Camera distortion point sorting method

Abstract

The invention discloses a camera distortion point sorting method, which comprises the following steps of: acquiring coordinates of distortion points in an image, and establishing a to-be-processed distortion point set; calculating the number of neighbors of the distortion points in the distortion point set to be processed; the distortion points with the neighbor number smaller than a preset number threshold value are determined as priority points, and a priority point set is established; calculating orientation scores of the priority ranking points; determining azimuth limit points according to the azimuth scores and the coordinates of the priority ranking points; calculating a center point coordinate based on the priority point set; calculating a limit coefficient according to the center point coordinate and the azimuth limit point coordinate; determining a top row point and a bottom row point based on the limit coefficient, and sorting the top row point and the bottom row point; and removing the top row points and the bottom row points from the to-be-processed distortion point set, carrying out iterative operation on the updated to-be-processed distortion point set, and determining a camera distortion point sequence. According to the method, the camera distortion points can be efficiently and accurately sequenced, and the camera calibration precision and reliability are improved.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and more specifically, to a camera distortion point sorting method. Background Art

[0002] Camera calibration is one of the core technologies in the field of machine vision and plays a vital role in many fields such as intelligent manufacturing and autonomous driving. Its basic principle is to identify the distorted image coordinates on the calibration pattern and correspond these coordinates to the known world coordinates, and then accurately solve the camera's internal and external parameter information based on the camera model. Before solving the camera's internal and external parameters, the identified camera distortion points must be accurately sorted to ensure that they can be one-to-one corresponded with the known world coordinates. However, in practical applications, due to the limitations of factors such as the calibration plate manufacturing accuracy, the image acquisition environment, and the performance of the camera itself, the calibration results often have certain errors, resulting in unsatisfactory distortion correction effects.

[0003] Therefore, the prior art has defects and is in urgent need of improvement. Summary of the invention

[0004] In view of the above problems, the purpose of the present invention is to provide a camera distortion point sorting method, which can efficiently and accurately sort the camera distortion points, thereby providing a solid foundation for subsequent camera calibration work and further improving the accuracy and reliability of camera calibration.

[0005] A first aspect of the present invention provides a camera distortion point sorting method, comprising: Obtain the coordinates of the distorted points in the image and establish a set of distorted points to be processed P; Calculate the distortion point P in the distortion point set P to be processed j The number of neighbors; The distorted points whose number of neighbors is less than the preset threshold are determined as the priority points M. i , establish a priority point set M; Calculate the priority point M i The orientation score s; According to the priority point M i The orientation score s and the coordinates are used to determine the orientation restriction points; the orientation restriction points include a first orientation restriction point, a second orientation restriction point, a third orientation restriction point and a fourth orientation restriction point; Calculate the coordinates of the center point based on the priority point set M; Calculate the restriction coefficients according to the coordinates of the center point and the coordinates of the azimuth restriction point; the restriction coefficients include a first restriction coefficient, a second restriction coefficient, a third restriction coefficient and a fourth restriction coefficient; Determine the top row point D from the prioritized point set M based on the restriction coefficient i and bottom row point Hi , for the top row point D i and bottom row point H i Sorting; From the set of distorted points to be processed P, the top row points D i and bottom row point H i Eliminate the points and iterate the updated set of distortion points to be processed P to determine the order of the camera distortion points.

[0006] In this solution, the calculation of the distortion point P in the set of distortion points to be processed P j The number of neighbors, including: The distortion point P j The upper left, upper right, lower left and lower right of are determined as traversal directions, and other distorted points in the set of distorted points to be processed P are traversed; When there are other distortion points in the traversal direction, the number of neighbors in the traversal direction is increased by one, and the traversal in the traversal direction is terminated; When the traversal is completed, count the number of neighbors in each traversal direction to determine the distortion point P j The number of neighbors.

[0007] In this solution, the calculation priority point M i The orientation score s includes: Calculate the priority point M i The Euclidean distance of other priority points in the priority point set M is used to determine the other priority points with the smallest Euclidean distance as the priority point M. i The first nearest neighbor point A is determined as the priority point M. i The second nearest neighbor point B; Calculate the priority point M based on the coordinates of the first nearest neighbor point A and the second nearest neighbor point B i The orientation score s; ; Among them, x i and i They are the priority points M i The x- and y-coordinates of A and A M i The x-coordinate and y-coordinate of the first nearest neighbor point A, y B and B M i The x-coordinate and y-coordinate of the second nearest neighbor point B.

[0008] In this solution, the priority order point M i The orientation score s and coordinates of the orientation restriction points are determined, including: Select the first four points with the smallest orientation scores from the priority point set M as candidate points; The x, y coordinates and the smallest candidate point are determined as the first orientation restriction point, and the x, y coordinates and the largest candidate point are determined as the fourth orientation restriction point; The candidate point with a larger x coordinate among the remaining candidate points is determined as the second orientation restriction point, and the candidate point with a smaller x coordinate among the remaining candidate points is determined as the third orientation restriction point.

[0009] In this solution, the calculation of the center point coordinates based on the priority sorting point set M includes: Calculate the center point coordinates (x c ,y c ); ; ; Among them, x max and x min are the maximum and minimum values ​​of the x coordinates in the priority sorting point set M, and y max and min are the maximum and minimum values ​​of the y coordinates in the priority sorting point set M, respectively.

[0010] In this solution, the calculation of the restriction coefficient according to the coordinates of the center point and the coordinates of the orientation restriction point includes: According to the center point coordinates (x c ,y c ), the first orientation limit point coordinates (x0, y0), the second orientation limit point coordinates (x1, y1), the third orientation limit point coordinates (x2, y2) and the fourth orientation limit point coordinates (x3, y3) calculate the first limit coefficient e0, the second limit coefficient e1, the third limit coefficient e2 and the fourth limit coefficient e3; ; ; ; .

[0011] In this solution, the top row point D is determined from the priority point set M based on the restriction coefficient. i and bottom row point H i ,include: According to the center point coordinates (x c ,y c ) Calculate the priority point M i The coordinates (x i ,y i ) is the limiting factor h i ; ; Compare the magnitudes of y i and y c ; When y i < y c , if both x1 < x i < x2 and e0 < h i < e1 are satisfied, then the priority sorting point M i is determined as the top row point D i , and the said top row point D i is added to the top row point set D; When y i > y c , if both x3 < x i < x4 and e2 < h i < e3 are satisfied, then the priority sorting point M i is determined as the bottom row point H i , and the said bottom row point H i is added to the bottom row point set H.

[0012] In this solution, the sorting of the said top row point D i and the bottom row point H i includes: Sort the top row points D within the top row point set D in ascending order of the x - coordinate; i ; Sort the bottom row points H within the bottom row point set H in ascending order of the x - coordinate. i The present invention discloses a method for sorting camera distortion points. The method includes: obtaining the coordinates of distortion points in an image and establishing a set of distortion points to be processed; calculating the number of neighbors of the distortion points in the set of distortion points to be processed; determining the distortion points with the number of neighbors less than a preset number threshold as priority sorting points and establishing a set of priority sorting points; calculating the azimuth scores of the priority sorting points; determining azimuth limit points based on the azimuth scores and coordinates of the priority sorting points; calculating the center point coordinates based on the set of priority sorting points; calculating the limit coefficient based on the center point coordinates and the coordinates of the azimuth limit points; determining the top row points and the bottom row points based on the limit coefficient, sorting the top row points and the bottom row points; removing the top row points and the bottom row points from the set of distortion points to be processed, and performing iterative operations on the updated set of distortion points to be processed to determine the sorting of camera distortion points. The present invention can efficiently and accurately sort camera distortion points, improving the accuracy and reliability of camera calibration. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 Shows a flowchart of a method for sorting camera distortion points provided by the present invention; Figure 2 Shows the distortion point P provided by the present invention​j A flowchart of a method for determining the number of neighbors; Figure 3 A flow chart showing a method for determining an orientation restriction point provided by the present invention is shown; Figure 4 A schematic diagram of the distribution of distortion points provided by the present invention is shown; Figure 5 A schematic diagram of the distortion point sorting result provided by the present invention is shown. DETAILED DESCRIPTION

[0014] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0015] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0016] Figure 1 A flow chart of a camera distortion point sorting method provided by the present invention is shown.

[0017] like Figure 1 As shown, the present invention discloses a camera distortion point sorting method, comprising: S102, obtaining coordinates of distortion points in the image and establishing a set P of distortion points to be processed; S104, calculating the distortion point P in the distortion point set P to be processed j The number of neighbors; S106: Determine the distortion point whose number of neighbors is less than the preset number threshold as the priority sorting point M. i , establish a priority point set M; S108, calculate the priority point M i The orientation score s; S110, according to the priority sorting point M i The orientation score s and the coordinates determine the orientation restriction points; the orientation restriction points include a first orientation restriction point, a second orientation restriction point, a third orientation restriction point and a fourth orientation restriction point; S112, calculating the coordinates of the center point based on the priority sorting point set M; S114, calculating restriction coefficients according to the coordinates of the center point and the coordinates of the azimuth restriction point; the restriction coefficients include a first restriction coefficient, a second restriction coefficient, a third restriction coefficient and a fourth restriction coefficient; S116, determine the top row point D from the priority point set M based on the restriction coefficienti and the bottom row point H i , for the top row point D i and the bottom row point H i sort; S118, from the set P of distortion points to be processed, for the top row point D i and the bottom row point H i perform elimination, perform iterative operations on the updated set P of distortion points to be processed, and determine the sorting of camera distortion points.

[0018] According to the embodiments of the present invention, obtain the coordinates of the distortion points in the input image. The corresponding distortion points in the image are distributed in n rows and m columns in the world coordinate system. The distortion points can be checkerboard corner points or other calibration feature points. Among them, the upper left corner coordinates of the input image can be determined as the coordinate origin, the positive X-axis direction is to the right, and the positive Y-axis direction is downward to establish a coordinate system. The distortion point coordinates of each distortion point are determined through the established coordinate system. Organize the distortion point coordinates of the distortion points in the image to establish a set P of distortion points to be processed. As Figure 4 shown, it is a schematic diagram of the distribution of distortion points with 9 rows and 15 columns, and the cyan points are distortion points.

[0019] Traverse the other distortion points in the set P of distortion points to be processed according to the pre-determined traversal direction, determine the number of neighbors of each distortion point in the set P of distortion points to be processed, and screen out the priority sorting points according to the number of neighbors of each distortion point. For each distortion point, if the number of neighbors of this point is less than the preset number threshold, then this point is classified as a priority sorting point, and this point is added to the set M of priority sorting points. Among them, the preset number threshold is set by the system, and its initial value is 4. For the priority sorting point M in the set M of priority sorting points i (i < k1, k1 is the size of the set M), calculate the Euclidean distance between the priority sorting point M i and other priority sorting points, and respectively determine the first nearest neighbor point A and the second nearest neighbor point B of the priority sorting point M i and calculate the azimuth score of the priority sorting point M i Select the top four points with the smallest azimuth scores from the set M of priority sorting points as candidate points, determine the azimuth limit points in combination with the coordinates of the candidate points, calculate the center point coordinates, and determine the corresponding limit coefficients of each azimuth limit point. According to the priority sorting point M iThe limiting coefficient of the coordinates, determine the top row points and the bottom row points from the set of prioritized points, establish the top row point set D and the bottom row point set H, and sort the points within the top row point set D and the bottom row point set H respectively in ascending order of the x coordinate. That is, complete the sorting of the distortion points in the current top row and bottom row. At the same time, remove the distortion points belonging to the top row and bottom row from the set P of distortion points to be processed, determine the updated set P of distortion points to be processed, and continue the above operations until all distortion points are sorted. As Figure 5 shown, it is the visualization effect after all distortion points are sorted. Among them, the numbers are the sorting serial numbers of the distortion points.

[0020] Figure 2 shows the distortion point P provided by the present invention j flowchart of the method for determining the number of neighbors.

[0021] As Figure 2 shown, according to the embodiment of the present invention, calculating the number of neighbors of the distortion point P in the set P of distortion points to be processed includes: j S202, determine the upper left, upper right, lower left, and lower right of the distortion point P as the traversal directions, and traverse other distortion points in the set P of distortion points to be processed; j S204, when there are other distortion points in the traversal direction, increment the number of neighbors in the traversal direction by one, and end the traversal of the traversal direction; S206, after the traversal ends, count the number of neighbors in each traversal direction to determine the number of neighbors of the distortion point P j j of the distortion point P

[0022] It should be noted that for the j-th point P j in the set P of distortion points to be processed (j < k0, where k0 is the size of the set P of distortion points to be processed), determine whether there are other distortion points in each traversal direction in turn according to the traversal directions of the upper left, upper right, lower left, and lower right. For example, if there are other distortion points above the upper left of the distortion point P j j j j j j j j

[0023] Among them, the upper left, upper right, lower left, and lower right are the preset traversal directions by the system, and those skilled in the art can set and adjust the traversal directions according to actual needs.

[0024] Calculate the priority sorting point M i The azimuth score s includes: Calculate the Euclidean distance between the priority sorting point M i and other priority sorting points in the priority sorting point set M, and determine the other priority sorting point with the smallest Euclidean distance as the first nearest neighbor point A of the priority sorting point M i and determine the other priority sorting point with the second smallest Euclidean distance as the second nearest neighbor point B of the priority sorting point M i ; Calculate the azimuth score s of the priority sorting point M i according to the coordinates of the first nearest neighbor point A and the second nearest neighbor point B; ; where x i and y i are the x-coordinate and y-coordinate of the priority sorting point M i respectively, x A and y A are the x-coordinate and y-coordinate of the first nearest neighbor point A of M i respectively, and y B and y B are the x-coordinate and y-coordinate of the second nearest neighbor point B of M i respectively.

[0025] It should be noted that for the priority sorting point M in the priority sorting point set M i (i < k1, where k1 is the size of the set M), input the coordinates of the priority sorting point M i and other priority sorting points into the Euclidean distance calculation formula to determine the Euclidean distance between the priority sorting point M i and each other priority sorting point, and respectively determine the other priority sorting points with the smallest and second smallest Euclidean distances as the first nearest neighbor point A and the second nearest neighbor point B. Then input the coordinates of the priority sorting point M i , the coordinates of the corresponding first nearest neighbor point A, and the coordinates of the corresponding second nearest neighbor point B into the azimuth score calculation formula preset in the system to determine the azimuth score s of the priority sorting point M i .

[0026] Traverse the entire priority sorting point set M to complete the calculation of the first nearest neighbor point, the second nearest neighbor point, and the azimuth score of all priority sorting points.

[0027] Figure 3 shows the flowchart of the azimuth limit point determination method provided by the present invention.

[0028] As Figure 3 shown, according to the embodiments of the present invention, according to the priority sorting point M iThe orientation score s and coordinates of the orientation restriction points are determined, including: S302, selecting the first four points with the smallest orientation scores from the priority point set M as candidate points; S304, determining the x, y coordinates and the smallest candidate point as the first orientation restriction point, and determining the x, y coordinates and the largest candidate point as the fourth orientation restriction point; S306: Determine the candidate point with a larger x coordinate among the remaining candidate points as the second orientation restriction point, and determine the candidate point with a smaller x coordinate among the remaining candidate points as the third orientation restriction point.

[0029] It should be noted that the x and y coordinates of the candidate point are obtained by adding the x coordinate value and the y coordinate value of the candidate point.

[0030] According to an embodiment of the present invention, calculating the coordinates of the center point based on the priority sorting point set M includes: Calculate the center point coordinates (x c ,y c ); ; ; Among them, x max and x min are the maximum and minimum values ​​of the x coordinates in the priority sorting point set M, and y max and min are the maximum and minimum values ​​of the y coordinates in the priority sorting point set M, respectively.

[0031] It should be noted that, each priority point M in the priority point set M is sequentially i Traverse and sort points M according to priority i The coordinates (x i ,y i ) respectively determine the maximum and minimum values ​​of the x-coordinate and the maximum and minimum values ​​of the y-coordinate in the priority point set M.

[0032] According to an embodiment of the present invention, calculating the restriction coefficient according to the coordinates of the center point and the coordinates of the orientation restriction point includes: According to the center point coordinates (x c ,y c ), the first orientation limit point coordinates (x0, y0), the second orientation limit point coordinates (x1, y1), the third orientation limit point coordinates (x2, y2) and the fourth orientation limit point coordinates (x3, y3) calculate the first limit coefficient e0, the second limit coefficient e1, the third limit coefficient e2 and the fourth limit coefficient e3; ; ; ; 。

[0033] It should be noted that each azimuth limit point corresponds to a unique limit coefficient, and the limit coefficient is obtained by calculating the ratio of the difference in the y-coordinate and the difference in the x-coordinate between the central coordinate point and the corresponding azimuth limit point.

[0034] According to the embodiment of the present invention, the top row point D i and the bottom row point H i are determined from the set of prioritized points M based on the limit coefficient, including: Calculating the limit factor h c of the coordinate (x c ) of the prioritized point M i according to the central point coordinates (x i , y i ); i ; ; Comparing the magnitude relationship between y i and y c ; When y i < y c , if x1 < x i < x2 and e0 < h i < e1 are satisfied simultaneously, then the prioritized point M i is determined as the top row point D i , and the top row point D i is added to the top row point set D; When y i > y c , if x3 < x i < x4 and e2 < h i < e3 are satisfied simultaneously, then the prioritized point M i is determined as the bottom row point H i , and the bottom row point H i is added to the bottom row point set H.

[0035] It should be noted that first, based on the coordinate information (including the central point coordinates and the prioritized point coordinates) and the limit coefficients (including the first limit coefficient, the second limit coefficient, the third limit coefficient, and the fourth limit coefficient), the top row sorting point and the bottom row sorting point are determined from the set of prioritized points. Traverse the set of prioritized points M. For the prioritized point M i in M, by calculating the ratio of the difference in the y-coordinate and the difference in the x-coordinate between the central coordinate point and the prioritized point M i , the limit factor h of the prioritized point M i is determined. For the prioritized point Mi The y coordinate of i and the y coordinate of the center point c For size comparison, when y i <y c When the top row sorting point is determined, if the priority sorting point M i The x-coordinate x i The coordinate size of the first orientation limit point and the second orientation limit point (i.e. x1<x i <x2), and at the same time satisfying e0<h<e1, then the priority point M i Determine the top row point D i , and add it to the top row point set D; otherwise, prioritize point M i Not the top row point. When y i >y c When the bottom row sorting point is determined, if the priority sorting point M i The x-coordinate x i The coordinate size is between the third position limit point and the fourth position limit point (i.e. x3<x i <x4), and at the same time satisfying e2<h<e3, then the priority point M i Determine the bottom row point H i , and add it to the bottom row point set H.

[0036] According to an embodiment of the present invention, for the top row point D i and bottom row point H i Sorting, including: According to the x coordinate from small to large, the top row point D in the top row point set D i Sort by According to the x coordinate from small to large, the bottom row point H in the bottom row point set H i Sort.

[0037] It should be noted that the top row point set D and the bottom row point set H are further sorted in the order from small to large x coordinates to determine the sorting order of the distortion points in the top row and the bottom row.

[0038] The information (including but not limited to user device information, user personal information, etc.), data (including but not limited to data used for analysis, stored data, displayed data, etc.) and signals (including but not limited to signals transmitted between user terminals and other devices, etc.) involved in this application are all authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions. For example, the "coordinates of distortion points in the image" involved in this disclosure are all obtained with full authorization.

[0039] The present invention discloses a method for sorting camera distortion points, the method comprising: obtaining the coordinates of distortion points in an image, establishing a set of distortion points to be processed; calculating the number of neighbors of the distortion points in the set of distortion points to be processed; determining distortion points whose number of neighbors is less than a preset number threshold as priority sorting points, and establishing a set of priority sorting points; calculating the orientation score of the priority sorting point; determining the orientation restriction point according to the orientation score and coordinates of the priority sorting point; calculating the coordinates of the center point based on the set of priority sorting points; calculating the restriction coefficient according to the coordinates of the center point and the coordinates of the orientation restriction point; determining the top row points and the bottom row points based on the restriction coefficient, and sorting the top row points and the bottom row points; removing the top row points and the bottom row points from the set of distortion points to be processed, iterating the updated set of distortion points to be processed, and determining the camera distortion point sorting. The present invention can efficiently and accurately sort camera distortion points, and improve the accuracy and reliability of camera calibration.

[0040] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0041] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0042] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0043] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0044] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

Claims

1. A camera distortion point sorting method, characterized in that: include: Obtain the coordinates of the distorted points in the image and establish a set of distorted points to be processed P; Calculate the distortion point P in the distortion point set P to be processed j The number of neighbors; The distorted points whose number of neighbors is less than the preset threshold are determined as the priority points M. i , establish a priority point set M; Calculate the priority point M i The orientation score s; According to the priority point M i The orientation score s and coordinates determine the orientation restriction point; The orientation restriction points include a first orientation restriction point, a second orientation restriction point, a third orientation restriction point and a fourth orientation restriction point; Calculate the coordinates of the center point based on the priority point set M; Calculate the restriction coefficients according to the coordinates of the center point and the coordinates of the azimuth restriction point; the restriction coefficients include a first restriction coefficient, a second restriction coefficient, a third restriction coefficient and a fourth restriction coefficient; Determine the top row point D from the prioritized point set M based on the restriction coefficient i and bottom row point H i , for the top row point D i and bottom row point H i Sorting; From the set of distorted points to be processed P, the top row points D i and bottom row point H i Eliminate the points and iterate the updated set of distortion points to be processed P to determine the order of the camera distortion points.

2. The camera distortion point sorting method according to claim 1, characterized in that: The calculation of the distortion point P in the distortion point set P to be processed j The number of neighbors, including: The distortion point P j The upper left, upper right, lower left and lower right of are determined as traversal directions, and other distorted points in the set of distorted points to be processed P are traversed; When there are other distortion points in the traversal direction, the number of neighbors in the traversal direction is increased by one, and the traversal in the traversal direction is terminated; When the traversal is completed, count the number of neighbors in each traversal direction to determine the distortion point P j The number of neighbors.

3. The camera distortion point sorting method according to claim 1, characterized in that: The calculation priority point M i The orientation score s includes: Calculate the priority point M i The Euclidean distance of other priority points in the priority point set M is used to determine the other priority points with the smallest Euclidean distance as the priority point M. i The first nearest neighbor point A is determined as the priority point M. i The second nearest neighbor point B; Calculate the priority point M based on the coordinates of the first nearest neighbor point A and the second nearest neighbor point B i The orientation score s; ； Among them, x i and i They are the priority points M i The x- and y-coordinates of A and A M i The x-coordinate and y-coordinate of the first nearest neighbor point A, y B and B M i The x-coordinate and y-coordinate of the second nearest neighbor point B.

4. The camera distortion point sorting method according to claim 1, characterized in that: The priority order point M i The orientation score s and coordinates of the orientation restriction points are determined, including: Select the first four points with the smallest orientation scores from the priority point set M as candidate points; The x, y coordinates and the smallest candidate point are determined as the first orientation restriction point, and the x, y coordinates and the largest candidate point are determined as the fourth orientation restriction point; The candidate point with a larger x coordinate among the remaining candidate points is determined as the second orientation restriction point, and the candidate point with a smaller x coordinate among the remaining candidate points is determined as the third orientation restriction point.

5. The camera distortion point sorting method according to claim 1, characterized in that: The calculating of the center point coordinates based on the priority sorted point set M includes: Calculate the center point coordinates (x c ,y c ); ； ； Among them, x max and x min are the maximum and minimum values ​​of the x coordinates in the priority sorting point set M, and y max and min are the maximum and minimum values ​​of the y coordinates in the priority sorting point set M, respectively.

6. The camera distortion point sorting method according to claim 1, characterized in that: The calculating of the restriction coefficient according to the coordinates of the center point and the coordinates of the orientation restriction point includes: According to the center point coordinates (x c ,y c ), the first orientation limit point coordinates (x0, y0), the second orientation limit point coordinates (x1, y1), the third orientation limit point coordinates (x2, y2) and the fourth orientation limit point coordinates (x3, y3) calculate the first limit coefficient e0, the second limit coefficient e1, the third limit coefficient e2 and the fourth limit coefficient e3; ; ； ； 。 7. The camera distortion point sorting method according to claim 1, characterized in that: The top row point D is determined from the priority point set M based on the restriction coefficient. i and bottom row point H i ,include: According to the center point coordinates (x c ,y c ) Calculate the priority point M i The coordinates (x i ,y i ) is the limiting factor h i ; ； Compare i and c The size relationship of When y i <y c When, if x1 < x i <x2 and e0 < h i <e1 are satisfied simultaneously, the priority sorting point M i will be determined as the top row point D i and the top row point D i will be added to the top row point set D; When y i > y c If at the same time x3 < x i < x4 and e2 < h i < e3, then the priority sorting point M i Is determined as the bottom row point H i And the bottom row point H i Is added to the bottom row point set H 8. The camera distortion point sorting method according to claim 7, characterized in that: The top row of points D i and bottom row point H i Sorting, including: According to the x coordinate from small to large, the top row point D in the top row point set D i Sort by According to the x coordinate from small to large, the bottom row point H in the bottom row point set H i Sort.

Images