Height measurement method, system and readable storage medium based on industrial camera

Abstract

A height measurement method, system and readable storage medium based on an industrial camera disclosed by the present invention. The method includes: calibrating the measurement zero point to determine the ratio of the actual length of the shooting backplane to the backplane pixels; collecting a human body picture of a person to be measured located at the position of the shooting backplane based on a preset image acquisition device; obtaining pixel coordinates based on the human body picture, and calculating a target feature value based on the pixel coordinates; calculating a predicted human height based on the target feature value in combination with a preset regression model, wherein the regression model includes a multiple linear regression equation. The present invention can be directly used for height measurement of patients who cannot stand. Among them, the height measurement result can be used for guiding the dosage of some drugs. By classifying several important bones of the human body, then calculating the distance between the bones, and predicting the height through the regression equation, the detection cost is relatively low, and convenient, fast and efficient detection can be achieved during application.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and more specifically, to a height measurement method, system and readable storage medium based on an industrial camera. Background Art

[0002] Height is an important health parameter adopted in fields such as healthcare, aesthetics and sports. There are many non-contact height measurement methods; however, most are limited to evaluating height in an upright posture.

[0003] Currently, it is crucial to have an accurate and convenient method to measure human height, which is an important variable for calculating body mass index and determining various treatment-related indicators in healthcare. Height measurement is usually carried out in an upright standing posture. For non-critical patients, contact methods such as platform scales, standing scales or medical measurement devices are usually adopted.

[0004] However, for critically ill patients in the intensive care unit, it is usually impractical to require them to move or take an upright posture for height measurement. In addition, since critically ill patients often lose consciousness or mobility, this brings difficulties to accurate height measurement. Summary of the Invention

[0005] The purpose of the present invention is to provide a height measurement method, system and readable storage medium based on an industrial camera, which can be directly used to measure the height of patients who cannot stand. Among them, the height measurement result can be used for guiding the dosage of some drugs. By classifying several important bones of the human body, then calculating the distance between the bones, and predicting the height through a regression equation, the detection cost is relatively low, and convenient, fast and efficient detection can be achieved during application.

[0006] The first aspect of the present invention provides a height measurement method based on an industrial camera, including the following steps:

[0007] Calibrate the measurement zero point to determine the ratio of the actual length of the shooting backboard to the backboard pixels;

[0008] Collect a human body picture of the person to be measured located at the position of the shooting backboard based on a preset image acquisition device;

[0009] Obtain pixel coordinates based on the human body picture, and calculate target feature values based on the pixel coordinates, where the target feature values include shoulder-hip distance value, hip-knee distance value, knee-ankle distance value, ankle-bottom distance value, shoulder-mouth distance value and mouth-nose distance value;

[0010] Calculate the predicted human height based on the target feature values in combination with a preset regression model, where the regression model includes a multiple linear regression equation.

[0011] In this solution, the calibration of the measurement zero point is performed to determine the ratio of the actual length of the shooting backplane to the backplane pixels, which specifically includes:

[0012] After the measurement zero point is calibrated, obtain the actual length of the shooting backplane;

[0013] Obtain the backplane pixels based on the shooting image corresponding to the shooting backplane;

[0014] Calculate the ratio of the actual length to the backplane pixels with the actual length as the numerator and the backplane pixels as the denominator.

[0015] In this solution, the acquisition of the human body picture of the person to be measured located at the position of the shooting backplane based on the preset image acquisition device specifically includes:

[0016] When the person to be measured is within the predicted range of the shooting backplane, start the shooting operation response;

[0017] Control the image acquisition device to shoot the person to be measured at the position of the shooting backplane, where the image acquisition device includes an industrial camera.

[0018] In this solution, obtaining the pixel coordinates based on the human body picture and calculating the shoulder-hip distance value and the hip-knee distance value based on the pixel coordinates specifically includes:

[0019] Obtain the number of pixels of the preset joint based on the human body picture, and establish a pixel coordinate system in combination with the ratio based on the number of pixels;

[0020] Extract the coordinate values of the shoulder feature point, the hip feature point, and the knee feature point based on the pixel coordinate system;

[0021] Calculate the shoulder-hip distance value based on the shoulder feature point and the hip feature point;

[0022] Calculate the hip-knee distance value based on the hip feature point and the knee feature point.

[0023] In this solution, calculating the knee-ankle distance value, the ankle-bottom distance value, the shoulder-mouth distance value, and the mouth-nose distance value based on the pixel coordinates specifically includes:

[0024] Extract the ankle feature point, the sole feature point, the mouth feature point, and the nose feature point based on the pixel coordinate system;

[0025] Calculate the knee-ankle distance value based on the knee feature point and the ankle feature point;

[0026] Calculate the ankle-bottom distance value based on the ankle feature point and the sole feature point;

[0027] Calculate the shoulder-mouth distance value based on the mouth feature point and the shoulder feature point;

[0028] Calculate the oral-nasal distance value based on the oral feature points and the nasal feature points.

[0029] The second aspect of the present invention further provides a height measurement system based on an industrial camera, including a memory and a processor. The memory includes a height measurement method program based on an industrial camera. When the height measurement method program based on an industrial camera is executed by the processor, the following steps are implemented:

[0030] Calibrate the measurement zero point to determine the ratio of the actual length of the shooting backboard to the backboard pixels.

[0031] Collect a human body picture of the person to be measured located at the position of the shooting backboard based on a preset image acquisition device.

[0032] Obtain pixel coordinates based on the human body picture, and calculate target feature values based on the pixel coordinates. Among them, the target feature values include shoulder-hip distance value, hip-knee distance value, knee-ankle distance value, ankle-bottom distance value, shoulder-mouth distance value, and oral-nasal distance value.

[0033] Calculate the predicted human height based on the target feature values in combination with a preset regression model. Among them, the regression model includes a multiple linear regression equation.

[0034] In this solution, the calibration of the measurement zero point to determine the ratio of the actual length of the shooting backboard to the backboard pixels specifically includes:

[0035] After calibrating the measurement zero point, obtain the actual length of the shooting backboard.

[0036] Obtain backboard pixels based on the shooting image corresponding to the shooting backboard.

[0037] Calculate the ratio of the actual length to the backboard pixels with the actual length as the numerator and the backboard pixels as the denominator.

[0038] In this solution, the collection of the human body picture of the person to be measured located at the position of the shooting backboard based on a preset image acquisition device specifically includes:

[0039] When the person to be measured is within the prediction range of the shooting backboard, initiate a shooting operation response.

[0040] Control the image acquisition device to shoot the person to be measured at the position of the shooting backboard. Among them, the image acquisition device includes an industrial camera.

[0041] In this solution, obtaining pixel coordinates based on the human body picture and calculating the shoulder-hip distance value and the hip-knee distance value based on the pixel coordinates specifically includes:

[0042] Obtain the number of pixels of a preset joint based on the human body picture, and establish a pixel coordinate system based on the number of pixels in combination with the ratio;

[0043] Extract the coordinate values of the shoulder feature point, hip feature point, and knee feature point based on the pixel coordinate system;

[0044] Calculate the shoulder-hip distance value based on the shoulder feature point and the hip feature point;

[0045] Calculate the hip-knee distance value based on the hip feature point and the knee feature point.

[0046] In this solution, calculating the knee-ankle distance value, ankle-bottom distance value, shoulder-mouth distance value, and mouth-nose distance value based on the pixel coordinates specifically includes:

[0047] Extract the ankle feature point, sole feature point, mouth feature point, and nose feature point based on the pixel coordinate system;

[0048] Calculate the knee-ankle distance value based on the knee feature point and the ankle feature point;

[0049] Calculate the ankle-bottom distance value based on the ankle feature point and the sole feature point;

[0050] Calculate the shoulder-mouth distance value based on the mouth feature point and the shoulder feature point;

[0051] Calculate the mouth-nose distance value based on the mouth feature point and the nose feature point.

[0052] The third aspect of the present invention provides a computer-readable storage medium, which includes a program for a method of measuring height based on an industrial camera for a machine. When the program for the method of measuring height based on an industrial camera is executed by a processor, the steps of a method of measuring height based on an industrial camera as described in any one of the above are implemented.

[0053] A method, system, and readable storage medium for measuring height based on an industrial camera disclosed by the present invention can be directly used to measure the height of patients who cannot stand. Among them, the height measurement result can be used for guiding the dosage of some drugs. By classifying several important bones of the human body, then calculating the distance between the bones, and predicting the height through a regression equation, the detection cost is relatively low, and convenient, fast, and efficient detection can be achieved during application. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 Shows a schematic diagram of the steps of a method for measuring height based on an industrial camera according to the present invention;

[0055] Figure 2Shows the height calculation flowchart of a height measurement method based on an industrial camera according to the present invention;

[0056] Figure 3 Shows the schematic diagram of the scene for taking pictures of the human body in a height measurement method based on an industrial camera according to the present invention;

[0057] Figure 4 Shows the schematic diagram of the human body measurement bones in a height measurement method based on an industrial camera according to the present invention;

[0058] Figure 5 Shows the block diagram of a height measurement system based on an industrial camera according to the present invention;

[0059] Figure 6 Shows the schematic diagram of the subject height measurement application when a height measurement system based on an industrial camera according to the present invention is applied. Detailed implementation manners

[0060] In order to be able to more clearly understand the above objects, features and advantages of the present invention, the present invention will be further described in detail below in conjunction with the drawings and specific implementation manners. It should be noted that, without conflict, the embodiments of the present application and the features in the embodiments can be combined with each other.

[0061] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited by the specific embodiments disclosed below.

[0062] Figure 1 Shows the flowchart of a height measurement method based on an industrial camera of the present application.

[0063] As Figure 1 shown, the present application discloses a height measurement method based on an industrial camera, including the following steps:

[0064] S102, calibrate the measurement zero point to determine the ratio of the actual length of the shooting backplane to the backplane pixels;

[0065] S104, collect a human body picture of the person to be measured located at the position of the shooting backplane based on a preset image acquisition device;

[0066] S106, obtain pixel coordinates based on the human body picture, and calculate target feature values based on the pixel coordinates, where the target feature values include shoulder-hip distance value, hip-knee distance value, knee-ankle distance value, ankle-bottom distance value, shoulder-mouth distance value and mouth-nose distance value;

[0067] S108. Calculate the predicted human height based on the target feature value in combination with a preset regression model, where the regression model includes a multiple linear regression equation.

[0068] It should be noted that in this embodiment, an innovative non-contact human height measurement method is proposed. Specifically, it combines the Media-Pipe library and the advanced YOLOv8 model to accurately extract joint coordinates and calculate bone lengths. By applying the multiple linear regression function, it can effectively predict human height from image data, demonstrating high accuracy and reliability. And in subsequent practical applications, it can be used to determine the height of individuals in various standing and lying positions, greatly expanding the application scenarios of industrial cameras through real-time measurement.

[0069] Specifically, as Figure 2 shown, it is a flowchart of height calculation. Among them, the features of the collected picture are recognized, and the features of the picture are converted into pixels and coordinates. Then, by calculating the lengths of each bone part, the final height is calculated using the multiple linear regression equation.

[0070] Furthermore, during measurement, first calibrate the measurement zero point to determine the ratio of the actual length of the shooting backplane to the backplane pixels, and collect a human picture of the person to be measured at the position of the shooting backplane based on a preset image acquisition device. After obtaining the human picture, obtain pixel coordinates based on the human picture, calculate the target feature value based on the pixel coordinates, where the target feature value includes the shoulder-hip distance value, hip-knee distance value, knee-ankle distance value, ankle-bottom distance value, shoulder-mouth distance value, and mouth-nose distance value. Finally, calculate the predicted human height based on the target feature value in combination with a preset regression model, where the regression model includes a multiple linear regression equation.

[0071] According to the embodiment of the present invention, the calibration of the measurement zero point to determine the ratio of the actual length of the shooting backplane to the backplane pixels specifically includes:

[0072] After calibrating the measurement zero point, obtain the actual length of the shooting backplane;

[0073] Obtain the backplane pixels based on the shooting image corresponding to the shooting backplane;

[0074] Calculate the ratio of the actual length to the backplane pixels with the actual length as the numerator and the backplane pixels as the denominator.

[0075] It should be noted that in this embodiment, first, calibration is required to recalibrate the zero point to determine the ratio k of the actual length of the shooting backplane to the backplane pixels:

[0076] ;

[0077] Among them, height (cm) represents the actual length of the shooting backplane, and dis (pixel) represents the backplane pixels of the shooting backplane.

[0078] According to an embodiment of the present invention, collecting a human body picture of a person to be measured located at the position of the shooting backplane by the preset image acquisition device specifically includes:

[0079] When the person to be measured is within the predicted range of the shooting backplane, a shooting operation response is enabled;

[0080] Controlling the image acquisition device to shoot the person to be measured at the position of the shooting backplane, wherein the image acquisition device includes an industrial camera.

[0081] It should be noted that in this embodiment, as Figure 3 shown, it is a schematic diagram of the scene of shooting a human body picture. Among them, when the person to be measured is within the predicted range of the shooting backplane, a shooting operation response is enabled. For example, when the person to be measured (patient) is within 1 meter of the shooting backplane, that is, the predicted range is 1 meter, so as to control the image acquisition device to shoot the person to be measured at the position of the shooting backplane, wherein the image acquisition device includes an industrial camera.

[0082] According to an embodiment of the present invention, obtaining pixel coordinates based on the human body picture, and calculating the shoulder-hip distance value and the hip-knee distance value based on the pixel coordinates specifically includes:

[0083] Obtaining the number of pixels of a preset joint based on the human body picture, and establishing a pixel coordinate system based on the number of pixels in combination with the ratio;

[0084] Extracting the coordinate values of the shoulder feature point, the hip feature point, and the knee feature point based on the pixel coordinate system;

[0085] Calculating the shoulder-hip distance value based on the shoulder feature point and the hip feature point;

[0086] Calculating the hip-knee distance value based on the hip feature point and the knee feature point.

[0087] According to an embodiment of the present invention, calculating the knee-ankle distance value, the ankle-bottom distance value, the shoulder-mouth distance value, and the mouth-nose distance value based on the pixel coordinates specifically includes:

[0088] Extracting the ankle feature point, the sole feature point, the mouth feature point, and the nose feature point based on the pixel coordinate system;

[0089] Calculating the knee-ankle distance value based on the knee feature point and the ankle feature point;

[0090] Calculating the ankle-bottom distance value based on the ankle feature point and the sole feature point;

[0091] Calculate the shoulder-mouth distance value based on the mouth feature points and the shoulder feature points;

[0092] Calculate the mouth-nose distance value based on the mouth feature points and the nose feature points.

[0093] It should be noted that in this embodiment, as Figure 4 shown, it is a schematic diagram of anthropometric bones. The OpenCV library was initially used for image processing, and then the Media-Pipe library was applied to extract the x, y, and z coordinates, as well as the number of pixels of each joint. According to the actual measurement results, this embodiment divides the human body into six parts and calculates the distances of the six parts respectively, namely the shoulder-hip distance value , the hip-knee distance value , the knee-ankle distance value , the ankle-bottom distance value , the shoulder-mouth distance value and the mouth-nose distance value .

[0094] Specifically, in this embodiment, the number of pixels of a preset joint is obtained based on the human body picture, and a pixel coordinate system is established based on the number of pixels in combination with the ratio to normalize the coordinates. The y i、 x i， are obtained from MediaPipe, and then the pixels are converted into a coordinate system using the following formula:

[0095] ;

[0096] where X i , Y i represent the converted pixel coordinate system, y i、 x i are obtained from Media-Pipe, image_width is the width of the captured image, image_height is the height of the captured image, and then the pixel coordinates are used to calculate the distances between landmarks and the lengths of the skeletal segments in the human body. The coordinates of the midpoint of the shoulder and the midpoint of the hip are used to calculate the distance :

[0097] ;

[0098] where the hip coordinates are ( , ) and ( , ), and the shoulder coordinates are ( , ) and ( , ), where k is the ratio of the actual length of the shooting backplane to the backplane pixels.

[0099] The distance from the hip to the knee in the skeletal part :

[0100] ;

[0101] Among them, the hip coordinates are ( , ), and the knee coordinates are ( , ).

[0102] Similarly, the distance from the knee to the ankle :

[0103] ;

[0104] Among them, the ankle coordinates are ( , ), and the knee coordinates are ( , ).

[0105] The distance from the ankle to the sole of the foot :

[0106] ;

[0107] Among them, the ankle coordinates are ( , ), and the sole coordinates are ( , ) and ( , ).

[0108] The distance from the midpoint of the shoulder to the midpoint of the mouth :

[0109] ;

[0110] Among them, the mouth coordinates are ( , ) and ( , ), and the shoulder coordinates are ( , ) and ( , ).

[0111] The calculation formula from the midpoint of the mouth to the nose :

[0112] ;

[0113] Among them, the mouth coordinates are ( , ) and ( , ) and the nose coordinates are ( , ).

[0114] According to an embodiment of the present invention, calculating the predicted human height based on the target feature value in combination with a preset regression model specifically includes:

[0115] Extracting a correlation coefficient table based on the multiple linear regression equation;

[0116] Matching the corresponding target feature value based on the correlation coefficient table for calculation to obtain the predicted human height, wherein the predicted human height is calculated by multiplying and summing the corresponding target feature values in combination with different correlation coefficients.

[0117] It should be noted that in this embodiment, after calculating the length of each bone segment, we applied a multiple linear regression equation to predict the human height. The formula is as follows:

[0118] ;

[0119] Wherein, is the predicted height; is the shoulder-hip distance value, is the hip-knee distance value, is the knee-ankle distance value, is the ankle-bottom distance value, is the shoulder-mouth distance value, is the mouth-nose distance value; , , ,…, are the correlation coefficients obtained during the training of the multiple linear regression model, and ε is a constant. Among them, in this embodiment, the value of ε after training is 73.78 cm in one embodiment and can be specifically adjusted according to actual applications.

[0120] Figure 5 shows a block diagram of a height measurement system based on an industrial camera according to the present invention.

[0121] As Figure 5 shown, the present invention discloses a height measurement system based on an industrial camera, including a memory and a processor. The memory includes a height measurement method program based on an industrial camera. When the height measurement method program based on an industrial camera is executed by the processor, the following steps are implemented:

[0122] Calibrating the measurement zero point to determine the ratio of the actual length of the shooting backplane to the backplane pixels;

[0123] Collect a human body picture of the person to be tested located at the position of the shooting backplane based on a preset image acquisition device;

[0124] Obtain pixel coordinates based on the human body picture, and calculate target feature values based on the pixel coordinates, where the target feature values include shoulder-hip distance value, hip-knee distance value, knee-ankle distance value, ankle-bottom distance value, shoulder-mouth distance value, and mouth-nose distance value;

[0125] Calculate the predicted human height based on the target feature values in combination with a preset regression model, where the regression model includes a multiple linear regression equation.

[0126] It should be noted that since the specific implementation manner of this embodiment corresponds to the foregoing method embodiment, the same details will not be repeated herein.

[0127] Specifically, in practical applications, as Figure 6 shown, it is a schematic diagram of the application for measuring the height of the subject. Among them, Figure 6 "black-cover" in it refers to that when training a model (such as image classification), a black square or mask part may be used to cover the image, aiming to improve the robustness of the model to occlusion. Among them, "black-cover, 0.94" represents the area ratio of the occlusion area (indicating the opacity of the black mask ("94%" is opaque and "6%" of the image content is revealed)), Figure 6 In (a) of it, an upright posture is shown, Figure 6 In (b) of it, a 45° rotation posture is shown, Figure 6 In (c) of it, a horizontal 90° rotation posture is shown, Figure 6 In (d) of it, a kneeling posture schematic diagram is shown. Specifically, first is the upright posture. The subject needs to stand straight and look straight ahead. This position simulates the human body in a natural state without inclination or rotation. The predicted height calculation formula is as follows:

[0128] ;

[0129] Among them, the predicted results of "17" subjects in the upright posture are shown in Table 1,

[0130] Table 1. Predicted result table of subjects in the upright posture

[0131] 。

[0132] Secondly is the 45° rotation posture. The subject needs to keep the body at 45° with the camera and look straight ahead at the same time. This posture simulates the human body shape at a small angle and may affect the way the bone segments are presented in the image. The predicted height calculation formula is as follows:

[0133] ;

[0134] Among them, the prediction results of "17" subjects in the 45° rotation posture are shown in Table 2,

[0135] Table 2. Prediction Results Table of Subjects in the 45° Rotation Posture

[0136] .

[0137] Furthermore, it is the horizontal 90° rotation posture. The subject rotates the body 90° from the camera direction and keeps looking straight ahead. This posture simulates the human body state at a larger angle and illustrates the body positions that patients may have in a hospital bed. This helps to better explore the differences in bone segment measurement values when the body is in a horizontal state, which is of great significance in medical applications. The predicted height calculation formula is as follows:

[0138] ;

[0139] Finally, it is the kneeling posture. The subject rotates the body 90° while bending the knees. When the body is in a bent-knee state, this posture is particularly crucial for understanding the changes in bone segments, simulating the situation where the body is not completely upright. The predicted height calculation formula is as follows:

[0140] ;

[0141] Among them, the prediction results of "17" subjects in the 90° rotation posture are shown in Table 3,

[0142] Table 3. Prediction Results Table of Subjects in the 90° Rotation Posture

[0143] .

[0144] The third aspect of the present invention provides a computer-readable storage medium, which includes a program for a height measurement method based on an industrial camera. When the program for the height measurement method based on an industrial camera is executed by a processor, the steps of a height measurement method based on an industrial camera as described in any one of the above are implemented.

[0145] A height measurement method, system and readable storage medium based on an industrial camera disclosed by the present invention can be directly used for height measurement of patients who cannot stand. Among them, the height measurement results can be used for guiding the dosage of some drugs. By classifying several important bones of the human body, then calculating the distances between the bones, and predicting the height through a regression equation, the detection cost is relatively low, and convenient, fast and efficient detection can be achieved during application.

[0146] In several embodiments provided by 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 merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, 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 couplings, direct couplings, or communication connections between the various components shown or discussed can be through some interfaces. The indirect coupling or communication connection of devices or units can be electrical, mechanical, or other forms.

[0147] The units described above as separate components may or may not be physically separated. The components shown as units may or may not be physical units. They can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0148] In addition, each functional unit in the embodiments of the present invention can be all integrated in a processing unit, or each unit can be separately used as a unit, or two or more units can be integrated in a unit. The above-mentioned integrated units can be implemented in the form of hardware, or in the form of a combination of hardware and software functional units.

[0149] Those of ordinary skill in the art can understand that all or part of the steps for implementing the above method embodiments can be completed by hardware related to program instructions. The foregoing program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiments. The foregoing storage medium includes various media that can store program codes, such as removable storage devices, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0150] Alternatively, if the above-mentioned integrated units of the present invention are implemented in the form of software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the embodiments of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the various embodiments of the present invention. The foregoing storage medium includes various media that can store program codes, such as removable storage devices, ROM, RAM, magnetic disks, or optical discs.

Claims

1. A height measurement method based on an industrial camera, characterized in that, Including the following steps: Calibrate the measurement zero point to determine the ratio of the actual length of the shooting backplane to the backplane pixels, specifically including: After calibrating the measurement zero point, obtain the actual length of the shooting backplane; Obtain the backplane pixels based on the shooting image corresponding to the shooting backplane; Calculate the ratio of the actual length to the backplane pixels with the actual length as the numerator and the backplane pixels as the denominator; Collect the human body picture of the person to be measured at the position of the shooting backplane based on a preset image acquisition device, specifically including: When the person to be measured is within the predicted range of the shooting backplane, initiate the shooting operation response; Control the image acquisition device to take a picture of the person to be measured at the position of the shooting backplane, where the image acquisition device includes an industrial camera; Obtain pixel coordinates based on the human body picture, and calculate the target feature values based on the pixel coordinates, where the target feature values include shoulder-hip distance value, hip-knee distance value, knee-ankle distance value, ankle-bottom distance value, shoulder-mouth distance value, and mouth-nose distance value; Calculate the predicted human height based on the target feature values in combination with a preset regression model, specifically including: Extract the correlation coefficient table based on the multiple linear regression equation; Match the corresponding target feature values based on the correlation coefficient table for calculation to obtain the predicted human height, where the predicted human height is calculated by multiplying and summing the corresponding target feature values in combination with different correlation coefficients; Among them, the regression model includes a multiple linear regression equation, and the formula is as follows: ； Among them, h is the predicted height; h1 is the shoulder-hip distance value, h2 is the hip-knee distance value, h3 is the knee-ankle distance value, h4 is the ankle-bottom distance value, h5 is the shoulder-mouth distance value, h6 is the mouth-nose distance value; β0, β1, β2, …, β6 are the correlation coefficients obtained during the training of the multiple linear regression model, and ε is a constant.

2. The height measurement method based on an industrial camera according to claim 1, wherein Obtain pixel coordinates based on the human body picture, and calculate the shoulder-hip distance value and the hip-knee distance value based on the pixel coordinates, specifically including: Obtain the number of pixels of the preset joint based on the human body picture, and establish a pixel coordinate system based on the number of pixels in combination with the ratio; Extract the coordinate values of the shoulder feature point, hip feature point, and knee feature point based on the pixel coordinate system; Calculate the shoulder-hip distance value based on the shoulder feature point and the hip feature point; Calculate the hip-knee distance value based on the hip feature point and the knee feature point.

3. The height measurement method based on an industrial camera according to claim 1, wherein, Calculate the knee-ankle distance value, ankle-bottom distance value, shoulder-mouth distance value, and mouth-nose distance value based on the pixel coordinates, specifically including: Extract the ankle feature point, sole feature point, mouth feature point, and nose feature point based on the pixel coordinate system; Calculate the knee-ankle distance value based on the knee feature point and the ankle feature point; Calculate the ankle-bottom distance value based on the ankle feature point and the sole feature point; Calculate the shoulder-mouth distance value based on the mouth feature point and the shoulder feature point; Calculate the mouth-nose distance value based on the mouth feature point and the nose feature point.

4. A height measurement system based on an industrial camera, characterized in that, It includes a memory and a processor. The memory includes a program for a height measurement method based on an industrial camera. When the program for the height measurement method based on the industrial camera is executed by the processor, the following steps are implemented: Calibrate the measurement zero point to determine the ratio of the actual length of the shooting backplane to the backplane pixels, specifically including: After calibrating the measurement zero point, obtain the actual length of the shooting backplane; Obtain the backplane pixels based on the shooting image corresponding to the shooting backplane; Calculate the ratio of the actual length to the backplane pixels with the actual length as the numerator and the backplane pixels as the denominator; Collect a human body picture of the person to be measured at the position of the shooting backplane based on a preset image acquisition device, specifically including: When the person to be measured is within the predicted range of the shooting backplane, initiate a shooting operation response; Control the image acquisition device to shoot the person to be measured at the position of the shooting backplane, where the image acquisition device includes an industrial camera; Obtain pixel coordinates based on the human body picture, and calculate a target feature value based on the pixel coordinates, where the target feature value includes a shoulder-hip distance value, a hip-knee distance value, a knee-ankle distance value, an ankle-bottom distance value, a shoulder-mouth distance value, and a mouth-nose distance value; Calculate the predicted human height based on the target feature value in combination with a preset regression model, specifically including: Extract a correlation coefficient table based on the multiple linear regression equation; Match the corresponding target feature value based on the correlation coefficient table for calculation to obtain the predicted human height, where the predicted human height is calculated by multiplying the corresponding target feature value by different correlation coefficients and then summing them up; Among them, the regression model includes a multiple linear regression equation with the formula as follows: ； Among them, h is the predicted height; h1 is the shoulder-hip distance value, h2 is the hip-knee distance value, h3 is the knee-ankle distance value, h4 is the ankle-bottom distance value, h5 is the shoulder-mouth distance value, h6 is the mouth-nose distance value; β0, β1, β2,..., β6 are correlation coefficients obtained during the process of training the multiple linear regression model, and ε is a constant.

5. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a program for a height measurement method based on an industrial camera. When the program for the height measurement method based on the industrial camera is executed by a processor, the steps of a height measurement method based on an industrial camera as described in any one of claims 1 to 3 are implemented.

Images