Aircraft taxiing track identification method and system

Abstract

The invention relates to an aircraft taxiing track identification method and system, and the method comprises the steps: obtaining camera internal parameters of an airborne monocular camera of an aircraft, and building a conversion relation between a camera coordinate system and a pixel coordinate system; acquiring an image captured by a camera of the aircraft and performing distortion correction processing; based on the image after distortion correction, aircraft wheel set key point coordinates and ground runway center line key point coordinates under a pixel coordinate system are extracted; based on the aircraft wheel set size information, the aircraft wheel set key point coordinates and the ground runway center line key point coordinates, calculating the three-dimensional coordinates of the aircraft wheel set and the ground runway center line feature points under the camera coordinate system by using the conversion relation between the camera coordinate system and the pixel coordinate system; and based on the three-dimensional coordinates of the aircraft wheel set and the ground runway center line, fitting to obtain the direction of the ground runway center line, calculating the offset information of the aircraft relative to the ground runway center line, and realizing the identification of the aircraft taxiing trajectory.

Description

Technical Field

[0001] The present invention relates to the field of computer vision technology, and in particular to a method and system for identifying an aircraft taxiing trajectory. Background Art

[0002] The aircraft runway trajectory is the core parameter of the airport pavement structure design and evaluation, affecting key indicators such as pavement panel thickness, pavement panel classification level, and cumulative damage factor. Comprehensively grasping the distribution range and regularity of aircraft runway trajectory information can not only improve pavement utilization efficiency and reduce maintenance costs, but also effectively improve the safety and economy of airport facilities, which is of great significance to the design and operation of long-life pavements.

[0003] Domestic and foreign technologies mainly use infrared, embedded sensors and laser sensing technologies to measure the taxiing trajectory. Among them, infrared technology relies on infrared beams to detect the position of the wheels, but is easily interfered by external heat sources and obstacles; embedded vibration sensors are based on optical fiber technology and are suitable for point-like monitoring of large areas, but they need to be buried in the road surface, which limits their application in service runways; laser ranging technology uses high-frequency lasers to measure the distance between the wheels and the centerline of the runway, which has high accuracy and anti-interference, but requires angle correction and has high equipment costs.

[0004] In addition, the existing methods are mainly cross-sectional monitoring, which makes it difficult to obtain the global trajectory distribution characteristics of taxiways and runways. The trajectory distribution of different aircraft varies significantly due to factors such as speed, taxiing status, and aircraft model. Single cross-sectional data is difficult to fully reflect its lateral and longitudinal distribution patterns, limiting the comprehensiveness of taxiing trajectory observations. In addition, limited trajectory data makes it difficult to fully reflect the long-term stress and damage accumulation characteristics of the pavement, affecting the safety and economy of pavement design. Summary of the invention

[0005] The purpose of the present invention is to overcome the defects of the above-mentioned prior art and provide an aircraft taxiing trajectory identification method and system to solve or partially solve the problem of incomplete taxiing trajectory observation.

[0006] The purpose of the present invention can be achieved by the following technical solutions: One aspect of the present invention provides a method for identifying an aircraft taxiing trajectory, comprising the following steps: Obtaining the camera intrinsic parameters of the aircraft's onboard monocular camera, and establishing a conversion relationship between the camera coordinate system and the pixel coordinate system based on the camera intrinsic parameters; Obtain images captured by the aircraft's camera and perform distortion correction processing; Based on the distortion-corrected image, the coordinates of the key points of the aircraft wheels and the key points of the centerline of the ground runway in the pixel coordinate system are extracted; Based on the pre-acquired aircraft wheel size information, as well as the coordinates of the key points of the aircraft wheel and the centerline of the ground runway, the three-dimensional coordinates of the feature points of the aircraft wheel and the centerline of the ground runway in the camera coordinate system are calculated by utilizing the conversion relationship between the camera coordinate system and the pixel coordinate system; Based on the three-dimensional coordinates of the aircraft wheel set and the ground runway centerline, the direction of the ground runway centerline is fitted, the offset information of the aircraft wheel set relative to the ground runway centerline is calculated, and a visualization signal including the runway centerline and the aircraft wheel set trajectory is output to realize the identification and visualization of the aircraft taxiing trajectory. The offset information includes an offset angle and an offset distance compared to the centerline of the ground runway, and the calculation process of the offset distance includes: Randomly select two points from the three-dimensional coordinate set of the centerline feature points of the ground runway to form a candidate line, calculate the distance between all feature points and the candidates, take the feature points whose distance is less than a preset threshold as the inliers, and take the candidate line with the largest number of inliers as the best line; For all the inner points corresponding to the best straight line, the direction vector of the fitted straight line is obtained by least square fitting, and the offset distance is calculated based on the direction vector.

[0007] As a preferred technical solution, the camera internal parameters of the aircraft are: , in, For the camera Axis and The focal length of the axis, is the camera principal point coordinate, is the camera internal parameter.

[0008] As a preferred technical solution, the conversion relationship between the camera coordinate system and the pixel coordinate system is: , in, For the camera Axis and The focal length of the axis, is the camera principal point coordinate, , They are the camera coordinate system coordinates and the pixel coordinate system coordinates respectively.

[0009] As a preferred technical solution, the distortion correction is implemented by the following formula: , , , , in, is the pixel coordinate of the distorted image, is the normalized pixel coordinate, is the radial distance of the normalized pixel coordinate from the principal point, is the radial distortion coefficient, is the tangential distortion coefficient, For the camera Axis and The focal length of the axis, is the camera principal point coordinate, are the coordinates after distortion correction.

[0010] As a preferred technical solution, the coordinates of the key points of the aircraft wheels in the pixel coordinate system and the key points of the center line of the ground runway are obtained by YOLO-Pose detection.

[0011] As a preferred technical solution, the three-dimensional coordinates of the characteristic points of the aircraft wheels and the centerline of the ground runway in the calculation camera coordinate system include: Using the pre-built three-dimensional model, based on the coordinates of the key points of the aircraft wheel assembly, and according to the conversion relationship between the camera coordinate system and the pixel coordinate system, the three-dimensional coordinates of the aircraft wheel assembly in the camera coordinate system are obtained; The PnP algorithm is used to calculate the camera posture, and the three-dimensional coordinates of the centerline feature points of the ground runway in the camera coordinate system are obtained according to the conversion relationship between the camera coordinate system and the pixel coordinate system.

[0012] As a preferred technical solution, the offset angle is calculated using the following formula: ,

[0013] in, Represents the aircraft nose heading vector, in the assumed space coordinate system, , represents transpose, It means that the ground runway centerline vector is obtained by performing RANSAC linear fitting on the three-dimensional coordinate set of the ground runway centerline feature points. represents the offset angle, Represents a modulo operation.

[0014] As a preferred technical solution, the aircraft wheel assembly includes a nose wheel, a left main wheel and a right main wheel.

[0015] As a preferred technical solution, the offset distance is calculated using the following formula: , , ,

[0016] in, is the offset distance, is the slope of the best straight line, The best straight line i The coordinates of the interior points, and is the average value of the interior point coordinates, is the direction vector of the best straight line, are the coordinates of the center points of the left and right wheels, is any point in the three-dimensional coordinate set of the centerline feature points of the ground runway. Represents a modulo operation.

[0017] Another aspect of the present invention provides an aircraft taxiing trajectory recognition system for implementing the above-mentioned aircraft taxiing trajectory recognition method, the system comprising: A coordinate system conversion construction module is used to obtain the camera intrinsic parameters of the aircraft's onboard monocular camera and establish a conversion relationship between the camera coordinate system and the pixel coordinate system based on the camera intrinsic parameters; An image capture and correction module, including a camera disposed on the belly of the aircraft, for acquiring images captured by the camera of the aircraft and performing distortion correction processing; An image key point extraction module is used to extract the coordinates of the key points of the aircraft wheels and the key points of the center line of the ground runway in the pixel coordinate system based on the distortion-corrected image; A three-dimensional coordinate extraction module, for calculating the three-dimensional coordinates of the characteristic points of the aircraft wheel group and the ground runway centerline in the camera coordinate system by using the conversion relationship between the camera coordinate system and the pixel coordinate system based on the pre-acquired aircraft wheel group size information, the coordinates of the key points of the aircraft wheel group and the ground runway centerline, and the three-dimensional coordinates of the characteristic points of the aircraft wheel group and the ground runway centerline in the camera coordinate system; The offset information calculation module is used to fit the direction of the ground runway centerline based on the three-dimensional coordinates of the aircraft wheel group and the ground runway centerline, calculate the offset information of the aircraft relative to the ground runway centerline, and realize the aircraft taxiing trajectory identification.

[0018] Compared with the prior art, the present invention has at least one of the following beneficial effects: (1) Realizing the recognition and visualization of aircraft trajectories: The present invention constructs a conversion relationship between pixel coordinates and camera coordinates, detects the captured images to obtain the coordinates of the wheel group and the ground runway centerline, and finally obtains the ground runway centerline direction by fitting, calculates the offset information of the aircraft relative to the ground runway centerline, and outputs a visualization signal including the runway centerline and the aircraft wheel group trajectory to realize the recognition and visualization of the aircraft taxiing trajectory. The present invention can effectively improve the recognition range and accuracy of the aircraft taxiing trajectory, and provide data basis for downstream applications such as airport pavement design evaluation and takeoff action guidance evaluation.

[0019] (2) Fully consider the distortion problem of the captured image: The present invention reduces the impact of image distortion on the recognition result by performing distortion correction processing on the acquired image.

[0020] (3) The calculation of the aircraft's taxiing offset distance is more accurate: Considering that during the high-speed taxiing of the aircraft, due to the quality of the onboard camera, there may be ground abnormal points (such as defects generated in the process of marking the runway centerline, reflective foreign objects on the ground, etc.) that produce trailing images and are thus mistakenly identified as the runway centerline. The present invention randomly selects two points from the three-dimensional coordinate set of the ground runway centerline feature points to form a candidate straight line, calculates the distances between all feature points and the candidates, takes the feature points with distances less than a preset threshold as inliers, takes the candidate straight line with the largest number of inliers as the best straight line, fits the straight line by least squares, obtains the direction vector of the fitted straight line, and finally calculates the offset distance to avoid the influence of the incorrect selection of the straight line on the calculation of the offset distance. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a flow chart of the aircraft taxiing trajectory identification method in the embodiment; Figure 2 Schematic diagram of the distances of the left and right wheels from the centerline of the ground runway in the current frame in the embodiment; Figure 3 It is a take-off run trajectory diagram in the embodiment; Figure 4 is a schematic diagram of an aircraft taxiing trajectory identification system in an embodiment; Figure 5 Schematic diagram of an electronic device in an embodiment. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0023] Example 1

[0024] In view of the problems existing in the above-mentioned prior art, this embodiment provides a method for identifying the taxiing trajectory of an aircraft, see Figure 1 , including the following steps: S1, obtain the intrinsic parameters of the camera installed on the belly of the aircraft, and establish the conversion relationship between the camera coordinate system and the pixel coordinate system.

[0025] Specifically, the equation form of the camera intrinsic parameter is as follows: , (1) Where: For the camera Axis and The focal length of the axis, is the camera principal point coordinate. Camera coordinate system With pixel coordinate system The relationship is: , (2) S2, uses the distortion parameters of the camera to correct the image, obtains the corrected image coordinates and uses filtering, histogram equalization and other methods to enhance the image quality and highlight the target features.

[0026] Specifically, image correction uses the camera’s distortion parameters (radial distortion coefficient and tangential distortion coefficient ), use the following formula to correct the image.

[0027] The image coordinates are normalized using the camera internal parameters: , (3) , (4) , (5) , (6) In the formula, is the pixel coordinate of the distorted image, is the normalized pixel coordinate, is the radial distance of the normalized pixel coordinates from the principal point.

[0028] S3, using the improved YOLO-Pose algorithm, performs target detection and key point extraction on the calibrated image. The left main wheel center point coordinates, the right main wheel center point coordinates, and the runway center line feature point set regarded as the center line.

[0029] Specifically, YOLO-Pose detection is a single-stage target detection and pose estimation method based on deep learning. Based on the YOLO detection framework, the algorithm adds a pose regression branch to achieve 3D pose estimation of the object by learning the key point coordinates of the target. YOLO-Pose has the advantages of real-time and high precision. The model returns the following parameters: Left main wheel key point set: , the key point set of the right main wheel: , nose wheel key point set: , the ground runway centerline feature point set: .

[0030] S4 uses the PnP (Perspective-n-Point) algorithm to calculate the three-dimensional coordinates and attitude of the main wheel and the centerline of the ground runway by combining the camera intrinsic parameters and the known physical dimensions of the main wheel.

[0031] Specifically, the three-dimensional position calculation of the main wheels, for the left and right main wheels and the nose wheel, the key point coordinates of their three-dimensional models in the world coordinate system are known The corresponding image coordinates , use the PnP algorithm to solve the camera posture The basic formula of the PnP problem is: , (7) In the formula, is the scale factor. Assume the ground is flat , using the estimated camera pose , map the image points of the ground runway centerline to the world coordinate system: , (8) Get the three-dimensional coordinate set of the ground runway centerline feature points in the world coordinate system .

[0032] S5, based on the three-dimensional coordinates of the main wheels and the centerline of the ground runway, calculate the aircraft heading, fit the straight line equation of the ground runway centerline, and obtain the offset angle of the aircraft relative to the centerline of the ground runway and offset distance , repeat the above process to draw the trajectory diagram of the aircraft taxiing process.

[0033] Specifically, for the offset angle and offset distance, the offset angle is calculated using the following formula: , (9) In the formula, Represents the aircraft nose heading vector, in the assumed space coordinate system, , represents transpose, represents the modulo operation, Represents the ground runway centerline vector, which is obtained by RANSAC linear fitting of the ground runway centerline key point set. Randomly select two points and calculate the candidate line model. Calculate the distance from all feature points to the line model and set the distance less than the threshold The points are counted as inliers. Record the number of inliers in the current model and repeat the above steps. The model with the largest number of inliers is selected as the best straight line model. For all inliers in the best model, the least squares method is used to refit the straight line and calculate the slope. : , (10) In the formula, are the interior point coordinates, and is the average value of the interior point coordinates.

[0034] Then calculate the direction vector of the line for: , (11) The offset distance is calculated using the following formula: , (12) In the formula, are the coordinates of the center points of the left and right wheels, is any point in the set of characteristic points of the centerline of the ground runway, Represents a modulo operation.

[0035] The following takes the taxiing trajectory recognition of an actual aircraft takeoff process as an example.

[0036] Near the nose wheel of the aircraft, a camera is installed facing the center point of the left and right wheels. The camera is installed at a height of 1.0 m , the resolution is 1250x690 pixels, and the field of view is 90 degrees. The Zhang Zhengyou calibration method is used to calibrate the camera internal parameters to obtain the camera internal parameters: , principal point coordinates , .The distortion parameters are: , , .

[0037] The original image is distorted using known distortion coefficients to eliminate the effects of image distortion, and the image is enhanced using median filtering and histogram equalization methods to improve the recognizability of key features.

[0038] Using the trained YOLO-Pose model, we performed target detection on the corrected and enhanced image and successfully detected the following feature points of the left main wheel: , right main wheel feature point , the ground runway centerline feature point set .

[0039] In this embodiment, since the camera is installed facing the center points of the left and right wheels, the plane where the left and right wheel feature points are located is relatively parallel to the plane where the ground runway centerline feature points are located without tilt. According to formula (7), the projection of each three-dimensional point to the camera plane can be calculated, and the depth change caused by perspective projection can be ignored. It is approximately assumed that there is a linear proportional relationship between the image coordinates and the actual coordinates. It is known that the actual distance between the main wheels is , the left and right wheel image coordinates are The directional pixel difference is 343 pixels, and the proportional relationship can be calculated as: ,

[0040] Calculate the midpoint coordinates of the left and right main wheels: , ,

[0041] The RANSAC algorithm and formula (10) are used to fit the centerline of the ground runway. The equation of the fitted line is: . Use equations (11) and (12) to calculate the pixel offset distance, convert the pixel distance into the actual distance, and draw the left and right wheel offset distances, as shown in Figure 2 As shown, the 0 on the horizontal axis represents the straight line corresponding to the center line of the ground runway, the left half dotted line represents the trajectory of the rear left wheel, the right half dotted line represents the trajectory of the rear right wheel, and the vertical axis represents the runway direction.

[0042] Repeat the above steps for the entire takeoff process to complete the takeoff trajectory diagram of the aircraft, such as Figure 3 shown.

[0043] In summary, by adopting the aircraft taxiing trajectory recognition method of this embodiment, the aircraft taxiing trajectory recognition range and accuracy can be effectively improved, providing a data basis for airport pavement design and evaluation.

[0044] Example 2

[0045] Based on Example 1, see Figure 4 This embodiment provides an aircraft taxiing trajectory recognition system, which is used to implement the above-mentioned aircraft taxiing trajectory recognition method. The system includes: (1) Coordinate system conversion construction module, which is used to obtain the camera intrinsic parameters of the aircraft and establish the conversion relationship between the camera coordinate system and the pixel coordinate system.

[0046] (2) An image capture and correction module, including a camera disposed on the belly of the aircraft, for acquiring images captured by the aircraft's camera and performing distortion correction processing.

[0047] (3) Image key point extraction module, which is used to extract the coordinates of the key points of the aircraft wheels and the centerline of the ground runway in the pixel coordinate system based on the distortion-corrected image.

[0048] (4) A three-dimensional coordinate extraction module is used to calculate the three-dimensional coordinates of the feature points of the aircraft wheel group and the ground runway centerline in the camera coordinate system based on the pre-acquired aircraft wheel group size information, the coordinates of the key points of the aircraft wheel group and the ground runway centerline, and the conversion relationship between the camera coordinate system and the pixel coordinate system.

[0049] (5) An offset information calculation module is used to fit the direction of the ground runway centerline based on the three-dimensional coordinates of the aircraft wheel set and the ground runway centerline, calculate the offset information of the aircraft relative to the ground runway centerline, and realize the aircraft taxiing trajectory identification.

[0050] Example 3

[0051] This embodiment provides an electronic device, including: one or more processors and a memory, wherein the memory stores one or more programs, and the one or more programs include instructions for executing the aircraft taxiing trajectory identification method as described in Example 1.

[0052] like Figure 5 As mentioned above, at the hardware level, the electronic device includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include other hardware required for the business. The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it to achieve the above Figure 1 Of course, in addition to the software implementation, the present invention does not exclude other implementations, such as logic devices or a combination of software and hardware, etc., that is, the execution subject of the following processing flow is not limited to each logic unit, but can also be hardware or logic devices.

[0053] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0054] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0055] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for identifying an aircraft taxiing trajectory, characterized in that: The steps include: Obtaining the camera intrinsic parameters of the aircraft's onboard monocular camera, and establishing a conversion relationship between the camera coordinate system and the pixel coordinate system based on the camera intrinsic parameters; Obtain images captured by the aircraft's camera and perform distortion correction processing; Based on the distortion-corrected image, the coordinates of the key points of the aircraft wheels and the key points of the centerline of the ground runway in the pixel coordinate system are extracted; Based on the pre-acquired aircraft wheel size information, as well as the coordinates of the key points of the aircraft wheel and the centerline of the ground runway, the three-dimensional coordinates of the feature points of the aircraft wheel and the centerline of the ground runway in the camera coordinate system are calculated by utilizing the conversion relationship between the camera coordinate system and the pixel coordinate system; Based on the three-dimensional coordinates of the aircraft wheel set and the ground runway centerline, the direction of the ground runway centerline is fitted, the offset information of the aircraft wheel set relative to the ground runway centerline is calculated, and a visualization signal including the runway centerline and the aircraft wheel set trajectory is output to realize the identification and visualization of the aircraft taxiing trajectory. The offset information includes an offset angle and an offset distance compared to the centerline of the ground runway, and the calculation process of the offset distance includes: Randomly select two points from the three-dimensional coordinate set of the centerline feature points of the ground runway to form a candidate line, calculate the distance between all feature points and the candidates, take the feature points whose distance is less than a preset threshold as the inliers, and take the candidate line with the largest number of inliers as the best line; For all the inner points corresponding to the best straight line, the direction vector of the fitted straight line is obtained by least square fitting, and the offset distance is calculated based on the direction vector.

2. The method for identifying an aircraft taxiing trajectory according to claim 1, characterized in that: The camera internal parameters of the aircraft are: ， in, For the camera Axis and The focal length of the axis, is the camera principal point coordinate, is the camera internal parameter.

3. The method for identifying an aircraft taxiing trajectory according to claim 1, characterized in that: The conversion relationship between the camera coordinate system and the pixel coordinate system is: ， in, For the camera Axis and The focal length of the axis, is the camera principal point coordinate, , They are the camera coordinate system coordinates and the pixel coordinate system coordinates respectively.

4. The method for identifying an aircraft taxiing trajectory according to claim 1, characterized in that: The distortion correction is achieved by the following formula: ， ， ， ， in, is the pixel coordinate of the distorted image, is the normalized pixel coordinate, is the radial distance of the normalized pixel coordinate from the principal point, is the radial distortion coefficient, is the tangential distortion coefficient, For the camera Axis and The focal length of the axis, is the camera principal point coordinate, are the coordinates after distortion correction.

5. The method for identifying an aircraft taxiing trajectory according to claim 1, characterized in that: The coordinates of the key points of the aircraft wheels in the pixel coordinate system and the key points of the ground runway centerline are obtained by YOLO-Pose detection.

6. The method for identifying an aircraft taxiing trajectory according to claim 1, characterized in that: The three-dimensional coordinates of the characteristic points of the aircraft wheels and the centerline of the ground runway in the calculation camera coordinate system include: Using the pre-built three-dimensional model, based on the coordinates of the key points of the aircraft wheel assembly, and according to the conversion relationship between the camera coordinate system and the pixel coordinate system, the three-dimensional coordinates of the aircraft wheel assembly in the camera coordinate system are obtained; The PnP algorithm is used to calculate the camera posture, and the three-dimensional coordinates of the centerline feature points of the ground runway in the camera coordinate system are obtained according to the conversion relationship between the camera coordinate system and the pixel coordinate system.

7. The method for identifying an aircraft taxiing trajectory according to claim 1, characterized in that: The offset angle is calculated using the following formula: ， in, Represents the aircraft nose heading vector, in the assumed space coordinate system, , represents transpose, It means that the ground runway centerline vector is obtained by performing RANSAC linear fitting on the three-dimensional coordinate set of the ground runway centerline feature points. represents the offset angle, Represents a modulo operation.

8. The method for identifying an aircraft taxiing trajectory according to claim 1, characterized in that: The aircraft wheel set includes a nose wheel, a left main wheel and a right main wheel.

9. The method for identifying an aircraft taxiing trajectory according to claim 1, characterized in that: The offset distance is calculated using the following formula: ， ， ， in, is the offset distance, is the slope of the best straight line, The best straight line The coordinates of the interior points, and is the average value of the interior point coordinates, is the direction vector of the best straight line, are the coordinates of the center points of the left and right wheels, is any point in the three-dimensional coordinate set of the centerline feature points of the ground runway, Represents a modulo operation.

10. An aircraft taxiing trajectory recognition system, characterized in that: For implementing the method for identifying the aircraft taxiing trajectory according to any one of claims 1 to 9, the system comprises: A coordinate system conversion construction module is used to obtain the camera intrinsic parameters of the aircraft's onboard monocular camera and establish a conversion relationship between the camera coordinate system and the pixel coordinate system based on the camera intrinsic parameters; An image capture and correction module, including a camera disposed on the belly of the aircraft, for acquiring images captured by the camera of the aircraft and performing distortion correction processing; An image key point extraction module is used to extract the coordinates of the key points of the aircraft wheels and the key points of the center line of the ground runway in the pixel coordinate system based on the distortion-corrected image; A three-dimensional coordinate extraction module, for calculating the three-dimensional coordinates of the characteristic points of the aircraft wheel group and the ground runway centerline in the camera coordinate system by using the conversion relationship between the camera coordinate system and the pixel coordinate system based on the pre-acquired aircraft wheel group size information, the coordinates of the key points of the aircraft wheel group and the ground runway centerline, and the three-dimensional coordinates of the characteristic points of the aircraft wheel group and the ground runway centerline in the camera coordinate system; The offset information calculation module is used to fit the direction of the ground runway centerline based on the three-dimensional coordinates of the aircraft wheel group and the ground runway centerline, calculate the offset information of the aircraft relative to the ground runway centerline, and realize the aircraft taxiing trajectory identification.

Images