on the high-precision line is a mobile obstacle, the correction route corresponding to the high-precision line is determined based on the positional relationship between the mobile obstacle and the characteristic area on the high-precision line and the movement of the mobile obstacle; the acquisition device moves along the correction route and acquires point information of the characteristic area on the high-precision line.

[0042] For moving obstacles, they will leave their original positions after a certain period of time and will no longer block the points. Therefore, it is only necessary to adjust the high-precision line according to the positional relationship between the moving obstacle and the characteristic area on the high-precision line and the movement of the moving obstacle so that it can avoid the moving obstacle within a specific time.

[0043] If the obstacle on the high-precision line is determined to be a stationary obstacle, perform the following steps: Determine a first corrected route and a second corrected route corresponding to the high-precision route according to a positional relationship between the obstacle and the characteristic area on the high-precision route; The collecting device moves along the first corrected route and collects first point information of the characteristic area on the high-precision route; the collecting device moves along the second corrected route and collects second point information of the characteristic area on the high-precision route; wherein the first point information and the second point information are information obtained by collecting the same point; Based on the first point information and the second point information, point information of a characteristic area on the high-precision line is determined.

[0044] In this optional embodiment, for stationary obstacles, they will always block the point. For this reason, map information can be collected from other angles or positions, but the accuracy is still not enough if it is collected from only one angle or one position. For example, for image data, once the camera is not facing the point, there will be distortion. The way to minimize the distortion is to offset the distortion through two or more pictures at different angles. For another example, for radar data, it often only has information on distance and angle. If radar data is only obtained from one position, there will be deviations in distance and angle, but the combination of radar data obtained from two or more positions can improve accuracy.

[0045] Further optionally, the first point information and the second point information are image information captured by a camera on a collection device; and based on the first point information and the second point information, determining the point information of the characteristic area on the high-precision line may include: Acquire a first coordinate when the acquisition device detects the first point information and a second coordinate when the acquisition device detects the second point information; Determine a geometric position relationship of a target camera between the first point information and the second point information according to the first coordinate and the second coordinate; According to the geometric position relationship and the internal parameters, external parameters and distortion coefficients of the target camera, the point coordinates are determined using the first point information and the second point information, and the point coordinates are determined to be the point information of the characteristic area on the high-precision line.

[0046] Specifically, the above operations may include: 1. Camera calibration: First, the camera needs to be calibrated to obtain the camera's intrinsic parameters (including focal length, principal point coordinates, etc.) and distortion coefficients (including radial and tangential distortion parameters). This is usually done by photographing a calibration plate (such as a chessboard) and using the calibration function in a computer vision library (such as OpenCV). During the calibration process, the intrinsic parameter matrix, distortion coefficients, rotation vectors, and translation vectors are calculated.

[0047] 2. Distortion correction: The image is corrected using the camera's distortion coefficient. The purpose of distortion correction is to eliminate the image distortion caused by lens distortion so that the point coordinates can be determined more accurately.

[0048] 3. Determine the point coordinates: Using the first point information and the second point information, combined with the camera's intrinsic and extrinsic parameters, the position of the point in the camera coordinate system is determined. This usually involves converting the point in the world coordinate system to the camera coordinate system, and then converting it to the pixel coordinate system through the intrinsic matrix.

[0049] The intrinsic matrix K and the extrinsic rotation matrix R and the translation vector t act together on the point in the world coordinate system , calculate the point in the pixel coordinate system by the following formula

[0050] in, is a point in the world coordinate system, is a point in pixel coordinates.

[0051] 4. Determination of high-precision line feature area point information: The pixel coordinates obtained through the above steps can be combined with the first point information and the second point information to determine the point information of the feature area.

[0052] In yet another optional embodiment, the above-mentioned acquisition device moves along the high-precision line and acquires point information of a characteristic area on the high-precision line, which may include: According to the panoramic image, determine the feature type corresponding to the feature area; According to the feature type corresponding to the feature area, determine the point information collection strategy corresponding to the feature area; For feature areas of different feature types, the acquisition device moves along the high-precision line and uses the corresponding point information acquisition strategy to acquire point information of the feature area on the high-precision line.

[0053] In order to further improve efficiency, different collection strategies can be used for different feature areas. For example, for the markings on a straight road, it is not necessary to collect too many points, and it is often sufficient to collect them once at a longer distance; for complex situations such as forks or curves, more dense points need to be set. Through the above design, the efficiency of highway positioning can be further improved.

[0054] In the above optional embodiment, it is further optional that the feature type includes a straight line type, a right angle type and a curve type; Among them, for feature areas of different feature types, the acquisition device moves along the high-precision line and uses the corresponding point information acquisition strategy to collect point information of the feature area on the high-precision line, including: For the straight line feature area, the acquisition device moves along the high-precision line and acquires point information of the straight line feature area on the high-precision line according to a preset point acquisition density.

[0055] For the right-angle feature area, the collection device moves along the high-precision line and adjusts the point collection density according to the distance between the current position of the collection device and the right-angle vertex, and collects point information of the right-angle feature area on the high-precision line based on different point collection densities; for example, the farther from the right angle, the sparser the collection points, and the closer to the right angle, the denser the collection points.

[0056] For the curve feature area, the acquisition device moves along the high-precision line and adjusts the point acquisition density according to the curvature radius of the curve line in the curve feature area, and collects point information of the curve feature area on the high-precision line based on different point acquisition densities. For example, the larger the curvature radius, the sparser the acquisition points, and the smaller the curvature radius, the denser the acquisition points.

[0057] In another optional embodiment, a camera and a radar device are provided on the acquisition device. When the acquisition device moves along the high-precision line, determining whether there is an obstacle on the high-precision line includes: When the acquisition device moves along the high-precision line, the acquisition device obtains image data through the camera. If the target obstacle is identified from the image data, the position of the obstacle cannot be determined by the image data alone. Furthermore, the height change of the acquisition device is controlled. When the acquisition device is at different heights, multiple radar data are obtained through the radar equipment; through the radar data at different heights, the obstacle position can be accurately obtained.

[0058] For each radar data, the radar data and image data are used to obtain the radar data corresponding to the radar data based on the radar-visual fusion technology; the radar-visual fusion technology analyzes and processes the image with the radar detection data and computer vision technology, and then fuses and displays it, thereby obtaining the three-dimensional data of similar obstacles. For image data, there is only one and it is plane data. For example, if a road post is blocked by a tree, it is difficult to construct a new correction route if the three-dimensional structure of the tree is not determined. Therefore, the three-dimensional structure of the tree can be determined by the radar-visual fusion of one image data and multiple radar data.

[0059] Finally, based on the radar-visual fusion data corresponding to all radar data, it is determined whether there are obstacles on the high-precision line and the positional relationship between the target obstacle and the characteristic area on the high-precision line is determined.

[0060] Embodiment 2 See also Figure 2 , Figure 2 Schematic diagram of the structure of a highway precise positioning device disclosed in an embodiment of the present invention. Figure 2 As shown, the highway precise positioning device may include: The coarse positioning module 201 is used to obtain a panoramic image of the road section to be positioned, perform coarse positioning on the panoramic image, and obtain a coarse positioning image corresponding to the panoramic image; A first line determination module 202 is used to determine the coarse positioning line corresponding to the acquisition device according to the coarse positioning image; The second route determination module 203 is used to obtain high-precision detection data according to the high-precision sensor provided on the acquisition device when the acquisition device moves based on the rough positioning route, and determine the high-precision route corresponding to the acquisition device based on the high-precision detection data and the rough positioning route; The acquisition device 204 is used to move along the high-precision route and obtain map data, and the map data is used to accurately locate the road section to be located.

[0061] In an optional embodiment, the specific manner in which the acquisition device 204 moves along the high-precision route and acquires the map data may include: When the acquisition device 204 moves along the high-precision line, it determines whether there is an obstacle on the high-precision line; If it is determined that there are no obstacles on the high-precision route, the acquisition device 204 moves along the high-precision route and acquires point information of a characteristic area on the high-precision route, where the characteristic area is an area used to represent the main road section features in the road section to be located; If it is determined that there is an obstacle on the high-precision line, the correction line corresponding to the high-precision line is determined based on the positional relationship between the obstacle and the characteristic area on the high-precision line; the collection device 204 moves along the correction line and collects point information of the characteristic area on the high-precision line.

[0062] In another optional embodiment, if the acquisition device 204 determines that there is an obstacle on the high-precision line, a correction line corresponding to the high-precision line is determined according to the positional relationship between the obstacle and the characteristic area on the high-precision line; the specific manner in which the acquisition device 204 moves along the correction line and acquires the point information of the characteristic area on the high-precision line may include: If it is determined that there is an obstacle on the high-precision line, it is further determined whether the obstacle on the high-precision line is a moving obstacle or a stationary obstacle; If it is determined that the obstacle on the high-precision line is a mobile obstacle, a correction line corresponding to the high-precision line is determined according to the positional relationship between the mobile obstacle and the characteristic area on the high-precision line and the movement of the mobile obstacle; the acquisition device 204 moves along the correction line and acquires point information of the characteristic area on the high-precision line; If the obstacle on the high-precision line is determined to be a stationary obstacle, perform the following steps: Determine a first corrected route and a second corrected route corresponding to the high-precision route according to a positional relationship between the obstacle and the characteristic area on the high-precision route; The collecting device 204 moves along the first corrected route and collects first point information of the characteristic area on the high-precision route; the collecting device 204 moves along the second corrected route and collects second point information of the characteristic area on the high-precision route; wherein the first point information and the second point information are information obtained by collecting the same point; Based on the first point information and the second point information, point information of a characteristic area on the high-precision line is determined.

[0063] In another optional embodiment, the first point information and the second point information are image information captured by a camera on the acquisition device 204; and the specific method of determining the point information of the characteristic area on the high-precision line based on the first point information and the second point information may include: Acquire a first coordinate when the acquisition device 204 detects the first point information and a second coordinate when the acquisition device 204 detects the second point information; Determine a geometric position relationship of a target camera between the first point information and the second point information according to the first coordinate and the second coordinate; According to the geometric position relationship and the internal parameters, external parameters and distortion coefficients of the target camera, the point coordinates are determined using the first point information and the second point information, and the point coordinates are determined to be the point information of the characteristic area on the high-precision line.

[0064] In another optional embodiment, the specific manner in which the acquisition device 204 moves along the high-precision line and acquires point information of the characteristic area on the high-precision line may include: According to the panoramic image, determine the feature type corresponding to the feature area; According to the feature type corresponding to the feature area, determine the point information collection strategy corresponding to the feature area; For feature areas of different feature types, the acquisition device 204 moves along the high-precision line and uses the corresponding point information acquisition strategy to acquire point information of the feature area on the high-precision line.

[0065] In yet another optional embodiment, the feature types may include a straight line type, a right angle type, and a curve type; Among them, for feature areas of different feature types, the specific manner in which the acquisition device 204 moves along the high-precision line and uses the corresponding point information acquisition strategy to acquire the point information of the feature area on the high-precision line may include: For the straight line feature area, the acquisition device 204 moves along the high-precision line and acquires point information of the straight line feature area on the high-precision line according to a preset point acquisition density; For the right-angle feature area, the acquisition device 204 moves along the high-precision line and adjusts the point acquisition density according to the distance between the current position of the acquisition device 204 and the right-angle vertex, and collects point information of the right-angle feature area on the high-precision line based on different point acquisition densities; For the curve feature area, the collection device 204 moves along the high-precision line and adjusts the point collection density according to the curvature radius of the curve line in the curve feature area, and collects point information of the curve feature area on the high-precision line based on different point collection densities.

[0066] In another optional embodiment, the acquisition device 204 is provided with a camera and a radar device. When the acquisition device 204 moves along the high-precision line, the specific method of determining whether there is an obstacle on the high-precision line may include: When the acquisition device 204 moves along the high-precision route, the acquisition device 204 acquires image data through a camera. If a target obstacle is identified from the image data, the height change of the acquisition device 204 is controlled. When the acquisition device 204 is at different heights, multiple radar data are acquired through a radar device. For each radar data, based on the radar data and the image data, the radar-visual fusion data corresponding to the radar data is obtained based on the radar-visual fusion technology; Based on the radar-visual fusion data corresponding to all radar data, it is determined whether there are obstacles on the high-precision line and the positional relationship between the target obstacle and the characteristic area on the high-precision line is determined.

[0067] Embodiment 3 See also Figure 3 , Figure 3 FIG. 1 is a schematic diagram of the structure of another highway precise positioning device disclosed in an embodiment of the present invention. Figure 3 As shown, the highway precise positioning device may include: A memory 301 storing executable program codes; a processor 302 coupled to the memory 301; The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the highway precise positioning method described in the first embodiment of the present invention.

[0068] Embodiment 4 An embodiment of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute the steps in the highway precise positioning method described in the first embodiment of the present invention.

[0069] Embodiment 5 An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps in the highway precise positioning method described in Example 1.

[0070] The device embodiments described above are only illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, i.e., they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0071] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0072] Finally, it should be noted that the method and device for precise positioning of highways and the storage medium disclosed in the embodiments of the present invention are only preferred embodiments of the present invention, and are only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for accurate positioning of a highway, characterized in that: The method comprises: Acquire a panoramic image of the road section to be positioned, perform coarse positioning on the panoramic image, and obtain a coarse positioning image corresponding to the panoramic image; Determine a coarse positioning line corresponding to the acquisition device according to the coarse positioning image; When the acquisition device moves based on the rough positioning route, high-precision detection data is acquired according to the high-precision sensor provided on the acquisition device, and the high-precision route corresponding to the acquisition device is determined based on the high-precision detection data and the rough positioning route; The acquisition device moves along the high-precision route and acquires map data, and the map data is used to accurately locate the road section to be located.

2. The highway precise positioning method according to claim 1, characterized in that: The acquisition device moves along the high-precision route and acquires map data, including: When the acquisition device moves along the high-precision line, it is determined whether there is an obstacle on the high-precision line; If it is determined that there are no obstacles on the high-precision route, the acquisition device moves along the high-precision route and acquires point information of a characteristic area on the high-precision route, where the characteristic area is an area used to represent the main section features of the section to be located; If it is determined that there is an obstacle on the high-precision line, a correction line corresponding to the high-precision line is determined based on the positional relationship between the obstacle and the characteristic area on the high-precision line; the acquisition device moves along the correction line and acquires point information of the characteristic area on the high-precision line.

3. The highway precise positioning method according to claim 2, characterized in that: If it is determined that there is an obstacle on the high-precision route, a correction route corresponding to the high-precision route is determined according to a positional relationship between the obstacle and a characteristic area on the high-precision route; The acquisition device moves along the corrected route and acquires point information of the characteristic area on the high-precision route, including: If it is determined that there is an obstacle on the high-precision route, further determining whether the obstacle on the high-precision route is a moving obstacle or a stationary obstacle; If it is determined that the obstacle on the high-precision route is a mobile obstacle, a correction route corresponding to the high-precision route is determined according to the positional relationship between the mobile obstacle and the characteristic area on the high-precision route and the movement of the mobile obstacle; the acquisition device moves along the correction route and acquires point position information of the characteristic area on the high-precision route; If it is determined that the obstacle on the high-precision route is a stationary obstacle, the following steps are performed: Determine a first corrected route and a second corrected route corresponding to the high-precision route according to a positional relationship between the obstacle and a characteristic area on the high-precision route; The collecting device moves along the first corrected route and collects first point information of the characteristic area on the high-precision route; the collecting device moves along the second corrected route and collects second point information of the characteristic area on the high-precision route; wherein the first point information and the second point information are information obtained by collecting the same point; Based on the first point information and the second point information, the point information of the characteristic area on the high-precision line is determined.

4. The highway precise positioning method according to claim 3 is characterized in that: The first point information and the second point information are image information captured by a camera on the acquisition device; And, determining the point information of the characteristic area on the high-precision line based on the first point information and the second point information includes: Acquire a first coordinate when the acquisition device detects the first point information and a second coordinate when the acquisition device detects the second point information; Determine a geometric position relationship of a target camera between the first point information and the second point information according to the first coordinate and the second coordinate; According to the geometric position relationship and the internal parameters, external parameters and distortion coefficient of the target camera, the point coordinates are determined using the first point information and the second point information, and the point coordinates are determined to be the point information of the characteristic area on the high-precision line.

5. The highway precise positioning method according to claim 2, characterized in that: The collecting device moves along the high-precision line and collects point information of a characteristic area on the high-precision line, including: Determining, according to the panoramic image, a feature type corresponding to the feature area; Determine, according to the feature type corresponding to the feature area, a point information collection strategy corresponding to the feature area; For the feature areas of different feature types, the acquisition device moves along the high-precision line and uses a corresponding point information acquisition strategy to acquire point information of the feature area on the high-precision line.

6. The highway precise positioning method according to claim 5, characterized in that: The feature types include straight line type, right angle type and curve type; Wherein, for the feature areas of different feature types, the acquisition device moves along the high-precision line and uses the corresponding point information acquisition strategy to acquire the point information of the feature area on the high-precision line, including: For a straight line feature area, the acquisition device moves along the high-precision line and acquires point information of the straight line feature area on the high-precision line according to a preset point acquisition density; For the right-angle feature area, the acquisition device moves along the high-precision line and adjusts the point acquisition density according to the distance between the current position of the acquisition device and the right-angle vertex, and acquires point information of the right-angle feature area on the high-precision line based on different point acquisition densities; For the curve feature area, the acquisition device moves along the high-precision line and adjusts the point acquisition density according to the curvature radius of the curve line in the curve feature area, and collects point information of the curve feature area on the high-precision line based on different point acquisition densities.

7. The highway precise positioning method according to claim 3, characterized in that: The acquisition device is provided with a camera and a radar device. When the acquisition device moves along the high-precision line, judging whether there is an obstacle on the high-precision line includes: When the acquisition device moves along the high-precision route, the acquisition device acquires image data through the camera. If a target obstacle is identified from the image data, the height change of the acquisition device is controlled, and a plurality of radar data are acquired through the radar device when the acquisition device is at different heights; For each radar data, obtaining radar-visual fusion data corresponding to the radar data based on the radar data and the image data based on the radar-visual fusion technology; According to the radar-vision fusion data corresponding to all the radar data, it is determined whether there is an obstacle on the high-precision route and the positional relationship between the target obstacle and the characteristic area on the high-precision route is determined.

8. A high-speed highway precise positioning device, characterized in that: The device comprises: A coarse positioning module is used to obtain a panoramic image of the road section to be positioned, perform coarse positioning on the panoramic image, and obtain a coarse positioning image corresponding to the panoramic image; A first line determination module, used to determine the coarse positioning line corresponding to the acquisition device according to the coarse positioning image; A second route determination module is used to obtain high-precision detection data according to a high-precision sensor provided on the acquisition device when the acquisition device moves based on the rough positioning route, and determine the high-precision route corresponding to the acquisition device based on the high-precision detection data and the rough positioning route; A collection device is used to move along the high-precision route and obtain map data, and the map data is used to accurately locate the road section to be located.

9. A highway precise positioning device, characterized in that: The device includes: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the highway precise positioning method as described in any one of claims 1-7.

10. A computer storage medium, characterized in that: The computer storage medium stores computer instructions, and when the computer instructions are called, they are used to execute the highway precise positioning method as described in any one of claims 1-7.

Images