Equipment for physical examination by utilizing machine vision and three-dimensional point cloud scanning technology

Abstract

The invention relates to a physical examination device using machine vision and a three-dimensional point cloud scanning technology, and belongs to the field of intelligent manufacturing. The equipment comprises a main control processor, an equipment chassis, a rotating disc, a pedal, a first telescopic rod, a second telescopic rod, a joint belt, a scanner up-down sliding concave track, a first support rod section, a first three-dimensional point cloud scanner module, a first infrared transmitting module, a first infrared receiving module, a first camera, a second support rod section and a second three-dimensional point cloud scanner module. The second infrared transmitting module, the second infrared receiving module, the heat dissipation module, the ultrasonic module and the ultrasonic distance measuring sensor are used for processing the collected three-dimensional point cloud data and image data, reconstructing the surface of each part of the to-be-measured person, measuring multiple body indexes and evaluating whether the part of the to-be-measured person is abnormal or not. The device is foldable in appearance structure, small in size and high in portability, machine vision and three-dimensional point cloud scanning surface reconstruction are combined, and the measurement precision is high.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent manufacturing, and in particular relates to a device for health examination using machine vision and three-dimensional point cloud scanning technology. Background Art

[0002] According to the Measures for the Administration of Physical Examinations for Primary and Secondary School Students, the physical examinations include the examination of students' height, weight, spine, limbs, neck, arms, waist, chest, etc. In the specific testing work, the testers often go to schools for testing. Because there are many test items, the testers need to carry a variety of testing equipment for testing. Because they need to go to schools and other areas for testing, the weight, volume and portability of the testing equipment have a negative impact on the efficiency of the testing work.

[0003] Currently, there is no device on the market that can detect height, weight, spine, neck, head, hips, arms, waist, and chest at one time and convert multiple test results into body mass index and body fat percentage. The items that can be detected by existing equipment on the market do not fully meet the above-mentioned student health examination and testing needs, and there are problems such as heavy weight and large size of the equipment, inconvenient to carry, high cost, complicated operation, large errors, etc. Or the testers detect some items through traditional manual methods such as looking and touching, and the monitoring accuracy is difficult to meet the relevant standards.

[0004] There are devices that use 3D scanners, cameras or infrared sensors to detect human body posture, but they have the following defects:

[0005] 1. It is not easy to carry, a single device can detect few items, and the cost is high.

[0006] 2. Large size, heavy weight, and cannot be folded.

[0007] 3. When people rotate 360° in place, they tend to sway and feel dizzy, resulting in inaccurate detection data and difficulty in later data processing;

[0008] People hold a 3D scanner and walk around the object to be measured, causing the scanner to swing. Handheld scanning does not have an odometer or rotation angle measurer, resulting in a lot of useless data, a high amount of calculation, and great processing difficulty.

[0009] 4. Only 3D scanning is available, and the accuracy is low.

[0010] 5. It is difficult to measure the geometric distance between point clouds, which is not conducive to accurate measurement of specific parts.

[0011] 6. The sensor position is fixed, and measuring the body shape of people of different heights requires manual adjustment or cannot be adjusted. Summary of the invention

[0012] In view of the above deficiencies in the prior art, the purpose of the invention is to provide a device for health examination using machine vision and three-dimensional point cloud scanning technology. The device has a foldable appearance, a small size, and high portability. It combines machine vision and three-dimensional point cloud scanning surface reconstruction and has high measurement accuracy.

[0013] The present invention proposes a device for health examination using machine vision and three-dimensional point cloud scanning technology, comprising: a device chassis; a main control processor installed inside the device chassis; a rotating disk rotatably installed on the device chassis, and a pedal installed on the rotating disk for the person to be tested to stand; a first retractable rod is fixedly connected to one side of the device chassis, a second retractable rod is laterally retractable and sleeve-connected with the first retractable rod, and the other end is connected to the joint belt; the joint belt is connected to the first section of the support rod; a scanner sliding concave track is arranged on the first section of the support rod, a first three-dimensional point cloud scanner module is slidably installed on the scanner sliding concave track, a first infrared transmitting module, a first infrared receiving module and a first camera are all installed on the first three-dimensional point cloud scanner module, and move up and down with the first three-dimensional point cloud scanner module; a second section of the support rod is connected to the upper end of the first section of the support rod, a second three-dimensional point cloud scanner module is installed on the second section of the support rod, and a second infrared transmitting module, a second infrared receiving module, a second camera and a heat dissipation hole are all installed on the second three-dimensional point cloud scanner module;

[0014] Under the control of the main control processor, the second retractable rod is first pushed out horizontally backward, and the joint point drives the first section of the support rod to stand up and enter a semi-expanded state. The first camera and the second camera measure the height of the person to be tested standing on the pedal. The second section of the support rod moves upward under the instruction of the main control processor to the best position for the second three-dimensional point cloud scanner module to scan the upper body of the person to be tested; then, according to the measured height, the first three-dimensional point cloud scanner module is controlled to move to the best position to scan the lower body of the person to be tested, and then the rotating disk is controlled to drive each component to rotate around the person to be tested, and the first three-dimensional point cloud scanner module and the second three-dimensional point cloud scanner module perform three-dimensional point cloud acquisition on the lower body and upper body of the person to be tested, and the first camera and the second camera perform image acquisition on the lower body and upper body of the person to be tested, and the main control processor processes the acquired three-dimensional point cloud data and image data, reconstructs the surface of each part of the person to be tested, measures multiple body indicators, and evaluates whether the person to be tested has any abnormal parts.

[0015] Furthermore, the main control processor adopts an ARM architecture chip, and is constructed into a main control circuit of the device with a GPIO interface, a control acquisition circuit, and USB and CAN peripheral circuits.

[0016] Furthermore, the first camera and the second camera use a binocular camera ranging principle to measure the height of the person to be measured standing on the pedal.

[0017] Furthermore, the first camera collects images of the buttocks, arms and legs of the person to be tested, and the second camera collects images of the head, neck, chest and back of the person to be tested;

[0018] The first three-dimensional point cloud scanner module collects three-dimensional point clouds of the hips, arms and legs of the person to be measured; the first three-dimensional point cloud scanner module collects three-dimensional point clouds of the head, chest, neck and back of the person to be measured.

[0019] Furthermore, the main control processor processes the three-dimensional point cloud data obtained from the whole body scan of the person to be tested, completes the reconstruction of the surface, processes the images collected by the first camera and the second camera, and uses the trained head, neck, spine measurement degree, and leg shape model to perform feature analysis to preliminarily determine whether the head is abnormal, whether the neck is abnormal, whether scoliosis exists, the degree of scoliosis, whether the leg shape is normal or the leg type.

[0020] Furthermore, the main control processor simultaneously filters the three-dimensional point cloud data using the PCL algorithm, segments the point cloud set after filtering, segments the human body from the external scene and the ground in the three-dimensional point cloud data, extracts the human body point cloud set, aligns the point cloud set using the ICP algorithm, captures the surface changes of the sample, and realizes the surfaceization of the three-dimensional point cloud data.

[0021] Furthermore, after completing the surfacing of the three-dimensional point cloud data, the main control processor performs surface reconstruction, uses the algorithm model to perform identification, tracking, and surface reconstruction, and performs high-precision surface reconstruction of the human back according to the spatial coordinate information of each point and analyzes it with an artificial intelligence model to obtain the degree of scoliosis and abnormal neck conditions, and display the curvature of the human spine and abnormal neck conditions in a visual manner. By analyzing the spatial coordinates of each point in the three-dimensional point cloud, the chest circumference, hip circumference, and waist circumference of the person to be tested are measured.

[0022] Furthermore, the pedal is provided with a weighing sensor for measuring the weight of the person to be measured, and at the same time, combining the height of the person to be measured, measuring the body fat percentage of the person to be measured.

[0023] Furthermore, it also includes: an ultrasonic module and an ultrasonic ranging sensor, both of which are installed on the top of the second three-dimensional point cloud scanner module. During the rotation process, the ultrasonic module emits an ultrasonic signal, and the ultrasonic sensor measures the distance in real time to avoid hitting other objects within the rotation range.

[0024] Furthermore, it also includes: a display screen installed on the first three-dimensional point cloud scanner module.

[0025] The beneficial effects of the present invention are as follows:

[0026] (1) The device is foldable, small in size and highly portable.

[0027] (2) The 3D point cloud data acquisition sensor rotates 360° around the human body. The 3D point cloud data acquisition sensor rotates around the human body, the human body is stable, no dizziness occurs, the data is collected accurately, the 3D point cloud surface is created with high accuracy, the data processing difficulty is low, and multiple body postures of the human body can be detected at one time.

[0028] (3) The combination of machine vision and 3D point cloud scanning surface reconstruction provides high measurement accuracy.

[0029] (4) PCL technology point cloud segmentation, registration, retrieval, feature extraction, recognition, tracking, surface reconstruction, and visualization.

[0030] PCL supports multiple point types, including three-dimensional coordinates, RGB color information, Alpha transparency channel, line information, curvature attributes, etc. for each point. It can accurately measure multiple features between any points, further improving measurement accuracy.

[0031] (5) The machine vision system automatically adjusts the optimal acquisition positions of the two sets of 3D point cloud acquisition sensors, automatically adjusts the sensor positions, and performs precise measurements.

[0032] The present invention avoids the problems of the equipment being difficult to carry, high cost, and a single device being able to detect only a small number of items by highly integrating multiple types of sensing technologies, efficiently utilizing algorithms, self-developed data processing logic, and reasonably designing the equipment structure. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The accompanying drawings are only used to illustrate specific embodiments and are not considered to limit the present invention. In the entire drawings, the same reference symbols represent the same components. Obviously, the drawings described below are only some embodiments recorded in the embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0034] Figure 1 This is a structural diagram of a device for health examination using machine vision and three-dimensional point cloud scanning technology in a non-working state / folded state according to an embodiment of the present invention;

[0035] Figure 2 This is a structural diagram of a device for health examination using machine vision and three-dimensional point cloud scanning technology in a semi-expanded state according to an embodiment of the present invention;

[0036] Figure 3This is a structural diagram of a device for health examination using machine vision and three-dimensional point cloud scanning technology in a fully expanded state according to an embodiment of the present invention;

[0037] Figure 4 Schematic diagram of the detection result of an embodiment of the present invention.

[0038] Reference numerals:

[0039] 1—equipment chassis; 2—rotating plate; 3—pedal; 4—first retractable rod; 5—second retractable rod; 6—joint belt; 7—concave track for scanner to slide up and down; 8—first bracket rod; 9—first 3D point cloud scanner module; 10—screen; 11—first infrared transmitting module; 12—first infrared receiving module; 13—first camera; 14—second bracket rod; 15—second 3D point cloud scanner module; 16—second infrared transmitting module; 17—second infrared receiving module; 18—heat dissipation hole; 19—second camera; 20—ultrasonic module; 21—ultrasonic ranging sensor. DETAILED DESCRIPTION

[0040] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. It should be understood that these descriptions are only exemplary and are not intended to limit the scope of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without making creative work should fall within the scope of protection of the present invention.

[0041] Furthermore, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessarily obscuring the concepts disclosed in the present invention.

[0042] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the orientation or position relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inside", "outside", etc. is based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention. In addition, the terms "first", "second", and "third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. The terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be a connection between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0043] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Instead, they are merely examples of methods and systems consistent with some aspects of the present invention as detailed in the appended claims.

[0044] The technical terms involved in the present invention are explained below:

[0045] PCL (Point Cloud Library) is an open source C++ programming library that implements a large number of general point cloud-related algorithms and efficient data structures, involving point cloud acquisition, filtering, segmentation, registration, retrieval, feature extraction, recognition, tracking, surface reconstruction, visualization, etc.

[0046] The main technologies based on machine vision and 3D point cloud are: machine vision, point cloud surface reconstruction and PCL point cloud processing. Usually, machine vision, point cloud surface reconstruction and PCL point cloud processing are used according to custom logic and algorithms to perform face recognition, distance measurement, body part posture recognition, height measurement, surface reconstruction, building a 3D human model, point cloud processing, point cloud filtering, geometric distance calculation between each point on the surface and any other point, etc., and finally realize that the human posture detection equipment based on machine vision and 3D point cloud technology can complete face recognition identity confirmation, height measurement, weight measurement, scoliosis measurement, leg posture measurement, neck abnormality measurement, head abnormality measurement, hip circumference measurement, waist circumference measurement, chest measurement, body mass index, and body fat percentage at one time.

[0047] The external structure of the health examination device using machine vision and three-dimensional point cloud scanning technology of the present invention includes three states: non-working state (such as Figure 1 as shown), semi-expanded state (as shown Figure 2 ) and fully expanded (as shown Figure 3 shown).

[0048] refer to Figure 1-4 The device for health examination using machine vision and three-dimensional point cloud scanning technology of the present invention includes: a main control processor, an equipment chassis 1, a rotating disk 2, a pedal 3, a first retractable rod 4, a second retractable rod 5, a joint belt 6, a scanner upper and lower sliding concave track 7, a first bracket rod 8, a first three-dimensional point cloud scanner module 9, a first infrared transmitting module 11, a first infrared receiving module 12, a first camera 13, a second bracket rod 14, a second three-dimensional point cloud scanner module 15, a second infrared transmitting module 16, a second infrared receiving module 17, a heat dissipation hole 18, an ultrasonic module 20, and an ultrasonic ranging sensor 21.

[0049] Specifically, the main control processor is installed inside the equipment chassis 1, the rotating disk 2 is rotatably installed on the equipment chassis 1, and the pedal 3 is installed on the rotating disk 2 for the person to be tested to stand. The first retractable rod 4 is fixedly connected to one side of the equipment chassis 1, the second retractable rod 5 is laterally retractable and sleeve-connected with the first retractable rod 4, and the other end is connected to the joint belt 6. The joint belt 6 is connected to the first bracket rod 8; the scanner slides up and down the concave track 7 is set on the first bracket rod 8.

[0050] The first three-dimensional point cloud scanner module 9 can be slidably installed on the scanner's up and down sliding concave track 7. The first infrared transmitting module 11, the first infrared receiving module 12 and the first camera 13 are all installed on the first three-dimensional point cloud scanner module 9 and move up and down with the first three-dimensional point cloud scanner module 9.

[0051] The second support rod 14 is connected to the upper end of the first support rod 8, the second three-dimensional point cloud scanner module 15 is installed on the second support rod 14, and the second infrared transmitting module 16, the second infrared receiving module 17, the second camera 19 and the heat dissipation hole 18 are all installed on the second three-dimensional point cloud scanner module 15.

[0052] The first camera 13 and the second camera 19 use the binocular camera ranging principle to measure the height of the person standing on the step 3. Among them, the two cameras use image recognition and image feature extraction methods, and the binocular camera ranging principle is used to measure the height of the person standing on the step 3. That is, the height of the person is measured by the first camera 13 and the second camera 19 using machine vision.

[0053] In addition, the equipment for health examination using machine vision and three-dimensional point cloud scanning technology of the present invention also includes: an ultrasonic module 20 and an ultrasonic ranging sensor 21, both of which are installed on the top of the second three-dimensional point cloud scanner module 15. During the rotation process, the ultrasonic module 20 emits an ultrasonic signal, and the ultrasonic sensor measures the distance in real time to avoid hitting other objects within the rotation range.

[0054] The device for health examination using machine vision and three-dimensional point cloud scanning technology of the present invention also includes: a screen 10 installed on the first three-dimensional point cloud scanner module 9.

[0055] In the embodiment of the present invention, the main control processor is an ARM architecture chip, and a plurality of peripheral circuits such as several GPIO interfaces, control motors, control cameras, ultrasonic distance acquisition, USB, CAN, etc. are used to construct the main control circuit, and the main control circuit is placed in the device chassis 1 in a waterproof and moisture-proof manner. The peripheral modules or sensor devices used for the functions of the present invention, such as power supply, camera, depth camera, ultrasonic sensor, display drive circuit, motor, electronic scale sensor, etc., are connected to the main control processor by lines.

[0056] The working process of the device of the present invention is described below.

[0057] The present invention is in a non-working state Figure 1 When the power switch is pressed, the device processor receives the start signal, the second retractable rod 5 is automatically pushed back, and the joint belt 6 drives the first bracket to rotate 90°, and the first bracket will stand up. Figure 2 Shown in semi-expanded state.

[0058] Equipment entry Figure 2 After the semi-expanded state, the main control processor instructs to turn on the first camera 13 and the second camera 19.

[0059] The height of the person to be tested standing on the pedal 3 is measured by the first camera 13 and the second camera 19, and the second bracket rod 14 moves upward to the best position for the second three-dimensional point cloud scanner module 15 to scan the upper body of the person to be tested under the instruction of the main control processor. Then, according to the measured height, the first three-dimensional point cloud scanner module 9 is controlled to move to the best position for scanning the lower body of the person to be tested, and then the rotating disk 2 is controlled to drive each component to rotate around the person to be tested, and the first three-dimensional point cloud scanner module 9 and the second three-dimensional point cloud scanner module 15 perform three-dimensional point cloud acquisition on the lower body and upper body of the person to be tested, and the first camera 13 and the second camera 19 perform image acquisition on the lower body and upper body of the person to be tested.

[0060] In the embodiment of the present invention, the first camera 13 collects images of the buttocks, arms and legs of the person to be measured, and the second camera 19 collects images of the head, neck, chest and back of the person to be measured. The first three-dimensional point cloud scanner module 9 collects three-dimensional point clouds of the buttocks, arms and legs of the person to be measured; the first three-dimensional point cloud scanner module 9 collects three-dimensional point clouds of the head, chest, neck and back of the person to be measured.

[0061] Specifically, the main control processor instructs the second bracket connecting shaft to control the motor to rotate, and the second bracket moves upward, moves to the best position to scan the head, chest, neck and spine (i.e., the best position to scan the upper body of the person to be tested), and then stops moving up and down. The second camera 19 collects human features, identifies the human chest and measures the chest position based on image recognition technology, and the visual ranging algorithm moves the second camera 19 to a position 5 cm above the middle horizontal line of the human chest. Because the second camera 19 is fixed to the second infrared receiving module 17 and is 5 cm higher than the second infrared receiving module 17, the second camera 19 is 5 cm higher than the horizontal line of the human chest, which is the best position for the second bracket to move into place.

[0062] At the same time, according to the height of the person measured by the first camera 13 and the second camera 19 using machine vision, the first 3D point cloud scanner module 9 of the 3D point cloud moves up and down along the concave track 7 of the scanner to adjust the position until it moves to the best position for scanning the arms, hips and legs of the human body. Similar to the principle of the second bracket moving to the best position, the first camera 13 is moved up and down together with the first 3D point cloud scanner module 9, and the camera uses image recognition technology to capture the human knee. Finally, the horizontal position of the camera is 5 cm higher than the knee. Because the first infrared receiving module 12 in the first 3D point cloud scanner module 9 is 5 cm away from the first camera 13, the first camera 13 recognizes that the position of the human knee is 5 cm higher than the best position (i.e., the best position for scanning the lower body of the person to be tested).

[0063] The main control processor processes the collected three-dimensional point cloud data and image data, reconstructs the surface of various parts of the person to be tested, measures multiple body indicators, and evaluates whether the person to be tested has any abnormalities.

[0064] Specifically, after the first three-dimensional point cloud scanner module 9 and the second three-dimensional point cloud scanner module 15 have adjusted their positions, the main control processor instructs the rotating disk 2 to rotate clockwise. Because the rotating disk 2 is connected to the first contraction rod 4 and the second contraction rod 5, the first bracket rod 8 and the second bracket rod 14, as the rotating disk 2 rotates, other connected parts rotate as well, and the main control processor instructs the first three-dimensional point cloud scanner module 9 and the second three-dimensional point cloud scanner module 15 to run and collect three-dimensional point cloud data, and the first camera 13 and the second camera 19 take precise photos of specific parts of the human body such as the head, neck, chest, buttocks, arms, legs, and back. During the rotation process, the ultrasonic ranging sensor 21 keeps measuring distance to avoid hitting other objects within the rotation range.

[0065] The rotating disk 2 rotates around the human body with other parts for 3 circles, each circle is 360°. After rotating for 3 circles, the main control processor instructs the rotating disk 2 to stop rotating. After stopping rotating, the main control processor starts to process the three-dimensional point cloud data obtained from the whole body scan of the human body, completes the reconstruction of the surface, and processes the image collected by the camera. The trained head, neck, spine measurement degree, and leg shape model in the processor of this device are used for feature analysis to preliminarily judge whether the head is abnormal, whether the neck is abnormal, whether there is scoliosis, the degree of scoliosis, whether the leg shape is normal or the leg type, etc.

[0066] We use multiple image datasets of different types and parts of the human body to classify, label, and normalize the images. We use the tensorflow machine learning framework and openCv machine vision library to extract features from multiple multi-class images. The machine is trained to become detection models and image recognition classifiers for the head, neck, chest, hips, arms, legs, and knees. We use machine learning algorithms to train normal or abnormal judgment models for each part. For scoliosis and legs, we further classify the abnormality type and degree of scoliosis based on the abnormality. We use the self-prepared test dataset to evaluate the credibility of the model. The model is packaged into a chip type that supports ARM architecture, and then the model is further deployed to the processor.

[0067] The main control processor also filters the three-dimensional point cloud data using the PCL algorithm. The filtering process uses a statistical filter (Statistical Outlier Removal). Point cloud scanning usually produces a point cloud data set with uneven density. In addition, errors in measurement will produce sparse outliers. Therefore, the point cloud algorithm usually removes measurement noise points (that is, outliers) from a point cloud data set. The principle is to calculate the average distance from each point in the point cloud to all its neighboring points. Assuming that the result is a Gaussian distribution, its shape is determined by the mean and standard deviation. Points with an average distance outside the standard range (defined by the global distance mean and variance) can be defined as outliers and can be removed from the data set. After filtering, the point cloud set is segmented, mainly to separate different objects or scene elements in the point cloud data.

[0068] The present invention mainly scans the human body in the point cloud data set, segments the external scene and the ground, extracts the human body point cloud set, further uses the ICP (Iterative Closest Point) algorithm to align the point cloud set, uses the kd tree to retrieve the point cloud data, finds the K neighbors closest to the query point, and uses PFH to parameterize the spatial difference between the query point and the neighborhood points, and forms a multidimensional histogram to describe the k-neighborhood geometric properties of the point. The high-dimensional hyperspace where the histogram is located provides a measurable information space for feature representation. It is invariant to the 6-dimensional posture of the surface corresponding to the point cloud, and is robust under different sampling densities or noise levels of the neighborhood. The relationship between the point and its k-neighborhood and their estimated normals, using all interactions between the estimated normal directions, captures the best sample surface changes.

[0069] After the surface is completed, the surface reconstruction is carried out, and the algorithm model is used for identification, tracking, and surface reconstruction. According to the spatial coordinate information of each point, the high-precision surface reconstruction of the human back is carried out and analyzed by the artificial intelligence model. The degree of scoliosis and abnormal neck conditions are visualized by software to display the curvature of the spine and abnormal neck conditions. By analyzing the spatial coordinates of each point in the three-dimensional point cloud, the spatial coordinate calculation algorithm is encapsulated in the pcl::compute3DCentroid() function in the PCL library. This function can calculate the center of mass of the point cloud, which can be regarded as a calculation method of the spatial coordinates of the point cloud. It is very convenient to measure the chest, hip circumference, and waist circumference through code. Because the pedal 3 has a weighing sensor, it is used to measure the weight of the person to be tested. When a person goes up to the pedal 3 to measure other parts, the pedal 3 can measure the weight of the person, and at the same time, combined with the height of the person to be tested, the body fat rate of the person to be tested can be measured.

[0070] BMI body mass index, t represents weight (in kg), s represents height squared (in m);

[0071]

[0072] The test results are displayed on the screen 10. The present invention supports Bluetooth communication and WiFi wireless network connection functions, so the test results can be wirelessly transmitted to the designated service terminal. Figure 4 A schematic diagram of the test results.

[0073] In summary, the equipment for health examination using machine vision and three-dimensional point cloud scanning technology of the present invention utilizes multiple sensors, processor chips, machine vision, three-dimensional point cloud acquisition and processing, unique functions and unique structures to realize functions such as face recognition identity confirmation, height measurement, weight measurement, scoliosis measurement, leg posture measurement, neck abnormality measurement, head abnormality measurement, hip circumference measurement, waist circumference measurement, chest measurement, body mass index, body fat percentage, etc.

[0074] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the embodiments of the present invention, rather than to limit them. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the above embodiments, or replace some of the technical features therein by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention. Any changes or replacements that can be easily thought of by those skilled in the art within the technical scope disclosed in the present invention should be covered within the protection scope of the present invention.

Claims

1. A device for health examination using machine vision and 3D point cloud scanning technology, characterized in that: include: Equipment site; A main control processor installed inside the chassis of the device; The rotating disk is rotatably installed on the equipment chassis, and the pedal is installed on the rotating disk for the person to be tested to stand; the first retractable rod is fixedly connected to one side of the equipment chassis, the second retractable rod is laterally retractable and is sleeved and connected with the first retractable rod, and the other end is connected to the joint belt; the joint belt is connected to the first section of the bracket rod; the scanner slides up and down concave track is arranged on the first section of the bracket rod, the first three-dimensional point cloud scanner module is slidably installed on the scanner slide up and down concave track, the first infrared transmitting module, the first infrared receiving module and the first camera are all installed on the first three-dimensional point cloud scanner module, and move up and down with the first three-dimensional point cloud scanner module; the second section of the bracket rod is connected to the upper end of the first section of the bracket rod, the second three-dimensional point cloud scanner module is installed on the second section of the bracket rod, and the second infrared transmitting module, the second infrared receiving module, the second camera and the heat dissipation hole are all installed on the second three-dimensional point cloud scanner module; Under the control of the main control processor, the second retractable rod is first pushed out horizontally backward, and the joint point drives the first section of the support rod to stand up and enter a semi-expanded state. The first camera and the second camera measure the height of the person to be tested standing on the pedal. The second section of the support rod moves upward under the instruction of the main control processor to the best position for the second three-dimensional point cloud scanner module to scan the upper body of the person to be tested; then, according to the measured height, the first three-dimensional point cloud scanner module is controlled to move to the best position to scan the lower body of the person to be tested, and then the rotating disk is controlled to drive each component to rotate around the person to be tested, and the first three-dimensional point cloud scanner module and the second three-dimensional point cloud scanner module perform three-dimensional point cloud acquisition on the lower body and upper body of the person to be tested, and the first camera and the second camera perform image acquisition on the lower body and upper body of the person to be tested, and the main control processor processes the acquired three-dimensional point cloud data and image data, reconstructs the surface of each part of the person to be tested, measures multiple body indicators, and evaluates whether the person to be tested has any abnormal parts.

2. The device for health examination using machine vision and three-dimensional point cloud scanning technology according to claim 1, characterized in that: The main control processor adopts an ARM architecture chip, and is combined with a GPIO interface, a control acquisition circuit, and USB and CAN peripheral circuits to form a main control circuit for the device.

3. The device for health examination using machine vision and three-dimensional point cloud scanning technology according to claim 1, characterized in that: The first camera and the second camera use the binocular camera distance measurement principle to measure the height of the person to be measured standing on the pedal.

4. The device for health examination using machine vision and three-dimensional point cloud scanning technology according to claim 1 or 3, characterized in that: The first camera collects images of the buttocks, arms and legs of the person to be tested, and the second camera collects images of the head, neck, chest and back of the person to be tested; The first three-dimensional point cloud scanner module collects three-dimensional point clouds of the hips, arms and legs of the person to be measured; the first three-dimensional point cloud scanner module collects three-dimensional point clouds of the head, chest, neck and back of the person to be measured.

5. The device for health examination using machine vision and three-dimensional point cloud scanning technology according to claim 1, characterized in that: The main control processor processes the three-dimensional point cloud data obtained from the full-body scan of the person to be tested, completes the reconstruction of the surface, processes the images captured by the first camera and the second camera, and uses the trained head, neck, spine measurement degree, and leg shape model to perform feature analysis to preliminarily determine whether the head is abnormal, whether the neck is abnormal, whether scoliosis exists, the degree of scoliosis, whether the leg shape is normal or the leg shape type.

6. The device for health examination using machine vision and three-dimensional point cloud scanning technology according to claim 1, characterized in that: The main control processor simultaneously filters the three-dimensional point cloud data using the PCL algorithm, segments the point cloud set after filtering, segments the human body from the external scene and the ground in the three-dimensional point cloud data, extracts the human body point cloud set, aligns the point cloud set using the ICP algorithm, captures the surface changes of the sample, and realizes the surface of the three-dimensional point cloud data.

7. The device for health examination using machine vision and three-dimensional point cloud scanning technology according to claim 1, characterized in that: After completing the surfacing of the three-dimensional point cloud data, the main control processor performs surface reconstruction, uses the algorithm model to perform identification, tracking, and surface reconstruction, and performs high-precision surface reconstruction of the human back based on the spatial coordinate information of each point and analyzes it using the artificial intelligence model to obtain the degree of scoliosis and abnormal neck conditions, and display the curvature of the human spine and abnormal neck conditions in a visual manner. By analyzing the spatial coordinates of each point in the three-dimensional point cloud, the chest circumference, hip circumference, and waist circumference of the person to be tested are measured.

8. The device for health examination using machine vision and three-dimensional point cloud scanning technology according to claim 1, characterized in that: The pedal is provided with a weighing sensor for measuring the weight of the person to be measured and the body fat percentage of the person to be measured in combination with the height of the person to be measured.

9. The device for health examination using machine vision and three-dimensional point cloud scanning technology according to claim 1, characterized in that: Also includes: The ultrasonic module and the ultrasonic ranging sensor are both installed on the top of the second 3D point cloud scanner module. During the rotation process, the ultrasonic module sends an ultrasonic signal and the ultrasonic sensor measures the distance in real time to avoid hitting other objects within the rotation range.

10. The device for health examination using machine vision and three-dimensional point cloud scanning technology according to claim 1, characterized in that: Also includes: A display screen is installed on the first three-dimensional point cloud scanner module.

Images