Holographic tunnel automatic calibration method and device, electronic equipment and computer readable medium

Abstract

The application discloses a kind of holographic tunnel automatic calibration method and device, electronic equipment and computer readable medium, belong to the technical field of tunnel calibration, method includes: based on the tunnel parameter information of physical tunnel constructs tunnel building information model map, and determines the virtual coordinates of section camera in tunnel building information model map;In the case where it is determined that there is vehicle in tunnel section frame image information, the pixel coordinates of vehicle are obtained;Lane line geometric feature is marked in tunnel section frame image information, and the pixel coordinates and plane world coordinates of at least three feature points are determined from lane line geometric feature;The pixel coordinates of vehicle, the pixel coordinates and plane world coordinates of at least three feature points are determined based on vehicle;Based on the pixel coordinates of vehicle, the virtual coordinates of vehicle in tunnel building information model map are determined based on the pixel coordinates of vehicle and tunnel building information model map.The virtual coordinates of vehicle are adjusted, and the calibration of holographic tunnel is completed.The application improves calibration efficiency.

Description

Technical Field

[0001] This invention belongs to the technical field of tunnel calibration, and specifically relates to an automatic calibration method and device for holographic tunnels, electronic equipment, and computer-readable medium. Background Technology

[0002] A holographic tunnel is a control system that integrates real-time tunnel cross-section frame image information captured by cross-section cameras and is built on the basis of the tunnel parameter information of the physical tunnel. It realizes the synchronous presentation of the structure of the physical tunnel and the vehicles passing through the physical tunnel.

[0003] However, the inventors of this application discovered that, in order to achieve digital presentation and management of the actual conditions inside the tunnel, traditional holographic tunnels require manual registration by measuring each monitoring section of the cross-section camera using a total station or laser scanner and then manually aligning it with the tunnel's architectural information model map. This registration method is cumbersome, complex, and inefficient. Furthermore, the digital presentation process using this calibration method can only display the calibrated image, resulting in poor real-time performance and accuracy.

[0004] The content of the background section is merely the technology known to the inventor and does not necessarily represent the prior art in this field. Summary of the Invention

[0005] The present invention aims to provide an automatic calibration method and apparatus for holographic tunnels, an electronic device and a computer-readable medium to solve at least one of the above-mentioned technical problems.

[0006] According to one aspect of this application, an automatic calibration method for a holographic tunnel is provided. The holographic tunnel is calibrated with a physical tunnel. The holographic tunnel is generated based on a tunnel architectural information model (TAM) map, and the physical tunnel is equipped with a cross-sectional camera. The cross-sectional camera is used to acquire tunnel cross-sectional frame image information. The automatic calibration method includes: constructing a TAM map based on the tunnel parameter information of the detected physical tunnel, and determining the virtual coordinates of the cross-sectional camera in the TAM map; when a vehicle is found in the tunnel cross-sectional frame image information, acquiring the pixel coordinates of the vehicle; marking lane line geometric features in the tunnel cross-sectional frame image information, and determining the pixel coordinates and planar world coordinates of at least three feature points from the lane line geometric features; determining the planar world coordinates of the vehicle based on the vehicle's pixel coordinates, the pixel coordinates of at least three feature points, and the planar world coordinates; and determining the virtual coordinates of the vehicle in the TAM map based on the vehicle's planar world coordinates and the TAM map. The holographic tunnel is automatically calibrated when the virtual coordinates of the vehicle in the tunnel building information model map and the vehicle in the tunnel building information model map are adjusted based on the preset overlay offset range. The coordinate deviation between the adjusted virtual coordinates of the vehicle and the vehicle's planar world coordinates meets the preset coordinate deviation range.

[0007] According to some embodiments of this application, the automatic calibration method further includes: constructing a digital twin image corresponding to the physical tunnel based on the tunnel building information model map and the virtual coordinates of the vehicle; calculating the coordinate deviation value between the vehicle's current planar world coordinates and the vehicle's virtual coordinates in the current frame of the digital twin image; and rendering and adjusting the vehicle's position in the digital twin image in real time to compensate for the coordinate deviation value.

[0008] According to some embodiments of this application, real-time rendering and adjustment of the vehicle's position in a digital twin image to compensate for coordinate deviation values ​​includes: obtaining a step size value between the current frame of the digital twin image and the next frame of the digital twin image; determining a forward step size adjustment value between the current frame of the digital twin image and the next frame of the digital twin image based on the coordinate deviation value; and adjusting the step size value based on the forward step size adjustment value to adjust the vehicle's position in the digital twin image to compensate for the coordinate deviation value.

[0009] According to some embodiments of this application, marking lane line geometric features in tunnel cross-section frame image information and determining the pixel coordinates and planar world coordinates of at least three feature points from the lane line geometric features includes: performing edge detection and feature extraction on the tunnel cross-section frame image information to mark lane geometric features and select at least three feature points; obtaining the pixel coordinates of at least three feature points through a cross-section camera; and compensating for coordinate deviation values ​​based on the virtual coordinates of the cross-section camera and the positions of at least three feature points relative to the cross-section camera.

[0010] According to some embodiments of this application, determining the planar world coordinates of a vehicle based on the vehicle's pixel coordinates, the pixel coordinates of at least three feature points, and the planar world coordinates includes: determining a homography matrix based on the pixel coordinates of at least three feature points and the planar world coordinates; and determining the vehicle's planar world coordinates based on the vehicle's pixel coordinates and the homography matrix.

[0011] According to some embodiments of this application, determining the virtual coordinates of a vehicle in a tunnel building information model map based on the vehicle's planar world coordinates and the tunnel building information model map includes: extracting coordinate system parameters of the tunnel building information model map; mapping the vehicle's planar world coordinates to the coordinate system of the tunnel building information model map to calibrate the initial virtual coordinates of the vehicle in the tunnel building information model map; and correcting the initial virtual coordinates based on the physical constraints of the tunnel building information model map on the vehicle's virtual coordinates to determine the vehicle's virtual coordinates.

[0012] According to another aspect of this application, an automatic calibration device for a holographic tunnel is also provided. The holographic tunnel is calibrated against a physical tunnel. The holographic tunnel is generated based on a tunnel architectural information model (TAM) map, and the physical tunnel is equipped with a cross-sectional camera used to acquire tunnel cross-sectional frame image information. The automatic calibration device includes a map construction module, a data acquisition module, and a data processing module. The map construction module is used to construct a TAM map based on the detected tunnel parameter information of the physical tunnel and determine the virtual coordinates of the cross-sectional camera in the TAM map. The data acquisition module is used to acquire the pixel coordinates of a vehicle when it is determined that a vehicle exists in the tunnel cross-sectional frame image information. The data processing module is used to calibrate the virtual coordinates of the cross-section camera in the tunnel architectural information model map, and to mark the lane line geometric features in the tunnel cross-section frame image information. It also determines the pixel coordinates and planar world coordinates of at least three feature points from these lane line geometric features. Furthermore, the data processing module is used to determine the vehicle's planar world coordinates based on the vehicle's pixel coordinates, the pixel coordinates of at least three feature points, and the planar world coordinates. Finally, it determines the vehicle's virtual coordinates in the tunnel architectural information model map based on the vehicle's planar world coordinates and the tunnel architectural information model map. The tunnel architectural information model map and the vehicle's virtual coordinates in the tunnel architectural information model map are adjusted based on a preset overlay offset range. Automatic calibration of the holographic tunnel is completed when the coordinate deviation between the adjusted virtual coordinates and the vehicle's planar world coordinates meets the preset coordinate deviation range.

[0013] According to another aspect of this application, an electronic device is also provided. The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the automatic calibration method described above.

[0014] According to another aspect of this application, a computer-readable medium having processor-executable non-volatile program code is also provided. The program code causes the processor to perform the automatic calibration method described above.

[0015] According to another aspect of this application, a computer program product is also provided. The computer program product includes a computer program stored on a computer-readable storage medium, the computer program including program instructions that, when executed by a computer, cause the computer to perform the automatic calibration method described above.

[0016] The beneficial effects of the technical solution provided by the embodiments of the present invention are as follows: This application constructs a tunnel architectural information model map using tunnel parameter information, achieving a 1:1 match between the tunnel architectural information model map and the physical tunnel. When a vehicle is identified in the tunnel cross-section frame image, its pixel coordinates are obtained. Using the dynamic vehicle as the calibration carrier, the virtual coordinates of the tunnel architectural information model map and the vehicle within the tunnel architectural information model map are adjusted according to a preset overlay offset range. Automatic calibration of the holographic tunnel is completed when the coordinate deviation between the adjusted virtual coordinates and the vehicle's planar world coordinates meets a preset deviation range. This achieves automatic calibration without interrupting traffic and improves calibration accuracy. Based on the vehicle's pixel coordinates, feature point pixel annotations, and planar world coordinates, the vehicle's planar world coordinates are determined, realizing a direct association between the image and physical space. This avoids reliance on total stations or laser scanners and improves calibration efficiency. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, 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 this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart illustrating an automatic calibration method for holographic tunnels according to an embodiment of this application is shown. Figure 2 This illustration shows another flowchart of the automatic calibration method for holographic tunnels according to an embodiment of this application; Figure 3 This paper illustrates a flowchart of step S900 of the automatic calibration method for holographic tunnels according to an embodiment of this application. Figure 4 A flowchart illustrating step S300 of the automatic calibration method for a holographic tunnel according to an embodiment of this application is shown. Figure 5 A schematic diagram of three feature points in an embodiment of this application is shown; Figure 6 A flowchart illustrating step S400 of the automatic calibration method for a holographic tunnel according to an embodiment of this application is shown. Figure 7 A flowchart illustrating step S500 of the automatic calibration method for a holographic tunnel according to an embodiment of this application is shown. Figure 8 A schematic diagram of the structure of the automatic calibration device for the holographic tunnel according to an embodiment of this application is shown.

[0019] Explanation of reference numerals in the attached figures: Automatic calibration device 1; map building module 11; data acquisition module 12; data processing module 13. Detailed Implementation

[0020] The present invention will now be described in detail with reference to the accompanying drawings and embodiments. Various examples are provided by way of explanation and not by way of limitation. Indeed, those skilled in the art will recognize that modifications and variations can be made to the invention without departing from its scope or spirit. For example, a feature shown or described as part of one embodiment may be used in another embodiment to produce yet another embodiment. Therefore, it is desirable that the invention encompass such modifications and variations falling within the scope of the appended claims and their equivalents.

[0021] In the description of this invention, the terms "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," and "bottom," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and do not require the invention to be constructed and operated in a specific orientation; therefore, they should not be construed as limitations on the invention. The terms "connected," "linked," and "set up" used in this invention should be interpreted broadly. For example, they can refer to a fixed connection or a detachable connection; a direct connection or an indirect connection through intermediate components; a wired connection, a radio connection, or a wireless communication signal connection. Those skilled in the art can understand the specific meaning of the above terms according to the specific circumstances.

[0022] The accompanying drawings illustrate one or more examples of the invention. The detailed description uses numerals and letters to refer to features in the drawings. Similar or analogous reference numerals in the drawings and description have been used to refer to similar or analogous parts of the invention. As used herein, the terms “first,” “second,” “third,” and “fourth,” etc., are used interchangeably to distinguish one component from another and are not intended to indicate the location or importance of a single component.

[0023] The technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some, not all, of the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0024] A holographic tunnel is a 1:1 digital twin scene control system that integrates real-time tunnel cross-section frame image information captured by cross-section cameras and is built based on the tunnel parameter information of the physical tunnel. It achieves a synchronized virtual-real presentation of the physical tunnel's structure and the status of vehicles passing through it. A cross-section refers to the monitoring area corresponding to the installation location of the cross-section camera within the physical tunnel. There are multiple cross-sections within the physical tunnel, and multiple cross-section cameras are installed inside the physical tunnel. Vehicles traveling through the physical tunnel are captured by the corresponding cross-section camera when they pass through each cross-section. The calibration of the holographic tunnel with the physical tunnel involves each cross-section within the physical tunnel. For example, the holographic tunnel is calibrated with the physical tunnel, and the holographic tunnel is generated based on a tunnel architectural information model map.

[0025] According to one aspect of this application, an automatic calibration method for holographic tunnels is provided. Figure 1 A flowchart illustrating an automatic calibration method for holographic tunnels according to an embodiment of this application is shown. According to an example embodiment, such as... Figure 1 As shown, the automatic calibration method includes steps S100-S600. Exemplarily, this automatic calibration method is performed by an automatic calibration device. For example, the automatic calibration device is an execution subject device that performs the automatic calibration method of this application.

[0026] In step S100, a tunnel building information model map is constructed based on the tunnel parameter information of the detected physical tunnel, and the virtual coordinates of the cross-section camera in the tunnel building information model map are determined.

[0027] For example, a tunnel building information model map is a tunnel BIM (Building Information Model) map. The tunnel building information model map contains tunnel BIM data. For example, a physical tunnel is a real-world, physically existing tunnel structure; it is the physical prototype of a holographic tunnel and the actual object of calibration work. A physical tunnel is the real spatial carrier for vehicle traffic and the deployment of cross-sectional cameras, encompassing the complete physical structure from the tunnel entrance to the tunnel exit, including the main tunnel structure and internal lanes. For example, tunnel parameter information includes the tunnel's length, width, and the latitude and longitude coordinates of the tunnel entrance.

[0028] For example, the length S and width M of the physical tunnel are not limited. The coordinate system of the tunnel building information model map has the tunnel entrance as the origin. The direction along the length S is the X-axis, and the direction along the width M is the Y-axis. For example, the virtual coordinates of the cross-section camera in the tunnel building information model map are determined based on the distance between the cross-section camera and the tunnel entrance. The virtual coordinates of the cross-section camera can be calculated based on the distance between the cross-section camera and the tunnel entrance and the latitude and longitude coordinates of the tunnel entrance. For example, the automatic calibration device constructs the tunnel building information model map segment by segment based on the tunnel parameter information of the physical tunnel and starting from the latitude and longitude coordinates of the tunnel entrance.

[0029] In step S200, if it is determined that a vehicle exists in the tunnel cross-section frame image information, the pixel coordinates of the vehicle are obtained.

[0030] For example, the feature information of vehicles in the tunnel cross-section frame image information can be extracted by using a cross-section camera, and the extracted vehicle feature information can be bounded and the vehicle pixel coordinates can be calculated to obtain the vehicle pixel coordinates.

[0031] In step S300, lane line geometric features are marked in the tunnel cross-section frame image information, and the pixel coordinates and planar world coordinates of at least three feature points are determined from the lane line geometric features.

[0032] For example, planar world coordinates are a coordinate system for the actual position of a labeled object on a two-dimensional plane, representing the surface of a physical tunnel. Planar world coordinates are a real, measurable coordinate system based on the extension directions of the X and Y axes of the physical tunnel. Feature points are fixed structures of the physical tunnel, such as lane line inflections, lane-side markers, or reflective road markings. An automatic calibration device can directly acquire the pixel coordinates of at least three feature points using a cross-sectional camera. The automatic calibration device can calculate the planar world coordinates of these at least three feature points based on their distances from the cross-sectional camera.

[0033] In step S400, the vehicle's planar world coordinates are determined based on the vehicle's pixel coordinates, the pixel coordinates of at least three feature points, and the planar world coordinates.

[0034] For example, the relationship between planar world coordinates and pixel coordinates is shown in formula (1).

[0035] , formula (1).

[0036] Where λ is a non-zero scale factor, H is the homography matrix, (x, y, 1) are the world coordinates in the plane, and (u, v, 1) are the pixel coordinates. For example, the automatic calibration device can calculate the result by substituting the pixel coordinates and world coordinates of at least three feature points into formula (1). The numerical values ​​and homography matrix H. The automatic calibration device can substitute the pixel coordinates of the vehicle into formula (1) to calculate the vehicle's planar world coordinates.

[0037] In step S500, the virtual coordinates of the vehicle in the tunnel building information model map are determined based on the vehicle's planar world coordinates and the tunnel building information model map.

[0038] For example, the automatic calibration device maps the vehicle's planar world coordinates to the coordinate system of the tunnel building information model map to obtain the vehicle's initial virtual coordinates in the tunnel building information model map, and corrects the initial virtual coordinates based on the physical constraints of the tunnel building information model map on the vehicle's virtual coordinates to obtain the vehicle's virtual coordinates.

[0039] For example, the physical constraints on the virtual coordinates of vehicles in the tunnel building information model map are based on the actual structure, functional layout, and traffic rules of the physical tunnel. The map defines the permissible spatial boundaries for the virtual coordinates of vehicles, used to correct deviations in the initial virtual coordinates. This prevents situations where the virtual coordinates of vehicles do not conform to physical logic.

[0040] In step S600, the tunnel architectural information model map and the vehicle's virtual coordinates in the tunnel architectural information model map are adjusted based on a preset overlay offset range. The automatic calibration of the holographic tunnel is completed when it is determined that the coordinate deviation between the adjusted virtual coordinates of the vehicle and the vehicle's planar world coordinates meets the preset coordinate deviation range.

[0041] For example, the preset overlay offset range is a rectangular area of ​​the spatial boundary of the holographic tunnel, preset by the user based on the position and coverage of preset reference objects within the physical tunnel, used to define the spatial range of the holographic tunnel. Exemplarily, the preset overlay offset range corresponds to preset reference objects. Exemplarily, preset reference objects include signs on both sides of the road within the physical tunnel. The preset overlay offset range is R(x1, y1, x2, y2). Where x1 and x2 represent the range of the preset overlay offset range in the X-axis direction, and y1 and y2 represent the range of the preset overlay offset range in the Y-axis direction. Exemplarily, the preset overlay offset range is a rectangular area to fit the shape of the road in the physical tunnel. The automatic calibration device adjusts the tunnel architectural information model map and the virtual coordinates of the vehicle in the tunnel architectural information model map segment by segment using the preset overlay offset range as the physical constraint boundary.

[0042] For example, the automatic calibration device calculates the coordinate deviation between the vehicle's virtual coordinates and its planar world coordinates, denoted as k. The automatic calibration device determines whether k falls within a preset coordinate deviation range; for example, the preset coordinate deviation range is -10 to 10m. For example, if the automatic calibration device determines that k is not within the preset coordinate deviation range, it performs the following operation: If K > 10m, meaning the vehicle's virtual coordinates are ahead of its planar world coordinates, following the principle of positive values ​​leading backward, the automatic calibration device will shift the preset overlay offset range of the corresponding section of the tunnel construction information model map by a preset distance in the negative X-axis direction, while simultaneously correcting the vehicle's virtual coordinates. For example, the preset distance is 0.5-1m.

[0043] If K < -10m, meaning the vehicle's virtual coordinates lag behind its planar world coordinates, the automatic calibration device will shift the preset overlay offset range of the corresponding section of the tunnel construction information model map by a preset distance in the positive X-axis direction, according to the principle of negative values ​​moving forward, and synchronously correct the vehicle's virtual coordinates.

[0044] The automatic calibration device repeatedly determines whether k falls within the preset coordinate deviation range, and adjusts the preset overlay offset range of the corresponding section of the tunnel building information model map and corrects the virtual coordinates of the vehicle based on the determination results. Finally, when it is determined that K is within the range of -10 to -10m, the automatic calibration of the holographic tunnel is completed.

[0045] Through the above embodiments, this application constructs a tunnel architectural information model map using tunnel parameter information, achieving a 1:1 match between the tunnel architectural information model map and the physical tunnel. When a vehicle is identified in the tunnel cross-section frame image information, its pixel coordinates are obtained. Using the dynamic vehicle as a calibration carrier, the virtual coordinates of the tunnel architectural information model map and the vehicle within the tunnel architectural information model map are adjusted according to a preset overlay offset range. Automatic calibration of the holographic tunnel is completed when the coordinate deviation between the adjusted virtual coordinates and the vehicle's planar world coordinates meets a preset coordinate deviation range. This achieves automatic calibration without interrupting traffic and improves calibration accuracy. By determining the vehicle's planar world coordinates based on its pixel coordinates, feature point pixel annotations, and planar world coordinates, a direct association between the image and physical space is achieved, avoiding reliance on total stations or laser scanners and improving calibration efficiency.

[0046] Figure 2 This illustration shows another flowchart of the automatic calibration method for holographic tunnels according to an embodiment of this application. According to the example embodiment, as... Figure 2 As shown, the automatic calibration method also includes steps S700-S900. In step S700, a digital twin image corresponding to the physical tunnel is constructed based on the tunnel construction information model map and the virtual coordinates of the vehicles.

[0047] For example, an automatic calibration device integrates the coordinate system parameters of the tunnel construction information model map with the vehicle's virtual coordinates to form a digital twin image corresponding to the physical tunnel. Exemplarily, the digital twin image is a digital and visual representation of the physical tunnel and a fundamental component of a holographic tunnel.

[0048] In step S800, the coordinate deviation value between the vehicle's current planar world coordinates and the vehicle's virtual coordinates in the current frame digital twin image is calculated.

[0049] In step S900, the position of the vehicle in the digital twin image is adjusted in real time to compensate for the coordinate deviation value.

[0050] For example, the automatic calibration device adjusts the rendering speed of the digital twin image based on the coordinate deviation value, thereby adjusting the vehicle's speed in the holographic tunnel to compensate for the coordinate deviation value. Specifically, to balance the weight of the current coordinate deviation value with the historical vehicle position adjustment value in the digital twin image and avoid rendering jitter caused by large adjustments in vehicle position, the automatic calibration device introduces a smoothing coefficient. For example, the smoothing coefficient ranges from 0 to 1. To avoid over-compensation or under-compensation, the automatic calibration device introduces a compensation coefficient, which is used to calibrate the strength of position compensation. For example, the compensation coefficient ranges from 0 to 1. For example, the automatic calibration device first calculates the vehicle position adjustment value by combining the smoothing coefficient with the current coordinate deviation value and the historical vehicle position adjustment value, and then calibrates the vehicle position adjustment value using the compensation coefficient to ultimately complete the compensation for the coordinate deviation value.

[0051] Through the above embodiments, this application calculates the coordinate deviation between the vehicle's current planar world coordinates and the vehicle's virtual coordinates in the constructed current frame digital twin image, and renders and adjusts the vehicle's position in the digital twin image to compensate for the coordinate deviation, thereby achieving real-time synchronization between the vehicle's position in the digital twin image and the vehicle's position in the physical tunnel.

[0052] Figure 3 A schematic flowchart of step S900 of the automatic calibration method for holographic tunnels according to an embodiment of this application is shown. According to an example embodiment, as... Figure 3 As shown, step S900 of the automatic calibration method includes steps S910-S930.

[0053] In step S910, the step size between the current frame of the digital twin and the next frame of the digital twin is obtained. For example, the automatic calibration device can detect the vehicle's current instantaneous speed in the physical tunnel and the vehicle's average speed in the current cross-section of the camera. Exemplarily, when the rendered vehicle position lags behind the vehicle's actual position, the maximum value between the vehicle's current instantaneous speed in the physical tunnel and the vehicle's average speed in the current cross-section of the camera is selected as the vehicle's reference speed. When the rendered vehicle position leads the vehicle's actual position, the minimum value between the vehicle's current instantaneous speed in the physical tunnel and the vehicle's average speed in the current cross-section of the camera is selected as the vehicle's reference speed. Exemplarily, the step size between the current frame of the digital twin and the next frame of the digital twin is the product of the vehicle's reference speed and the time interval between adjacent frames of the digital twin, i.e., step size = vehicle's reference speed * time interval between adjacent frames.

[0054] In step S920, the forward step length adjustment value between the current frame digital twin image and the next frame digital twin image is determined based on the coordinate deviation value.

[0055] For example, the forward stride adjustment value is the vehicle position adjustment value. The automatic calibration device can calculate the forward stride adjustment value that the vehicle needs to compensate for based on the coordinate deviation value. The automatic calibration device first calculates the compensated position difference between the current frame of the digital twin and the next frame of the digital twin. For example, the compensated position difference = coordinate deviation value * smoothing coefficient + (1 - smoothing coefficient) * the compensated position difference of the previous frame. The automatic calibration device then determines the forward stride adjustment value based on the compensated position difference and the compensation coefficient. For example, the forward stride adjustment value = compensated position difference * compensation coefficient.

[0056] In step S930, the step size value is adjusted based on the forward step size adjustment value to adjust the position of the vehicle in the digital twin image to compensate for the coordinate deviation value.

[0057] For example, the automatic calibration device adjusts the step size value by adjusting the forward step size adjustment value, thereby changing the rendering process of the digital twin image corresponding to the vehicle to compensate for coordinate deviation values. For example, the adjusted step size value = the original step size value + the forward step size adjustment value.

[0058] Through the above embodiments, this application adjusts the step size between the current frame of the digital twin and the next frame of the digital twin by adjusting the coordinate deviation value, thereby realizing the real-time synchronization of the vehicle position in the digital twin and the vehicle position in the physical tunnel. By introducing a smoothing coefficient and a compensation coefficient, the smoothness and accuracy of the vehicle position adjustment are further optimized. The smoothing coefficient avoids the vehicle rendering jitter problem caused by sudden changes in coordinate deviation, and improves the visual coherence of the digital twin.

[0059] Figure 4 A schematic flowchart of step S300 of the automatic calibration method for holographic tunnels according to an embodiment of this application is shown. According to an example embodiment, as... Figure 4 As shown, step S300 of the automatic calibration method includes steps S310-S330.

[0060] In step S310, edge detection and feature extraction are performed on the tunnel cross-section frame image information to mark the lane geometric features and select at least three feature points. Figure 5 A schematic diagram of three feature points according to an embodiment of this application is shown. For example, the at least three feature points are fixed structures of a physical tunnel, such as lane line inflection points, lane line side markers, or road surface reflective markings. Exemplarily, the three feature points are labeled A1, A2, and A3.

[0061] In step S320, the pixel coordinates of at least three feature points are acquired using a cross-sectional camera.

[0062] In step S330, the planar world coordinates of at least three feature points are determined based on the virtual coordinates of the cross-sectional camera and the positional relationship between at least three feature points and the cross-sectional camera. For example, the automatic calibration device directly acquires the pixel coordinates of the at least three feature points through the cross-sectional camera. The automatic calibration device calculates the planar world coordinates of the at least three feature points based on their distances from the cross-sectional camera.

[0063] Through the above embodiments, this application performs edge detection and feature extraction on tunnel cross-section frame image information to mark lane geometric features and select at least three feature points. Then, based on the virtual coordinates of the cross-section camera and the positional relationship between the at least three feature points and the cross-section camera, the planar world coordinates of at least three feature points are determined, which reduces the number and complexity of feature point acquisition and simplifies the calibration steps.

[0064] Figure 6 A schematic flowchart of step S400 of the automatic calibration method for holographic tunnels according to an embodiment of this application is shown. According to an example embodiment, as... Figure 6 As shown, step S400 of the automatic calibration method includes steps S410-S420.

[0065] In step S410, the homography matrix is ​​determined based on the pixel coordinates and world coordinates of at least three feature points. For example, the automatic calibration device can calculate the homography matrix by substituting the pixel coordinates and world coordinates of at least three feature points into formula (1). The numerical values ​​and the homography matrix H.

[0066] In step S420, the vehicle's planar world coordinates are determined based on the vehicle's pixel coordinates and homography matrix. For example, the automatic calibration device can substitute the vehicle's pixel coordinates into formula (1) to calculate the vehicle's planar world coordinates.

[0067] Through the above embodiments, this application calculates the vehicle's planar world coordinates by using the formula relationship between planar world coordinates and pixel coordinates and the pixel coordinates and planar world coordinates of at least three feature points, thereby improving the accuracy of vehicle coordinate transformation. The entire process is automated, thereby improving the efficiency of coordinate transformation.

[0068] Figure 7 A schematic flowchart of step S500 of the automatic calibration method for holographic tunnels according to an embodiment of this application is shown. According to an example embodiment, as... Figure 7 As shown, step S500 of the automatic calibration method includes steps S510-S530.

[0069] In step S510, the coordinate system parameters of the tunnel building information model map are extracted. For example, the coordinate system parameters of the tunnel building information model map are the coordinate data parameter set of the two-dimensional plane coordinate system of the tunnel building information model map.

[0070] In step S520, the vehicle's planar world coordinates are mapped to the coordinate system of the tunnel building information model map to calibrate the vehicle's initial virtual coordinates in the tunnel building information model map. For example, the vehicle's planar world coordinates are coordinates in the physical tunnel's planar world coordinate system, and the origin of both the vehicle's planar world coordinates and the tunnel building information model map's coordinate system is the tunnel entrance. The X-axis and Y-axis of the vehicle's planar world coordinates and the tunnel building information model map's coordinate system extend in the same direction. The automatic calibration device maps and calibrates the vehicle's initial virtual coordinates in the tunnel building information model map according to the correspondence between the physical tunnel's planar world coordinate system and the tunnel building information model map's coordinate system along the X-axis and Y-axis.

[0071] In step S530, the initial virtual coordinates are corrected based on the physical constraints of the vehicle's virtual coordinates on the tunnel building information model map to determine the vehicle's virtual coordinates. For example, the physical constraints of the vehicle's virtual coordinates on the tunnel building information model map are the allowed spatial boundaries defined for the vehicle's virtual coordinates in the tunnel building information model map based on the actual structure, functional layout, and traffic rules of the physical tunnel.

[0072] According to another aspect of this application, an automatic calibration device for a holographic tunnel is also provided. Figure 8 A schematic diagram of the structure of an automatic calibration device for a holographic tunnel according to an embodiment of this application is shown. According to an example embodiment, such as... Figure 8 As shown, the automatic calibration device 1 includes a map building module 11, a data acquisition module 12, and a data processing module 13.

[0073] The map building module 11 is used to build a tunnel building information model map based on the tunnel parameter information of the detected physical tunnel, and to determine the virtual coordinates of the cross-section camera in the tunnel building information model map.

[0074] For example, a tunnel building information model map is a tunnel BIM (Building Information Model) map. The tunnel building information model map contains BIM data. For example, a physical tunnel is a real-world tunnel structure that exists as a physical entity; it is the physical prototype of a holographic tunnel and the actual object of calibration work. A physical tunnel is the real spatial carrier for vehicle traffic and the deployment of cross-sectional cameras, encompassing the complete physical structure from the tunnel entrance to the tunnel exit, including the main tunnel structure and internal driveways. For example, tunnel parameter information includes the tunnel's length, width, and the latitude and longitude coordinates of the tunnel entrance.

[0075] For example, the length S and width M of the physical tunnel are not limited. The coordinate system of the tunnel building information model map has the tunnel entrance as the origin. The direction along the length S is the X-axis, and the direction along the width M is the Y-axis. For example, the virtual coordinates of the cross-section camera in the tunnel building information model map are determined based on the distance between the cross-section camera and the tunnel entrance. The virtual coordinates of the cross-section camera can be calculated based on the distance between the cross-section camera and the tunnel entrance and the latitude and longitude coordinates of the tunnel entrance.

[0076] The data acquisition module 12 is used to obtain the pixel coordinates of a vehicle when it is determined that a vehicle exists in the tunnel cross-section frame image information. For example, the automatic calibration device 1 can extract the feature information of the vehicle in the tunnel cross-section frame image information through the cross-section camera, and then select the extracted vehicle feature information and calculate the vehicle pixel coordinates to obtain the vehicle pixel coordinates.

[0077] The data processing module 13 is used to calibrate the virtual coordinates of the cross-section camera in the tunnel building information model map, and to mark the lane line geometric features in the tunnel cross-section frame image information, and determine the pixel coordinates and planar world coordinates of at least three feature points from the lane line geometric features. For example, the planar world coordinates are the coordinate system of the actual position of the marked object on the two-dimensional plane of the road surface of a physical tunnel. The planar world coordinates are the actual measurable real coordinate system based on the extension directions of the X-axis and Y-axis of the physical tunnel. Feature points are fixed structures of the physical tunnel, such as lane line inflection points, lane line side markers, or road surface reflective markings. The automatic calibration device 1 can directly obtain the pixel coordinates of the at least three feature points through the cross-section camera. The automatic calibration device 1 can calculate the planar world coordinates of the at least three feature points based on the distance of the at least three feature points from the cross-section camera.

[0078] The data processing module 13 is also used to determine the vehicle's planar world coordinates based on the vehicle's pixel coordinates, the pixel coordinates of at least three feature points, and the planar world coordinates, and to calibrate the vehicle's virtual coordinates in the tunnel building information model map based on the vehicle's planar world coordinates and the tunnel building information model map.

[0079] For example, the relationship between planar world coordinates and pixel coordinates is shown in formula (1).

[0080] , formula (1).

[0081] Where λ is a non-zero scale factor, H is the homography matrix, (x, y, 1) are the world coordinates in the plane, and (u, v, 1) are the pixel coordinates. For example, the automatic calibration device 1 can calculate the result by substituting the pixel coordinates and world coordinates of at least three feature points into formula (1). The numerical values ​​and homography matrix H. The automatic calibration device 1 can substitute the pixel coordinates of the vehicle into formula (1) to calculate the planar world coordinates of the vehicle.

[0082] For example, the physical constraints on the virtual coordinates of vehicles in the tunnel building information model map are based on the actual structure, functional layout, and traffic rules of the physical tunnel. The map defines the permissible spatial boundaries for the virtual coordinates of vehicles, used to correct deviations in the initial virtual coordinates. This prevents situations where the virtual coordinates of vehicles do not conform to physical logic.

[0083] For example, the data processing module 13 is also used to adjust the tunnel building information model map and the virtual coordinates of the vehicle in the tunnel building information model map based on a preset overlay offset range, and to complete the automatic calibration of the holographic tunnel when it is determined that the coordinate deviation between the adjusted virtual coordinates of the vehicle and the vehicle's planar world coordinates meets the preset coordinate deviation range.

[0084] For example, the preset overlay offset range is a rectangular area of ​​the spatial boundary of the holographic tunnel, preset by the user based on the position and coverage of preset reference objects within the physical tunnel. This area is used to define the spatial region for holographic tunnel fitting and rendering. For example, the preset overlay offset range corresponds to a preset reference object. For example, the preset reference object is a signboard on both sides of the road within the physical tunnel. The preset overlay offset range is R(x1, y1, x2, y2). Here, x1 and x2 represent the range of the preset overlay offset range in the X-axis direction, and y1 and y2 represent the range of the preset overlay offset range in the Y-axis direction. For example, the preset overlay offset range is a rectangular area to fit the shape of the road in the physical tunnel. The automatic calibration device adjusts the tunnel architectural information model map and the virtual coordinates of the vehicle in the tunnel architectural information model map segment by segment using the preset overlay offset range as the physical constraint boundary.

[0085] For example, the automatic calibration device calculates the coordinate deviation between the vehicle's virtual coordinates and its planar world coordinates, denoted as k. The automatic calibration device determines whether k falls within a preset coordinate deviation range; for example, the preset coordinate deviation range is -10 to 10m. For example, if the automatic calibration device determines that k is not within the preset coordinate deviation range, it performs the following operation: If K > 10m, meaning the vehicle's virtual coordinates are ahead of its planar world coordinates, following the principle of positive values ​​leading backward, the automatic calibration device will shift the preset overlay offset range of the corresponding section of the tunnel construction information model map by a preset distance in the negative X-axis direction, while simultaneously correcting the vehicle's virtual coordinates. For example, the preset distance is 0.5-1m.

[0086] If K < -10m, meaning the vehicle's virtual coordinates lag behind its planar world coordinates, the automatic calibration device will shift the preset overlay offset range of the corresponding section of the tunnel construction information model map by a preset distance in the positive X-axis direction, according to the principle of negative values ​​moving forward, and synchronously correct the vehicle's virtual coordinates.

[0087] The automatic calibration device repeatedly determines whether k falls within the preset coordinate deviation range, and adjusts the preset overlay offset range of the corresponding section of the tunnel building information model map and corrects the virtual coordinates of the vehicle based on the determination results. Finally, when it is determined that K is within the range of -10 to -10m, the automatic calibration of the holographic tunnel is completed.

[0088] Through the above embodiments, this application constructs a tunnel architectural information model map using tunnel parameter information, achieving a 1:1 match between the tunnel architectural information model map and the physical tunnel. When a vehicle is identified in the tunnel cross-section frame image information, its pixel coordinates are obtained. Using the dynamic vehicle as a calibration carrier, the virtual coordinates of the tunnel architectural information model map and the vehicle within the tunnel architectural information model map are adjusted according to a preset overlay offset range. Automatic calibration of the holographic tunnel is completed when the coordinate deviation between the adjusted virtual coordinates and the vehicle's planar world coordinates meets a preset coordinate deviation range. This achieves automatic calibration without interrupting traffic and improves calibration accuracy. By determining the vehicle's planar world coordinates based on its pixel coordinates, feature point pixel annotations, and planar world coordinates, a direct association between the image and physical space is achieved, avoiding reliance on total stations or laser scanners and improving calibration efficiency.

[0089] According to another aspect of this application, an electronic device is also provided. The electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the automatic calibration method described above.

[0090] According to another aspect of this application, a computer-readable medium having processor-executable non-volatile program code is also provided. The program code causes the processor to perform the automatic calibration method described above.

[0091] According to another aspect of this application, a computer program product is also provided. The computer program product includes a computer program stored on a computer-readable storage medium, the computer program including program instructions that, when executed by a computer, cause the computer to perform the automatic calibration method as described above.

[0092] As is known from common technical knowledge, this invention can be implemented through other embodiments that do not depart from its spirit or essential characteristics. Therefore, the disclosed embodiments described above are merely illustrative and not exhaustive. All modifications within the scope of this invention or its equivalents are included in this invention.

Claims

1. An automatic calibration method for holographic tunnels, characterized in that, The holographic tunnel is calibrated with the physical tunnel. The holographic tunnel is generated based on a tunnel architectural information model map, and the physical tunnel is equipped with a cross-sectional camera to acquire tunnel cross-sectional frame image information. The automatic calibration method includes: Based on the detected tunnel parameter information of the physical tunnel, a tunnel architectural information model map is constructed, and the virtual coordinates of the cross-section camera in the tunnel architectural information model map are determined. If a vehicle is found to be present in the tunnel cross-section frame image information, the pixel coordinates of the vehicle are obtained. Lane line geometric features are marked in the tunnel cross-section frame image information, and the pixel coordinates and planar world coordinates of at least three feature points are determined from the lane line geometric features; The planar world coordinates of the vehicle are determined based on the pixel coordinates of the vehicle, the pixel coordinates of the at least three feature points, and the planar world coordinates. Based on the vehicle's planar world coordinates and the tunnel construction information model map, the virtual coordinates of the vehicle in the tunnel construction information model map are determined; The tunnel architectural information model map and the vehicle's virtual coordinates in the tunnel architectural information model map are adjusted based on a preset overlay offset range. The automatic calibration of the holographic tunnel is completed when it is determined that the coordinate deviation between the adjusted virtual coordinates of the vehicle and the vehicle's planar world coordinates meets the preset coordinate deviation range.

2. The automatic calibration method according to claim 1, characterized in that, The automatic calibration method further includes: Based on the tunnel construction information model map and the vehicle's virtual coordinates, a digital twin image corresponding to the physical tunnel is constructed. Calculate the coordinate deviation between the vehicle's current planar world coordinates and the vehicle's virtual coordinates in the current frame of the digital twin image; The position of the vehicle in the digital twin is adjusted in real time to compensate for the coordinate deviation value.

3. The automatic calibration method according to claim 2, characterized in that, The real-time rendering adjustment of the vehicle's position in the digital twin image to compensate for the coordinate deviation includes: Obtain the step size value between the current frame of the digital twin and the next frame of the digital twin; Based on the coordinate deviation value, determine the forward step length adjustment value between the current frame digital twin and the next frame digital twin; The step size is adjusted based on the aforementioned forward step size adjustment value to adjust the position of the vehicle in the digital twin image, thereby compensating for the coordinate deviation value.

4. The automatic calibration method according to claim 1, characterized in that, The step of marking lane line geometric features in the tunnel cross-section frame image information and determining the pixel coordinates and planar world coordinates of at least three feature points from the lane line geometric features includes: Edge detection and feature extraction are performed on the tunnel cross-section frame image information to mark the lane geometric features and select at least three feature points; The pixel coordinates of the at least three feature points are obtained using the cross-sectional camera; The planar world coordinates of the at least three feature points are determined based on the virtual coordinates of the cross-sectional camera and the positional relationship between the at least three feature points and the cross-sectional camera.

5. The automatic calibration method according to claim 1, characterized in that, The determination of the vehicle's planar world coordinates based on the vehicle's pixel coordinates, the pixel coordinates of the at least three feature points, and the planar world coordinates includes: The homography matrix is ​​determined based on the pixel coordinates and planar world coordinates of the at least three feature points; The planar world coordinates of the vehicle are determined based on the vehicle's pixel coordinates and the homography matrix.

6. The automatic calibration method according to claim 1, characterized in that, The process of determining the virtual coordinates of the vehicle in the tunnel construction information model map based on the vehicle's planar world coordinates and the tunnel construction information model map includes: Extract the coordinate system parameters of the tunnel construction information model map; The planar world coordinates of the vehicle are mapped to the coordinate system of the tunnel building information model map to determine the initial virtual coordinates of the vehicle in the tunnel building information model map; The initial virtual coordinates are corrected based on the physical constraints of the vehicle's virtual coordinates on the tunnel construction information model map to determine the vehicle's virtual coordinates.

7. An automatic calibration device for holographic tunnels, characterized in that, The holographic tunnel is calibrated with the physical tunnel. The holographic tunnel is generated based on a tunnel architectural information model map, and the physical tunnel is equipped with a cross-sectional camera for acquiring tunnel cross-sectional frame image information. The automatic calibration device includes: The map building module is used to build the tunnel architectural information model map based on the detected tunnel parameter information of the physical tunnel, and to determine the virtual coordinates of the cross-section camera in the tunnel architectural information model map; The data acquisition module is used to acquire the pixel coordinates of the vehicle when it is determined that a vehicle exists in the tunnel cross-section frame image information. The data processing module is used to determine the virtual coordinates of the cross-section camera in the tunnel architectural information model map, and to mark lane line geometric features in the tunnel cross-section frame image information, and to determine the pixel coordinates and planar world coordinates of at least three feature points from the lane line geometric features. The data processing module is also used to determine the planar world coordinates of the vehicle based on the vehicle's pixel coordinates, the pixel coordinates of the at least three feature points, and the planar world coordinates, and to determine the vehicle's virtual coordinates in the tunnel architectural information model map based on the vehicle's planar world coordinates and the tunnel architectural information model map. The data processing module is also used to adjust the tunnel architectural information model map and the vehicle's virtual coordinates in the tunnel architectural information model map based on a preset overlay offset range, and to complete the automatic calibration of the holographic tunnel when the coordinate deviation between the adjusted virtual coordinates and the vehicle's planar world coordinates meets the preset coordinate deviation range.

8. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the automatic calibration method according to any one of claims 1-6.

9. A computer-readable medium having processor-executable non-volatile program code, characterized in that, The program code causes the processor to execute the automatic calibration method according to any one of claims 1-6.

10. A computer program product, characterized in that, It includes a computer program stored on a computer-readable storage medium, the computer program including program instructions that, when executed by a computer, cause the computer to perform the automatic calibration method as described in any one of claims 1-6.

Images