A method, device and system for measuring planar area based on machine vision

Abstract

The present invention discloses a method, device and system for measuring the planar area based on machine vision. The method includes: acquiring an image of an object to be measured collected under camera parameters; performing preprocessing of distortion correction on the image of the object to be measured and then intercepting a rectangular region image including the complete object to be measured; converting the pixel coordinates of the rectangular region image into world coordinates according to the conversion relationship between the pixel coordinate system and the world coordinate system; calculating the area of the rectangular region image according to the world coordinates; performing perspective transformation on the rectangular region image to obtain a top view image of the object to be measured; performing color-based K-means clustering on the top view image to segment the top view image into the object to be measured region, the background region and the blank region after perspective transformation; calculating the proportion of the object to be measured region; and calculating the area of the object to be measured according to the proportion of the object to be measured region and the area of the rectangular region image. The non-contact automatic measurement of planar objects is realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of machine vision image measurement, and relates to a method, device and system for measuring the planar area based on machine vision. Background Art

[0002] Machine vision has the characteristics of being easy to obtain a large amount of information, being easy to integrate with the digital design information of products and the feedback information of the processing control system to form a closed-loop control of the product production process, and is widely used in modern production fields. With the development of machine vision, how to apply vision measurement technology to achieve online measurement and non-contact measurement has attracted wide attention. Summary of the Invention

[0003] Objective: In order to overcome the deficiencies in the prior art, the present invention provides a method, device and system for measuring the planar area based on machine vision, so as to achieve non-contact area measurement of planar objects.

[0004] The present invention relates to technologies related to machine vision and image processing, mainly including camera calibration, image undistortion, perspective transformation, image segmentation, etc. For three-dimensional reconstruction to restore the world coordinate system, the accuracy of camera calibration and the rationality of constructing the conversion formula from the pixel coordinate system to the world coordinate system are particularly important.

[0005] First, build a measurement system and adjust the camera to a suitable position; then collect checkerboard images to calibrate the monocular camera, obtain camera parameters, and perform preprocessing such as distortion correction on the planar object image; at the same time, restore the image coordinates to world coordinates according to the transformation relationship between the pixel coordinate system and the world coordinate system, and calculate the planar area in the world coordinate system; use perspective transformation to project the image into a top view image, perform image segmentation, calculate the proportion occupied by the object to be measured, and complete the area measurement of the planar object.

[0006] Technical Solution: To solve the above technical problems, the technical solution adopted by the present invention is as follows:

[0007] In a first aspect, a method for measuring the planar area based on machine vision is provided, including:

[0008] Obtain camera parameters and the image of the object to be measured collected under the camera parameters, wherein the image of the object to be measured is taken by a monocular camera, and the camera parameters are obtained by calibrating the monocular camera, including the internal parameters and distortion parameters of the camera;

[0009] Perform preprocessing of distortion correction on the image of the object to be measured;

[0010] Intercept a rectangular region image including the complete object to be measured on the preprocessed image of the object to be measured;

[0011] According to the conversion relationship between the pixel coordinate system and the world coordinate system, combined with the camera parameters, convert the pixel coordinates of the rectangular region image into world coordinates; calculate the area of the rectangular region image based on the world coordinates;

[0012] Perform perspective transformation on the rectangular region image to obtain a top-down view image of the object to be measured;

[0013] Perform color-based K-means clustering on the top-down view image to segment the top-down view image into the object region to be measured, the background region, and the blank region after perspective transformation; calculate the proportion of the object region to be measured;

[0014] Calculate the area of the object to be measured based on the proportion of the object region to be measured and the area of the rectangular region image.

[0015] In some embodiments, obtaining camera parameters includes: installing the measurement system, adjusting the focal length of the monocular camera so that the camera can clearly capture the object to be measured, then collecting calibration board images and transmitting them to a computer for monocular camera calibration to obtain camera parameters.

[0016] Further, the method for monocular camera calibration includes:

[0017] Step 1.1: Fix the monocular camera, adjust the focal length of the monocular camera, place a checkerboard on the workbench; change the placement position of the checkerboard and use the monocular camera to take multiple pictures to obtain multiple images;

[0018] Step 1.2: Perform camera calibration in MATLAB: Use the function detectCheckerboardPoints() to detect and identify the corner coordinates of the checkerboard in each image, and store the corner coordinates of all images in the variable i_Points; generate the world coordinates of the checkerboard corners in the coordinate system centered on the checkerboard pattern through the function generateCheckerboardPoints(), and make the upper left corner coordinates be (0, 0, 0), and also store the world coordinates of all images in the variable w_Points; finally, input the variables i_Points and w_Points into the calibration function estimateCameraParameters() to calibrate and obtain the monocular camera parameter variable camera_Params.

[0019] In some embodiments, the distortion correction preprocessing includes:

[0020] Perform it through the function undistortImage() in MATLAB; input the camera internal parameters and distortion parameters, correct the initial image edge, and output the image after distortion correction.

[0021] In some embodiments, performing a perspective transformation on the rectangular region image to obtain a top view image of the object to be measured, including:

[0022] There are 4 basic coordinate pairs between the top view image of the object to be measured and the rectangular region image. Solving for the mapping matrix, the projection transformation relationship between a pair of pixel coordinates in the top view image of the object to be measured and the rectangular region image is:

[0023]

[0024] Among them, the projection transformation matrix contains 8 unknowns: a0, a1... a7; (M0, N0) is the pixel coordinate point in the rectangular region image; (M′0, N′0) is the pixel coordinate point in the top view image; constructing the following equations through 4 sets of coordinate pairs:

[0025]

[0026] Among them, (M0, N0), (M1, N1), (M2, N2), (M3, N3) are 4 sets of pixel coordinate points in the rectangular region image; (M′0, N′0), (M′1, N′1), (M′2, N′2), (M′3, N′3) are the corresponding 4 sets of pixel coordinate points in the top view image.

[0027] In some embodiments, according to the conversion relationship between the pixel coordinate system and the world coordinate system, and in combination with the camera parameters, converting the pixel coordinates of the rectangular region image into world coordinates, including:

[0028] The conversion formula for a point from the pixel coordinate system to the world coordinate system is:

[0029]

[0030] Among them, the point in the world coordinate system is (X W , Y W , Z W ), the point in the pixel coordinate system is (u, v), Z C is the projection value of the target point camera coordinate system in the Z-axis direction, K is the internal parameter matrix of the camera, R is the rotation matrix, and T is the translation vector.

[0031] In some embodiments, calculating the area of the rectangular region image according to the world coordinates, including:

[0032] Among them, S C is the area of the rectangular region image, and the world coordinates of the 4 vertices of the rectangular region image are respectively denoted as (X1, Y1), (X2, Y2), (X3, Y3), (X4, Y4).

[0033] In some embodiments, performing color-based K-means clustering on the top-down image includes: establishing a three-dimensional rectangular coordinate system with the RGB three channels of the color image as the x-y-z axes, and aggregating the classes with the same color in the image into one class to achieve color-based image segmentation.

[0034] In some embodiments, calculating the area of the object to be measured according to the proportion of the area occupied by the object to be measured and the area of the rectangular region image includes:

[0035] S = R * S C

[0036] Where S is the area of the object to be measured, R is the proportion of the area occupied by the object to be measured, and S C is the area of the rectangular region image.

[0037] In a second aspect, the present invention provides a planar area measurement device based on machine vision, including a processor and a storage medium;

[0038] The storage medium is used to store instructions;

[0039] The processor is configured to operate according to the instructions to execute the steps of the method according to the first aspect.

[0040] In a third aspect, the present invention provides a planar area measurement system based on machine vision, including a monocular camera and the planar area measurement device based on machine vision according to the second aspect;

[0041] The monocular camera is configured to: collect an image and upload it to the planar area measurement device based on machine vision.

[0042] Beneficial effects: The planar area measurement method, device, and system based on machine vision provided by the present invention have the following advantages:

[0043] The present invention fully considers the problems of existing planar area measurement devices that mostly use infrared scanning for measurement, such as insufficient portability and high cost. The proposed planar area measurement system and method based on machine vision can accurately and efficiently measure the area of the object to be measured through methods such as monocular camera calibration, image de-distortion, perspective transformation, and image segmentation. The present invention effectively reduces costs and has a high degree of automation, with high market application value. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a schematic diagram of the measurement system setup in the embodiment of the present invention;

[0045] Figure 2 It is a schematic flow diagram of the measurement method in the embodiment of the present invention;

[0046] Figure 3This is the checkerboard calibration board in the embodiments of the present invention;

[0047] Figure 4 This is the relationship diagram of each coordinate system in the embodiments of the present invention. Specific embodiments

[0048] The present invention will be further described below with reference to the drawings and embodiments. The following embodiments are only used to more clearly illustrate the technical solutions of the present invention and cannot be used to limit the protection scope of the present invention.

[0049] In the description of the present invention, the meaning of several is more than one, the meaning of multiple is more than two, and understandings such as greater than, less than, exceeding, etc. do not include the present number, and understandings such as above, below, within, etc. include the present number. If it is described as first and second, it is only for the purpose of distinguishing technical features and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features or implicitly indicating the sequence relationship of the indicated technical features.

[0050] In the description of the present invention, the description of reference terms such as "one embodiment", "some embodiments", "schematic embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0051] Embodiment 1

[0052] A method for measuring the planar area based on machine vision, comprising:

[0053] Obtain the camera parameters and the image of the object to be measured collected under the camera parameters, wherein the image of the object to be measured is taken by a monocular camera, and the camera parameters are obtained by calibrating the monocular camera, including the internal parameters and distortion parameters of the camera;

[0054] Perform preprocessing of distortion correction on the image of the object to be measured;

[0055] Intercept a rectangular area image including the complete object to be measured on the preprocessed image of the object to be measured;

[0056] According to the conversion relationship between the pixel coordinate system and the world coordinate system, and in combination with the camera parameters, convert the pixel coordinates of the rectangular area image into world coordinates; calculate the area of the rectangular area image according to the world coordinates;

[0057] Perform perspective transformation on the rectangular area image to obtain a top view image of the object to be measured;

[0058] Perform color - based K - means clustering on the top - down image, and segment the top - down image into the area of the object to be measured, the background area, and the blank area after perspective transformation; calculate the proportion of the area of the object to be measured;

[0059] Calculate the area of the object to be measured according to the proportion of the area of the object to be measured and the area of the rectangular region image.

[0060] In some embodiments, as Figure 1 shown, a schematic diagram of building a planar area measurement system based on machine vision provided by an embodiment of the present invention is used to build the measurement system. The measurement system includes a fixed - focus monocular camera, an industrial computer equipped with a Windows operating system, and a camera bracket; the camera bracket is fixed on the operating table; the monocular camera is installed on the bracket in a clamped - fixed manner and is connected to the computer through a USB2.0 standard interface. The computer includes a processor and a storage medium;

[0061] The storage medium is used to store instructions;

[0062] The processor is used to operate according to the instructions to execute the steps of the method described in Embodiment 1.

[0063] Please refer to Figure 2 , a schematic flowchart of a planar area measurement system and method based on machine vision provided by an embodiment of the present invention, which includes the following steps:

[0064] Step 1: First, install the measurement system, adjust the focal length of the monocular camera so that the camera can clearly capture the object to be measured, then collect the calibration board images, transmit them to the computer for monocular camera calibration, and obtain the camera parameters;

[0065] The specific steps of monocular camera calibration are as follows:

[0066] Step 1.1: Fix the monocular camera, place a checkerboard on the workbench. Here, the checkerboard specifications are 12 * 9, and the side length of each grid is 15 mm; change the placement position of the checkerboard and use the monocular camera to take multiple shots. Here, 12 images are taken.

[0067] Step 1.2: Perform camera calibration in MATLAB. Use the function detectCheckerboardPoints() to detect and identify the coordinates of the corner points of the checkerboard in each image. The coordinates of the corner points of all images are stored in the variable i_Points. Use the function generateCheckerboardPoints() to generate the world coordinates of the checkerboard corner points in a coordinate system centered on the checkerboard pattern, and make the coordinates of the upper left corner (0,0,0). Similarly, the world coordinates of all images are stored in the variable w_Points. Finally, input the variables i_Points and w_Points in the calibration function estimateCameraParameters() to calibrate the monocular camera parameter variable camera_Params, which includes the camera's intrinsic distortion parameters.

[0068] Step 2: As in step 1, the monocular camera is fixed in position and the image of the object to be measured is collected, and the collected image is distorted and corrected. The specific process of the algorithm and process is based on MATLAB.

[0069] In particular, the undistortImage() function in MATLAB is used to input the camera intrinsic parameters and distortion parameters, correct the edges of the initial image, and output the distortion-corrected image.

[0070] Step 3: Cut out a rectangular area image from the image of the object to be tested, which must include the complete object to be tested, and then perform perspective transformation on the image to obtain a top-view image of the object to be tested.

[0071] a In particular, in this embodiment, obtaining the top view image of the object to be measured requires finding four basic coordinate pairs on the original image and the desired top view image, solving the mapping matrix, and the projection transformation relationship between the top view image of the measured object and a pair of pixel coordinates in the rectangular area image is:

[0072]

[0073] The 3*3 matrix is the projection transformation matrix, which contains 8 unknown quantities: a0, a1...a7; the following equation is constructed through 4 sets of coordinate pairs:

[0074]

[0075] Among them, (M0, N0), (M1, N1), (M2, N2), (M3, N3) are the pixel coordinate points in the rectangular area image; (M′0, N′0), (M′1, N′1), (M′2, N′2), (M′3, N′3) are the pixel coordinate points in the corresponding overhead image;

[0076] b Specifically, in this embodiment, after obtaining the 3×3 projection transformation matrix, the imwarp() function in MATLAB is used, with the cropped rectangular region image and the projection transformation matrix, and the 'FillValues' parameter is selected to ensure that the output image includes all the initial image pixels, and the output image is the top view image.

[0077] Step 4: According to the conversion relationship between the pixel coordinate system and the world coordinate system, substitute the camera parameters into the conversion formula to restore the pixel coordinates to world coordinates and calculate the area of the rectangular region image.

[0078] a Specifically, in this embodiment, the conversion of pixel coordinates to world coordinates is as follows: The point in the world coordinate system is (X W , Y W , Z W ), the point in the pixel coordinate system is (u, v), Z C is the projection value of the target point camera coordinate system in the Z-axis direction, K is the internal parameter matrix of the camera, R is the rotation matrix, and T is the translation vector;

[0079] The conversion formula for a point from the pixel coordinate system to the world coordinate system is:

[0080]

[0081] Let R -1 ×K -1 ×[u, v, 1] -1 = U1, R -1 ×T = U2. Since the third row of the [u, v, 1] T vector is 1, it can be deduced that Z C = (Z W + U2[3, 1]) / U1[3, 1]. Also, in the world coordinate system, the value of the Z-axis direction of the plane where the checkerboard is located is 0, that is, Z W = 0, then Z C = U2[3, 1] / U1[3, 1].

[0082] b Specifically, in this embodiment, the world coordinates of the four vertices of the rectangular region image are respectively denoted as (X1, Y1), (X2, Y2), (X3, Y3), (X4, Y4), and the area of the rectangular region image is calculated according to the world coordinates, denoted as S C , and the calculation formula is:

[0083]

[0084] Step 5: Perform color-based K-means clustering on the top view image to segment the top view image into the region of the object to be measured, the background region, and the blank region after perspective transformation.

[0085] Specifically, in this embodiment, a three-dimensional rectangular coordinate system is established with the RGB three channels of the color image as the x-y-z axes, and a one-to-one mapping relationship is established between each pixel point on an image and this three-dimensional rectangular coordinate system. Three points are taken from the three-dimensional rectangular coordinate system according to the number of image colors as the centers of the three clusters respectively. The distances from all pixel points to the three cluster centers are calculated, and all pixel points are divided into the cluster class with the smallest distance to it. After multiple iterations, the points within the cluster are made to be as closely connected as possible, while the distances between clusters are made as large as possible, so as to distinguish different color parts in the image and achieve image segmentation.

[0086] Step 6: Obtain the proportion of the object to be measured according to the sizes of the regions obtained after image segmentation, and calculate the area of the object to be measured from the known area of the rectangular region.

[0087] Specifically, in this embodiment, the proportion of the object to be measured is denoted as R, and the area of the object to be measured is denoted as S. The calculation formula is as follows:

[0088] S = R * S C 。

[0089] The main innovation points of the method of the present invention are:

[0090] 1) In the field of machine vision measurement, a measurement system and method for the area of planar objects are disclosed;

[0091] 2) When photographing planar objects, it is very difficult to obtain a true top-down image. Due to the problem of perspective projection where objects are larger when closer and smaller when farther away, there are large errors in directly calculating the area ratio. The projection transformation is used to obtain the top-down image to obtain an accurate area ratio;

[0092] 3) In terms of three-dimensional reconstruction and restoring world coordinate points, a novel solution method for the Z C value is proposed, which can obtain the Z C value corresponding to each pixel point, so as to accurately solve the corresponding world coordinates;

[0093] 4) The functions of camera calibration, image de-distortion, image projection transformation, and image segmentation are realized in an intelligent and integrated manner, with good stability, and can achieve the goals of low cost and high precision on the premise of meeting the accuracy requirements for most planar area measurements.

[0094] Embodiment 2

[0095] In the second aspect, this embodiment provides a planar area measurement device based on machine vision, including a processor and a storage medium;

[0096] The storage medium is used to store instructions;

[0097] The processor is configured to operate according to the instructions to execute the steps of the method according to Embodiment 1.

[0098] Embodiment 3

[0099] In a third aspect, this embodiment provides a planar area measurement system based on machine vision, including a monocular camera and the planar area measurement device based on machine vision described in the second aspect;

[0100] The monocular camera is configured to: acquire an image and upload it to the planar area measurement device based on machine vision.

[0101] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0102] The present application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of flows and / or blocks in the flowchart and / or block diagram can also be implemented. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the specified function in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0103] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device that implements the specified function in Figure 1 one or more flows and / or blocks Figure 1 one or more blocks.

[0104] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide for implementing the specified function in Figure 1One or more processes and / or boxes Figure 1 Steps of the functions specified in one or more boxes.

[0105] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A method for measuring planar area based on machine vision, characterized in that Including: Obtain camera parameters and an image of the object to be measured acquired under the camera parameters, where the image of the object to be measured is captured by a monocular camera, and the camera parameters are obtained through calibration of the monocular camera, including the internal parameters and distortion parameters of the camera; Perform preprocessing of distortion correction on the image of the object to be measured; Intercept a rectangular region image including the complete object to be measured on the preprocessed image of the object to be measured; According to the conversion relationship between the pixel coordinate system and the world coordinate system, combined with the camera parameters, convert the pixel coordinates of the rectangular region image into world coordinates; calculate the area of the rectangular region image based on the world coordinates; Perform perspective transformation on the rectangular region image to obtain a top view image of the object to be measured; Perform color-based K-means clustering on the top view image to segment the top view image into the object to be measured region, the background region, and the blank region after perspective transformation; Calculate the proportion of the object to be measured region; Calculate the area of the object to be measured based on the proportion of the object to be measured region and the area of the rectangular region image.

2. The planar area measurement method based on machine vision according to claim 1, wherein Obtain camera parameters, including: install the measurement system, adjust the focal length of the monocular camera so that the camera can clearly capture the object to be measured, then collect calibration board images, transfer them to the computer for monocular camera calibration, and obtain camera parameters.

3. The method for measuring the planar area based on machine vision according to claim 1 or 2, characterized in that, The method for monocular camera calibration includes: Step 1.1: Fix the monocular camera, adjust the focal length of the monocular camera, place a checkerboard on the workbench; change the placement position of the checkerboard, and use the monocular camera to take multiple pictures to obtain multiple images; Step 1.2: Perform camera calibration in MATLAB: use the function detectCheckerboardPoints() to detect and identify the corner coordinates of the checkerboard in each image, and store the corner coordinates of all images in the variable i_Points; generate the world coordinates of the checkerboard corners in the coordinate system centered on the checkerboard pattern through the function generateCheckerboardPoints(), and make the upper left corner coordinates be (0, 0, 0), and also store the world coordinates of all images in the variable w_Points; finally, input the variables i_Points and w_Points into the calibration function estimateCameraParameters() to calibrate and obtain the monocular camera parameter variable camera_Params.

4. The method for measuring planar area based on machine vision according to claim 1, wherein The preprocessing of distortion correction includes: Perform it through the function undistortImage() in MATLAB; input the camera internal parameters and distortion parameters, correct the initial image edge, and output the image after distortion correction.

5. The method for measuring planar area based on machine vision according to claim 1, characterized in that Perform perspective transformation on the rectangular region image to obtain a top view image of the object to be measured, including: There are 4 basic coordinate pairs between the top view image of the object to be measured and the rectangular region image, solve the mapping matrix, and the projection transformation relationship between a pair of pixel coordinates in the top view image of the object to be measured and the rectangular region image is: Among them, the projection transformation matrix contains 8 unknowns: a0, a1... a7; (M0, N0) is the pixel coordinate point in the image of the rectangular area; (M0′, N0′) is the pixel coordinate point in the top-down view image; the following equations are constructed through 4 groups of coordinate pairs: Among them, (M0, N0), (M1, N1), (M2, N2), (M3, N3) are 4 groups of pixel coordinate points in the image of the rectangular area; (M′0, N′0), (M′1, N′1), (M′2, N′2), (M′3, N′3) are the corresponding 4 groups of pixel coordinate points in the top-down view image.

6. The method for measuring planar area based on machine vision according to claim 1, wherein According to the conversion relationship between the pixel coordinate system and the world coordinate system, combined with the camera parameters, the pixel coordinates of the image in the rectangular area are converted into world coordinates, including: The conversion formula for a point from the pixel coordinate system to the world coordinate system is: Among them, the point in the world coordinate system is (X W , Y W , Z W ), the point in the pixel coordinate system is (u, v), and Z C is the projection value of the target point in the camera coordinate system in the Z-axis direction, K is the internal parameter matrix of the camera, R is the rotation matrix, and T is the translation vector.

7. The method for measuring planar area based on machine vision according to claim 1, characterized in that, Calculate the area of the image in the rectangular area according to the world coordinates, including: where S C is the area of the rectangular region image, and the world coordinates of the four vertices of the rectangular region image are denoted as (X1, Y1), (X2, Y2), (X3, Y3), and (X4, Y4), respectively.

8. The method for measuring the planar area based on machine vision according to claim 1, characterized in that Perform color-based K-means clustering on the top-down view image, including: establishing a three-dimensional rectangular coordinate system with the RGB three channels of the color image as the x-y-z axes, and aggregating the classes with the same color in the image into one class to achieve color-based image segmentation; And / or, calculate the area of the object to be measured according to the proportion of the area occupied by the object to be measured and the area of the image in the rectangular area, including: S = R * S C where S is the area of the object to be measured, R is the proportion of the area occupied by the object to be measured, and S C is the area of the rectangular region image.

9. A planar area measurement device based on machine vision, characterized in that, Comprising a processor and a storage medium; The storage medium is used for storing instructions; The processor is used to operate according to the instructions to execute the steps of the method according to any one of claims 1 to 8.

10. A planar area measurement system based on machine vision, characterized in that, Comprising a monocular camera and the device for measuring the planar area based on machine vision according to claim 9; The monocular camera is configured to: collect an image and upload it to the device for measuring the planar area based on machine vision.

Images