A method, device and server for generating high-precision map road signs

Abstract

The present disclosure relates to a method, device and server for generating high-precision map road signs. The method includes: obtaining two images containing road signs; obtaining the geographic coordinate information of the camera when taking the two images respectively; recognizing the images, and obtaining the image pixel coordinates of the same element in the road sign in the two images respectively according to preset rules; and converting the image pixel coordinates into the coordinate sets of the element relative to the two world coordinate systems of the camera respectively; and calculating the geographic coordinate information of the element in the road sign according to the coordinate sets of the two world coordinate systems and the geographic coordinate information when the two images were taken. The solution provided by the present disclosure can generate road signs for high-precision maps.

Description

Technical Field

[0001] The present invention relates to the technical field of high-precision map surveying and mapping, and in particular to a method, device and equipment for generating high-precision map road signs. Background Art

[0002] With the development of space technology and information technology, the unified management and intelligent interaction of urban infrastructure have gradually entered the public's field of vision. As the information carrier of urban geographical entities, road signs have the function of guiding place name information. At the same time, as infrastructure distributed at the intersections of urban roads, they have their own particularity in space and are a good carrier of the urban basic Internet of Things.

[0003] Maps created from satellite photos are readily available. These maps show the nature of the terrain, including the structures of roads and road adjoinings. The accuracy of such roads is usually in the meter range, so satellite-created maps are usually not accurate enough for vehicle routing purposes. Various mapping companies have made significant revisions to these maps by using special mapping vehicles, which usually use LiDAR technology to create vehicle routing maps on a global scale. However, such maps are usually only accurate to a few meters. While such vehicle routing maps are sufficient for routing purposes, the location of street signs in such maps is not accurate enough for vehicles traveling at high speeds to recognize road signs on the side of the road in a timely manner. Summary of the invention

[0004] In order to overcome the problems existing in the related art, the present disclosure provides a method for generating high-precision map road signs. The method comprises:

[0005] Acquire two images containing a road sign; acquire geographic coordinate information of the camera when taking the two images respectively; recognize the images, and acquire image pixel coordinates of the same element in the road sign in the two images respectively according to preset rules; and convert the image pixel coordinates into coordinate sets of the element relative to two world coordinate systems of the camera respectively; and calculate the geographic coordinate information of the element in the road sign according to the coordinate sets of the two world coordinate systems and the geographic coordinate information when the two images were taken.

[0006] The method further includes: calculating the height of the element in the road sign relative to the camera according to the two world coordinate system coordinates and the geographic coordinate information.

[0007] In the above method, the elements are vertices of the road sign; and the geographic coordinate information of at least three vertices of the road sign and their height relative to the camera are calculated.

[0008] The method of obtaining two images containing road signs specifically includes: selecting an image in which the size of the road sign is larger than a preset threshold value; or selecting an image in which the size of the road sign is larger than the preset threshold value compared with the image size.

[0009] The above method obtains two images containing road signs when the shooting time is greater than the preset time length.

[0010] In the above method, calculating the geographic coordinate information of the element in the road sign according to the coordinates of the two world coordinate systems and the geographic coordinate information when the two images were taken includes: determining two rays from the camera optical center to the element in the image, and calculating the geographic coordinate information of the intersection of the two rays.

[0011] The present invention also provides an embodiment of a device for generating high-precision map road signs, comprising: an image acquisition module, used to acquire two images containing road signs; a pixel coordinate acquisition module, used to acquire the image pixel coordinates of the same element of the road signs in the two images according to preset rules; a geographic coordinate information acquisition module, used to acquire the geographic coordinate information of the camera at the time of image shooting; and a spatial coordinate acquisition module, used to calculate the geographic coordinate information of the road sign based on the image pixel coordinates of specific elements in the two pictures and the geographic coordinate information when the images were shot.

[0012] Another embodiment of a device for generating high-precision map road signs provided by the present invention includes: an image acquisition module, used to acquire two images containing road signs; a pixel coordinate acquisition module, used to acquire the image pixel coordinates of the same element of the road signs in the two images according to preset rules; a geographic coordinate information acquisition module, which acquires the geographic coordinate information of the camera at the time of image shooting; and a sending module, which sends the pixel coordinate information of specific elements in the two images and the geographic coordinate information of the camera to a cloud server.

[0013] A server embodiment provided by the present invention includes: a receiving module, which obtains two images containing road signs sent by a vehicle computer and obtained according to preset rules, as well as geographic coordinate information when the two images are taken; a processor module, which recognizes the two images and obtains the pixel coordinates of the same element in the road signs in the images according to preset rules; and calculates the geographic coordinate information of the element of the road sign based on the two obtained pixel coordinates and the geographic coordinate information of the camera when the two images were taken.

[0014] Another embodiment of a server provided by the present invention includes a receiving module, which obtains two pixel coordinates sent by a vehicle computer according to preset rules, and geographic coordinate information corresponding to the two pixel coordinates respectively; a processor module, which calculates geographic coordinate information based on the two pixel coordinates obtained and the corresponding geographic coordinate information.

[0015] The technical solution provided by the embodiments of the present disclosure may have the following beneficial effects:

[0016] It can be found that the method for generating high-precision map road signs in the embodiment of the present disclosure obtains different road sign images; obtains the image pixel coordinates of the road sign according to the road sign images; and obtains the spatial coordinates of the road sign according to the geographic coordinate information when the different road sign images are obtained and the image pixel coordinates. Compared with the prior art, the road signs in the high-precision map can be generated through the road sign images and geographic coordinates, and no special mapping vehicle is required.

[0017] Furthermore, in the method for generating high-precision map road signs of the disclosed embodiment, different road sign images are obtained through a monocular camera. The monocular camera can be on a driving recorder or on a mobile phone, so that the spatial position of the road sign can be obtained using an ordinary vehicle and the commonly used monocular camera, and then the road sign in the high-precision map can be drawn.

[0018] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and other objects, features and advantages of the present disclosure will become more apparent through a more detailed description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, wherein like reference numerals generally represent like components in the exemplary embodiments of the present disclosure.

[0020] Figure 1 It is a flowchart of a method for generating a high-precision map road sign shown in an exemplary embodiment of the present disclosure;

[0021] Figure 2 It is an image captured by a camera device of a moving vehicle at a certain moment;

[0022] Figure 3 is a schematic diagram of conversion between image pixel coordinates and world coordinate system shown in an exemplary embodiment of the present disclosure;

[0023] Figure 4 is a schematic diagram of a method according to an embodiment of the present disclosure;

[0024] Figure 5 It is a schematic structural diagram of a first embodiment of a device for generating high-precision map road signs disclosed in the present invention;

[0025] Figure 6 It is a structural schematic diagram of a second embodiment of a device for generating high-precision map road signs disclosed in the present invention. DETAILED DESCRIPTION

[0026] The preferred embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the preferred embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to make the present disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0027] The terms used in this disclosure are for the purpose of describing specific embodiments only and are not intended to limit the disclosure. The singular forms of "a", "said" and "the" used in this disclosure and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0028] It should be understood that although the terms "first", "second", "third", etc. may be used in the present disclosure to describe various information, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the present disclosure, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present disclosure, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0029] The present invention provides a method for generating high-precision map road signs.

[0030] The technical solution of the embodiments of the present disclosure is described in detail below with reference to the accompanying drawings.

[0031] Figure 1 FIG. 1 is a flow chart of a method for generating a high-precision map road sign according to an exemplary embodiment of the present disclosure. Figure 1 The method includes:

[0032] In step 101, an image including a road sign and geographic coordinate information when the image is obtained are obtained.

[0033] In the present disclosure, a camera device installed on a car, such as a driving recorder, obtains a video of the driving process while the car is driving. When the vehicle is driving on the road and approaches a road sign, the camera device on the vehicle obtains multiple road sign images at different times, that is, multiple frames of images in the video.

[0034] like Figure 2 The image shown is taken when a vehicle passes a road sign at a certain moment. Figure 2As shown in the figure, a rectangular road sign is displayed on the right side of the captured image. When the surveying vehicle is driving on the road and approaches the road sign, the monocular camera turned on on the surveying vehicle terminal can obtain the road sign image at the current angle according to the preset acquisition frequency. When the surveying vehicle approaches the road sign, the monocular camera starts to acquire the road sign image. During the process of acquiring the road sign image, the surveying vehicle continues to drive, so each frame of the road sign image is acquired by the monocular camera from different angles. Obtain road sign images at different angles through the monocular camera.

[0035] Select two different road sign images. For example, if the vehicle moves from far to near a road sign for 2 seconds, then obtain any two frames of images containing the road sign in the 2-second video.

[0036] In one embodiment, the area of ​​the road sign in the image can be obtained by image recognition according to a preset strategy, and the image whose area occupied by the road sign is larger than a preset threshold value is selected. The road sign area can be measured in pixels or other sizes; or the ratio of the area occupied by the road sign to the whole image is larger than the threshold value. Figure 1 A threshold value.

[0037] In another embodiment, an image with better image quality is selected according to certain rules, and the image quality can be judged by various methods in the prior art, such as resolution.

[0038] In the present invention, at least two images need to be selected to calculate the spatial position of the road sign. Therefore, there should be a certain time interval between the two selected pictures, such as a preset duration; the road sign in the image can also be identified, the total duration of the road sign appearing in the image can be calculated, and the interval between the second image and the first image can be calculated according to a certain ratio. In another method, as the vehicle approaches the road sign from far to near, the size of the road sign in the image changes from small to large, until a part of the road sign in the image begins to exceed the range of the image, and the road sign no longer appears in the image when the vehicle passes the road sign. Therefore, an image in which a part of the road sign begins to exceed the range of the image can be found, and the image taken before the image is selected as the second image.

[0039] Record the geographic coordinates when acquiring different road sign images. During the process of acquiring road sign images, the surveying vehicle continues to drive and record the geographic coordinate information. According to the time of the two image information acquired, find the geographic coordinate information at that time.

[0040] In step 102, the image pixel coordinates of the same element in the road sign in the at least two images are obtained.

[0041] Based on the method in step 101, see Figure 4, select image A and image B when the vehicle is at position A or time A, and position B or time B, respectively. Both image A and image B contain road signs.

[0042] The image pixel coordinates of one vertex among the four vertices of the road sign in the image at time A and the image pixel coordinates of the vertex of the road sign in the image at time B are further obtained.

[0043] The so-called image pixel coordinates are used to describe the coordinates of the image points on the digital image after the object is imaged. The coordinate system where the information read from the camera is located. The unit is (number of pixels). The upper left corner vertex of the image plane is the coordinate origin, and the X-axis and Y-axis are parallel to the X-axis and Y-axis of the image coordinate system respectively, and its coordinate value is represented by (u, v). The image captured by the digital camera is first formed in the form of a standard electrical signal, and then converted into a digital image through analog-to-digital conversion. The storage format of each image is an M×N array, and the value of each element in the image with M rows and N columns represents the grayscale of the image point. Each such element is called a pixel, and the pixel coordinate system is an image coordinate system with pixels as units.

[0044] The image pixel coordinates of the vertices of the road sign selected in the above step 102 are used for calculating the spatial position of the road sign in the subsequent steps. The present invention is not intended to limit the elements of the road sign in the image to be selected, and it can be any element of the road sign that can be identified. For example, a part of the text or numbers in the road sign. For example, the vertices of a recognizable rectangle in the road sign. Or the vertices of a recognizable font, etc. The font can be a traffic identifier, such as an exclamation mark, a rest area sign, etc., or a distance unit km, etc. Therefore, the road sign described in the present invention is not limited to Figure 2 The road signs shown are actually square or rectangular, but also include road signs in shapes such as triangle, circle, etc.

[0045] In step 103, as described above, two different road sign images have corresponding two different geographic coordinate information, and the spatial position of the road sign is calculated based on the two different geographic coordinate information and the image pixel coordinates of the road sign. The spatial position of the present invention includes geographic coordinate information and may further include the height value of the element.

[0046] Reference Figure 3 A schematic diagram of calculating image pixel coordinates and a world coordinate system provided by an embodiment of the present invention.

[0047] The camera is placed in a three-dimensional space, so the world coordinate system is used as the reference coordinate system to describe the position of the camera, and the position of the camera is used to describe the position of any other object placed in this three-dimensional environment. Assume that P is a point in the real world, and its position in the world coordinate system is P(x w ,y w ,z w), P is the actual position of a certain point on the road sign in the embodiment of the present invention.

[0048] O C -X C Y C Z C is the camera coordinate system, with the optical center as the origin. The camera coordinate system takes the optical center of the camera as the origin, which means the pinhole is the optical center in the pinhole model. The z axis coincides with the optical axis, that is, the z axis points to the front of the camera, and the positive directions of the x axis and y axis are parallel to the object coordinate system. Where f is the focal length of the camera, Figure 3 As can be seen, f is the origin of the camera coordinate system O C The distance from o in the image's physical coordinate system.

[0049] o-xy is the physical coordinate system of the image, also called the plane coordinate system. The position of the pixel is expressed in physical units, and the origin of the coordinate is the intersection of the camera optical axis and the physical coordinate system of the image, that is, the optical center is the center of the image. The unit of the o-xy coordinate system is millimeter (mm), which is adapted to the size of the CCD sensor inside the camera. After the photo is imaged, it is in pixels, such as 640×480, so it is necessary to further convert the physical coordinates of the image into image pixel coordinates.

[0050] Image pixel coordinate system uv, such as Figure 3 As shown. The coordinate origin is the upper left corner of the image, with pixels as the unit. The conversion relationship between the physical coordinates of the image pixel and the image pixel coordinates is the relationship between millimeters and pixels, that is, pixels / mm. For example, the camera CCD sensor is 8mm×6mm, and the image pixel size is 640×480. If d x represents the physical size of each pixel in the image pixel coordinate system, then d x It is 1 / 80mm.

[0051] In the world coordinate system, P(x w ,y w ,z w ) The imaging point of point in the image is p, the coordinates in the image physical coordinate system are (x, y), and the coordinates in the image pixel coordinate system are (u, v).

[0052] According to the conversion relationship, the world coordinates of point P relative to the camera position are calculated based on the pixel coordinates of point P in the image. According to the following conversion formula, point P is located on a straight line with the camera as the starting point and a determined direction relative to the camera.

[0053]

[0054] Among them, d x and d yRespectively represent the number of length units occupied by a pixel in the x direction and the y direction. u0, v0 represent the horizontal and vertical pixel numbers of the difference between the center pixel coordinates of the image and the pixel coordinates of the image origin. f is the focal length of the camera. R is the rotation matrix in the camera external parameters, and T is the offset vector of the camera external parameters. The external parameters of the camera can be obtained according to the existing technology.

[0055] According to the above method, the coordinate sets of the element relative to the two world coordinate systems of the camera are obtained through the intrinsic and extrinsic parameters of the camera and the image pixels, that is, the world coordinates P of a certain point (i.e., a certain element) on the road sign relative to the vehicle camera in the images taken at point A and point B are calculated respectively. A (x w ,y w ,z w ) and P B (x w ,y w ,z w ). The coordinates of point P obtained at this time are A (x w ,y w ,z w ) and P B (x w ,y w ,z w ) are located on a straight line starting from the camera when the vehicle is at point A and the camera when the vehicle is at point B, respectively.

[0056] The image pixel coordinates are respectively converted into coordinate sets of two world coordinate systems of the element relative to the camera.

[0057] By setting the external parameters of the monocular camera on the vehicle, including the translation parameters relative to the GPS device installed in the vehicle, the geographic coordinate information of the monocular camera on the vehicle at the same time can be calculated based on the geographic coordinate information measured by the vehicle. The setting of the camera external parameters can refer to the methods of the prior art, which will not be repeated herein. However, the embodiments of the present invention do not intend to exclude the method of directly using the geographic coordinate information measured by the vehicle GPS device as the geographic coordinate information of the camera. In this method, the translation parameters of the camera are not set. Although the accuracy of the spatial position of the road sign finally calculated according to the method described in the present invention will be affected, the spatial position of the road sign can also be obtained.

[0058] In the embodiment of the present invention, two geographic coordinate information of the camera are obtained based on the geographic coordinate information measured by the vehicle at point A and point B respectively, with reference to the external parameters of the camera. Figure 4As shown, they are located on the straight lines starting from the camera when the vehicle is at point A and the camera when the vehicle is at point B, respectively. Therefore, the intersection of the two straight lines is point P. That is, the intersection of the two rays determined from the optical center of the camera to the element in the image is point P.

[0059] Further, based on the known geographic coordinate information of the camera when the vehicle is at points A and B, the geographic coordinate information of point P and the height of point P relative to the camera are calculated to obtain the spatial position of the road sign.

[0060] In the above embodiment, each frame of the road sign image obtained, the time and geographic coordinate information corresponding to each frame of the road sign image can be stored together on the surveying and mapping vehicle, processed on the surveying and mapping vehicle to obtain the spatial coordinates of the road sign, and then the spatial coordinates of the road sign are uploaded to the server;

[0061] Alternatively, each frame of the acquired road sign image and the time and geographic coordinate information corresponding to each frame of the road sign image may be uploaded to a server, which processes the information to obtain the spatial coordinates of the road sign;

[0062] Alternatively, each frame of the road sign image, the time and geographic coordinate information corresponding to each frame of the road sign image are stored on the surveying and mapping vehicle, processed on the surveying and mapping vehicle to obtain the image pixel coordinates of the road sign, and then the time, geographic coordinate information and image pixel coordinates corresponding to each frame of the road sign image are uploaded to the server, processed by the server to obtain the spatial coordinates of the road sign.

[0063] It can be found that the method for generating high-precision map road signs in the embodiment of the present disclosure obtains different road sign images; obtains the image pixel coordinates of the road sign according to the road sign images; and obtains the spatial coordinates of the road sign according to the geographic coordinate information and image pixel coordinates when obtaining different road sign images. Compared with the related art, the spatial position of the road sign can be obtained through the geographic coordinate information of the road sign image, and the road signs of high-precision maps can be generated without the need for a special mapping vehicle.

[0064] Furthermore, the method for generating high-precision map road signs of the disclosed embodiment obtains different road sign images through a monocular camera. The monocular camera can be a camera of a driving recorder or a camera on a mobile phone, so that the required images can be obtained using an ordinary vehicle and a commonly used monocular camera.

[0065] In a preferred embodiment of the present invention, the spatial position of the vertex can be obtained by selecting the image pixel coordinates of the vertex of the road sign in the image for calculation. Therefore, for a square road sign, the image pixel coordinates of at least three vertices of the road sign are selected for calculation to obtain the spatial positions of the three vertices, which can determine the position of the outer boundary of the square road sign, and the obtained spatial position of the road sign is more accurate. Compared with selecting the pixel coordinates of the text and pattern pixel points in the road sign for calculation, the outer dimensions of the road sign cannot be obtained by using the pixel coordinates of the text and pattern pixel points in the road sign. The calculation result is the spatial position of a point in the road sign. Although it can also achieve the purpose of identifying the position of the road sign, the outer contour of the road sign cannot be obtained.

[0066] In another implementation, based on the result of recognizing the square road sign, two vertices located on the diagonal line are selected to calculate the spatial position, and the shape size and outline of the square are calculated in combination with the graphic recognition method.

[0067] In the above embodiment, the spatial position of the road sign is determined by using road sign images obtained by a monocular camera at two different times / positions. Obviously, based on this, the spatial position of the road sign can be determined by using images obtained at more than two times / positions. For example, for the same road sign, the obtained 4 frames of images are divided into two groups to calculate the spatial position of the road sign respectively, and the two spatial positions of the road sign are obtained. The two spatial positions are optimized and fused according to certain rules to obtain a more accurate spatial position of the road sign.

[0068] The present disclosure also provides a road sign terminal device to implement the above method. The terminal device described in the embodiment of the present invention can be a driving recorder, or a smart device such as a smart phone, which relies on the program installed in these terminal devices to achieve the purpose of the present invention.

[0069] Figure 5 It is a structural schematic diagram of a device for generating high-precision map road signs according to an exemplary embodiment of the present disclosure.

[0070] See also Figure 5 A device for generating high-precision map road signs includes an image acquisition module 501, a pixel coordinate acquisition module 502, a spatial coordinate acquisition module 503, and a geographic coordinate information acquisition module 504.

[0071] The image acquisition module 501 is used to acquire two images containing road signs.

[0072] When a vehicle is driving on the road and approaches a road sign, the terminal device of the embodiment of the present invention installed on the vehicle uses the image acquisition module 501 to capture multiple road sign images at different times. For example, the road ahead video captured by a driving recorder; or a series of photos captured by other equipment at a certain time interval according to a preset rule.

[0073] The pixel coordinate acquisition module 502 is used to obtain the image pixel coordinates of specific elements in the road sign according to the road sign image acquired by the image acquisition module 501 according to the preset rules. The pixel coordinate acquisition module 502 selects two different road sign images with clear road signs to obtain the image pixel coordinates of the road sign. The rules are described in the above method.

[0074] The geographic coordinate information acquisition module 504 is used to acquire the geographic coordinate information of the camera at that moment according to the image shooting time of the image selected by the pixel coordinate acquisition module 502. The geographic coordinate information of the camera should be based on the geographic coordinate information measured by the vehicle equipment and calculated according to the external parameters of the camera. However, the present invention does not exclude the implementation method of directly using the geographic coordinate information measured by the vehicle as the geographic coordinate information of the camera.

[0075] The spatial coordinate acquisition module 503 calculates the spatial coordinates of the road sign according to the image pixel coordinates of the specific elements in the two pictures obtained by the pixel coordinate acquisition module 502 and the geographic coordinate information when the two pictures were taken obtained by the geographic coordinate information acquisition module 504. For specific methods, please refer to the description of the method part above.

[0076] Another embodiment of the device for generating high-precision map road signs of the present invention includes: an image acquisition module 501, a pixel coordinate acquisition module 502, a geographic coordinate information acquisition module 504, and a sending module 505.

[0077] The image acquisition module 501 is used to acquire different road sign images.

[0078] When a vehicle is driving on the road and approaches a road sign, the terminal device installed on the vehicle uses the image acquisition module 501 to capture multiple road sign images at different times. For example, the road ahead video captured by a driving recorder; or a series of photos captured by other equipment at a certain time interval according to preset rules.

[0079] The pixel coordinate acquisition module 502 is used to obtain the image pixel coordinates of specific elements in the road sign according to the road sign image acquired by the image acquisition module 501 according to the preset rules. The pixel coordinate acquisition module 502 selects two different road sign images with clear road signs to obtain the image pixel coordinates of the road sign. The method is described in the above method.

[0080] The geographic coordinate information acquisition module 504 is used to acquire the geographic coordinate information at that moment according to the image shooting time of the image selected by the pixel coordinate acquisition module 502 .

[0081] The sending module 505 sends the pixel coordinate information of the specific elements in the two images obtained by the pixel coordinate obtaining module 502 and the geographic coordinate information obtained by the geographic coordinate information obtaining module 504 to the cloud server.

[0082] In other embodiments of the device for generating high-precision map road signs of the present invention, the sending module 505 can send the two selected images and the geographic coordinate information obtained by the geographic coordinate information acquisition module 504 to the cloud server. That is, after the device selects the two images, it does not perform image recognition and obtain pixel coordinate information, that is, it does not need to identify the vertex of the road sign and calculate the image information of the vertex. Therefore, the pixel coordinate acquisition module 502 does not perform the function of calculating the pixel coordinates, and the server performs this step.

[0083] Alternatively, after measuring the geographic coordinate information, the geographic information acquisition module 504 further calculates the geographic coordinate information of the camera according to the external parameters of the camera, and sends the geographic coordinate information of the camera to the cloud server through the sending module 505.

[0084] The embodiment of the present invention also provides a cloud server, including:

[0085] A receiving module receives two images sent by the vehicle computer, which are acquired according to preset rules, and the images contain road signs; and geographic coordinate information when the two images are taken. In this embodiment, the geographic coordinate information uploaded by the vehicle computer is the geographic coordinate information collected by the vehicle equipment and adjusted based on the camera external parameters, that is, the geographic coordinate information of the camera;

[0086] A processor module recognizes the two images and obtains pixel coordinates of the same element in the road signs in the images according to a preset rule, wherein the element is, for example, a vertex of the road sign; the rule is described in the relevant part of the method above;

[0087] According to the two pixel coordinates obtained and the geographic coordinate information of the camera when the two pictures were taken, the spatial position of the element of the road sign is calculated, including the geographic coordinate information of the road sign and the height of the element relative to the camera.

[0088] In another embodiment of the cloud server of the present invention, it includes:

[0089] A receiving module receives two images sent by the vehicle computer and acquired according to preset rules, wherein the images include road signs; and geographic coordinate information when the two images are taken. In this embodiment, the geographic coordinate information uploaded by the vehicle computer is the geographic coordinate information collected by the vehicle equipment;

[0090] A preprocessing module is used to calculate the camera's geographic coordinate information based on the external parameters of the camera corresponding to the vehicle computer stored in the cloud and the obtained vehicle geographic coordinate information;

[0091] A processor module recognizes the two images and obtains pixel coordinates of the same element in the road signs in the images according to a preset rule, wherein the element is, for example, a vertex of the road sign; the rule is described in the relevant part of the method above;

[0092] According to the two pixel coordinates obtained and the geographic coordinate information of the camera when the two pictures were taken, the spatial position of the element of the road sign is calculated, including the geographic coordinate information of the road sign and the height of the element relative to the camera.

[0093] Based on the above two cloud server embodiments, the cloud server may further include an image preprocessing module to preprocess and correct the image according to the external parameters of the camera stored in the cloud. The method of correcting the image according to the external parameters of the camera can refer to the existing technology.

[0094] The scheme of the present disclosure has been described in detail above with reference to the accompanying drawings. In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. It can be understood that the steps in the method of the embodiment of the present disclosure can be adjusted in order, merged and deleted according to actual needs, and the modules in the device of the embodiment of the present disclosure can be merged, divided and deleted according to actual needs.

[0095] In addition, the method according to the present disclosure may also be implemented as a computer program or a computer program product, which includes computer program code instructions for executing some or all of the steps in the above method of the present disclosure.

[0096] Alternatively, the present disclosure may also be implemented as a non-temporary machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) on which executable code (or computer program, or computer instruction code) is stored. When the executable code (or computer program, or computer instruction code) is executed by a processor of an electronic device (or computing device, server, etc.), the processor executes part or all of the steps of the above-mentioned method according to the present disclosure.

[0097] Those skilled in the art will further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the disclosure herein may be implemented as electronic hardware, computer software, or a combination of both.

[0098] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for generating high-precision map road signs, characterized in that: include: Get two images containing road signs; get the geographic coordinate information of the camera when taking the two images; Recognize the image, and obtain the image pixel coordinates of the same element in the road sign in the two images respectively according to the preset rules; and convert the image pixel coordinates into the coordinate sets of the element in the two world coordinate systems relative to the camera respectively; Calculating the geographic coordinate information of the element in the road sign according to the coordinate sets of the two world coordinate systems and the geographic coordinate information of the camera when the two images were taken; Calculating the height of the element in the road sign relative to the camera according to the coordinate sets of the two world coordinate systems and the geographic coordinate information of the camera when the two images were taken; These include: The elements are vertices of the square road signs; as well as, According to the coordinate sets of the two world coordinate systems and the geographic coordinate information of the camera when the two images were taken, the geographic coordinate information of at least three vertices of the square road sign or two vertices located on the diagonal line and their height relative to the camera are calculated.

2. The method according to claim 1, characterized in that Get two images containing road signs as follows: Select images in which the road sign size is larger than a preset threshold; or, The image size of the road sign is larger than the preset threshold.

3. The method according to claim 2, characterized in that The shooting time of the two acquired images containing the road sign is greater than the preset time duration.

4. The method according to claim 1, characterized in that: The geographic coordinate information of the element in the road sign calculated according to the coordinates of the two world coordinate systems and the geographic coordinate information when the two images were taken includes: Determine two rays from the camera optical center to the element in the image, and calculate the geographic coordinate information of the intersection of the two rays.

5. A device for generating high-precision map road signs, characterized in that: include: An image acquisition module, used to acquire two images containing road signs; A pixel coordinate acquisition module is used to recognize the image and obtain the image pixel coordinates of the same element in the road sign in two images according to preset rules; A geographic coordinate information acquisition module is used to acquire the geographic coordinate information of the camera when taking two images respectively; A spatial coordinate acquisition module, used to convert the image pixel coordinates into coordinate sets of two world coordinate systems of the same element in the road sign relative to the camera, and calculate the geographic coordinate information of the element in the road sign according to the coordinate sets of the two world coordinate systems and the geographic coordinate information of the camera when the two images were taken, and calculate the height of the element in the road sign relative to the camera according to the coordinate sets of the two world coordinate systems and the geographic coordinate information of the camera when the two images were taken; These include: The elements are vertices of the square road signs; as well as, According to the coordinate sets of the two world coordinate systems and the geographic coordinate information of the camera when the two images were taken, the geographic coordinate information of at least three vertices of the square road sign or two vertices located on the diagonal line and their height relative to the camera are calculated.

6. A device for generating high-precision map road signs, characterized in that: include: An image acquisition module, used to acquire two images containing road signs; A pixel coordinate acquisition module is used to recognize the image and obtain the image pixel coordinates of the same element of the road sign in the two images according to preset rules; A geographic coordinate information acquisition module is used to acquire the geographic coordinate information of the camera when taking two images respectively; A sending module, used for sending the image pixel coordinates of the same element of the road sign in the two images respectively, and the geographic coordinate information of the camera when the two images are taken, to a cloud server, so that the cloud server converts the image pixel coordinates of the same element of the road sign in the two images respectively into coordinate sets of two world coordinate systems of the element relative to the camera, calculates the geographic coordinate information of the element in the road sign according to the coordinate sets of the two world coordinate systems and the geographic coordinate information of the camera when the two images are taken, and calculates the height of the element in the road sign relative to the camera according to the coordinate sets of the two world coordinate systems and the geographic coordinate information of the camera when the two images are taken; These include: The elements are vertices of the square road signs; as well as, According to the coordinate sets of the two world coordinate systems and the geographic coordinate information of the camera when the two images were taken, the geographic coordinate information of at least three vertices of the square road sign or two vertices located on the diagonal line and their height relative to the camera are calculated.

7. A server, characterized in that: include: The receiving module is used to obtain two images containing road signs sent by the vehicle computer, as well as the geographic coordinate information of the camera when the two images were taken respectively; A processor module, for recognizing images, obtaining image pixel coordinates of the same element in the road sign in the two images respectively according to preset rules, and converting the image pixel coordinates into coordinate sets of the element in two world coordinate systems relative to the camera respectively, calculating the geographic coordinate information of the element in the road sign according to the coordinate sets of the two world coordinate systems and the geographic coordinate information of the camera when the two images were taken, and calculating the height of the element in the road sign relative to the camera according to the coordinate sets of the two world coordinate systems and the geographic coordinate information of the camera when the two images were taken; These include: The elements are vertices of the square road signs; as well as, According to the coordinate sets of the two world coordinate systems and the geographic coordinate information of the camera when the two images were taken, the geographic coordinate information of at least three vertices of the square road sign or two vertices located on the diagonal line and their height relative to the camera are calculated.

8. A server, characterized in that: include: The receiving module is used to obtain the image pixel coordinates and geographic coordinate information sent by the vehicle computer, where: The vehicle computer obtains two images containing the road sign, obtains the geographic coordinate information of the camera when the two images are taken respectively, recognizes the images, and obtains the image pixel coordinates of the same element in the road sign in the two images respectively according to a preset rule; A processor module, used to convert the image pixel coordinates into coordinate sets of two world coordinate systems of the same element in the road sign relative to the camera, calculate the geographic coordinate information of the same element in the road sign according to the coordinate sets of the two world coordinate systems and the geographic coordinate information of the camera when the two images were taken, and calculate the height of the element in the road sign relative to the camera according to the coordinate sets of the two world coordinate systems and the geographic coordinate information of the camera when the two images were taken; including: The elements are vertices of a square road sign; and, According to the coordinate sets of the two world coordinate systems and the geographic coordinate information of the camera when the two images were taken, the geographic coordinate information of at least three vertices of the square road sign or two vertices located on the diagonal line and their height relative to the camera are calculated.

Images