Method for positioning target on plane based on monocular vision

Abstract

The invention discloses a method for positioning a target on a plane based on monocular vision. The method comprises the following steps: determining related parameters of a shooting device on a target plane and an external parameter relationship between the shooting device and the target plane; calibrating the shooting device, determining an internal reference matrix and a distortion coefficient of the shooting device, and performing distortion correction on the internal reference of the shooting device; establishing a three-dimensional coordinate system on the target plane, shooting an image, establishing a pixel coordinate system on the image, and determining pixel coordinates of a target point; constructing a visual cone model of the shooting device, and calculating the coordinates of the target point in a target plane coordinate system according to the pixel coordinates of the target point, the related parameters and the external parameter relationship between the shooting device and the target plane; according to the coordinates of the target point in the target plane coordinate system, adjustment calculation is carried out through a linear interpolation method to obtain the final position coordinates of the target point in the target plane, and target positioning on the plane is completed.

Description

Technical Field

[0001] The invention belongs to the technical field of target positioning and ranging, and in particular relates to a method for positioning a target on a plane based on monocular vision. Background Art

[0002] With the continuous development of the field of artificial intelligence, machine vision ranging has also become an important means of accurately locating target objects in this field, and can obtain the three-dimensional coordinate information and scale information from the object to the camera. The existing visual ranging methods currently include monocular ranging and binocular ranging. In addition, the basic principles of some other visual ranging methods based on image recognition still come from monocular and binocular technology. However, the current visual ranging technology has the disadvantages of high requirements for the target object's test environment or complex calculation process and low measurement accuracy. At present, the monocular vision system generally uses the corresponding point calibration method to obtain the depth information of the image. The corresponding point calibration method refers to solving the conversion relationship of the coordinate system through the corresponding coordinates of the corresponding points in different coordinate systems. However, the corresponding point calibration method, due to equipment limitations during the calibration process, still cannot accurately record the corresponding coordinates of a point in the world coordinate system and the image coordinate system. If its coordinates are not accurate enough, the accuracy of the obtained transformation matrix will also be restricted, and the accuracy of the coordinate conversion result will fluctuate. Therefore, it is urgent to find a new visual positioning method that can provide positioning data more effectively and promote the development of visual positioning technology. Summary of the invention

[0003] In order to solve the above technical problems, the present invention proposes a target positioning method on a plane based on monocular vision. According to geometric deduction, a general formula for the transformation of image pixel coordinates and three-dimensional coordinates of the measured plane is obtained, and adjustment optimization is performed to improve the positioning accuracy and application breadth in practical engineering applications.

[0004] To achieve the above object, the present invention provides a method for locating a target on a plane based on monocular vision, comprising:

[0005] Determining relevant parameters of a photographing device and an external parameter relationship between the photographing device and the target plane on a target plane;

[0006] Calibrate the camera device, determine the internal parameter matrix and distortion coefficient of the camera device, and perform distortion correction on the internal parameters of the camera device;

[0007] Establishing a three-dimensional coordinate system on the target plane, capturing an image, establishing a pixel coordinate system on the image, and determining the pixel coordinates of the target point;

[0008] Constructing a frustum model of the shooting device, and calculating the coordinates of the target point in the target plane coordinate system according to the pixel coordinates of the target point, relevant parameters, and an external parameter relationship between the shooting device and the target plane;

[0009] According to the coordinates of the target point in the target plane coordinate system, the final position coordinates of the target point in the target plane are obtained by adjusting the linear interpolation method to complete the target positioning on the plane.

[0010] Optionally, the relevant parameters include: the height and width resolution of the shooting device, the field of view angles in the vertical and horizontal directions, and the coordinates of the principal point on the pixel plane.

[0011] Optionally, the external parameter relationship between the shooting device and the target plane includes: a height and a pitch angle of the shooting device from the plane.

[0012] Optionally, performing distortion correction on the internal parameters of the shooting device includes:

[0013]

[0014]

[0015] (r 2 =x 2 +y 2 )

[0016] The (x, y) on the right side of the equation is the ideal point in the obtained image. corrected ,y corrected ) is the actual point coordinate after distortion correction, d r is the radial distortion, {k1, k2, k3} are the radial distortion parameters, d t is the tangential distortion, {p1, p2} are the tangential distortion parameters, and r is the distance from the pixel to the center of the image.

[0017] Optionally, establishing a three-dimensional coordinate system on the target plane includes:

[0018] The projection point of the optical center on the target plane is taken as the origin, the projection of the optical axis on the target plane is the positive direction of the Y axis, the upward direction perpendicular to the target plane is the Z axis, the positive direction of the X axis is determined according to the right-hand rule, and the coordinate system of the target plane is established.

[0019] Optionally, establishing a pixel coordinate system on the image includes:

[0020] A pixel coordinate system is established with the upper left corner vertex of the image pixel plane as the origin, the horizontal rightward direction as the positive direction of the u axis, and the vertical downward direction as the positive direction of the v axis.

[0021] Optionally, calculating the coordinates of the target point in the target plane coordinate system includes:

[0022] For the target point on the target plane, the projection mapping relationship between the target point on the Y-axis of the target plane coordinate system and the projection mapping relationship on the Y-axis of the pixel coordinate system is calculated according to the imaging model in the Y-axis direction of the target plane; for the projection coordinates of the target point on the X-axis, the projection mapping relationship between the target point on the X-axis of the target plane coordinate system and the projection mapping relationship on the X-axis of the pixel coordinate system is calculated according to the imaging model in the u-axis direction; the coordinate of the target point on the Z-axis is a fixed value of 0.

[0023] Optionally, calculating and obtaining a mapping relationship between a projection of a target point on the Y axis of a target plane coordinate system and a projection mapping relationship of a target point on the Y axis of a pixel coordinate system includes:

[0024]

[0025] Y p =H·tan(γ0±α),

[0026] Among them, Y p is the Y-axis coordinate of the target point in the measured plane, v is the v-axis coordinate of the target point in the pixel coordinate system, α0 is the vertical field of view of the camera, h is the high resolution of the camera, H is the height of the optical center from the measured plane, γ0 is the top view of the camera, α is the angle between the projection of the target point on the Y-axis and the line connecting the optical center and the optical axis, and v0 is the v-axis coordinate of the principal point in the pixel coordinate system.

[0027] Optionally, calculating and obtaining a mapping relationship between a projection of a target point on an X-axis of a target plane coordinate system and a projection mapping relationship of a target point on an X-axis of a pixel coordinate system includes:

[0028]

[0029]

[0030] Among them, X p is the X-axis coordinate of the target point on the measured plane, u is the u-axis coordinate of the target point in the pixel coordinate system, u0 is the u-axis coordinate of the principal point in the pixel coordinate system, β0 is the horizontal field of view of the camera, w is the wide resolution of the camera, H is the height of the optical center from the measured plane, γ0 is the top view of the camera, β is the angle between the projection of the target point on the X-axis and the line connecting the optical center and the optical axis, and α is the angle between the projection of the target point on the Y-axis and the line connecting the optical center and the optical axis.

[0031] Optionally, obtaining the final position coordinates of the target point on the target plane by adjusting the linear interpolation method includes:

[0032] y=β0+β1X1+β2X2+β3D+β4X1 2 +β5X2 2 +β6D 2 +…+βn X1 a X2 b D c ,

[0033] Where y is the adjusted distance from the target point to the origin of the target plane, X is the X-axis coordinate of the target point, Y is the Y-axis coordinate of the target point, and D is the actual distance from the target point to the origin of the target plane; β0, β1, β2, β3, …, β n are the coefficients that need to be fitted by linear regression.

[0034] Technical effect of the present invention: The present invention discloses a method for locating a target on a plane based on monocular vision. Compared with other monocular ranging methods, it does not require other reference objects, nor does it require accurate calibration of corresponding points. The present invention derives through geometric relationships, and then obtains the conversion relationship between the measured plane coordinate system and the image coordinate system to achieve target positioning. The present invention is monocular positioning, and does not require binocular positioning. It only needs to calibrate the two cameras separately, and the calibration difficulty is greatly reduced. The present invention combines this method with the binocular method, and uses their respective advantages to improve the ranging accuracy. Different from the traditional binocular algorithm, which requires complex binocular positioning, this method is a facing binocular, using two cameras to perform monocular positioning respectively, and the two cameras are exposed at the same time. For objects in the measured plane within the field of view of the two cameras, their length and position information can be accurately measured. Although this algorithm is different from the traditional binocular algorithm, it supports this layout detection. The formula given by the present invention through a variety of modeling methods is a general formula for monocular positioning and binocular length measurement. When using monocular positioning, the point on the measured plane can be located; when using binocular length measurement, the distance between the two cameras is known, and the distance between the two ends of the bottom of the object and the cameras at each end is subtracted to get the binocular length measurement formula. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0036] Figure 1 A schematic diagram of a camera viewing cone and a measured plane according to an embodiment of the present invention;

[0037] Figure 2 A schematic diagram of an image plane taken by a camera according to an embodiment of the present invention;

[0038] Figure 3 A schematic diagram of geometric modeling of the projection of a target point on the Y-axis of a measured plane according to an embodiment of the present invention;

[0039] Figure 4 A schematic diagram of geometric modeling of the projection of a target point on the X-axis of a measured plane according to an embodiment of the present invention;

[0040] Figure 5 This is a schematic diagram of the principle of using a monocular camera to expand the length measurement to a binocular camera according to an embodiment of the present invention;

[0041] Figure 6 The figure is a flow chart of a method for locating a target on a plane based on monocular vision according to an embodiment of the present invention. DETAILED DESCRIPTION

[0042] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0043] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0044] The invention discloses a planar target positioning method based on monocular vision, comprising: building a monocular positioning device, so that a camera is fixed at a fixed height of a measured plane and maintains a certain tilt angle, and performing internal parameter distortion correction of the camera; establishing a three-dimensional coordinate system of the measured plane, respectively modeling the measured plane target in the measured plane coordinates and pixel coordinates in the X-axis and Y-axis directions, deriving a general formula for transforming pixel coordinates into measured plane coordinates, and calibrating parameters in the positioning formula; when shooting, controlling reasonable exposure, obtaining a clear image of the target on the measured plane, and determining any intersection point of the target and the measured plane in the image; substituting the coordinates of the obtained intersection point in the image coordinates into the calibrated general formula to calculate the position coordinates of the measured plane target in the measured plane; under the opposite binocular layout, two synchronous photos can be used to measure the length of objects in a common area.

[0045] First, build a monocular positioning device such as Figure 1 The monocular positioning device shown is as follows: build a monocular positioning device, obtain the camera principal point coordinates, focal length, distortion parameters and other parameters through Zhang Zhengyou calibration method, install the camera on the measured plane, maintain a certain tilt angle, so that it is at a fixed height, and input the collected picture information into the computer through the image acquisition card. Then process the collected pictures, use the target detection network YOLOV8 to detect the detection frame of the target to be measured, take the midpoint of the bottom edge of the target detection frame as the target point, determine the pixel coordinates of the midpoint of the bottom edge of the detection frame, and substitute it into the coordinate conversion formula to obtain the three-dimensional coordinates of the point on the measured plane.

[0046] This method mainly involves two coordinate systems. One is the coordinate system of the measured plane, with the projection point of the optical center on the measured plane as the origin of the coordinate system, the projection of the camera optical axis on the measured plane as the positive direction of the Y axis, the positive direction of the X axis is determined by the right-hand rule, and the direction perpendicular to the measured plane and pointing to the optical center is the positive direction of the Z axis; the other is the image pixel coordinate system with the upper left corner of the image as the origin, with the u axis horizontal to the right and the v axis horizontal downward.

[0047] Figure 1 is the camera frustum model and projection model. IXYZ, uav are the measured space coordinate system and image pixel coordinate system respectively, 0 is the camera origin, i.e. the position of the lens optical center, plane ABCD represents the measured plane, ABCD is the trapezoidal area captured by the camera, OF is the camera optical axis, point F is the intersection of the camera optical axis and the measured plane, and point I is the vertical projection of point O on the measured plane. The corresponding points of points A, B, C, and D in the image plane are as follows: Figure 2 As shown in the figure, a, b, c, d are the four endpoints of the image plane rectangle, h and w are the height and width resolution of the pixel respectively. f is the coordinate of the camera principal point, and the upper left corner of the image rectangle, point a, is defined as the origin of the image plane coordinate system, forming a two-dimensional coordinate system.

[0048] like Figure 6 As shown, this embodiment provides a method for locating a target on a plane based on monocular vision, including: determining relevant parameters of a shooting device and an external parameter relationship between the shooting device and the target plane on the target plane;

[0049] Calibrate the camera device, determine the internal parameter matrix and distortion coefficient of the camera device, and perform distortion correction on the internal parameters of the camera device;

[0050] Establishing a three-dimensional coordinate system on the target plane, capturing an image, establishing a pixel coordinate system on the image, and determining the pixel coordinates of the target point;

[0051] Constructing a frustum model of the shooting device, and calculating the coordinates of the target point in the target plane coordinate system according to the pixel coordinates of the target point, relevant parameters, and an external parameter relationship between the shooting device and the target plane;

[0052] According to the coordinates of the target point in the target plane coordinate system, the final position coordinates of the target point in the target plane are obtained by adjusting the linear interpolation method to complete the target positioning on the plane.

[0053] like Figure 1 As shown, the coordinate system of the measured plane is defined as follows:

[0054] Any lens has an optical center O and an optical axis passing through the optical center.

[0055] 1) Draw a line perpendicular to the measured plane through the optical center O, the intersection point is I, and the intersection point of the optical axis and the measured plane is G.

[0056] 2) Take point I as the origin and connect IG, which is the positive direction of the Y axis. According to the right-hand rule, the direction perpendicular to the Y axis is the positive direction of the X axis.

[0057] 3) The positive direction of the Z axis is perpendicular to the measured plane and upward.

[0058] like Figure 2 As shown, the image pixel coordinate system is defined as follows:

[0059] The image taken by the camera is a rectangle, whose area is the tangent plane between the camera's viewing cone and the measured plane.

[0060] 1) The pixel at the upper left of the image is the origin.

[0061] 2) Horizontally to the right is the positive direction of the u-axis, and vertically downward is the positive direction of the v-axis.

[0062] The method of geometric modeling is:

[0063] like Figure 1 As shown in the figure, plane ABCD represents the measured plane, ABCD is the trapezoidal area on the road plane captured by the camera, point O is the center point of the camera lens, OF is the optical axis of the camera, point F is the intersection of the optical axis of the camera and the measured plane, and point I is the vertical projection of point O on the road plane. In the measured plane coordinate system, the corresponding points of points A, B, C, and D in the image plane are as follows: Figure 2 As shown in the figure, a, b, c, d are the four endpoints of the image plane rectangle, h and w are the height and width resolutions of the image plane respectively. Take a point P on the measured plane, and its coordinates in the measured plane coordinate system are (X p , Y p , 0), the corresponding point of point P in the image plane is p, and its coordinates in the pixel coordinate system are (u, v). The corresponding relationship between the measured plane coordinates and the pixel coordinates can be derived using geometric relationships:

[0064] Furthermore, the relevant parameters include: the height and width resolution of the shooting device, the field of view angles in the vertical and horizontal directions, and the coordinates of the principal point on the pixel plane.

[0065] Furthermore, the external parameter relationship between the shooting device and the target plane includes: the height and pitch angle of the shooting device from the plane.

[0066] Furthermore, performing distortion correction on the internal parameters of the shooting device includes:

[0067]

[0068]

[0069] (r 2 =x 2 +y 2 )

[0070] The (x, y) on the right side of the equation is the ideal point in the obtained image. corrected ,y corrected ) is the actual point coordinate after distortion correction, d r is the radial distortion, {k1, k2, k3} are the radial distortion parameters, d t is the tangential distortion, {p1, p2} are the tangential distortion parameters, and r is the distance from the pixel to the center of the image.

[0071] The internal parameters of the two cameras, including the principal point (c x , c y ) and distortion parameters can be obtained through Zhang Zhengyou calibration method.

[0072] Furthermore, establishing a three-dimensional coordinate system on the target plane includes:

[0073] The projection point of the optical center on the target plane is taken as the origin, the projection of the optical axis on the target plane is the positive direction of the Y axis, the upward direction perpendicular to the target plane is the Z axis, the positive direction of the X axis is determined according to the right-hand rule, and the coordinate system of the target plane is established.

[0074] Furthermore, establishing a pixel coordinate system on the image includes:

[0075] A pixel coordinate system is established with the upper left corner vertex of the image pixel plane as the origin, the horizontal rightward direction as the positive direction of the u axis, and the vertical downward direction as the positive direction of the v axis.

[0076] Furthermore, the coordinates of the target point in the target plane coordinate system are calculated and obtained by:

[0077] For the target point on the target plane, the projection mapping relationship between the target point on the Y-axis of the target plane coordinate system and the projection mapping relationship on the Y-axis of the pixel coordinate system is calculated according to the imaging model in the Y-axis direction of the target plane; for the projection coordinates of the target point on the X-axis, the projection mapping relationship between the target point on the X-axis of the target plane coordinate system and the projection mapping relationship on the X-axis of the pixel coordinate system is calculated according to the imaging model in the u-axis direction; the coordinate of the target point on the Z-axis is a fixed value of 0.

[0078] Further, such as Figure 3 The calculated projection mapping relationship between the target point on the Y axis of the target plane coordinate system and the projection mapping relationship on the Y axis of the pixel coordinate system includes:

[0079]

[0080] Y p =H·tan(γ0±α),

[0081] Among them, Y p is the Y-axis coordinate of the target point in the measured plane, v is the v-axis coordinate of the target point in the pixel coordinate system, α0 is the vertical field of view of the camera, h is the high resolution of the camera, H is the height of the optical center from the measured plane, γ0 is the top view of the camera, α is the angle between the projection of the target point on the Y-axis and the line connecting the optical center and the optical axis, and v0 is the v-axis coordinate of the principal point in the pixel coordinate system.

[0082] Further, such as Figure 4 As shown, for the projection point of the target point on the X-axis of the measured plane coordinate system, its projection point on the image plane is p, the projection of point p on the x-axis of the image plane coordinate system and the optical center are connected, and the projection of point P on the X-axis of the measured plane coordinate system and the optical center are connected. The angle between the optical axis and the two projection points is β, and the angle β can be obtained according to the pixel coordinates of point p. The length of the intersection point G of the camera optical center O and the optical axis and the measured plane can be obtained by the height of the optical center from the measured plane and the camera pitch angle. The X-axis coordinate of point P is obtained according to the trigonometric function. The calculation of the projection mapping relationship between the target point on the X-axis of the target plane coordinate system and the projection on the X-axis of the pixel coordinate system includes:

[0083]

[0084]

[0085] Among them, X p is the X-axis coordinate of the target point on the measured plane, u is the u-axis coordinate of the target point in the pixel coordinate system, u0 is the u-axis coordinate of the principal point in the pixel coordinate system, β0 is the horizontal field of view of the camera, w is the wide resolution of the camera, H is the height of the optical center from the measured plane, γ0 is the top view of the camera, β is the angle between the projection of the target point on the X-axis and the line connecting the optical center and the optical axis, and α is the angle between the projection of the target point on the Y-axis and the line connecting the optical center and the optical axis.

[0086] Explanation: Why the relationship between the projection coordinates and the focal length is not used when calculating the angles α and β between the optical axis and the line connecting the projection of point p and the optical center: The present invention is based on the known field of view angle and pixel resolution of the lens in the horizontal and vertical directions. According to the linear relationship between the distance from the projection point of the target point on the axis to the principal point and the sine value of the angle α and β, the sine value of the angle can be calculated according to the ratio of the projection point to the height and width of the pixel plane. The use of this method is more accurate than the method in the question, because the main source of error of this method is the accuracy of the principal point coordinates (whether the principal point coordinates are located at the center of the image), and the camera focal length is not used, which can reduce the error to a certain extent. This is the innovation of the present invention. The specific explanation is: the parameters required for the derivation of the general formula in the implementation process of the invention are: the vertical height H of the camera optical center from the measured plane, the horizontal field of view angle β0 of the camera lens, the vertical field of view angle α0 of the camera lens, the top angle γ0 of the camera lens, the high resolution h of the image, and the wide resolution w of the image; the camera focal length F is not used.

[0087] Furthermore, the final position coordinates of the target point on the target plane are obtained by adjusting the linear interpolation method, including:

[0088] y=β0+β1X1+β2X2+β3D+β4X1 2 +β5X2 2 +β6D 2 +…+β n X1 a X2 b D c ,

[0089] Where y is the adjusted distance from the target point to the origin of the target plane, X is the X-axis coordinate of the target point, Y is the Y-axis coordinate of the target point, and D is the actual distance from the target point to the origin of the target plane; β0, β1, β2, β3, …, β n are the coefficients that need to be fitted by linear regression.

[0090] a, b, c represent different power combinations. The specific number of terms depends on the order d of the polynomial, that is:

[0091] max(a+b+c)=d

[0092] The goal of the model is to determine these regression coefficients β0, β1, β2, β3, …, β n , to minimize the predicted value The error between the true value y. Its objective function is:

[0093]

[0094] in, is the predicted true coordinate calculated based on the predicted coordinate and distance of the i-th sample, y (i) is the true coordinate of the ith sample.

[0095] Based on the above monocular vision planar target positioning method, monocular ranging can be achieved. On this basis, two cameras at fixed positions can be used to respectively calculate the distances between the two ends of the object and the two cameras, thereby measuring the length of the object.

[0096] The present invention discloses a method for locating a target on a plane based on monocular vision. Compared with other monocular ranging methods, no other reference objects are required, and no corresponding points need to be accurately calibrated. The present invention derives through geometric relationships, and then obtains the conversion relationship between the measured plane coordinate system and the image coordinate system to achieve target positioning. The present invention is monocular positioning, and there is no need to perform binocular positioning. It only needs to calibrate two cameras separately, and the calibration difficulty is greatly reduced. The present invention combines this method with the binocular method, and uses their respective advantages to improve the ranging accuracy. Different from the traditional binocular algorithm, complex binocular positioning is required. This method is a facing binocular, using two cameras to perform monocular positioning respectively, and the two cameras are exposed at the same time. For objects in the measured plane within the field of view of the two cameras, their length and position information can be accurately measured. Although this algorithm is different from the traditional binocular algorithm, it supports this layout detection. The formula given by the present invention through a variety of modeling methods is a general formula for monocular positioning and binocular length measurement. Figure 1 During monocular positioning, points on the measured plane can be located; Figure 5 When measuring length with binoculars, if the distance between the two cameras is known, subtract the distance between the two ends of the bottom of the object and the cameras at each end to get the binocular length measurement formula.

[0097] The above are only preferred specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for locating a target on a plane based on monocular vision, characterized in that: include: Determining relevant parameters of a photographing device and an external parameter relationship between the photographing device and the target plane on a target plane; Calibrate the camera device, determine the internal parameter matrix and distortion coefficient of the camera device, and perform distortion correction on the internal parameters of the camera device; Establishing a three-dimensional coordinate system on the target plane, capturing an image, establishing a pixel coordinate system on the image, and determining the pixel coordinates of the target point; Constructing a frustum model of the shooting device, and calculating the coordinates of the target point in the target plane coordinate system according to the pixel coordinates of the target point, relevant parameters, and an external parameter relationship between the shooting device and the target plane; According to the coordinates of the target point in the target plane coordinate system, the final position coordinates of the target point in the target plane are obtained by adjusting the linear interpolation method to complete the target positioning on the plane.

2. The method for locating a target on a plane based on monocular vision as claimed in claim 1, characterized in that: The related parameters include: the height and width resolution of the shooting device, the field of view angles in the vertical and horizontal directions, and the coordinates of the principal point on the pixel plane.

3. The method for locating a target on a plane based on monocular vision as claimed in claim 1, characterized in that: The external parameter relationship between the shooting device and the target plane includes: the height and pitch angle of the shooting device from the plane.

4. The method for locating a target on a plane based on monocular vision as claimed in claim 1, characterized in that: Performing distortion correction on the internal parameters of the shooting device includes: The (x, y) on the right side of the equation is the ideal point in the obtained image. corrected ,y corrected ) is the actual point coordinate after distortion correction, d r is the radial distortion, {k1, k2, k3} are the radial distortion parameters, d t is the tangential distortion, {p1, p2} are the tangential distortion parameters, and r is the distance from the pixel to the center of the image.

5. The method for locating a target on a plane based on monocular vision as claimed in claim 1, characterized in that: Establishing a three-dimensional coordinate system on the target plane includes: The projection point of the optical center on the target plane is taken as the origin, the projection of the optical axis on the target plane is the positive direction of the Y axis, the upward direction perpendicular to the target plane is the Z axis, the positive direction of the X axis is determined according to the right-hand rule, and the coordinate system of the target plane is established.

6. The method for locating a target on a plane based on monocular vision as claimed in claim 1, characterized in that: Establishing a pixel coordinate system on the image includes: A pixel coordinate system is established with the upper left corner vertex of the image pixel plane as the origin, the horizontal rightward direction as the positive direction of the u axis, and the vertical downward direction as the positive direction of the v axis.

7. The method for locating a target on a plane based on monocular vision as claimed in claim 1, characterized in that: Calculating the coordinates of the target point in the target plane coordinate system includes: For the target point on the target plane, the projection mapping relationship between the target point on the Y-axis of the target plane coordinate system and the projection mapping relationship on the Y-axis of the pixel coordinate system is calculated according to the imaging model in the Y-axis direction of the target plane; for the projection coordinates of the target point on the X-axis, the projection mapping relationship between the target point on the X-axis of the target plane coordinate system and the projection mapping relationship on the X-axis of the pixel coordinate system is calculated according to the imaging model in the u-axis direction; the coordinate of the target point on the Z-axis is a fixed value of 0.

8. The method for locating a target on a plane based on monocular vision as claimed in claim 1, characterized in that: The relationship between the projection of the target point on the Y axis of the target plane coordinate system and the projection mapping on the Y axis of the pixel coordinate system is calculated as follows: AND p =H·tan(γ0±α), Among them, Y p is the Y-axis coordinate of the target point on the measured plane, v is the v-axis coordinate of the target point in the pixel coordinate system, α0 is the vertical field of view of the camera, h is the high resolution of the camera, H is the height of the optical center from the measured plane, γ0 is the top view of the camera, α is the angle between the projection of the target point on the Y-axis and the line connecting the optical center and the optical axis, and v0 is the v-axis coordinate of the principal point in the pixel coordinate system.

9. The method for locating a target on a plane based on monocular vision as claimed in claim 1, characterized in that: The relationship between the projection of the target point on the X-axis of the target plane coordinate system and the projection mapping on the X-axis of the pixel coordinate system is calculated as follows: Among them, X p is the X-axis coordinate of the target point on the measured plane, u is the u-axis coordinate of the target point in the pixel coordinate system, u0 is the u-axis coordinate of the principal point in the pixel coordinate system, β0 is the horizontal field of view of the camera, w is the wide resolution of the camera, H is the height of the optical center from the measured plane, γ0 is the top view of the camera, β is the angle between the projection of the target point on the X-axis and the line connecting the optical center and the optical axis, and α is the angle between the projection of the target point on the Y-axis and the line connecting the optical center and the optical axis.

10. The method for locating a target on a plane based on monocular vision according to claim 1, characterized in that: The final position coordinates of the target point on the target plane obtained by adjusting the linear interpolation method include: y=β0+β1X1+β2X2+β3D+β4X1 2 +β5X2 2 +β6D 2 +…+b n X1 a X2 b D c , Where y is the adjusted distance from the target point to the origin of the target plane, X is the X-axis coordinate of the target point, Y is the Y-axis coordinate of the target point, and D is the actual distance from the target point to the origin of the target plane; β0, β1, β2, β3, ..., β n are the coefficients that need to be fitted by linear regression.

Images