A method, system, and terminal for mileage calibration of vehicles suitable for tunnels.

Abstract

This invention belongs to the field of detection technology and discloses a method, system, and terminal for mileage calibration of vehicles in tunnels. It involves acquiring a first frame image of the tunnel taken by a first image acquisition device at a first time point, a second frame image of the tunnel surface taken by a second image acquisition device at the same time point, and inertial navigation data from the vehicle's status feedback detected by an inertial navigation system at the same time point. When the first frame image at the first time point does not contain mileage markers, the mileage of the vehicle is calculated based on the second frame image, historical frame images, and the time difference between the historical frame images and the inertial navigation data. When the first frame image at the first time point contains mileage markers, the mileage of the vehicle is calibrated based on the character information in the first frame image containing the mileage markers. This method can improve the accuracy of mileage measurement of vehicles in tunnels, thereby enhancing the accuracy of vehicle positioning within tunnels.

Description

Technical Field

[0001] This invention belongs to the field of detection technology, and in particular relates to a mileage calibration method, system and terminal for vehicles traveling in tunnels. Background Technology

[0002] Currently, in real-world environments, some tunnels experience problems after construction due to complex and constantly changing geological conditions, such as lining cracking, segment cracking, misalignment, and tunnel leakage. Furthermore, issues like surrounding soil cavities and overall settlement of the subway tunnel may also arise. Therefore, construction personnel need to regularly inspect tunnel fault points, which requires locating tunnel inspection vehicles.

[0003] Existing methods for locating tunnel inspection vehicles rely on GPS (Global Positioning System) information and wheel rotations to calculate the tunnel's mileage and determine the vehicle's position. However, due to weak GPS signals within the tunnel, or even complete loss of signals in some areas, as well as wheel slippage, accurate positioning of the tunnel inspection vehicle becomes impossible. Therefore, machine vision-based positioning solutions for tunnel inspection vehicles have emerged.

[0004] In existing technologies, the steps for locating tunnel inspection vehicles based on machine vision are as follows:

[0005] Two frames of images are acquired, and the displacement difference between the two frames is determined by feature comparison. The actual position of the tunnel inspection vehicle is then calculated. However, due to various factors within the tunnel (such as tunnel surface discontinuities, railway stations, single-tunnel, and double-tunnel configurations), the clarity of the frame images changes with the surrounding environment, affecting the accuracy of machine vision-based tunnel inspection vehicle positioning. Therefore, achieving accurate positioning within the tunnel is a problem that urgently needs to be solved.

[0006] Based on the above analysis, the problems and shortcomings of the existing technology are as follows:

[0007] (1) The accuracy of the mileage of the vehicle in the tunnel is poor in the prior art, which makes the positioning accuracy of the vehicle in the tunnel low.

[0008] (2) Due to the discontinuity of the tunnel surface, the presence of station, single tunnel, double tunnel and other image factors in the tunnel, the clarity of the frame image cannot change with the surrounding environment, which reduces the accuracy of tunnel positioning. Summary of the Invention

[0009] To address the problems existing in the prior art, the present invention provides a mileage calibration method, system, and terminal for vehicles traveling in tunnels.

[0010] This invention is implemented as follows: a mileage calibration method for vehicles traveling in tunnels includes:

[0011] The system acquires a first frame image of the tunnel captured by a first image acquisition device at a first time point, a second frame image of the tunnel surface captured by a second image acquisition device at a first time point, and inertial navigation data of the vehicle status feedback detected by an inertial navigation device at a first time point.

[0012] Mileage markers are placed along the passageways (including tunnels), and the mileage markers are marked with character information.

[0013] The first image capturing device and the second image capturing device move synchronously with the vehicle, and the shooting angle of the first image capturing device is between the vertical tunnel wall and the parallel tunnel wall.

[0014] When the first frame image at the first time point does not contain the mileage marker, the mileage of the vehicle is calculated based on the second frame image at the first time point, the historical frame image, and the time difference between the historical frame image and the inertial navigation data. The historical frame image is the first frame image used when the vehicle was last calibrated.

[0015] When the first frame image at the first time point contains the mileage marker, the mileage of the vehicle is calibrated based on the character information in the first frame image containing the mileage marker at the first time point.

[0016] Optionally, prior to the step of calibrating the mileage of a vehicle based on character information in a first frame image containing mileage markers at a first time point, the mileage calibration method for a vehicle suitable for tunnels provided in the first aspect embodiment of the present invention further includes:

[0017] When the first frame image at the first time point contains a mileage marker, the character information of the first frame image containing the mileage marker is identified to obtain the identification result, which is: whether the character information in the first frame image is identified;

[0018] When the recognition result is that no character information is recognized, the second historical frame image of the tunnel surface captured by the second image acquisition device is obtained from the last calibration of the driving vehicle mileage to the first time point.

[0019] Based on the second historical frame image, the first cumulative mileage of the vehicle is calculated;

[0020] Based on the inertial navigation data and the time difference between the historical frame image and the inertial navigation data, the second cumulative mileage of the vehicle is calculated.

[0021] The average of the first cumulative mileage and the second cumulative mileage is determined as the cumulative mileage of the vehicle.

[0022] Sum the mileage from the last calibration with the preset value to obtain the first summation result;

[0023] Sum the mileage from the last calibration with the cumulative mileage to obtain the second summation result;

[0024] The steps for calibrating the mileage of a vehicle based on character information in the first frame image containing mileage markers at the first time point include:

[0025] The first summation result is compared with the second summation result to calibrate the mileage of the vehicle at the first time point.

[0026] Optionally, the step of comparing the first summation result with the second summation result to calibrate the mileage of the vehicle at the first time point includes:

[0027] When the difference between the first summation result and the second summation result does not exceed the first difference threshold, the difference between the first summation result and the preset second value is determined as the mileage of the vehicle at the first time point;

[0028] When the difference between the first summation result and the second summation result exceeds the first difference threshold, the difference between the second summation result and the preset second value is determined as the mileage of the vehicle at the first time point.

[0029] Optionally, before the step of calibrating the mileage of a vehicle based on the character information in the first frame image containing the mileage marker at the first time point, when the first frame image at the first time point contains a mileage marker, the mileage calibration method for a vehicle suitable for tunnels provided in the first aspect embodiment of the present invention further includes:

[0030] Detect whether the first frame of the first time point contains mileage markers;

[0031] When there are multiple first frame images containing mileage markers, the target frame image is determined from the multiple first frame images. The target frame image is the first frame image whose center point is closest to the center point of the mileage marker.

[0032] The steps for calibrating the mileage of a vehicle based on character information in the first frame image containing mileage markers at the first time point include:

[0033] The mileage of the vehicle is calibrated based on the character information in the target frame image.

[0034] Optionally, after the step of detecting whether the first frame image at the first time point contains mileage markers, the mileage calibration method for a vehicle traveling in a tunnel provided in the first aspect embodiment of the present invention further includes:

[0035] When there are multiple first-frame images containing mileage markers, the character information of the mileage markers in each first-frame image containing mileage markers is identified to obtain the recognition result, which is: whether the character information is recognized.

[0036] For the recognition results of the identified character information, count the number of times the character information in the recognition results is the same as the other character information.

[0037] When the number of identical characters in the recognition result exceeds a preset threshold, the mileage of the vehicle at the first time point is calibrated based on the number of identical characters exceeding the preset threshold.

[0038] Optional, the character information includes: the distance between the mileage marker and the starting point;

[0039] When the first frame image at the first time point contains a mileage marker, the step of calibrating the mileage of the vehicle based on the character information in the first frame image containing the mileage marker at the first time point includes:

[0040] The distance of the mileage marker from the starting point is summed with the initial mileage of the vehicle, and the sum is determined as the mileage of the vehicle at the first time point.

[0041] Optionally, the step of calibrating the mileage of a vehicle based on character information in the first frame image containing mileage markers at a first time point includes:

[0042] When the recognition result is that character information is recognized, the character information includes: the distance of the mileage marker from the starting point, and whether the difference between the distance in the historical character information and the distance in the character information at the first time point exceeds the second difference threshold. The historical character information is the character information of the last mileage calibration.

[0043] When the difference between the distance in the character information at the first time point and the distance in the historical character information does not exceed the second difference threshold, the sum of the distance in the character information at the first time point and the initial mileage of the vehicle is determined as the mileage of the vehicle at the first time point.

[0044] When the difference between the distance in the character information at the first time point and the distance in the historical character information exceeds the second difference threshold, acquire the second historical frame image captured by the second image acquisition device from the last calibration of the driving vehicle mileage to the first time point.

[0045] Based on the aforementioned second historical frame image, calculate the first cumulative mileage;

[0046] Based on the inertial navigation data and the time difference between the historical frame image and the inertial navigation data, the second cumulative mileage of the vehicle is calculated.

[0047] The average of the first cumulative mileage and the second cumulative mileage is determined as the cumulative mileage of the vehicle.

[0048] The sum of the accumulated mileage and the distance in the historical character information is determined as the mileage of the vehicle at the first point in time.

[0049] Optionally, before the step of calculating the mileage of the vehicle based on the second frame image at the first time point, historical frame images, and the time difference between the historical frame images and the inertial navigation data when the first frame image at the first time point does not contain the mileage marker, the mileage calibration method for a vehicle suitable for tunnels provided in this embodiment of the invention further includes:

[0050] Based on the same timestamp, the first time point and the first frame image before the first time point, the second frame image and the inertial navigation data are synchronized and paired.

[0051] The step of calculating the mileage of the vehicle based on the second frame image at the first time point, historical frame images, and the time difference between the historical frame images and the inertial navigation data includes:

[0052] Obtain the second historical frame image from the timestamp of the historical frame image to the first time point;

[0053] Based on the second historical frame image, the first cumulative mileage of the vehicle is calculated;

[0054] Based on the inertial navigation data and the time difference between the historical frame image and the inertial navigation data, the second cumulative mileage of the vehicle is calculated.

[0055] The average of the first cumulative mileage and the second cumulative mileage, plus the sum of the mileage from the last calibration, is determined as the mileage of the vehicle.

[0056] Optionally, the step of calculating cumulative mileage based on the historical second frame image includes:

[0057] Calculate the actual size of the object space corresponding to each pixel in the second historical frame image;

[0058] Using a preset matching algorithm, the homography matrix of adjacent historical second-frame images is calculated. The homography matrix represents the magnitude of the change between adjacent historical second-frame images.

[0059] Based on the homography matrix, calculate the image displacement of the next historical second frame image relative to the previous historical second frame image in adjacent historical second frame images;

[0060] The product of the actual size of the object space corresponding to each pixel and the image displacement is determined as the actual displacement of the second historical frame image of the next frame relative to the second historical frame image of the previous frame.

[0061] The actual displacement is accumulated to determine the cumulative mileage.

[0062] Optionally, after the step of calibrating the mileage of a vehicle based on character information in the first frame image containing mileage markers at a first time point, the mileage calibration method for a vehicle suitable for tunnels provided in the first aspect embodiment of the present invention further includes:

[0063] Based on the calibrated mileage of the vehicle and tunnel information, the position of the vehicle in the tunnel is determined. The tunnel information includes: the length of the tunnel, the location of the tunnel entrance, the location of the tunnel exit, and the curvature angle of the tunnel at different locations.

[0064] Another objective of this invention is to provide a server comprising a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus; a machine-readable storage medium stores machine-executable instructions that can be executed by the processor, and the processor is prompted by the machine-executable instructions to implement the steps of the mileage calibration method for a vehicle suitable for tunnels provided in the first aspect of the present invention.

[0065] Another objective of this invention is to provide a mileage calibration system for vehicles traveling in tunnels, wherein mileage markers are installed beside the tunnel, and the mileage markers are marked with character information. The mileage calibration system for vehicles traveling in tunnels includes:

[0066] The first image capturing device is mounted on the vehicle and moves synchronously to capture the first frame image of the tunnel at the first time point, with the shooting angle between the vertical tunnel wall and the parallel tunnel wall.

[0067] The second image acquisition device is mounted on the vehicle and moves synchronously to capture a second frame image of the tunnel surface at the first time point.

[0068] An inertial navigation system, mounted on and moving synchronously with the vehicle, is used to detect inertial navigation data fed back from the vehicle's status at the first point in time.

[0069] The vehicle mileage calculation module is used to calculate the mileage of the vehicle based on the second frame image at the first time point, the historical frame image, and the time difference between the historical frame image and the inertial navigation data when the first frame image at the first time point does not contain the mileage marker. The historical frame image is the first frame image used when the vehicle was calibrated last time.

[0070] The vehicle mileage calibration module is used to calibrate the mileage of the vehicle based on the character information in the first frame image containing the mileage marker at the first time point when the first frame image at the first time point contains the mileage marker.

[0071] Another object of the present invention is to provide a computer device comprising a memory and a processor, the memory storing a computer program that, when executed by the processor, causes the processor to perform the mileage calibration method for a vehicle traveling in a tunnel.

[0072] Another object of the present invention is to provide a computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the mileage calibration method for a vehicle traveling in a tunnel.

[0073] Another objective of this invention is to provide an information data processing terminal for implementing the mileage calibration method for vehicles traveling in tunnels.

[0074] Based on the above technical solutions and the technical problems solved, please analyze the advantages and positive effects of the technical solution to be protected by this invention from the following aspects:

[0075] First, addressing the technical problems existing in the prior art and the difficulty in solving them, this paper closely analyzes, in conjunction with the technical solution to be protected by this invention and the results and data obtained during the research and development process, how the technical solution of this invention solves the technical problems, and the inventive technical effects brought about by solving these problems. The specific description is as follows:

[0076] Underground or mountainous tunnels and utility tunnels are not covered by communication networks, and GPS signals are weak, which cannot provide positioning information for driving equipment, thus making the mileage of the vehicle inaccurate.

[0077] Measuring mileage by relying on wheel circumference and number of rotations can be inaccurate due to factors such as wheel slippage or low tire pressure, leading to errors in the mileage readings on the vehicle.

[0078] Effects of the invention:

[0079] The driving equipment can break free from the limitations of communication networks or GPS, and independently complete high-precision positioning calculations, thereby calibrating the mileage of the driving vehicle.

[0080] By calculating the displacement of the driving equipment using a homography matrix, the influence of various factors such as the temperature and material of the driving equipment, acceleration, and braking temperature and humidity on the mileage is eliminated.

[0081] By dividing a tunnel into several smaller sections and identifying the mileage information in the mileage markers, the position information is calibrated multiple times to further improve the accuracy of the quasi-positioning, thereby improving the accuracy of the mileage of the vehicle.

[0082] Second, considering the technical solution as a whole or from a product perspective, the technical effects and advantages of the technical solution to be protected by this invention are specifically described as follows:

[0083] This invention provides a method for calibrating the mileage of a vehicle in a tunnel. The method involves acquiring a first frame image of the tunnel captured by a first image acquisition device at a first time point, a second frame image of the tunnel surface captured by a second image acquisition device at the same time point, and inertial navigation data from the vehicle's status feedback detected by an inertial navigation system at the same time point. When the first frame image at the first time point does not contain mileage markers, the mileage of the vehicle is calculated based on the second frame image, historical frame images, and the time difference between the historical frame images and the inertial navigation data. When the first frame image at the first time point contains mileage markers, the mileage of the vehicle is calibrated based on the character information in the first frame image containing the mileage markers. This method improves the accuracy of mileage measurement of the vehicle in the tunnel, thereby enhancing the accuracy of vehicle positioning within the tunnel and ultimately improving the accuracy of mileage measurement.

[0084] The expected benefits and commercial value of the technical solution of this invention after transformation are as follows:

[0085] The technical solution of this invention fills a technological gap in the industry both domestically and internationally:

[0086] This invention achieves high-precision positioning within tunnels without relying on infrastructure such as GPS or communication networks, thereby enabling accurate mileage correction of vehicles and filling a gap in this field both domestically and internationally.

[0087] Does the technical solution of this invention solve a technical problem that people have long desired to solve but have never been able to successfully address?

[0088] This invention provides a practical and effective method and device for achieving high-precision positioning of vehicles in underground or mountainous areas, such as tunnels and utility tunnels, which are not covered by communication networks. It solves the technical problem of inaccurate positioning in tunnel construction, inspection, maintenance, and repair operations, which leads to inaccurate mileage of vehicles. Attached Figure Description

[0089] Figure 1 This is a flowchart of a mileage calibration method for a vehicle traveling in a tunnel, provided in an embodiment of the present invention.

[0090] Figure 2 A flowchart for determining the mileage of a vehicle at a first time point, provided in an embodiment of the present invention;

[0091] Figure 3 A flowchart of the implementation step S13 provided in an embodiment of the present invention;

[0092] Figure 4 A schematic diagram of a mileage calibration system for vehicles traveling in tunnels, provided in an embodiment of the present invention:

[0093] In the figure: 1. First image acquisition device; 2. Second image acquisition device; 3. Inertial navigation device; 4. Vehicle mileage calculation module; 5. Vehicle mileage calibration module. Detailed Implementation

[0094] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0095] I. Explanatory and Illustrative Embodiments. To enable those skilled in the art to fully understand how the present invention is specifically implemented, this section provides an explanatory and illustrative description of the embodiments described in the claims.

[0096] Example 1

[0097] like Figure 1 As shown in the figure, an embodiment of the present invention provides a mileage calibration method for vehicles traveling in tunnels, comprising:

[0098] S11, the first image capturing device captures the first frame image of the tunnel at the first time point, the second image capturing device captures the second frame image at the first time point (not limited to capturing the road surface or the roadbed), and the inertial navigation device detects the inertial navigation data of the driving vehicle status feedback at the first time point.

[0099] The first image capturing device, the second image capturing device, and the inertial navigation device move synchronously with the vehicle. The shooting angle of the first image capturing device is between the vertical tunnel wall and the parallel tunnel wall. Mileage markers are set up beside the tunnel, and the mileage markers are marked with character information. The character information includes: the distance of the mileage marker from the starting point.

[0100] It is understood that the vehicle can be a car, subway, light rail, train, or other transportation vehicle, or an engineering vehicle used for tunnel inspection, or a trailer attached to an engineering vehicle. This vehicle is equipped with an image acquisition device and an inertial navigation system (INS). An INS is an inertial measurement unit that measures an object's three-axis attitude angles (or angular rates) and acceleration. To improve reliability, more sensors can be equipped for each axis. Generally, the INS is mounted at the center of gravity of the object being measured. The first and second image acquisition devices can be cameras, cameras, or other devices with imaging capabilities. The camera of the first image acquisition device can capture images of the mileage markers inside the tunnel. The starting point can be at the tunnel entrance or somewhere away from the tunnel entrance; this starting point varies depending on the actual situation and serves as the initial position for engineers to calibrate the distances on the mileage markers.

[0101] Taking engineering vehicles as an example, existing tunnels are equipped with mileage markers at predetermined locations. These markers can be 100-meter markers, 50-meter markers, etc. The mileage markers record the distance from the tunnel entrance to the marker and also indicate the vehicle's direction of travel. Engineers can use these markers to determine the marker's position within the tunnel and its distance from the starting point. Since tunnels are two-way passages, the mileage markers can have both sides. Engineers entering from the tunnel entrance can mark the distance from the entrance on the front and the distance from the exit on the back. Alternatively, the markers can mark the distance from the starting point on both sides, with the markings varying according to the actual situation.

[0102] Mileage markers are precisely measured and set by technicians, ensuring high accuracy. In tunnels, mileage markers are visually distinct from their surroundings. The inventors discovered through experiments that mileage markers stand out more prominently in images than surrounding lights or markings on tunnel walls, are less affected by the environment, and exhibit high accuracy in machine vision recognition. Furthermore, these mileage markers contain character information indicating distance. By recognizing these markers, the distance of vehicles, such as cars, relative to a reference point (typically the starting point of the tunnel or road) can be quickly and accurately determined.

[0103] For example, when the engineering vehicle activates its camera function, if the mileage marker is within the vehicle's camera range during the vehicle's movement, the vehicle can capture the first frame image containing the mileage marker; if the mileage marker is not within the vehicle's camera range, the first frame image will only contain images of the environment surrounding the tunnel, such as the tunnel walls, tunnel surface, and tunnel lights.

[0104] When the mileage marker is affixed to the tunnel wall, the camera of the first image capturing device can be positioned on the side wall of the construction vehicle, facing the tunnel wall. When the mileage marker is placed next to the tunnel wall, with its face facing the construction vehicle, the camera can be positioned in front of the construction vehicle, or positioned within a 90-degree range to the left and right of the vehicle's central axis in the direction of travel. The height of the camera must be within a preset range to ensure the mileage marker is within the camera's field of view. This camera can be a movable lens camera, used to rotate and capture images of the mileage marker within a 0-degree range in the direction of travel and a 180-degree range in the opposite direction.

[0105] It is understandable that mileage markers are highly distinctive, detailed, and accurately positioned, thus ensuring their reliability and usability. Furthermore, using mileage markers to locate vehicles requires only two image acquisition devices, making the solution easy to implement and inexpensive.

[0106] S12, when the first frame image at the first time point does not contain mileage markers, calculate the mileage of the vehicle based on the second frame image at the first time point, historical frame images, and the time difference between historical frame images and inertial navigation data.

[0107] Among them, the historical frame image is the first frame image used during the last calibration of the driving vehicle.

[0108] It is understandable that the cumulative mileage is calculated using the second frame image before the first time point. The initial mileage of the vehicle is added to the cumulative mileage to obtain the cumulative mileage of the vehicle. If the mileage of the vehicle was previously calibrated, and the vehicle continues to travel to its current position at the first time point, there are multiple frames between the second frame image at the first time point and the historical frame images. The mileage of the previous calibration is added to the cumulative mileage calculated using the time difference between the multiple frames and the historical frame images and the inertial navigation data to obtain the mileage of the vehicle at the first time point.

[0109] S13, when the first frame image is detected to contain a mileage marker, the mileage of the driving vehicle is calibrated based on the character information in the first frame image containing the mileage marker at the first time point.

[0110] It is understood that the features of mileage markers are relatively obvious in the image. When searching for the first frame image containing mileage markers, feature points of the mileage markers can be extracted, such as SIFT (Scale Invariant Feature Transform) feature points and corner points. This invention does not impose any limitations on these features.

[0111] It is understandable that by comparing the distance recorded on the mileage marker from the starting point with the mileage of the vehicle at the first point in time, based on the distance from the starting point in the character information, the mileage of the vehicle can be calibrated.

[0112] This invention provides a method for calibrating the mileage of a vehicle in a tunnel. The method involves acquiring a first frame image of the tunnel taken by a first image capturing device at a first time point, and a second frame image of the tunnel surface taken by a second image capturing device at the same time point. The mileage of the vehicle is calculated based on the second frame image and historical frame images. When a mileage marker is detected in the first frame image at the first time point, the mileage of the vehicle is calibrated based on character information within that image. Compared to existing technologies, this invention improves the accuracy of mileage measurement in tunnels by identifying character information in the first frame image containing mileage markers with high positioning accuracy and prominent image features. This character information is then used to calibrate the mileage calculated based on the second frame image and historical frame images, thereby enhancing the accuracy of the vehicle's positioning within the tunnel.

[0113] Example 2

[0114] As one possible implementation method of the present invention, such as Figure 2 As shown, prior to step S13 above, the mileage calibration method for a vehicle suitable for tunnels provided in this embodiment of the invention further includes:

[0115] S21, when the first frame image at the first time point is detected to contain a mileage marker, the character information of the first frame image containing the mileage marker is identified to obtain the identification result.

[0116] The recognition result is whether the character information in the first frame image is recognized.

[0117] It is understandable that when recognizing the character information of mileage markers in the first frame image containing them, the image's clarity, scale, or position within the frame can affect the results. For example, when only part of the mileage marker is in the first frame image, the character information cannot be recognized due to missing text.

[0118] S22, when the recognition result is that no character information is recognized, acquire the second historical frame image of the tunnel surface captured by the second image capturing device from the last calibration of the driving vehicle mileage to the first time point;

[0119] It is understandable that if the recognition result is that no character information is recognized, it means that the distance of the mileage marker from the starting point cannot be obtained. Therefore, the mileage marker cannot be used to calibrate the mileage of the vehicle at the first time point. In this case, the frame image from the last mileage calibration to the first time point is needed to know the distance traveled by the vehicle from the last mileage calibration to the first time point.

[0120] S23, Calculate the first cumulative mileage of the vehicle based on the second historical frame image;

[0121] It is understandable that when a vehicle is moving, there is a displacement difference between adjacent historical second-frame images. Based on the displacement difference between adjacent historical second-frame images, the cumulative mileage of the vehicle from the last calibration mileage to the first time point can be determined.

[0122] S24, calculate the second cumulative mileage of the vehicle based on inertial navigation data and the time difference between historical frame images and inertial navigation data;

[0123] The inertial navigation data includes the vehicle's acceleration and three-axis attitude angles.

[0124] It can be understood that the acceleration of the vehicle in the direction of travel is obtained from inertial navigation data, denoted as 'a', and the time difference between the historical frame image and the inertial navigation data is denoted as 't'. Then, the second cumulative mileage Δs' is: Δs' = v*t + (a*t*t) / 2. The process of calculating the second cumulative mileage of the vehicle using inertial navigation data and the time difference between the historical frame image and the inertial navigation data is described. V represents velocity.

[0125] S25, the average of the first cumulative mileage and the second cumulative mileage is determined as the cumulative mileage of the vehicle;

[0126] S26, sum the mileage from the last calibration with the preset value to obtain the first summation result;

[0127] The first value is the distance between adjacent mileage markers. If the mileage marker is a 50-meter marker, the first value is 50. If the mileage marker is a 100-meter marker, the first value is 100.

[0128] It's understandable that once the vehicle enters the tunnel, all captured frame images can be stored in a database, which could be an onboard database or a cloud database. The vehicle uploads the captured frame images to the cloud database and records the capture time of each frame image. When a frame image is needed, it can be retrieved from the database. Simultaneously, the time of each mileage calibration is recorded. If the mileage marker recognition fails at the first time point, the mileage from the previous calibration is added to the distance between the two adjacent mileage markers to determine the vehicle's mileage at that first time point.

[0129] S27 sums the mileage from the last calibration with the cumulative mileage to obtain the second summation result.

[0130] Furthermore, step S13 above can compare the first summation result with the second summation result to calibrate the mileage of the vehicle at the first time point.

[0131] Example 3

[0132] As an optional implementation method of the present invention, combined with Figure 1 as well as Figure 2 The step of comparing the first summation result with the second summation result to calibrate the vehicle's mileage at the first time point is achieved through the following steps:

[0133] Step 1: When the difference between the first summation result and the second summation result does not exceed the first difference threshold, the difference between the first summation result and the preset second value is determined as the mileage of the vehicle at the first time point;

[0134] The second value is the distance between the actual location of the mileage marker in the tunnel and the camera in the first frame image, i.e., the object distance.

[0135] It is understood that the object distance will be different if different frame images containing the same mileage marker are selected. In this embodiment of the invention, the object distance selected for each mileage calibration is the same, that is, if the selected frame image containing the same mileage marker is a single image, then the position of the mileage marker in the first frame image is the same each time the mileage is calibrated.

[0136] For example, suppose that when a mileage marker is selected to enter the camera's shooting range, the first frame captured by the camera contains an image of the mileage marker; the nth frame captured by the camera contains an image of the mileage marker. The distance between the mileage marker and the camera is different in these two frames, and the value of the second value is different.

[0137] Step 2: When the difference between the first summation result and the second summation result exceeds the first difference threshold, the difference between the second summation result and the preset second value is determined as the mileage of the vehicle at the first time point.

[0138] The first difference threshold is a value preset based on tunnel length and practical experience, and can be set to 10 meters in actual application.

[0139] It's understandable that the camera might have already captured a frame containing the mileage marker before the vehicle even reaches it; the distance between the vehicle and the marker at this point is the second value. By comparing the first and second summations, the estimated mileage is verified to determine if it meets the accuracy standard. If so, the difference between the second summation and the second value is taken to obtain the vehicle's mileage at the first time point. The estimated mileage is the first summation result.

[0140] Example 4

[0141] As an optional implementation of the present invention, prior to step S13 above, the mileage calibration method for a vehicle traveling in a tunnel provided by the present invention further includes:

[0142] Step 1: Detect whether the first frame image at the first time point contains mileage markers;

[0143] Step 2: When there are multiple first frame images containing mileage markers, determine the target frame image from the multiple first frame images. The target frame image is the first frame image whose center point is closest to the center point of the mileage marker.

[0144] Furthermore, step S13 above can be used to calibrate the mileage of the vehicle based on the character information in the target frame image.

[0145] This implementation method can calculate the center coordinates (x, y) of the same mile marker in multiple consecutive frames of images. i ,y i ), (i = 1…n), where n represents the number of frames captured by the camera containing the same mileage marker. Then, the distance Dist between the center coordinates of the mileage marker and the center coordinates of the frame image is calculated. i (i = 1…n), select the frame image with the smallest distance as the target frame image.

[0146] This embodiment calculates the distance between the center coordinates of the mileage marker in the frame image and the center coordinates of the frame image, and selects the frame image with the smallest distance as the target frame image, so that the mileage marker is as close to the center of the frame image as possible, thereby improving the accuracy of character information recognition and mileage calibration.

[0147] Example 5

[0148] As an optional embodiment of the present invention, after the step of detecting whether the first frame image at the first time point contains mileage markers, the mileage calibration method for vehicles traveling in tunnels provided by the present invention further includes:

[0149] Step 1: When there are multiple first-frame images containing mileage markers, identify the character information of the mileage markers in each first-frame image containing mileage markers to obtain the recognition result.

[0150] The recognition result is whether character information was recognized.

[0151] It is understandable that when a mileage marker enters the shooting range of the first image capturing device, if the vehicle is moving, the first image capturing device may capture multiple target frame images containing the mileage marker.

[0152] Step 2: For the recognition results of the identified character information, count the number of times the character information in the recognition results is the same as the other character information;

[0153] Step 3: When the number of identical characters in the recognition result exceeds a preset threshold, the mileage of the driving vehicle at the first time point is calibrated based on the number of identical characters exceeding the preset threshold.

[0154] It is understandable that some areas in some frame images may be blurry. When there are multiple frame images with the same mileage marker, the text information in multiple frame images can be identified to determine the same character information of the same mileage marker and the number of the same character information. Based on the distance corresponding to the character information whose number exceeds the threshold, the mileage of the driving vehicle at the first time point can be calibrated, which can improve the reliability of calibrating the mileage of the driving vehicle at the first time point.

[0155] As an optional implementation of the present invention, the mileage of the vehicle can be calibrated by summing the distance of the mileage marker from the starting point to the initial mileage of the vehicle, and the summation result is determined as the mileage of the vehicle at the first time point.

[0156] Example 6

[0157] As one possible implementation method of the present invention, such as Figure 3 As shown, step S13 above can be implemented as follows:

[0158] S31, when the recognition result is that character information is recognized, determine whether the difference between the distance in the historical character information and the distance in the character information at the first time point exceeds the second difference threshold. The historical character information is the character information of the last calibration mileage.

[0159] The character information includes the distance of the mileage marker from the starting point.

[0160] S32, when the difference between the distance in the character information at the first time point and the distance in the historical character information does not exceed the second difference threshold, the sum of the distance in the character information at the first time point and the initial mileage of the vehicle is determined as the mileage of the vehicle at the first time point;

[0161] The second difference threshold is a preset value, which can be 10 meters in practice.

[0162] S33, when the difference between the distance in the character information at the first time point and the distance in the historical character information exceeds the second difference threshold, acquire the historical second frame image captured by the second image capturing device from the last calibration of the driving vehicle mileage to the first time point;

[0163] S34, Calculate the first cumulative mileage based on the historical second frame image;

[0164] S35, calculate the second cumulative mileage of the vehicle based on inertial navigation data and the time difference between historical frame images and inertial navigation data;

[0165] S36, The average of the first cumulative mileage and the second cumulative mileage is determined as the cumulative mileage of the vehicle;

[0166] S37 determines the mileage of the vehicle at the first point in time by summing the accumulated mileage with the distance in the historical character information.

[0167] It is understood that this embodiment compares the distance in the character information at the first time point with the distance in the historical character information to determine whether the frame image containing the mileage marker at the first time point can be used to calibrate the mileage, thereby improving the accuracy of calibrating the mileage of the driving vehicle.

[0168] Example 7

[0169] As an optional implementation of the present invention, prior to step S12 above, the mileage calibration method for a vehicle suitable for tunnels provided by the present invention further includes:

[0170] Based on the same timestamp, the first time point, the first frame image before the first time point, the second frame image, and the inertial navigation data are synchronized and paired.

[0171] It is understood that each frame of image captured by the first and second image capturing devices will have a corresponding timestamp. Inertial navigation is used to output the acceleration and pose of the vehicle, decompose the acceleration into the direction of travel of the vehicle, and synchronize the first frame image, the second frame image, and the inertial navigation data according to the timestamp. In this way, when the vehicle is at any position in the tunnel, the first frame image, the second frame image, and the inertial navigation data are obtained at that position. This can improve the accuracy of mileage calibration in subsequent mileage calibration.

[0172] Furthermore, the above-mentioned step S12 includes:

[0173] Step 1: Obtain the second historical frame image from the timestamp of the historical frame image to the first time point;

[0174] Step 2: Based on the historical second frame image, calculate the first cumulative mileage of the vehicle;

[0175] Step 3: Calculate the second cumulative mileage of the vehicle based on the inertial navigation data and the time difference between the historical frame image and the inertial navigation data;

[0176] Step 4: The average of the first cumulative mileage and the second cumulative mileage, plus the mileage from the last calibration, is used to determine the mileage of the vehicle.

[0177] In this embodiment of the invention, the first cumulative mileage of the vehicle is calculated by using the second historical frame image, and then the second cumulative mileage is calculated based on inertial navigation data. The average value is then used to determine the mileage of the vehicle, thus avoiding a decrease in mileage accuracy due to a single data offset, thereby improving the accuracy of mileage calculation.

[0178] Example 8

[0179] As an optional implementation of this invention, the step of calculating the cumulative mileage based on the historical second frame image includes:

[0180] Step 1: Calculate the actual size of the object space corresponding to each pixel in the second historical frame image;

[0181] Step 2: Using a preset matching algorithm, calculate the homography matrix of adjacent historical second-frame images. The homography matrix represents the magnitude of change between adjacent historical second-frame images.

[0182] Step 3: Based on the homography matrix, calculate the image displacement of the next historical second frame image relative to the previous historical second frame image in adjacent historical second frame images;

[0183] Step 4: Based on the product of the actual size of the object space corresponding to each pixel and the image displacement, determine the actual displacement of the next historical second frame image relative to the previous historical second frame image.

[0184] Step 5: Accumulate the actual displacement to determine the cumulative mileage.

[0185] It can be understood that if the image displacement of the next frame relative to the previous frame is x, and the actual size of the object space corresponding to each pixel is d, then the actual displacement of the next historical frame relative to the previous historical frame is s = d * x.

[0186] Example 9

[0187] As an optional implementation of the present invention, after step S13 above, the mileage calibration method for a vehicle suitable for tunnels provided by the present invention further includes:

[0188] Based on the calibrated mileage of the vehicle and tunnel information, the position of the vehicle in the tunnel is determined. The tunnel information includes: the length of the tunnel, the location of the tunnel entrance, the location of the tunnel exit, and the curvature angle of the tunnel at different locations.

[0189] It's understandable that when a construction vehicle is in a tunnel, the distance traveled within the tunnel can be determined based on the mileage. Knowing this distance, the vehicle's exact location within the tunnel can be determined using tunnel information. For tunnels with significant curvature, the direction of the construction vehicle needs to be determined based on the tunnel's curvature angle, and then the distance traveled can be used to pinpoint the vehicle's exact location within the tunnel.

[0190] Example 10

[0191] As an optional implementation of the present invention, a trained region recognition model can be used to find the first frame image containing mileage markers in the frame image.

[0192] The region recognition model can be a Cascade R-CNN model. The process of obtaining a trained region recognition model is as follows:

[0193] Step 1: Obtain the sample set, which includes frame images containing mileage markers collected at different locations. Each frame image is a sample.

[0194] Step 2: Label the samples in the sample set, indicating the location of the mileage markers in the tunnel.

[0195] Step 3: Input standard samples into the preset network model, use the standard results as the training target of the Cascade RCNN model, and iteratively adjust the internal parameters of the network model until the number of iterations or the training target is reached.

[0196] Step 4: Use the network model that has reached the required number of iterations or the training target as the training number for the trained network model.

[0197] It is understood that this embodiment trains a region recognition model using standard samples, and using this region recognition model to recognize frame images can improve the accuracy of the recognition results.

[0198] Example 11

[0199] As an optional implementation of the present invention, a trained character recognition model can be used to recognize character information in the first frame image containing mileage markers.

[0200] The character recognition model can be a ResNet model. The process of obtaining a trained character recognition model is as follows:

[0201] Step 1: Collect the different types of characters contained in the mileage marker images and use each character as a training sample.

[0202] Step 2: For each training sample, input the training sample into the preset character recognition model, use the distance information corresponding to the training sample as the training target, and iteratively train the preset character recognition model until the number of iterations is reached to obtain the trained character recognition model.

[0203] It is understood that this embodiment trains a character recognition model by using different types of characters contained in the mileage marker image, and using the character recognition model to recognize the frame image can improve the accuracy of the recognition results.

[0204] Example 12

[0205] As an optional embodiment of the present invention, before step S11 above, the mileage calibration method for a vehicle suitable for tunnels provided by the present invention further includes: calibrating the camera.

[0206] The steps for calibrating a camera are as follows:

[0207] (a) Keep the camera position fixed, place the calibration plate at different positions in the tunnel, collect m frames of images, and detect corner points in the frames. Assume that n corner points can be detected in each frame.

[0208] (b) Iterate through each frame of the image and solve for the homography matrix H. j H jThe initial value is used to perform nonlinear optimization on the identity matrix; j represents the sequence number of the frame image.

[0209] (c) Solve for the camera intrinsic parameter matrix K;

[0210] (d) Solve for the camera's extrinsic parameters and calculate R. j and t j .

[0211] Among them, R j Let t represent the rotation matrix. j This represents the translation vector.

[0212] (e) Solve for the camera distortion coefficients K1 and K2.

[0213] (f) Parameter optimization: Optimize K and R using nonlinear least squares method. j t j K1 and K2 are used to obtain the camera's intrinsic and extrinsic parameters.

[0214] Example 13

[0215] like Figure 4 As shown, the present invention provides a mileage calibration system for vehicles traveling in tunnels. Mileage markers are installed beside the tunnel, and these markers are labeled with character information. The mileage calibration system for vehicles traveling in tunnels includes:

[0216] The first image capturing device 1 is mounted on the vehicle and moves synchronously to capture the first frame image of the tunnel at the first time point, with the shooting angle between the vertical tunnel wall and the parallel tunnel wall.

[0217] The second image capturing device 2 is mounted on the vehicle and moves synchronously to capture a second frame image of the tunnel surface at the first time point.

[0218] The inertial navigation device 3 is mounted on the vehicle and moves synchronously to detect the inertial navigation data fed back from the vehicle's status at the first point in time.

[0219] The vehicle mileage calculation module 4 is used to calculate the mileage of the vehicle based on the second frame image at the first time point, the historical frame image, and the time difference between the historical frame image and the inertial navigation data when the first frame image at the first time point does not contain the mileage marker. The historical frame image is the first frame image used when the vehicle was calibrated last time.

[0220] The vehicle mileage calibration module 5 is used to calibrate the mileage of the vehicle based on the character information in the first frame image containing the mileage marker at the first time point when the first frame image at the first time point contains the mileage marker.

[0221] II. Application Examples. To demonstrate the inventiveness and technical value of the technical solution of this invention, this section provides application examples of the technical solution of the claims on specific products or related technologies.

[0222] The method provided by the present invention can be applied to a computer-readable storage medium containing a computer program that, when executed by a processor, implements the steps of any of the above-described mileage calibration methods applicable to tunnels.

[0223] The method provided by the present invention can be applied to a computer program product containing instructions, which, when run on a computer, causes the computer to execute any of the mileage calibration methods applicable to tunnels described above.

[0224] The mileage calibration method for tunnels of the present invention can be implemented wholly or partially through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented wholly or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid state disks (SSDs)).

[0225] It should be noted that in this invention, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0226] The various embodiments in this specification are described in a related manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0227] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications, equivalent substitutions, and improvements made by those skilled in the art within the scope of the technology disclosed in the present invention, and within the spirit and principles of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A method for calibrating the mileage of a vehicle suitable for use in tunnels, characterized in that, Mileage markers are installed beside the passageway, and the mileage markers are marked with character information indicating the mileage. The mileage calibration method for vehicles traveling in tunnels includes: The system acquires a first frame image of the tunnel captured by a first image acquisition device at a first time point, a second frame image of the tunnel road surface captured by a second image acquisition device at a first time point, and inertial navigation data of the vehicle status feedback detected by the inertial navigation device at a first time point. The first image capturing device, the second image capturing device, and the inertial navigation device move synchronously with the vehicle, and the shooting angle of the first image capturing device is between the vertical tunnel wall and the parallel tunnel wall. When the first frame image at the first time point does not contain the mileage marker, the mileage of the vehicle is calculated based on the second frame image at the first time point, the historical frame image, and the time difference between the historical frame image and the inertial navigation data. The historical frame image is the first frame image used when the vehicle was last calibrated. When the first frame image at the first time point contains the mileage marker, the mileage of the vehicle is calibrated based on the character information in the first frame image at the first time point containing the mileage marker; Before the step of calibrating the mileage of the vehicle based on the character information in the first frame image containing the mileage marker at the first time point, the method further includes: When the first frame image at the first time point contains the mileage marker, the character information of the first frame image containing the mileage marker is identified to obtain a recognition result, wherein the recognition result is: whether the character information in the first frame image is identified; When the recognition result is that the character information is not recognized, the second historical frame image of the tunnel surface captured by the second image capturing device is obtained from the last calibration of the vehicle mileage to the first time point. Based on the second historical frame image, the first cumulative mileage of the vehicle is calculated; Based on the inertial navigation data and the time difference between the historical frame image and the inertial navigation data, the second cumulative mileage of the vehicle is calculated. The average of the first cumulative mileage and the second cumulative mileage is determined as the cumulative mileage of the vehicle. The mileage from the last calibration is summed with the preset first value to obtain the first summation result; The mileage from the last calibration is summed with the cumulative mileage to obtain a second summation result; The step of calibrating the mileage of the vehicle based on the character information in the first frame image containing the mileage marker at a first time point includes: The first summation result is compared with the second summation result to calibrate the mileage of the vehicle at the first time point; The step of comparing the first summation result with the second summation result to calibrate the mileage of the vehicle at the first time point includes: When the difference between the first summation result and the second summation result does not exceed the first difference threshold, the difference between the first summation result and the preset second value is determined as the mileage of the vehicle at the first time point; When the difference between the first summation result and the second summation result exceeds the first difference threshold, the difference between the second summation result and the preset second value is determined as the mileage of the vehicle at the first time point.

2. The mileage calibration method for vehicles traveling in tunnels according to claim 1, characterized in that, Before the step of calibrating the mileage of the vehicle based on the character information in the first frame image containing the mileage marker at the first time point when the first frame image at the first time point contains the mileage marker, the method further includes: Detect whether the first frame image at the first time point contains the mileage marker; When there are multiple first frame images containing the mileage marker, a target frame image is determined from the multiple first frame images. The target frame image is the first frame image whose center point is closest to the center point of the mileage marker. The step of calibrating the mileage of the vehicle based on the character information in the first frame image containing the mileage marker at a first time point includes: The mileage of the vehicle is calibrated based on the character information in the target frame image; After the step of detecting whether the mileage marker is contained in the first frame image at the first time point, the method further includes: When there are multiple first frame images containing the mileage markers, the character information of the mileage markers in each first frame image containing the mileage markers is identified to obtain a recognition result, wherein the recognition result is: whether the character information is identified; For the recognition results that identify the character information, count the number of times the character information in the recognition results is the same as the other character information; When the number of identical characters in the recognition result exceeds a preset threshold, the mileage of the vehicle at the first time point is calibrated based on the number of identical characters exceeding the preset threshold.

3. The mileage calibration method for vehicles traveling in tunnels according to claim 1, characterized in that, The character information includes: the distance between the mileage marker and the starting point; When the first frame image at the first time point contains the mileage marker, the step of calibrating the mileage of the vehicle based on the character information in the first frame image containing the mileage marker at the first time point includes: The distance of the mileage marker from the starting point is summed with the initial mileage of the vehicle, and the sum is determined as the mileage of the vehicle at the first time point.

4. The mileage calibration method for vehicles traveling in tunnels according to claim 1, characterized in that, The step of calibrating the mileage of the vehicle based on the character information in the first frame image containing the mileage marker at a first time point includes: When the recognition result is that the character information is recognized, the character information includes: the distance of the mileage marker from the starting point, and whether the difference between the distance in the historical character information and the distance in the character information at the first time point exceeds a second difference threshold. The historical character information is the character information of the last mileage calibration. When the difference between the distance in the character information at the first time point and the distance in the historical character information does not exceed the second difference threshold, the sum of the distance in the character information at the first time point and the initial mileage of the vehicle is determined as the mileage of the vehicle at the first time point. When the difference between the distance in the character information at the first time point and the distance in the historical character information exceeds the second difference threshold, a second historical frame image captured by the second image capturing device from the last calibration of the vehicle mileage to the first time point is acquired. Based on the aforementioned second historical frame image, calculate the first cumulative mileage; Based on the inertial navigation data and the time difference between the historical frame image and the inertial navigation data, the second cumulative mileage of the vehicle is calculated. The average of the first cumulative mileage and the second cumulative mileage is determined as the cumulative mileage of the vehicle. The sum of the cumulative mileage and the distance in the historical character information is determined as the mileage of the vehicle at the first time point.

5. The mileage calibration method for vehicles traveling in tunnels according to claim 1, characterized in that, Before the step of calculating the mileage of the vehicle based on the second frame image at the first time point, historical frame images, and the time difference between the historical frame images and the inertial navigation data when the first frame image at the first time point does not contain the mileage marker, the method further includes: Based on the same timestamp, the first time point and the first frame image before the first time point, the second frame image and the inertial navigation data are synchronized and paired. The step of calculating the mileage of the vehicle based on the second frame image at the first time point, historical frame images, and the time difference between the historical frame images and the inertial navigation data includes: Obtain the second historical frame image from the timestamp of the historical frame image to the first time point; Based on the second historical frame image, the first cumulative mileage of the vehicle is calculated; Based on the inertial navigation data and the time difference between the historical frame image and the inertial navigation data, the second cumulative mileage of the vehicle is calculated. The average of the first cumulative mileage and the second cumulative mileage, plus the mileage of the last calibration, is determined as the mileage of the vehicle. The step of calculating the first cumulative mileage based on the historical second frame image includes: Calculate the actual size of the object space corresponding to each pixel in the second historical frame image; Using a preset matching algorithm, the homography matrix of adjacent historical second-frame images is calculated, and the homography matrix represents the magnitude of the change in the adjacent historical second-frame images; Based on the homography matrix, calculate the image displacement of the next historical second frame image relative to the previous historical second frame image in adjacent historical second frame images; The product of the actual size of the object space corresponding to each pixel and the image displacement is determined as the actual displacement of the previous historical frame image relative to the next historical frame image. The actual displacements are accumulated to obtain the first accumulated mileage; After the step of calibrating the mileage of the vehicle based on the character information in the first frame image containing the mileage marker at the first time point, the method further includes: Based on the calibrated mileage of the vehicle and the tunnel information, the position of the vehicle in the tunnel is determined. The tunnel information includes: the length of the tunnel, the location of the tunnel entrance, the location of the tunnel exit, and the curvature angle of the tunnel at different locations.

6. A mileage calibration system for vehicles traveling in tunnels, characterized in that, Mileage markers are installed beside the tunnel, and the mileage markers are marked with character information. The mileage calibration system for vehicles traveling in the tunnel includes: The first image capturing device is mounted on the vehicle and moves synchronously to capture the first frame image of the tunnel at the first time point, with the shooting angle between the vertical tunnel wall and the parallel tunnel wall. The second image acquisition device is mounted on the vehicle and moves synchronously to capture a second frame image of the tunnel surface at the first time point. An inertial navigation system, mounted on and moving synchronously with the vehicle, is used to detect inertial navigation data fed back from the vehicle's status at the first point in time. The vehicle mileage calculation module is used to calculate the mileage of the vehicle based on the second frame image at the first time point, the historical frame image, and the time difference between the historical frame image and the inertial navigation data when the first frame image at the first time point does not contain the mileage marker. The historical frame image is the first frame image used when the vehicle was calibrated last time. A vehicle mileage calibration module is used to calibrate the mileage of the vehicle based on the character information in the first frame image containing the mileage marker at the first time point when the first frame image at the first time point contains the mileage marker. When the first frame image at the first time point contains the mileage marker, the character information of the first frame image containing the mileage marker is identified to obtain a recognition result, wherein the recognition result is: whether the character information in the first frame image is identified; When the recognition result is that the character information is not recognized, the second historical frame image of the tunnel surface captured by the second image capturing device is obtained from the last calibration of the vehicle mileage to the first time point. Based on the second historical frame image, the first cumulative mileage of the vehicle is calculated; Based on the inertial navigation data and the time difference between the historical frame image and the inertial navigation data, the second cumulative mileage of the vehicle is calculated. The average of the first cumulative mileage and the second cumulative mileage is determined as the cumulative mileage of the vehicle. The mileage from the last calibration is summed with the preset first value to obtain the first summation result; The mileage from the last calibration is summed with the cumulative mileage to obtain a second summation result; The first summation result is compared with the second summation result to calibrate the mileage of the vehicle at the first time point; When the difference between the first summation result and the second summation result does not exceed the first difference threshold, the difference between the first summation result and the preset second value is determined as the mileage of the vehicle at the first time point; When the difference between the first summation result and the second summation result exceeds the first difference threshold, the difference between the second summation result and the preset second value is determined as the mileage of the vehicle at the first time point.

7. A computer device, characterized in that, The computer device includes a memory and a processor. The memory stores a computer program, which, when executed by the processor, causes the processor to perform the mileage calibration method for a vehicle traveling in a tunnel as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, which, when executed by a processor, causes the processor to perform the mileage calibration method for a vehicle traveling in a tunnel as described in any one of claims 1 to 5.

9. An information data processing terminal, characterized in that, The information data processing terminal is used to implement the mileage calibration method for a vehicle suitable for tunnels as described in any one of claims 1 to 5.

Images