Positioning method, device, equipment, medium and program product for plaque orientation

Abstract

The application provides a positioning method, device, equipment, medium and program product of a signboard direction, and can be applied to a map, navigation and the like. The method comprises the following steps: acquiring a junction scene image of a first road and a second road photographed on the first road; identifying a signboard pixel box of a junction POI in the junction scene image to obtain a target signboard pixel box; determining the position of the target signboard pixel box in the junction scene image, the upper edge line and the lower edge line of the target signboard pixel box; and positioning the direction of the signboard corresponding to the target signboard pixel box based on the position of the target signboard pixel box in the junction scene image, the upper edge line and the lower edge line of the target signboard pixel box. Since the positioning method is consistent with the actual direction of the signboard, the accuracy of the positioning of the signboard direction is ensured.

Description

Technical Field

[0001] This application relates to information processing technology, and more particularly to a method, apparatus, device, medium, and program product for positioning the orientation of a sign. Background Technology

[0002] To optimize the coordinates of Points of Interest (POIs) on a map, it is usually necessary to determine the orientation of the signs of the shops, schools, and other buildings corresponding to these POIs. Therefore, the location of the sign orientation is particularly important.

[0003] Typically, dashcams record road scenes while driving. When a dashcam captures a sign, it assumes that the sign is facing the vehicle's current road. However, in intersection scenarios, the sign may not be facing the vehicle's current road; for example, it might be facing another road that intersects with the current road. Therefore, current methods for determining the sign's orientation are not accurate enough. Summary of the Invention

[0004] This application provides a method, device, equipment, medium, and program product for positioning the orientation of a sign. Because this positioning method matches the actual orientation of the sign, it ensures the accuracy of the sign orientation positioning.

[0005] In a first aspect, embodiments of this application provide a method for locating the orientation of a sign. The method includes: acquiring an image of an intersection scene between a first road and a second road taken on a first road; identifying the sign pixel frame of the intersection POI in the intersection scene image to obtain a target sign pixel frame; determining the position of the target sign pixel frame in the intersection scene image, and the upper and lower edges of the target sign pixel frame; and locating the orientation of the sign corresponding to the target sign pixel frame based on the position of the target sign pixel frame in the intersection scene image, and the upper and lower edges of the target sign pixel frame.

[0006] Secondly, embodiments of this application provide a positioning device for the orientation of a sign, comprising: an acquisition module, an identification module, a determination module, and a positioning module. The acquisition module acquires an image of the intersection scene between the first road and the second road, captured on the first road. The identification module identifies the sign pixel frame of the intersection POI in the intersection scene image to obtain a target sign pixel frame. The determination module determines the position of the target sign pixel frame in the intersection scene image, as well as its upper and lower edges. The positioning module positions the sign orientation corresponding to the target sign pixel frame based on its position in the intersection scene image and its upper and lower edges.

[0007] In some implementations, the positioning module is specifically used to: determine the vanishing point of the target sign pixel frame based on the top and bottom edges of the target sign pixel frame; determine the positional relationship between the vanishing point and the target sign pixel frame; and locate the sign orientation corresponding to the target sign pixel frame based on the position of the target sign pixel frame in the intersection scene image and the positional relationship between the vanishing point and the target sign pixel frame.

[0008] In some implementations, the determining module is further used to determine the angles of the top and bottom edges of the target sign pixel frame before the positioning module determines the sign orientation corresponding to the target sign pixel frame based on the position of the target sign pixel frame in the intersection scene image and the positional relationship between the vanishing point and the target sign pixel frame. Accordingly, the positioning module is specifically used to: determine the sign orientation corresponding to the target sign pixel frame based on the position of the target sign pixel frame in the intersection scene image, the positional relationship between the vanishing point and the target sign pixel frame, and the angles of the top and bottom edges of the target sign pixel frame.

[0009] In some possible implementations, the positioning module is specifically used to: if a first preset condition or a second preset condition is met, locate the direction of the sign corresponding to the target sign pixel frame towards the second road; if the first preset condition and the second preset condition are not met, locate the direction of the sign corresponding to the target sign pixel frame towards the first road; wherein, the first preset condition includes: the target sign pixel frame is on the left side of the intersection scene image, the vanishing point of the target sign pixel frame is on the left side of the target sign pixel frame, and the angles of the upper and lower edges of the target sign pixel frame are both less than the first preset angle; the second preset condition includes: the target sign pixel frame is on the right side of the intersection scene image, the vanishing point of the target sign pixel frame is on the right side of the target sign pixel frame, and the angles of the upper and lower edges of the target sign pixel frame are both greater than the second preset angle.

[0010] In some possible implementations, the first preset angle is 270 degrees and the second preset angle is 90 degrees.

[0011] In some possible implementations, the positioning module is specifically used to: if the third or fourth preset condition is met, locate the direction of the sign corresponding to the target sign pixel frame towards the second road; if the third and fourth preset conditions are not met, locate the direction of the sign corresponding to the target sign pixel frame towards the first road; wherein, the third preset condition includes: the target sign pixel frame is on the left side of the intersection scene image, and the vanishing point of the target sign pixel frame is on the left side of the target sign pixel frame; the fourth preset condition includes: the target sign pixel frame is on the right side of the intersection scene image, and the vanishing point of the target sign pixel frame is on the right side of the target sign pixel frame.

[0012] In some implementations, the positioning module is specifically used to: determine the angles of the top and bottom edges of the target sign pixel frame; and, based on the position of the target sign pixel frame in the intersection scene image and the top and bottom edges of the target sign pixel frame, locate the sign orientation corresponding to the target sign pixel frame, including: locating the sign orientation corresponding to the target sign pixel frame based on the position of the target sign pixel frame in the intersection scene image and the angles of the top and bottom edges of the target sign pixel frame.

[0013] In some implementation methods, the positioning module is specifically used to: if the fifth or sixth preset condition is met, locate the direction of the sign corresponding to the target sign pixel frame towards the second road; if the fifth and sixth preset conditions are not met, locate the direction of the sign corresponding to the target sign pixel frame towards the first road; wherein, the fifth preset condition includes: the target sign pixel frame is on the left side of the intersection scene image, and the angles of the upper and lower edges of the target sign pixel frame are both greater than the third preset angle and less than the fourth preset angle; the sixth preset condition includes: the target sign pixel frame is on the right side of the intersection scene image, and the angles of the upper and lower edges of the target sign pixel frame are both greater than the fifth preset angle and less than the sixth preset angle.

[0014] In some possible implementations, the third preset angle is 180 degrees, the fourth preset angle is 270 degrees, the fifth preset angle is 90 degrees, and the sixth preset angle is 180 degrees.

[0015] In some implementation methods, the recognition module is specifically used to: recognize the sign pixel frame of the intersection POI in the intersection scene image to obtain at least one sign pixel frame; and filter out the sign pixel frames that do not include the top or bottom edge of the at least one sign pixel frame to obtain the target sign pixel frame.

[0016] Thirdly, embodiments of this application provide an electronic device, including: a processor and a memory, the memory being used to store a computer program, and the processor being used to call and run the computer program stored in the memory to perform the methods as described in the first aspect or its various implementations.

[0017] Fourthly, embodiments of this application provide a computer-readable storage medium for storing a computer program that causes a computer to perform the methods described in the first aspect or its various implementations.

[0018] Fifthly, embodiments of this application provide a computer program product including computer program instructions that cause a computer to perform the methods as described in the first aspect or its various implementations.

[0019] Sixthly, embodiments of this application provide a computer program that causes a computer to perform the methods described in the first aspect or its various implementations.

[0020] The technical solution provided in this application determines the orientation of a sign based on its pixel frame position in an intersection scene image and its top and bottom edges. This positioning method matches the actual orientation of the sign, thus ensuring the accuracy of the sign orientation positioning. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a diagram illustrating a vanishing point.

[0023] Figure 2 This is a schematic diagram of another type of vanishing point;

[0024] Figure 3 This is another type of vanishing point diagram;

[0025] Figure 4 This is a schematic diagram of an application scenario provided by an embodiment of this application;

[0026] Figure 5 A flowchart illustrating a method for locating the orientation of a tag, as provided in an embodiment of this application;

[0027] Figure 6 An intersection scene image provided in an embodiment of this application;

[0028] Figure 7 Another intersection scene image provided in this application embodiment;

[0029] Figure 8 This application provides another intersection scene image;

[0030] Figure 9 This is a schematic diagram of the angle of the tag pixel frame provided in an embodiment of this application;

[0031] Figure 10 A schematic diagram of a 360-degree coordinate system provided for an embodiment of this application;

[0032] Figure 11 A schematic diagram of a tag orientation positioning device 1100 provided in an embodiment of this application;

[0033] Figure 12 This is a schematic block diagram of the electronic device provided in the embodiments of this application. Detailed Implementation

[0034] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0035] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0036] Before introducing the technical solution of this application, the relevant knowledge involved in this application will be explained below:

[0037] A Point of Interest (POI) is a record of a location on a map that is considered useful or interesting. A POI is typically defined by its geographic coordinates and some additional attributes, such as name and category. For example, Hotel A, located at latitude 1.286546 and longitude 103.853721, or Building B, located at latitude 40.748817 and longitude -73.985428, are both POIs.

[0038] II. Optical Character Recognition (OCR) algorithms are divided into two-stage algorithms and end-to-end algorithms. Two-stage OCR algorithms consist of text detection and recognition algorithms. The text detection algorithm obtains bounding boxes for text lines from the image, and then the recognition algorithm identifies the content within the text boxes. End-to-end OCR algorithms use a single model to simultaneously perform text detection and text recognition; therefore, end-to-end models are smaller and faster.

[0039] III. Perspective projection, a type of central projection. A perspective projection drawing, also known as a perspective view or perspective drawing, is a graphic obtained by projecting an object onto a single projection plane from a projection center.

[0040] IV. Vanishing Point: In perspective projection, the projections of a bundle of parallel lines parallel to the projection plane remain parallel, while the projections of parallel lines not parallel to the projection plane converge at a single point, called the vanishing point. The vanishing point can be viewed as the projection of a point at infinity onto the projection plane.

[0041] For example, Figure 1 This is a diagram of a vanishing point. Figure 1 There are three vanishing points on the projection surface shown. Figure 2 This is another diagram illustrating the vanishing point. Figure 3 This is another example of a vanishing point diagram. In this diagram, a vehicle's dashcam can record the vehicle's movement in real time and transmit the images to an electronic device for image processing. These real-time images can be understood as projection surfaces, that is, projected images of actual three-dimensional objects captured by the dashcam. When the electronic device acquires such... Figure 2 When the real-time image shown is displayed, it can identify the tag pixel frame 210, where, according to the definition of a vanishing point, the upper and lower edges of the tag pixel frame form a vanishing point. When the electronic device acquires such... Figure 3 When the image shown is displayed, it can identify the tag pixel frame 310, tag pixel frame 320 and tag pixel frame 330. According to the definition of vanishing point, the upper and lower edges of each tag pixel frame form a vanishing point.

[0042] The technical problem to be solved, the inventive concept, and the application scenarios of the technical solution of this application will be described below:

[0043] As mentioned above, dashcams typically record road scenes while driving. When a dashcam captures a sign, it assumes that the sign is facing the vehicle's current road. However, in intersection scenarios, the sign may not be facing the vehicle's current road; for example, it might be facing another road intersecting the current road. Therefore, current sign orientation positioning methods are not accurate enough.

[0044] To address the aforementioned technical problems, this application proposes a method to determine the orientation of a sign based on its pixel frame position within an intersection scene image and the top and bottom edges of that pixel frame. This positioning method aligns with the actual orientation of the sign, thus ensuring the accuracy of the sign orientation positioning.

[0045] The embodiments of this application can be applied. Figure 4 The application scenarios shown are not limited to these:

[0046] For example, Figure 4 This is a schematic diagram of an application scenario provided in an embodiment of this application, such as... Figure 4As shown, the application scenario includes a shooting device 410 and an electronic device 420, wherein the shooting device 410 and the electronic device 420 can be connected by wired or wireless means.

[0047] The shooting device 410 is used to capture the scene at the intersection. The shooting device 410 can be a dashcam installed on a vehicle, or a camera or video camera, but is not limited to these.

[0048] In some possible implementations, the electronic device 420 may be a terminal device or a server, but is not limited thereto.

[0049] In some possible implementations, the terminal device can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, etc., but is not limited to these.

[0050] In some implementations, the server can be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0051] It should be understood that, Figure 4 Taking a shooting device 410 and an electronic device 420 as an example, in fact, the embodiments of this application do not limit the number of shooting devices 410 and electronic devices 420.

[0052] The following will combine Figure 4 The application scenarios shown illustrate the technical solution of this application in detail:

[0053] Figure 5 This flowchart illustrates a method for determining the orientation of a sign, as provided in an embodiment of this application. The method is applied to an electronic device, which can be a terminal device or a server. The terminal device can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, etc., but is not limited to these. The server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms, but is not limited to these. Figure 5 As shown, the method may include:

[0054] S510: Acquire the intersection scene image of the first road and the second road captured on the first road;

[0055] In some implementations, the electronic device acquires an image of the intersection scene from a camera. The camera is used to capture the intersection scene.

[0056] In some possible implementations, the recording device can be a dashcam installed in a vehicle, or a camera or video camera, but is not limited to these.

[0057] It should be understood that, in order to clearly illustrate the intersection scenario of the first road and the second road, the following will be combined with... Figure 6 Describe the scene at this intersection, such as... Figure 6 As shown, the camera device can record the scene at the intersection of the first road and the second road on the first road. For example, when the camera device is a dashcam, and the vehicle is currently traveling on the first road, the dashcam in the vehicle can record the scene at the intersection of the first road and the second road, forming a scene like... Figure 6 The image shown depicts a scene at the intersection.

[0058] S520: Identify the pixel bounding box of the sign at the intersection POI in the intersection scene image to obtain the target sign pixel bounding box;

[0059] It should be understood that an intersection POI refers to the POI corresponding to a building located at an intersection in a roadside scene. Here, intersection POI is a map concept, corresponding to actual buildings such as shops, schools, hospitals, and banks at the intersection.

[0060] In some feasible ways, electronic devices can use OCR methods to recognize the pixel bounding boxes of signs for intersection POIs in intersection scene images, but this is not the only option.

[0061] When the electronic device uses the OCR method to recognize the sign pixel frame of the intersection POI in the intersection scene image, regardless of whether the embodiment of this application uses a two-stage OCR algorithm or an end-to-end OCR algorithm, firstly, the electronic device can perform binarization processing on the intersection scene image, that is, set the gray value of each pixel in the intersection scene image to 0 or 255. At this time, the intersection scene image will highlight the outline of the effective area. For example, the sign pixel frame of the intersection POI can be effectively highlighted. Furthermore, after the electronic device recognizes the text content using the OCR method, the electronic device recognizes the area with text content in the frame as the sign pixel frame of the intersection POI.

[0062] In other possible implementations, electronic devices can segment an intersection scene image into multiple sub-images and input these sub-images into a classification model to obtain the category of each sub-image, thereby identifying the pixel bounding box of the intersection POI sign.

[0063] The training device can acquire training samples, which include: multiple training sub-images and a label (category) for each training sub-image. Among the multiple training sub-images are sub-images whose category is the pixel-box category of intersection POI signs. Furthermore, the training device can train the aforementioned classification model based on these training samples.

[0064] In some implementations, the above classification model can be a binary classification model, meaning the classification result includes: the pixel frame category of the signage for intersection POIs and the pixel frame category of the signage for non-intersection POIs. Of course, the above classification model can also be a multi-classification model; in short, the embodiments of this application do not limit the above classification model.

[0065] In some possible implementations, the training device and the electronic device described above may be the same device or two different devices, and the embodiments of this application do not impose any restrictions on this.

[0066] In some implementations, the training device can use any of the following loss functions when training the classification model, but is not limited to: zero-one loss, logistic loss, hinge loss, exponential loss, and cross-entropy loss function.

[0067] It should be understood that when the electronic device identifies the sign pixel frame of the intersection POI in the intersection scene image, it can identify at least one target sign pixel frame. In S530 and S540, the electronic device uses any target sign pixel frame as an example to explain the sign orientation positioning method.

[0068] It should be understood that, for any given sign positioning pixel frame, the electronic device needs to utilize the top and bottom edges of the sign pixel frame when determining its orientation. Therefore, if the sign pixel frame does not include either the top or bottom edge, the electronic device can filter it out. This filtering process can be referred to as the denoising process of the electronic device on the intersection scene image. The electronic device can implement the denoising process in the following ways, but is not limited to them:

[0069] In some implementations, the electronic device identifies the sign pixel bounding boxes of intersection POIs in the intersection scene image, obtaining at least one sign pixel bounding box. If any of the at least one sign pixel bounding boxes does not include a top or bottom border, then those at least one sign pixel bounding box are filtered out to obtain a target sign pixel bounding box. If none of the at least one sign pixel bounding boxes does not include a top or bottom border, then the at least one sign pixel bounding box is taken as the target sign pixel bounding box. In other words, the target sign pixel bounding box is a sign pixel bounding box that includes both a top and bottom border.

[0070] For example, Figure 7 Another intersection scene image provided in this application embodiment, such as Figure 7 As shown, the intersection scene image includes: sign pixel frame 710, sign pixel frame 720, and sign pixel frame 730. The sign pixel frame 710 does not include the top edge. Based on this, when determining the target sign pixel frame, the electronic device can filter out the sign pixel frame 710. In other words, the target sign pixel frames in the intersection scene image are sign pixel frames 720 and 730.

[0071] S530: Determine the position of the target sign pixel frame in the intersection scene image, and the top and bottom edges of the target sign pixel frame;

[0072] In some possible implementations, such as Figure 8 As shown, the electronic device can divide the intersection scene image into left and right parts according to the center line of the intersection scene image, and the position of the target sign pixel frame in the intersection scene image refers to whether the target sign pixel frame is on the left or right side of the intersection scene image.

[0073] S540: Based on the position of the target sign pixel frame in the intersection scene image, and the top and bottom edges of the target sign pixel frame, locate the orientation of the sign corresponding to the target sign pixel frame.

[0074] In this embodiment of the application, the electronic device may locate the orientation of the tag corresponding to the pixel frame of the target tag using any of the following feasible methods, but is not limited thereto:

[0075] In the first implementation, S540 may include:

[0076] S540-1A: Determine the vanishing point of the target tag pixel frame based on the top and bottom edges of the target tag pixel frame;

[0077] For example, such as Figure 3As shown, the intersection scene image includes: sign pixel frame 310, sign pixel frame 320, and sign pixel frame 330, all of which are target sign pixel frames. According to the definition of a vanishing point, the top and bottom edges of each target sign pixel frame form a vanishing point.

[0078] S540-2A: Determine the positional relationship between the vanishing point of the target tag pixel frame and the target tag pixel frame;

[0079] In some implementations, the vanishing point of the target tag pixel frame can be positioned relative to the target tag pixel frame itself, either with the vanishing point to the left of the target tag pixel frame or with the vanishing point to the right of the target tag pixel frame.

[0080] For example, such as Figure 3 As shown, the vanishing point of the tag pixel frame 310 is to the left of the tag pixel frame 310, the vanishing point of the tag pixel frame 320 is to the right of the tag pixel frame 320, and the vanishing point of the tag pixel frame 330 is to the left of the tag pixel frame 330.

[0081] S540-3A: Based on the position of the target sign pixel frame in the intersection scene image and the positional relationship between the vanishing point of the target sign pixel frame and the target sign pixel frame, locate the sign orientation corresponding to the target sign pixel frame.

[0082] In some implementations, S540-3A may include:

[0083] S540-3A-1: Determine the angles of the top and bottom edges of the target tag pixel frame;

[0084] S540-3A-2: Based on the position of the target sign pixel frame in the intersection scene image, the positional relationship between the vanishing point of the target sign pixel frame and the target sign pixel frame, and the angles of the top and bottom edges of the target sign pixel frame, locate the sign orientation corresponding to the target sign pixel frame.

[0085] S540-3A-2 may include:

[0086] If either the first or second preset condition is met, the electronic device positions the target sign pixel frame so that the sign faces the second road; if neither the first nor the second preset condition is met, the electronic device positions the target sign pixel frame so that the sign faces the first road.

[0087] The first preset conditions include: the target sign pixel frame is on the left side of the intersection scene image, the vanishing point of the target sign pixel frame is on the left side of the target sign pixel frame, and the angles of the upper and lower edges of the target sign pixel frame are both less than the first preset angle.

[0088] The second preset conditions include: the target sign pixel frame is on the right side of the intersection scene image, the vanishing point of the target sign pixel frame is on the right side of the target sign pixel frame, and the angles of the top and bottom edges of the target sign pixel frame are both greater than the second preset angle.

[0089] In other words, if the target sign pixel frame is on the left side of the intersection scene image, the vanishing point of the target sign pixel frame is on the left side of the target sign pixel frame, and the angles of the upper and lower edges of the target sign pixel frame are both less than the first preset angle, then the electronic device will determine that the sign corresponding to the target sign pixel frame is facing the second road.

[0090] If the target sign pixel frame is on the left side of the intersection scene image and the vanishing point of the target sign pixel frame is on the right side of the target sign pixel frame, then the electronic device determines that the sign corresponding to the target sign pixel frame faces the first road.

[0091] If the target sign pixel frame is on the left side of the intersection scene image, the vanishing point of the target sign pixel frame is on the left side of the target sign pixel frame, and the angle of the upper edge of the target sign pixel frame is greater than or equal to the first preset angle, then the electronic device positions the sign corresponding to the target sign pixel frame to face the first road.

[0092] If the target sign pixel frame is on the left side of the intersection scene image, the vanishing point of the target sign pixel frame is on the left side of the target sign pixel frame, and the angle of the bottom edge of the target sign pixel frame is greater than or equal to the first preset angle, then the electronic device positions the sign corresponding to the target sign pixel frame to face the first road.

[0093] If the target sign pixel frame is on the right side of the intersection scene image, the vanishing point of the target sign pixel frame is on the right side of the target sign pixel frame, and the angles of the upper and lower edges of the target sign pixel frame are both greater than the second preset angle, then the electronic device positions the sign corresponding to the target sign pixel frame to face the second road.

[0094] If the target sign pixel frame is on the right side of the intersection scene image and the vanishing point of the target sign pixel frame is on the left side of the target sign pixel frame, then the electronic device determines that the sign corresponding to the target sign pixel frame faces the first road.

[0095] If the target sign pixel frame is on the right side of the intersection scene image, the vanishing point of the target sign pixel frame is on the right side of the target sign pixel frame, and the angle of the upper edge of the target sign pixel frame is less than or equal to the second preset angle, then the electronic device positions the sign corresponding to the target sign pixel frame to face the second road.

[0096] If the target sign pixel frame is on the right side of the intersection scene image, the vanishing point of the target sign pixel frame is on the right side of the target sign pixel frame, and the angle of the bottom edge of the target sign pixel frame is less than or equal to the second preset angle, then the electronic device positions the sign corresponding to the target sign pixel frame to face the second road.

[0097] It should be understood that, in the embodiments of this application, as Figure 9 As shown, for any sign pixel frame located in the intersection scene image, when determining the angle of the upper edge and the angle of the lower edge of the sign pixel frame, the starting point of the upper edge and the ending point are close to the center side of the intersection scene image, and far away from the center side of the intersection scene image.

[0098] It should be understood that, in the embodiments of this application, the orientation angle of the sign is defined based on a 360-degree coordinate system. Figure 10 A schematic diagram of a 360-degree coordinate system is provided for an embodiment of this application, as shown below. Figure 10 As shown, in this coordinate system, the angles directly above are 0 degrees and 360 degrees, and the angles increase in a clockwise direction.

[0099] In some possible implementations, the first preset angle is 270 degrees, or the value range of the first preset angle can be [270-α, 270+α] degrees, where α can be 5 degrees, 10 degrees, etc., but is not limited to this.

[0100] In some possible implementations, the second preset angle is 90 degrees, or the range of the second preset angle can be [90-β, 90+β] degrees, where β can be 5 degrees, 10 degrees, etc., but is not limited to this.

[0101] The following examples illustrate the method for determining the orientation of a sign:

[0102] Example 1, such as Figure 3 As shown, the sign pixel frame 310 is on the left side of the intersection scene image, and the vanishing point of the sign pixel frame 310 is on the left side of the sign pixel frame 310. Furthermore, the angles of the upper and lower edges of the sign pixel frame 310 are both less than 270 degrees. Based on this, the electronic device positions the sign corresponding to the sign pixel frame 310 to face the second road.

[0103] Example 2, such as Figure 3 As shown, the sign pixel frame 320 is on the right side of the intersection scene image, and the vanishing point of the sign pixel frame 320 is on the right side of the sign pixel frame 320. Furthermore, the angles of the upper and lower edges of the sign pixel frame 320 are both greater than 90 degrees. Based on this, the electronic device positions the sign corresponding to the sign pixel frame 320 to face the second road.

[0104] Example 3, such as Figure 3As shown, the sign pixel frame 330 is on the right side of the intersection scene image, and the vanishing point of the sign pixel frame 330 is on the left side of the sign pixel frame 330. Based on this, the electronic device positions the sign corresponding to the sign pixel frame 330 to face the first road.

[0105] In some other possible implementations, S540-3A may include: if a third preset condition or a fourth preset condition is met, the electronic device positions the target tag pixel frame corresponding to the tag facing the second road; if the third preset condition and the fourth preset condition are not met, the electronic device positions the target tag pixel frame corresponding to the tag facing the first road.

[0106] The third preset condition includes: the target sign pixel frame is on the left side of the intersection scene image, and the vanishing point of the target sign pixel frame is on the left side of the target sign pixel frame.

[0107] The fourth preset condition includes: the target sign pixel frame is on the right side of the intersection scene image, and the vanishing point of the target sign pixel frame is on the right side of the target sign pixel frame.

[0108] In other words, if the target sign pixel frame is on the left side of the intersection scene image and the vanishing point of the target sign pixel frame is on the left side of the target sign pixel frame, then the electronic device will determine that the sign corresponding to the target sign pixel frame is facing the second road.

[0109] If the target sign pixel frame is on the left side of the intersection scene image and the vanishing point of the target sign pixel frame is on the right side of the target sign pixel frame, then the electronic device determines that the sign corresponding to the target sign pixel frame faces the first road.

[0110] If the target sign pixel frame is on the right side of the intersection scene image and the vanishing point of the target sign pixel frame is on the right side of the target sign pixel frame, then the electronic device determines that the sign corresponding to the target sign pixel frame faces the second road.

[0111] If the target sign pixel frame is on the right side of the intersection scene image and the vanishing point of the target sign pixel frame is on the left side of the target sign pixel frame, then the electronic device determines that the sign corresponding to the target sign pixel frame faces the first road.

[0112] The following examples illustrate the method for determining the orientation of a sign:

[0113] Example 4, such as Figure 3 As shown, the sign pixel frame 310 is on the left side of the intersection scene image, and the vanishing point of the sign pixel frame 310 is on the left side of the sign pixel frame 310. Based on this, the electronic device positions the sign corresponding to the sign pixel frame 310 to face the second road.

[0114] Example 5, such as Figure 3As shown, the sign pixel frame 320 is on the right side of the intersection scene image, and the vanishing point of the sign pixel frame 320 is on the right side of the sign pixel frame 320. Based on this, the electronic device positions the sign corresponding to the sign pixel frame 320 to face the second road.

[0115] Example 6, such as Figure 3 As shown, the sign pixel frame 330 is on the right side of the intersection scene image, and the vanishing point of the sign pixel frame 330 is on the left side of the sign pixel frame 330. Based on this, the electronic device positions the sign corresponding to the sign pixel frame 330 to face the first road.

[0116] The second possible implementation method for S540 is as follows:

[0117] Alternatively, in the second implementation, S540 may include:

[0118] S540-1B: Determine the angles of the top and bottom edges of the target tag pixel frame;

[0119] S540-2B: Based on the position of the target sign pixel frame in the intersection scene image, the angle of the top edge and the angle of the bottom edge of the target sign pixel frame, the orientation of the sign corresponding to the target sign pixel frame is determined.

[0120] In some implementations, S540-2B may include:

[0121] If the fifth or sixth preset condition is met, the electronic device positions the target sign pixel frame with the sign facing the second road; if the fifth and sixth preset conditions are not met, the electronic device positions the target sign pixel frame with the sign facing the first road.

[0122] The fifth preset condition includes: the target sign pixel frame is on the left side of the intersection scene image, and the angles of the top and bottom edges of the target sign pixel frame are both greater than the third preset angle and less than the fourth preset angle.

[0123] The sixth preset condition includes: the target sign pixel frame is on the right side of the intersection scene image, and the angles of the top and bottom edges of the target sign pixel frame are both greater than the fifth preset angle and less than the sixth preset angle.

[0124] In other words, if the target sign pixel frame is on the left side of the intersection scene image, and the angles of the top and bottom edges of the target sign pixel frame are both greater than the third preset angle and less than the fourth preset angle, then the electronic device will determine that the sign corresponding to the target sign pixel frame is facing the second road.

[0125] If the angle between the top edge of the target sign pixel frame and the left side of the intersection scene image is less than or equal to the third preset angle, or greater than or equal to the fourth preset angle, then the electronic device positions the sign corresponding to the target sign pixel frame to face the first road.

[0126] If the angle between the bottom edge of the target sign pixel frame and the left side of the intersection scene image is less than or equal to the third preset angle, or greater than or equal to the fourth preset angle, then the electronic device positions the sign corresponding to the target sign pixel frame to face the first road.

[0127] If the target sign pixel frame is on the right side of the intersection scene image, and the angles of the top and bottom edges of the target sign pixel frame are both greater than the fifth preset angle and less than the sixth preset angle, then the electronic device will locate the sign corresponding to the target sign pixel frame to face the second road.

[0128] If the target sign pixel frame is on the right side of the intersection scene image, and the angle of the top edge of the target sign pixel frame is less than or equal to the fifth preset angle, or greater than or equal to the sixth preset angle, then the electronic device positions the sign corresponding to the target sign pixel frame to face the first road.

[0129] If the target sign pixel frame is on the right side of the intersection scene image, and the angle of the bottom edge of the target sign pixel frame is less than or equal to the fifth preset angle, or greater than or equal to the sixth preset angle, then the electronic device positions the sign corresponding to the target sign pixel frame to face the first road.

[0130] In some implementations, the third preset angle is 180 degrees and the fourth preset angle is 270 degrees, but it is not limited to these.

[0131] In some possible implementations, the fifth preset angle is 90 degrees and the sixth preset angle is 180 degrees, but it is not limited to these.

[0132] The following examples illustrate the method for determining the orientation of a sign:

[0133] Example 7, such as Figure 3 As shown, the sign pixel frame 310 is on the left side of the intersection scene image, and the angle of the upper edge of the sign pixel frame 310 is greater than 180 degrees and less than 270 degrees, and the angle of the lower edge is also greater than 180 degrees and less than 270 degrees. Based on this, the electronic device positions the sign corresponding to the sign pixel frame 310 to face the second road.

[0134] Example 8, such as Figure 3As shown, the sign pixel frame 320 is on the right side of the intersection scene image, and the angle of the upper edge of the sign pixel frame 320 is greater than 90 degrees and less than 180 degrees, and the angle of the lower edge is also greater than 90 degrees and less than 180 degrees. Based on this, the electronic device positions the sign corresponding to the sign pixel frame 320 to face the second road.

[0135] Example 9, such as Figure 3 As shown, the sign pixel frame 330 is on the right side of the intersection scene image, and the angle of the upper edge of the sign pixel frame 320 is greater than 180 degrees, and the angle of the lower edge is also greater than 180 degrees. Based on this, the electronic device positions the sign corresponding to the sign pixel frame 330 to face the first road.

[0136] In some possible implementations, the method for determining the orientation of the tag may also include: after S540, the electronic device optimizes the coordinates of the target tag pixel frame based on the tag orientation corresponding to the target tag pixel frame.

[0137] For example, assuming that, according to related technologies, the default orientation of the target sign pixel frame is the road the vehicle is currently traveling on, denoted as the first road, and assuming that, based on the positioning method provided in this application, the orientation of the target sign pixel frame is determined to be another road intersecting the road the vehicle is currently traveling on, denoted as the second road, then the left edge of the target sign pixel frame can be kept stationary while the right edge rotates around the left edge as an axis, causing the target sign pixel frame to rotate from the first road to the second road. Based on this rotation angle, the coordinates of the upper right and lower right corners of the target sign pixel frame are calculated, while the coordinates of the upper left and lower left corners of the target sign pixel frame remain unchanged. Based on this, the optimized coordinates of the target sign pixel frame are obtained.

[0138] In summary, this application provides a method for locating the orientation of a sign. The method includes: acquiring an image of the intersection scene between a first road and a second road, captured on a first road; identifying the sign pixel bounding boxes of the points of interest (POIs) at the intersection scene image to obtain a target sign pixel bounding box; determining the position of the target sign pixel bounding box in the intersection scene image, and its upper and lower edges; and locating the orientation of the sign corresponding to the target sign pixel bounding box based on its position and the upper and lower edges. Because this positioning method matches the actual orientation of the sign, the accuracy of the sign orientation positioning is ensured.

[0139] Furthermore, since the sign orientation positioning method provided in this application embodiment has high accuracy, the sign orientation positioning method provided in this application embodiment can better optimize the coordinates of intersection POIs in the map. If the map is applied to a navigation system, the navigation accuracy of the navigation system can be improved. For example, if the navigation destination is a shop located at an intersection, the navigation system can accurately navigate to the direction the shop entrance faces.

[0140] The preferred embodiments of this application have been described in detail above with reference to the accompanying drawings. However, this application is not limited to the specific details of the above embodiments. Within the scope of the technical concept of this application, various simple modifications can be made to the technical solutions of this application, and these simple modifications all fall within the protection scope of this application. For example, the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. To avoid unnecessary repetition, this application will not describe the various possible combinations separately. Furthermore, various different embodiments of this application can also be arbitrarily combined, as long as they do not violate the spirit of this application, they should also be considered as the content disclosed in this application.

[0141] It should also be understood that, in the various method embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0142] The methods provided in the embodiments of this application have been described above. The apparatus provided in the embodiments of this application will be described below.

[0143] Figure 11 A schematic diagram of a tag orientation positioning device 1100 provided in an embodiment of this application is shown below. Figure 11 As shown, the device 1100 includes: an acquisition module 1110, an identification module 1120, a determination module 1130, and a positioning module 1140. The acquisition module 1110 is used to acquire an image of the intersection scene between the first road and the second road taken on the first road. The identification module 1120 is used to identify the sign pixel frame of the intersection POI in the intersection scene image to obtain the target sign pixel frame. The determination module 1130 is used to determine the position of the target sign pixel frame in the intersection scene image, as well as the upper and lower edges of the target sign pixel frame. The positioning module 1140 is used to locate the sign orientation corresponding to the target sign pixel frame based on the position of the target sign pixel frame in the intersection scene image and the upper and lower edges of the target sign pixel frame.

[0144] In some implementations, the positioning module 1140 is specifically used to: determine the vanishing point of the target sign pixel frame based on the upper and lower edges of the target sign pixel frame; determine the positional relationship between the vanishing point of the target sign pixel frame and the target sign pixel frame; and locate the sign orientation corresponding to the target sign pixel frame based on the position of the target sign pixel frame in the intersection scene image and the positional relationship between the vanishing point of the target sign pixel frame and the target sign pixel frame.

[0145] In some implementations, the determining module 1130 is further used to determine the angles of the top and bottom edges of the target sign pixel frame before the positioning module 1140 determines the sign orientation corresponding to the target sign pixel frame based on the position of the target sign pixel frame in the intersection scene image and the positional relationship between the vanishing point and the target sign pixel frame. Accordingly, the positioning module 1140 is specifically used to: determine the sign orientation corresponding to the target sign pixel frame based on the position of the target sign pixel frame in the intersection scene image, the positional relationship between the vanishing point and the target sign pixel frame, and the angles of the top and bottom edges of the target sign pixel frame.

[0146] In some possible implementations, the positioning module 1140 is specifically used to: if a first preset condition or a second preset condition is met, locate the sign corresponding to the target sign pixel frame to face the second road; if the first preset condition and the second preset condition are not met, locate the sign corresponding to the target sign pixel frame to face the first road; wherein, the first preset condition includes: the target sign pixel frame is on the left side of the intersection scene image, the vanishing point of the target sign pixel frame is on the left side of the target sign pixel frame, and the angles of the upper and lower edges of the target sign pixel frame are both less than the first preset angle; the second preset condition includes: the target sign pixel frame is on the right side of the intersection scene image, the vanishing point of the target sign pixel frame is on the right side of the target sign pixel frame, and the angles of the upper and lower edges of the target sign pixel frame are both greater than the second preset angle.

[0147] In some possible implementations, the first preset angle is 270 degrees and the second preset angle is 90 degrees.

[0148] In some possible implementations, the positioning module 1140 is specifically used to: if a third preset condition or a fourth preset condition is met, locate the sign corresponding to the target sign pixel frame to face the second road; if the third and fourth preset conditions are not met, locate the sign corresponding to the target sign pixel frame to face the first road; wherein, the third preset condition includes: the target sign pixel frame is on the left side of the intersection scene image, and the vanishing point of the target sign pixel frame is on the left side of the target sign pixel frame; the fourth preset condition includes: the target sign pixel frame is on the right side of the intersection scene image, and the vanishing point of the target sign pixel frame is on the right side of the target sign pixel frame.

[0149] In some implementations, the positioning module 1140 is specifically used to: determine the angle of the top edge and the angle of the bottom edge of the target sign pixel frame; and locate the sign orientation corresponding to the target sign pixel frame based on the position of the target sign pixel frame in the intersection scene image and the top and bottom edges of the target sign pixel frame, including: locating the sign orientation corresponding to the target sign pixel frame based on the position of the target sign pixel frame in the intersection scene image and the angle of the top and bottom edges of the target sign pixel frame.

[0150] In some possible implementations, the positioning module 1140 is specifically used to: if the fifth or sixth preset condition is met, locate the sign corresponding to the target sign pixel frame to face the second road; if the fifth and sixth preset conditions are not met, locate the sign corresponding to the target sign pixel frame to face the first road; wherein, the fifth preset condition includes: the target sign pixel frame is on the left side of the intersection scene image, and the angles of the upper and lower edges of the target sign pixel frame are both greater than the third preset angle and less than the fourth preset angle; the sixth preset condition includes: the target sign pixel frame is on the right side of the intersection scene image, and the angles of the upper and lower edges of the target sign pixel frame are both greater than the fifth preset angle and less than the sixth preset angle.

[0151] In some possible implementations, the third preset angle is 180 degrees, the fourth preset angle is 270 degrees, the fifth preset angle is 90 degrees, and the sixth preset angle is 180 degrees.

[0152] In some implementations, the recognition module 1120 is specifically used to: recognize the sign pixel frame of the intersection POI in the intersection scene image to obtain at least one sign pixel frame; and filter out the sign pixel frames that do not include the top or bottom edge of the at least one sign pixel frame to obtain the target sign pixel frame.

[0153] It should be understood that the device embodiments and method embodiments can correspond to each other, and similar descriptions can be referred to the method embodiments. To avoid repetition, further details will not be provided here. Specifically, Figure 11 The device 1100 shown can perform Figure 5 The corresponding method embodiments, and the foregoing and other operations and / or functions of each module in the device 1100 are respectively for implementing Figure 5 For the sake of brevity, the corresponding processes in each method are not described in detail here.

[0154] The apparatus 1100 of this application embodiment has been described above from the perspective of functional modules in conjunction with the accompanying drawings. It should be understood that this functional module can be implemented in hardware, in software instructions, or in a combination of hardware and software modules. Specifically, the steps of the method embodiments in this application can be completed by integrated logic circuits in the processor's hardware and / or by software instructions. The steps of the method disclosed in this application embodiment can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. Optionally, the software module can be located in a mature storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, etc. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps in the above method embodiments.

[0155] Figure 12 This is a schematic block diagram of the electronic device provided in the embodiments of this application.

[0156] like Figure 12 As shown, the electronic device may include:

[0157] The system includes a memory 1210 and a processor 1220. The memory 1210 stores computer programs and transfers the program code to the processor 1220. In other words, the processor 1220 can retrieve and run the computer program from the memory 1210 to implement the methods described in the embodiments of this application.

[0158] For example, the processor 1220 can be used to execute the above-described method embodiments according to instructions in the computer program.

[0159] In some embodiments of this application, the processor 1220 may include, but is not limited to:

[0160] General-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.

[0161] In some embodiments of this application, the memory 1210 includes, but is not limited to:

[0162] Volatile memory and / or non-volatile memory. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), and Direct Rambus RAM (DR RAM).

[0163] In some embodiments of this application, the computer program may be divided into one or more modules, which are stored in the memory 1210 and executed by the processor 1220 to perform the method provided in this application. The one or more modules may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the electronic device.

[0164] like Figure 12 As shown, the electronic device may further include:

[0165] Transceiver 1230, which can be connected to processor 1220 or memory 1210.

[0166] The processor 1220 can control the transceiver 1230 to communicate with other devices; specifically, it can send information or data to other devices or receive information or data sent by other devices. The transceiver 1230 may include a transmitter and a receiver. The transceiver 1230 may further include antennas, and the number of antennas may be one or more.

[0167] It should be understood that the various components in the electronic device are connected through a bus system, which includes a data bus, a power bus, a control bus, and a status signal bus.

[0168] This application also provides a computer storage medium storing a computer program thereon, which, when executed by a computer, enables the computer to perform the methods of the above-described method embodiments. Alternatively, embodiments of this application also provide a computer program product containing instructions that, when executed by a computer, cause the computer to perform the methods of the above-described method embodiments.

[0169] When implemented using software, it can be implemented entirely or partially as a computer program product. This computer program product includes one or more computer instructions. When these computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., digital video disc (DVD)), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0170] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0171] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or modules may be electrical, mechanical, or other forms.

[0172] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. For example, the functional modules in the various embodiments of this application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0173] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method for determining the orientation of a sign, characterized in that, include: Acquire the intersection scene image of the first road and the second road taken on the first road; The pixel bounding boxes of signs at points of interest (POIs) in the intersection scene image are identified to obtain the target sign pixel bounding box. Determine the position of the target sign pixel frame in the intersection scene image, as well as the top and bottom edges of the target sign pixel frame; Based on the position of the target sign pixel frame in the intersection scene image, and the top and bottom edges of the target sign pixel frame, the orientation of the sign corresponding to the target sign pixel frame is determined; The step of locating the orientation of the sign corresponding to the target sign pixel frame based on its position in the intersection scene image and its top and bottom edges includes: determining the vanishing point of the target sign pixel frame based on its top and bottom edges; determining the positional relationship between the vanishing point and the target sign pixel frame; and locating the orientation of the sign corresponding to the target sign pixel frame based on its position in the intersection scene image and its positional relationship with the vanishing point. Alternatively... The step of locating the orientation of the sign corresponding to the target sign pixel frame based on the position of the target sign pixel frame in the intersection scene image, and the top and bottom edges of the target sign pixel frame, includes: determining the angles of the top and bottom edges of the target sign pixel frame; and locating the orientation of the sign corresponding to the target sign pixel frame based on the position of the target sign pixel frame in the intersection scene image, and the angles of the top and bottom edges of the target sign pixel frame.

2. The method according to claim 1, characterized in that, Before determining the orientation of the sign corresponding to the target sign pixel frame based on its position in the intersection scene image and the positional relationship between the vanishing point and the target sign pixel frame, the method further includes: Determine the angles of the top and bottom edges of the target tag pixel frame; The step of locating the orientation of the sign corresponding to the target sign pixel frame based on the position of the target sign pixel frame in the intersection scene image and the positional relationship between the vanishing point of the target sign pixel frame and the target sign pixel frame includes: Based on the position of the target sign pixel frame in the intersection scene image, the positional relationship between the vanishing point of the target sign pixel frame and the target sign pixel frame, and the angles of the top and bottom edges of the target sign pixel frame, the orientation of the sign corresponding to the target sign pixel frame is determined.

3. The method according to claim 2, characterized in that, The step of locating the orientation of the sign corresponding to the target sign pixel frame based on the position of the target sign pixel frame in the intersection scene image, the positional relationship between the vanishing point of the target sign pixel frame and the target sign pixel frame, and the angles of the top and bottom edges of the target sign pixel frame includes: If the first preset condition or the second preset condition is met, the orientation of the sign corresponding to the target sign pixel frame is determined to be towards the second road; If the first preset condition and the second preset condition are not met, then the orientation of the sign corresponding to the target sign pixel frame is determined to be the first road. The first preset condition includes: the target sign pixel frame is on the left side of the intersection scene image, the vanishing point of the target sign pixel frame is on the left side of the target sign pixel frame, and the angles of the upper and lower edges of the target sign pixel frame are both less than the first preset angle. The second preset condition includes: the target sign pixel frame is on the right side of the intersection scene image, the vanishing point of the target sign pixel frame is on the right side of the target sign pixel frame, and the angles of the upper and lower edges of the target sign pixel frame are both greater than the second preset angle.

4. The method according to claim 3, characterized in that, The first preset angle is 270 degrees, and the second preset angle is 90 degrees.

5. The method according to claim 1, characterized in that, The step of locating the orientation of the sign corresponding to the target sign pixel frame based on the position of the target sign pixel frame in the intersection scene image and the positional relationship between the vanishing point of the target sign pixel frame and the target sign pixel frame includes: If the third or fourth preset condition is met, then the orientation of the sign corresponding to the target sign pixel frame is determined to be towards the second road; If the third and fourth preset conditions are not met, then the orientation of the sign corresponding to the target sign pixel frame is determined to be the first road. The third preset condition includes: the target sign pixel frame is on the left side of the intersection scene image, and the vanishing point of the target sign pixel frame is on the left side of the target sign pixel frame; The fourth preset condition includes: the target sign pixel frame is on the right side of the intersection scene image, and the vanishing point of the target sign pixel frame is on the right side of the target sign pixel frame.

6. The method according to claim 1, characterized in that, The step of locating the orientation of the sign corresponding to the target sign pixel frame based on the position of the target sign pixel frame in the intersection scene image, the angle of the top edge of the target sign pixel frame, and the angle of the bottom edge of the target sign pixel frame includes: If the fifth or sixth preset condition is met, then the orientation of the sign corresponding to the target sign pixel frame is determined to be that of the second road. If the fifth and sixth preset conditions are not met, then the orientation of the sign corresponding to the target sign pixel frame is determined to be the first road. The fifth preset condition includes: the target sign pixel frame is on the left side of the intersection scene image, and the angles of the upper and lower edges of the target sign pixel frame are both greater than the third preset angle and less than the fourth preset angle. The sixth preset condition includes: the target sign pixel frame is on the right side of the intersection scene image, and the angles of the upper and lower edges of the target sign pixel frame are both greater than the fifth preset angle and less than the sixth preset angle.

7. The method according to claim 6, characterized in that, The third preset angle is 180 degrees, the fourth preset angle is 270 degrees, the fifth preset angle is 90 degrees, and the sixth preset angle is 180 degrees.

8. The method according to any one of claims 1-7, characterized in that, The step of identifying the pixel bounding box of the sign at the point of interest (POI) in the intersection scene image to obtain the target sign pixel bounding box includes: The pixel frame of the sign at the intersection POI in the intersection scene image is identified to obtain at least one pixel frame of the sign. The target tag pixel frame is obtained by filtering out the tag pixel frames that do not include the top or bottom edge.

9. A positioning device for determining the orientation of a tag, characterized in that, include: The acquisition module is used to acquire the intersection scene image of the first road and the second road captured on the first road; The recognition module is used to recognize the sign pixel frame of the intersection POI in the intersection scene image to obtain the target sign pixel frame; The determination module is used to determine the position of the target sign pixel frame in the intersection scene image, as well as the top and bottom edges of the target sign pixel frame; The positioning module is used to locate the orientation of the sign corresponding to the target sign pixel frame based on the position of the target sign pixel frame in the intersection scene image, the top edge and the bottom edge of the target sign pixel frame; Specifically, the positioning module is used for: The vanishing point of the target sign pixel frame is determined based on its top and bottom edges; the positional relationship between the vanishing point and the target sign pixel frame is determined; based on the position of the target sign pixel frame in the intersection scene image and the positional relationship between the vanishing point and the target sign pixel frame, the orientation of the sign corresponding to the target sign pixel frame is determined; or... Determine the angles of the top and bottom edges of the target sign pixel frame; based on the position of the target sign pixel frame in the intersection scene image, and the angles of the top and bottom edges of the target sign pixel frame, determine the sign orientation corresponding to the target sign pixel frame.

10. An electronic device, characterized in that, include: A processor and a memory, the memory being used to store a computer program, the processor being used to invoke and run the computer program stored in the memory to perform the method of any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that, Used to store a computer program that causes a computer to perform the method as described in any one of claims 1 to 8.

12. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instruction is executed by the processor, it implements the method as described in any one of claims 1 to 8.

Images