Elevated Navigation Method, Electronic Device and Storage Medium

Abstract

The present invention discloses an elevated navigation method, an electronic device, and a storage medium. The method includes: in response to navigating to a distance within a preset distance threshold from an elevated fork, intercepting one or more driving images, and identifying a feature region containing a guide line from the driving images; comparing the feature region with the driving route, and judging whether the vehicle enters the elevated road according to the comparison result; and displaying a corresponding navigation route according to whether the vehicle enters the elevated road. By identifying the guide line, determining the feature region, and judging the position of the vehicle driving route relative to the feature region of the guide line, and through the comprehensive processing of the vehicle route selection and navigation data, the present invention can accurately judge whether the vehicle is on the elevated road or on the ground and timely switch the route. The identification scheme of the present invention is simple and has low hardware dependence. Only by adding vehicle-side parameters to the navigation software, accurate navigation can be performed in various urban elevated road scenarios.

Description

Technical Field

[0001] The present invention relates to the technical field related to automobiles, and particularly to an elevated navigation method, an electronic device, and a storage medium. Background Art

[0002] There are many roads in the city where the elevated roads and the roads are in a straight line. When running on the urban roads, the existing positioning methods cannot accurately distinguish whether the vehicle has driven onto the elevated road, which is prone to misjudgment and leads to navigation errors. If the vehicle position is misjudged and not corrected in time, the navigation of this section of the route will fail, and a long detour is required for correction.

[0003] Since relying solely on the Global Positioning System (GPS) cannot distinguish whether the vehicle is driving onto the elevated road. Therefore, some navigation software has added a function of manually switching positions, however, the manual switching of positions is not intelligent enough.

[0004] For this reason, the prior art proposes to judge whether it is on a ramp by the change of the intersection of lane lines, or to judge the position by the image features above and below the elevated road through a large amount of data classification.

[0005] However, the existing solutions for visually identifying whether a vehicle is on an elevated road need to use high-computing power devices, and judge the vehicle position by combining the images of multiple cameras through neural network or deep learning methods, and the cost is very high. Summary of the Invention

[0006] Based on this, in view of the technical problem that the prior art uses a visual solution to identify whether a vehicle is on an elevated road with high cost, it is necessary to provide an elevated navigation method, an electronic device, and a storage medium.

[0007] The present invention provides an elevated navigation method, including:

[0008] In response to navigating to a distance within a preset distance threshold from the elevated fork, intercept and save one or more driving images, and identify a feature area containing a guide line from the driving images;

[0009] Compare the feature area with the driving route, and judge whether the vehicle enters the elevated road according to the comparison result, where the driving route is the estimated trajectory that will appear in the driving image when the vehicle drives in the direction of taking the driving image;

[0010] Display the corresponding navigation route according to whether the vehicle enters the elevated road.

[0011] Further, the feature area is the smallest rectangle in the driving image that contains all the V-shaped lines or diagonal lines of the guide line. The comparison of the feature area with the driving route and the judgment of whether the vehicle enters the elevated road according to the comparison result specifically include:

[0012] Compare the center of the feature area with the driving route. If the driving route is on the left side of the center of the feature area, it is determined that the vehicle is on the left side of the guide line. If the driving route is on the right side of the center of the feature area, it is determined that the vehicle is on the right side of the guide line;

[0013] Obtain navigation information, and determine whether the vehicle enters the elevated road according to the navigation information and the relative direction of the vehicle to the guide line.

[0014] Further, if multiple driving images are saved, the comparing the center of the feature area with the driving route. If the driving route is on the left side of the center of the feature area, it is determined that the vehicle is on the left side of the guide line. If the driving route is on the right side of the center of the feature area, it is determined that the vehicle is on the right side of the guide line, specifically includes:

[0015] Compare the feature area in the saved multiple driving images with the driving route. If the number of driving images in which the driving route is on the left side of the center of the feature area exceeds half of the number of saved driving images, it is determined that the vehicle is on the left side of the guide line. If the number of driving images in which the driving route is on the right side of the center of the feature area exceeds half of the number of saved driving images, it is determined that the vehicle is on the right side of the guide line.

[0016] Further, the comparing the center of the feature area with the driving route specifically includes:

[0017] Establish a two-dimensional coordinate system for the driving image, where the two-dimensional coordinate system includes an X-axis extending in the left-right direction and a Y-axis extending in the upward direction;

[0018] Obtain the center coordinates of the feature area;

[0019] Calculate the X-axis coordinate value of the point where the Y-axis coordinate value of the driving route in the two-dimensional coordinate system is consistent with the Y-axis coordinate value of the center coordinates of the feature area. If the X-axis coordinate value of this point is on the left side of the X-axis coordinate value of the center coordinates of the feature area, the driving route is on the left side of the center of the feature area. If the X-axis coordinate value of this point is on the right side of the X-axis coordinate value of the center coordinates of the feature area, the driving route is on the right side of the center of the feature area.

[0020] Further, the responding to the navigation to a distance within a preset distance threshold from the elevated road fork, intercepting one or more driving images, and identifying the feature area including the guide line from the driving images specifically includes:

[0021] Responding to the navigation to a distance within a preset distance threshold from the elevated road fork, start continuously intercepting driving images at a preset frequency;

[0022] From the driving image, identify the feature area containing the guide line. If the feature area can be identified from the driving image, the driving image is a valid image. If the feature area cannot be identified from the driving image, the driving image is an invalid image;

[0023] When a valid image is detected, start saving the driving image. If an invalid image is detected after starting to save the driving image, stop intercepting and saving the driving image.

[0024] Further, the identifying the feature area containing the guide line from the driving image specifically includes:

[0025] Filter and delete the roads and decorations in the driving image through color matrix features;

[0026] Identify and delete the bright colors in the upper part of the driving image;

[0027] For the driving image after deletion, adopt the contour recognition method to identify the feature area containing the guide line.

[0028] Further, the driving route is a straight line starting from a preset starting coordinate at the bottom of the driving image and extending upward along the driving angle. The driving angle is the included angle between the driving route and the central axis of the driving image.

[0029] Even further, it further includes: in response to a driving route automatic correction request, obtain multiple driving images as correction reference images within a preset time period;

[0030] Identify the lane lines on both sides from the correction reference images;

[0031] If for multiple consecutive correction reference images, the change difference in the position of each lane line in the correction reference image is less than a preset difference threshold, then use the starting coordinate of the midline of the lane lines on both sides as the starting coordinate of the driving route, and use the included angle between the midline of the lane lines on both sides and the central axis of the correction reference image as the driving angle of the driving route.

[0032] Even further, it further includes: obtain the correction result of the user for the navigation route, and according to the correction result, correct the starting coordinate or the driving angle.

[0033] Even more further, the obtaining the correction result of the user for the navigation route and correcting the starting coordinate or the driving angle according to the correction result specifically includes:

[0034] Obtain the correction result of the user for the navigation route, and according to the correction result, adjust the starting coordinate or the driving angle until the positional relationship between the driving route and the center of the feature area conforms to the correction result.

[0035] The present invention provides an electronic device, comprising:

[0036] at least one processor; and,

[0037] a memory communicatively connected to the at least one processor; wherein,

[0038] the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the elevated navigation method as described above.

[0039] The present invention provides a storage medium that stores computer instructions, which are used to execute all steps of the elevated navigation method as described above when a computer executes the computer instructions.

[0040] By identifying the guide line, determining the characteristic area, and judging the position of the vehicle driving route relative to the characteristic area of the guide line, and through the comprehensive processing of the vehicle route selection and navigation data, the present invention can accurately judge whether the vehicle is on the elevated road or on the ground and switch the route in time. The identification scheme of the present invention is simple and has low hardware dependence. Only by adding vehicle-side parameters to the navigation software can accurate navigation be performed in various urban elevated road scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 is a flowchart of the working process of an elevated navigation method according to an embodiment of the present invention;

[0042] Figure 2 is a flowchart of the working process of an elevated navigation method according to another embodiment of the present invention;

[0043] Figure 3 is the driving image in an example of the present invention;

[0044] Figure 4 is for Figure 3 the image obtained by filtering the road and decorations in the driving image through color matrix feature filtering;

[0045] Figure 5 is for Figure 4 the image obtained by identifying and deleting the bright color in the upper part of the driving image;

[0046] Figure 6 is Figure 5 the contour map;

[0047] Figure 7 is a schematic diagram of characteristic area identification according to an embodiment of the present invention;

[0048] Figure 8 is a schematic diagram of comparison between the characteristic area and the driving route according to an embodiment of the present invention;

[0049] Figure 9 Schematic diagram of misjudgment comparison between the feature area and the driving route in an embodiment of the present invention;

[0050] Figure 10 Flowchart of the working process of an elevated navigation method according to the best embodiment of the present invention;

[0051] Figure 11 Schematic diagram of the hardware structure of an electronic device according to the present invention. Detailed implementation manners

[0052] The following further describes the detailed implementation manners of the present invention with reference to the accompanying drawings. The same components are denoted by the same reference numerals. It should be noted that the terms "front", "rear", "left", "right", "upper" and "lower" used in the following description refer to the directions in the drawings, and the terms "inner" and "outer" refer to the directions towards or away from the geometric center of a specific component respectively.

[0053] As Figure 1 shown is the flowchart of the working process of an elevated navigation method according to an embodiment of the present invention, including:

[0054] Step S101, in response to the vehicle navigating to a distance within a preset distance threshold from the elevated fork, capture one or more driving images, and identify a feature area containing a guide line from the driving images.

[0055] Step S102, compare the feature area with the driving route, and determine whether the vehicle enters the elevated road according to the comparison result. The driving route is the estimated trajectory that will appear in the driving image when the vehicle drives in the direction of taking the driving image.

[0056] Step S103, display the corresponding navigation route according to whether the vehicle enters the elevated road.

[0057] Specifically, the present invention can be applied to the electronic control unit (ECU) of a vehicle.

[0058] When the vehicle navigates to a distance within a preset distance threshold from the elevated fork, for example, close to the preset distance threshold of the elevated ramp, step S101 will be triggered to capture and save one or more driving images. The distance threshold is a value greater than or equal to 0. If the distance threshold is large, the driving images will be captured in advance to avoid omission, but it may increase the calculation amount. If the distance threshold is small, the calculation amount can be reduced, but the guide line may be omitted when the vehicle speed is fast. The specific distance threshold can be calibrated through multiple measurements.

[0059] Since the guide line can be set at intersections with complex driving conditions, ramp entrances of grade-separated intersections or other special locations. Therefore, by triggering step S101 at the elevated fork, it is possible to avoid misidentifying the guide line when collecting and identifying it on non-elevated sections.

[0060] In some embodiments, the driving image can be obtained by shooting with the front camera device of the vehicle. For example, it can be obtained by shooting with the front camera of the vehicle.

[0061] In some embodiments, one or more driving images are intercepted from the video shot by the front camera device of the vehicle and saved.

[0062] Then, a feature area containing the guide line is identified from the driving image. The form of the guide line is mainly one or several white V-shaped lines or diagonal line areas set according to the terrain of the intersection. It can be identified by means of image processing. Among them, one side of the guide line at the elevated fork is the road leading to the elevated road, and the other side of the guide line is the road that does not lead to the elevated road. Therefore, when the guide line is identified and the position of the vehicle relative to the guide line is determined, it is possible to determine whether the vehicle is on the elevated road.

[0063] Since the guide line is not a regular image, if the position of the guide line and the vehicle is directly identified, the calculation is complex and requires very high computing power.

[0064] Therefore, in this embodiment, a feature area containing the guide line is generated. By identifying the position of the vehicle with the feature area, the calculation complexity is greatly reduced and the computing power requirement is reduced.

[0065] In some embodiments, the feature area contains all the guide lines in the driving image.

[0066] In some embodiments, the feature area is a regular area containing all the guide lines in the driving image.

[0067] The regular area includes a rectangular area, an elliptical area, or a trapezoidal area.

[0068] Preferably, the feature area is a regular area containing all the guide lines in the driving image.

[0069] Then, step S102 is executed to compare the feature area with the driving route.

[0070] In some embodiments, the feature area is a regular area, and the center of the feature area is used to compare with the driving route.

[0071] Since the vehicle itself does not exist in the driving image. Therefore, if the vehicle itself is used for comparison, it is necessary to calculate the position of the vehicle itself in the driving image, which is computationally complex and requires high computing power. Therefore, in step S102, the driving route is compared with the feature area, rather than the vehicle itself with the feature area. Since the imaging device is fixed on the vehicle, its position and angle can be determined in advance. Therefore, the driving route can be represented by a fixed straight line in the driving image, thus greatly reducing the computational complexity and the requirement for computing power.

[0072] The driving route is the estimated trajectory that the vehicle will appear in the driving image when driving in the direction of taking the driving image. Since the driving image is obtained from the image of the vehicle's front camera, generally, the image of the in-vehicle driving recorder can be used as the driving image. And the vehicle's front camera, such as the driving recorder, is fixed in position on the vehicle. Therefore, the vehicle manufacturer can pre-calibrate a certain straight line in the driving image as the driving route before leaving the factory.

[0073] Finally, execute step S103 to display the corresponding navigation route according to whether the vehicle enters the viaduct.

[0074] In some embodiments, the judgment result of whether the vehicle enters the viaduct is sent to the navigation system, and the navigation system displays the corresponding navigation route.

[0075] If the vehicle enters the viaduct, the navigation route on the viaduct is displayed. If the vehicle does not enter the viaduct, the navigation route under the viaduct, that is, on the ground, is displayed.

[0076] By identifying the guide line, determining the feature area, and judging the position of the vehicle's driving route relative to the feature area of the guide line, and through the comprehensive processing of the vehicle route selection and navigation data, the present invention can accurately judge whether the vehicle is on the viaduct or on the ground and switch the route in time. The recognition scheme of the present invention is simple and has low hardware dependence. Only by adding vehicle-side parameters to the navigation software, accurate navigation can be performed in various urban viaduct scenarios.

[0077] As Figure 2 shown is the flowchart of the operation of an elevated navigation method in another embodiment of the present invention, including:

[0078] Step S201, in response to the distance to the viaduct fork being within a preset distance threshold, start continuously intercepting driving images at a preset frequency.

[0079] Step S202: Identify the feature region containing the guide line from the driving image. If the feature region can be identified from the driving image, the driving image is a valid image; if the feature region cannot be identified from the driving image, the driving image is an invalid image. The feature region is the smallest rectangle in the driving image that contains all the V-shaped lines or diagonal lines of the guide line.

[0080] Step S203: When a valid image is detected, start saving the driving image. If an invalid image is detected after starting to save the driving image, stop intercepting and saving the driving image.

[0081] In one embodiment, the identifying the feature region containing the guide line from the driving image specifically includes:

[0082] Filter and delete the roads and decorations in the driving image through color matrix features;

[0083] Identify and delete the bright colors in the upper part of the driving image;

[0084] For the driving image after deletion, adopt the contour recognition method to identify the feature region containing the guide line.

[0085] Step S204: Compare the center of the feature region with the driving route. If the driving route is located on the left side of the center of the feature region, it is determined that the vehicle is on the left side of the guide line; if the driving route is located on the right side of the center of the feature region, it is determined that the vehicle is on the right side of the guide line. The driving route is the predicted trajectory that the vehicle will appear in the driving image when driving in the direction of taking the driving image. The driving route is a straight line extending upward from the starting coordinate preset at the bottom of the driving image at the traveling angle. The traveling angle is the included angle between the driving route and the central axis of the driving image.

[0086] In one embodiment, it further includes:

[0087] In response to the driving route automatic correction request, obtain multiple driving images as correction reference images within a preset time period;

[0088] Identify the lane lines on both sides from the correction reference images;

[0089] If the change difference in the position of each lane line on each side in the correction reference images for multiple consecutive correction reference images is less than the preset difference threshold, use the starting coordinate of the midline of the lane lines on both sides as the starting coordinate of the driving route, and use the included angle between the midline of the lane lines on both sides and the central axis of the correction reference image as the traveling angle of the driving route.

[0090] In one embodiment, it further includes: obtaining the correction result of the user for the navigation route, and correcting the starting coordinate or the traveling angle according to the correction result.

[0091] In one embodiment, the obtaining the correction result of the user for the navigation route, and correcting the starting coordinate or the traveling angle according to the correction result specifically includes:

[0092] Obtaining the correction result of the user for the navigation route, and adjusting the starting coordinate or the traveling angle according to the correction result until the positional relationship between the driving route and the center of the feature area conforms to the correction result.

[0093] In one embodiment, if multiple driving images are saved, comparing the center of the feature area with the driving route. If the driving route is on the left side of the center of the feature area, it is determined that the vehicle is on the left side of the guide line. If the driving route is on the right side of the center of the feature area, it is determined that the vehicle is on the right side of the guide line. Specifically includes:

[0094] Comparing the feature area and the driving route in the multiple saved driving images. If the number of driving images in which the driving route is on the left side of the center of the feature area exceeds half of the number of saved driving images, it is determined that the vehicle is on the left side of the guide line. If the number of driving images in which the driving route is on the right side of the center of the feature area exceeds half of the number of saved driving images, it is determined that the vehicle is on the right side of the guide line.

[0095] In one embodiment, the comparing the center of the feature area with the driving route specifically includes:

[0096] Establishing a two-dimensional coordinate system for the driving image, the two-dimensional coordinate system including an X-axis extending in the left-right direction and a Y-axis extending in the upward direction;

[0097] Obtaining the center coordinate of the feature area;

[0098] Calculating the X-axis coordinate value of the point where the Y-axis coordinate value of the driving route in the two-dimensional coordinate system is consistent with the Y-axis coordinate value of the center coordinate of the feature area. If the X-axis coordinate value of this point is on the left side of the X-axis coordinate value of the center coordinate of the feature area, the driving route is on the left side of the center of the feature area. If the X-axis coordinate value of this point is on the right side of the X-axis coordinate value of the center coordinate of the feature area, the driving route is on the right side of the center of the feature area.

[0099] Step S205, obtaining navigation information, and judging whether the vehicle enters the viaduct according to the navigation information and the relative direction between the vehicle and the guide line.

[0100] Step S206: Display the corresponding navigation route according to whether the vehicle enters the elevated road.

[0101] Specifically, after the vehicle is navigated to the elevated fork, step S201 is triggered, and continuous driving images are intercepted at a preset frequency, and each image is analyzed according to the communication frequency until the navigation route is confirmed.

[0102] Assume that the vehicle speed is 80 km / h at this time, then the traveling distance per second is about 22 m. Setting the period within 0.1 s can ensure that there are multiple effective images.

[0103] After starting to intercept the driving images, steps S202 to S203 are executed to judge the effective images. Specifically: from the driving images, identify the guide lines. If the guide lines can be identified from the driving images, then the driving image is an effective image; if the guide lines cannot be identified from the driving images, then the driving image is an invalid image. When an effective image is detected, start saving the driving images. If an invalid image is detected after starting to save the driving images, stop intercepting and saving the driving images. When no effective images appear anymore, take the effective images and output the judgment, and no longer extract images until the navigation sends the next signal.

[0104] In one embodiment, preprocess the driving images. There are too many interference factors in the directly extracted images, and certain processing can be performed first to simplify them, thereby reducing resource consumption and operation time.

[0105] Figure 3 is one of the driving images. As Figure 3 shown, perform the following operations on the driving images:

[0106] Delete the roads and decorations in the driving images through color matrix feature filtering to obtain an image such as Figure 4 ;

[0107] Then only focus on the objects near (lower) the image, identify the large bright areas in the upper part and delete them according to the coordinates for filtering to obtain an image such as Figure 5 ;

[0108] For the deleted Figure 5 driving image, convert it to a Figure 6 contour map, and adopt the contour recognition method to identify the feature area containing the guide lines.

[0109] Since the guide line includes V-shaped lines or twill lines, the guide line has specific features. The existing image recognition method can be used to recognize the guide line with specific features. For the filtered image with only a few interference items, the canny algorithm can be used to extract the edge contour. Feature recognition is performed on the extracted image to recognize a rectangular area and its center. The recognized rectangular area is the feature area, and the recognized center is the center of the feature area.

[0110] Since the image is processed and simplified, the resources and operation time consumed during recognition are greatly reduced.

[0111] As Figure 7 shown, for the sake of convenience of explanation, Figure 6 is subjected to an inversion process of black and white colors to obtain Figure 7 . In actual operation and recognition, the white contour line in Figure 6 can be used for recognition, or the black contour line in Figure 7 can be used for recognition. Among them, the feature area 73 includes all the V-shaped lines or twill lines 72 of the guide line 71. And the feature area 73 is the smallest rectangle that can contain all the V-shaped lines or twill lines 72. That is, the feature area 73 contains all the V-shaped lines or twill lines 72, and among the rectangles that contain all the V-shaped lines or twill lines 72, the feature area 73 has the smallest area.

[0112] Then, step S204 is executed. As Figure 8 shown, the center 74 of the feature area is compared with the driving route 81. If the driving route is on the left side of the center of the feature area, it is determined that the vehicle is on the left side of the guide line. If the driving route is on the right side of the center of the feature area, it is determined that the vehicle is on the right side of the guide line.

[0113] Among them, the driving route is a straight line starting from the starting coordinate in the driving image and extending upward in the driving image at the traveling angle. Since the driving image is obtained from the image of the vehicle's front camera, generally, the image of the vehicle's driving recorder can be used as the driving image. And for the vehicle's front camera, such as the driving recorder, its position on the vehicle is fixed, generally on the right side of the driver. Therefore, through multiple calibrations, the starting coordinate of the driving route at the bottom of the driving image and the traveling angle can be determined. The traveling angle is the angle between the driving route and the central axis of the driving image. The central axis of the driving image is perpendicular to the bottom of the driving image.

[0114] Since the driving image comes from the vehicle's front camera, such as the driving recorder. Considering that the vehicle's front camera, especially the driving recorder, may be adjusted by the user, resulting in a deviation of the driving route determined by starting from the starting coordinate in the driving image and extending upward at the traveling angle. Therefore, the driving route can be corrected.

[0115] One way is to perform automatic centering correction during normal driving. The automatic correction of the driving route is to identify the lane lines on both sides of the vehicle in the normal straight road section. If the positions of these two lines in the image view hardly change after a certain period of time, it is considered that the vehicle is driving straight along the lane lines during this period of time, and the midline of these two lines is taken as the driving route. If the positions change significantly, the correction fails and the driving route is not adjusted.

[0116] Specifically, the automatic correction request of the driving route can be triggered at every preset time interval, or the user can click a button on the in-vehicle screen to trigger the automatic correction request of the driving route.

[0117] After starting the automatic correction of the driving route, multiple driving images are taken as correction reference images;

[0118] From the correction reference images, the lane lines on both sides are identified;

[0119] If, in multiple consecutive correction reference images, the change difference in the position of each lane line in the correction reference image is less than a preset difference threshold, then the starting coordinates of the midline of the lane lines on both sides are taken as the starting coordinates of the driving route, and the included angle between the midline of the lane lines on both sides and the central axis of the correction reference image is taken as the driving angle of the driving route.

[0120] The change difference in the position of each lane line in the correction reference image can be calculated by calculating the coordinate difference of the starting point coordinates or the ending point coordinates of each lane line in multiple correction reference images. If the coordinate differences are all less than the preset difference threshold, it is determined that the change difference in the position of the lane line in the correction reference image is less than the preset difference threshold. The coordinate difference can be the X coordinate difference, the Y coordinate difference, or the vector difference of the two-dimensional coordinates. Among them, the comparison of vectors can be performed by comparing the vector norms.

[0121] Another way is to correct the driving route according to the user's evaluation of the system's judgment result.

[0122] Specifically, after the system automatically determines whether the user has entered the elevated road, the user can evaluate the judgment result. If the vehicle has not entered the elevated road but the system shows that it has, the user can, by means of input such as clicking a button, notify the system that the vehicle has not entered the elevated road, thereby generating a correction result for the navigation route. Or if the vehicle has entered the elevated road but the system shows that it has not, the user can, by means of input such as clicking a button, notify the system that the vehicle has actually entered the elevated road, thereby generating a correction result for the navigation route. According to the correction result, the starting coordinates or the traveling angle are adjusted in the direction that meets the correction result, and the adjusted driving route is calculated in real time until the positional relationship between the driving route and the center of the feature area conforms to the correction result.

[0123] Since lane changes occur during driving. For some lane change processes or incomplete direction adjustments after lane changes, the collected images may be misjudged. For example, Figure 9 as shown, the vehicle is on the left side of the guide line 71, but the driving route 81 is on the right side of the center 74 of the feature area, then the vehicle will be judged to be on the right side of the guide line. Therefore, in some embodiments, the feature area in multiple saved driving images is compared with the driving route. If the number of driving images in which the driving route is on the left side of the center of the feature area exceeds half of the number of saved driving images, it is determined that the vehicle is on the left side of the guide line. If the number of driving images in which the driving route is on the right side of the center of the feature area exceeds half of the number of saved driving images, it is determined that the vehicle is on the right side of the guide line.

[0124] In the above manner, the misjudgment of some images will not affect the result.

[0125] For the determination of the positional relationship between the driving route and the center of the feature area, a two-dimensional coordinate system of the driving image can be established. Then, the X-axis coordinate value of the point where the Y-axis coordinate value of the driving route in the two-dimensional coordinate system is the same as the Y-axis coordinate value of the center coordinate of the feature area is calculated. If the X-axis coordinate value of this point is on the left side of the X-axis coordinate value of the center coordinate of the feature area, the driving route is on the left side of the center of the feature area. If the X-axis coordinate value of this point is on the right side of the X-axis coordinate value of the center coordinate of the feature area, the driving route is on the right side of the center of the feature area.

[0126] For example, Figure 8 as shown, the point 82 where the Y-axis coordinate value of the driving route 81 in the two-dimensional coordinate system is the same as the Y-axis coordinate value of the center coordinate of the feature area is determined. Since the point 82 is on the left side of the center 74 of the feature area, it is determined that the driving route is on the left side of the center of the feature area.

[0127] Then, step S205 obtains navigation information.

[0128] If in the navigation information, the road above the viaduct is on the left side of the guide line and the road under the viaduct is on the right side, then when it is determined that the vehicle is on the left side of the guide line, it is determined that the vehicle enters the viaduct; when it is determined that the vehicle is on the right side of the guide line, it is determined that the vehicle does not enter the viaduct.

[0129] If in the navigation information, the road above the viaduct is on the right side of the guide line and the road under the viaduct is on the left side, then when it is determined that the vehicle is on the left side of the guide line, it is determined that the vehicle does not enter the viaduct; when it is determined that the vehicle is on the right side of the guide line, it is determined that the vehicle enters the viaduct.

[0130] After that, step S206 is executed. If the vehicle enters the viaduct, the navigation route on the viaduct is displayed; if the vehicle does not enter the viaduct, the navigation route under the viaduct is displayed.

[0131] The present invention simplifies the image, reduces resource consumption and operation time. Through multiple inspections, misjudgments caused by the lane-changing process or uncompleted direction adjustment after lane-changing are avoided. By comparing the center of the feature area with the driving route, the direction of the vehicle relative to the guide line is quickly determined, the amount of calculation is reduced, and the judgment speed is increased. Finally, through user correction, the judgment accuracy is further improved.

[0132] As Figure 10 shown is the flowchart of the working process of an elevated navigation method according to the best embodiment of the present invention, including:

[0133] Step S1001: Determine whether the navigation emits a signal approaching the ramp. If so, execute step S1002; otherwise, end.

[0134] Step S1002: Continuously intercept image data for subsequent analysis.

[0135] Step S1003: Process the image, identify the contour and the feature area, and record the number N of valid images. The feature area is a rectangular area.

[0136] Step S1004: Determine the relative position of the feature area and the vehicle according to the relative position of the center of the feature area and the traveling direction, and record the total number M of images with the vehicle on the right.

[0137] Step S1005: If M / N < 0.5 and N > 5, execute step S1006; otherwise, if M / N > 0.5 and N > 5, execute step S1007; otherwise, it is a fault condition and end.

[0138] Step S1006: Determine that the vehicle is on the left, output a route selection signal to the navigation, and the navigation selects the corresponding route, and end.

[0139] Step S1007: Determine that the vehicle is on the right, output a route selection signal to the navigation, and the navigation selects the corresponding route, and end.

[0140] Example Six

[0141] As Figure 11 shown in the schematic diagram of the hardware structure of an electronic device according to the present invention, it includes:

[0142] At least one processor 1101; and,

[0143] A memory 1102 communicatively connected to at least one of the processors 1101; wherein,

[0144] The memory 1102 stores instructions executable by at least one of the processors, and the instructions are executed by at least one of the processors so that at least one of the processors can execute the elevated navigation method as described above.

[0145] Figure 11 Taking one processor 1101 as an example.

[0146] The electronic device may further include: an input device 1103 and a display device 1104.

[0147] The processor 1101, the memory 1102, the input device 1103, and the display device 1104 may be connected by a bus or other means. In the figure, it is taken as an example of being connected by a bus.

[0148] The memory 1102, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to the elevated navigation method in the embodiments of the present application. For example, Figure 1 , Figure 2 The method flow shown. The processor 1101 executes various functional applications and data processing by running the non-volatile software programs, instructions, and modules stored in the memory 1102, that is, implements the elevated navigation method in the above embodiments.

[0149] The memory 1102 may include a program storage area and a data storage area. Among them, the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created according to the use of the elevated navigation method, etc. In addition, the memory 1102 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some embodiments, the memory 1102 may optionally include a memory remotely provided with respect to the processor 1101, and these remote memories may be connected to the device executing the elevated navigation method through a network. Examples of the above network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0150] The input device 1103 can receive the input user clicks and generate signal inputs related to the user settings and function control of the elevated navigation method. The display device 1104 can include display devices such as a display screen.

[0151] When the one or more modules are stored in the memory 1102 and run by the one or more processors 1101, they execute the elevated navigation method in any of the above method embodiments.

[0152] By identifying the guide line, determining the characteristic area, and judging the position of the vehicle driving route relative to the characteristic area of the guide line, and through the comprehensive processing of the vehicle route selection and navigation data, the present invention can accurately judge whether the vehicle is on the elevated road or on the ground and switch the route in time. The identification scheme of the present invention is simple and has low hardware dependence. Only by adding vehicle-side parameters to the navigation software can accurate navigation be performed in various urban elevated road scenarios.

[0153] An embodiment of the present invention provides a storage medium that stores computer instructions, which are used to execute all steps of the elevated navigation method as described above when the computer executes the computer instructions.

[0154] The above embodiments only represent several implementation manners of the present invention. The description is relatively specific and detailed, but it cannot be understood as a limitation to the scope of the patent of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention should be subject to the appended claims.

Claims

1. An elevated navigation method, characterized in that, Including: In response to navigating to a distance within a preset distance threshold from an elevated turnout, capturing one or more driving images, and identifying a feature region containing a guide line from the driving images; Comparing the feature region with the driving route, and judging whether the vehicle enters the elevated area according to the comparison result, where the driving route is the estimated trajectory that will appear in the driving image when the vehicle travels in the direction at the time of capturing the driving image; Displaying a corresponding navigation route according to whether the vehicle enters the elevated area; The driving route is a straight line starting from a preset starting coordinate at the bottom of the driving image and extending upward in the traveling angle above the driving image, where the traveling angle is the included angle between the driving route and the central axis of the driving image; The method further includes: In response to a driving route automatic correction request, obtaining multiple driving images as correction reference images within a preset time period; Identifying the lane lines on both sides from the correction reference images; If, in multiple consecutive correction reference images, the change difference in the position of each lane line on each side in the correction reference image is less than a preset difference threshold, then using the starting coordinate of the midline of the lane lines on both sides as the starting coordinate of the driving route, and using the included angle between the midline of the lane lines on both sides and the central axis of the correction reference image as the traveling angle of the driving route.

2. The elevated navigation method according to claim 1, characterized in that: The feature region is the smallest rectangle in the driving image that contains all the V-shaped lines or diagonal lines of the guide line. The comparing the feature region with the driving route and judging whether the vehicle enters the elevated area according to the comparison result specifically includes: Comparing the center of the feature region with the driving route. If the driving route is on the left side of the center of the feature region, it is judged that the vehicle is on the left side of the guide line. If the driving route is on the right side of the center of the feature region, it is judged that the vehicle is on the right side of the guide line; Obtaining navigation information, and judging whether the vehicle enters the elevated area according to the navigation information and the relative direction of the vehicle to the guide line.

3. The elevated navigation method according to claim 2, characterized in that: If multiple driving images are saved, the comparing the center of the feature region with the driving route. If the driving route is on the left side of the center of the feature region, it is judged that the vehicle is on the left side of the guide line. If the driving route is on the right side of the center of the feature region, it is judged that the vehicle is on the right side of the guide line specifically includes: Comparing the feature regions in the multiple saved driving images with the driving route. If the number of driving images in which the driving route is on the left side of the center of the feature region exceeds half of the number of saved driving images, it is judged that the vehicle is on the left side of the guide line. If the number of driving images in which the driving route is on the right side of the center of the feature region exceeds half of the number of saved driving images, it is judged that the vehicle is on the right side of the guide line.

4. The elevated navigation method according to claim 2, characterized in that: The comparing the center of the feature region with the driving route specifically includes: Establishing a two-dimensional coordinate system for the driving image, where the two-dimensional coordinate system includes an X-axis extending in the left-right direction and a Y-axis extending in the upward direction; Obtaining the center coordinates of the feature region; Calculate the X-axis coordinate value of the point where the Y-axis coordinate value of the driving route in the two-dimensional coordinate system is the same as the Y-axis coordinate value of the center coordinate of the feature area. If the X-axis coordinate value of this point is on the left side of the X-axis coordinate value of the center coordinate of the feature area, the driving route is on the left side of the center of the feature area. If the X-axis coordinate value of this point is on the right side of the X-axis coordinate value of the center coordinate of the feature area, the driving route is on the right side of the center of the feature area.

5. The elevated navigation method according to claim 1, characterized in that: In response to navigating to a distance within a preset distance threshold from the elevated fork, intercept one or more driving images, and identify a feature area containing a guide line from the driving images, specifically including: In response to navigating to a distance within a preset distance threshold from the elevated fork, start continuously intercepting driving images at a preset frequency; From the driving images, identify a feature area containing a guide line. If a feature area can be identified from the driving images, then this driving image is a valid image. If a feature area cannot be identified from the driving images, then this driving image is an invalid image; When a valid image is detected, start saving the driving images. If an invalid image is detected after starting to save the driving images, stop intercepting and saving the driving images.

6. The elevated navigation method according to claim 1, characterized in that: The identifying a feature area containing a guide line from the driving images specifically includes: Filter and delete roads and decorations in the driving images through color matrix features; Identify and delete the bright colors in the upper part of the driving images; For the driving images after deletion, use the contour recognition method to identify the feature area containing the guide line.

7. The elevated navigation method according to claim 1, characterized in that: It also includes: Obtain the correction result of the user for the navigation route, and according to the correction result, correct the starting coordinate or the traveling angle.

8. The elevated navigation method according to claim 7, characterized in that: The obtaining the correction result of the user for the navigation route and correcting the starting coordinate or the traveling angle according to the correction result specifically includes: Obtain the correction result of the user for the navigation route, and according to the correction result, adjust the starting coordinate or the traveling angle until the positional relationship between the driving route and the center of the feature area conforms to the correction result.

9. An electronic device, characterized in that, It includes: At least one processor; And, A memory communicatively connected to at least one of the processors; wherein, The memory stores instructions executable by at least one of the processors, and the instructions are executed by at least one of the processors so that at least one of the processors can execute the elevated navigation method according to any one of claims 1 to 8.

10. A storage medium, characterized in that, The storage medium stores computer instructions, and when the computer executes the computer instructions, it is used to execute all the steps of the elevated navigation method according to any one of claims 1 to 8.

Images