Human parameter measurement method and device based on infrared thermal imaging and health monitoring system

Abstract

The application discloses a human parameter measurement method and device based on infrared thermal imaging, a health monitoring system and a storage medium. The measurement method comprises the following steps: acquiring a front infrared thermal image and a side infrared thermal image collected by a measured person; based on the difference between the surface temperature of the human body and the environmental background temperature, extracting the overall external contour of the human body from the front infrared thermal image and the side infrared thermal image; positioning a target area on the overall external contour of the human body, and extracting the front target area width and the side target area width respectively; taking the front target area width and the side target area width as the long axis and the short axis of a model respectively, and calculating the human body shape size parameter. The infrared image has extremely high contrast in a complex background and a weak light environment, and is combined with adaptive threshold segmentation and model fitting, so that the visual interference of part of light and thin clothes or the edge of loose clothes can be effectively penetrated or eliminated, and the accuracy and robustness of parameter measurement are significantly improved.

Description

Technical Field

[0001] This invention relates to the field of human body parameter measurement technology, specifically to a method, device, health monitoring system, and storage medium for measuring human body parameters based on infrared thermal imaging. Background Technology

[0002] With the increasing demand for biometric technology and health monitoring, non-contact measurement of human morphological parameters has become a research hotspot. As key indicators reflecting the risk of central obesity and metabolic syndrome, accurate measurement of human morphological parameters is of great significance for clinical medicine, clothing customization, and daily health management.

[0003] Existing parameter measurement methods mainly include contact-based tape measure measurement and non-contact measurement based on visible light vision. However, contact-based measurement suffers from problems such as high operational subjectivity, low efficiency, and privacy and hygiene risks in public places. While visible light vision-based solutions achieve non-contact measurement, they are highly susceptible to interference from ambient light intensity, background complexity, and the color and material of the subject's clothing. Furthermore, visible light images contain sensitive information such as faces and clothing, posing a serious risk of privacy breaches. In addition, when the subject is wearing loose clothing, visible light solutions struggle to accurately extract the true contours of the human body, leading to a significant decrease in measurement accuracy. Summary of the Invention

[0004] In order to overcome the shortcomings of the prior art, the purpose of this invention is to provide a method, device, health monitoring system and storage medium for measuring human body parameters based on infrared thermal imaging, which improves measurement accuracy and environmental adaptability while protecting privacy through infrared thermal imaging technology.

[0005] This invention is achieved using the following technical solution:

[0006] On the one hand, a method for measuring human body parameters based on infrared thermal imaging is provided, including: acquiring a frontal infrared thermal image and a side infrared thermal image of the subject; extracting the overall outer contour of the human body from the frontal infrared thermal image and the side infrared thermal image based on the difference between the human body surface temperature and the ambient background temperature; locating target areas on the overall outer contour of the human body, and extracting the width of the frontal target area and the width of the side target area respectively; and calculating the human body shape and size parameters by using the width of the frontal target area and the width of the side target area as the major axis and the minor axis of the model respectively.

[0007] Preferably, before acquiring the infrared thermal image of the subject, a system calibration step is included: acquiring the infrared image of a standard-sized calibration plate; calculating the pixel-to-physical-length ratio conversion factor using the known physical length of the standard-sized calibration plate and the corresponding pixel length in the image; the extraction of the width of the front target area and the width of the side target area includes: acquiring the pixel width of the front target area and the pixel width of the side target area, and converting them into the actual width of the front target area and the width of the side target area using the ratio conversion factor.

[0008] Preferably, the step of extracting the overall human body contour from the frontal infrared thermal image and the side infrared thermal image includes: calculating the average temperature and standard deviation of the infrared thermal image to generate an adaptive segmentation threshold; performing binarization processing on the infrared thermal image according to the adaptive segmentation threshold to generate an initial binary image; performing morphological opening and closing operations on the initial binary image in sequence, and retaining the largest connected region through connected component analysis to extract a smooth overall human body contour.

[0009] Preferably, the step of locating the target region on the overall outer contour of the human body and extracting the width of the front target region and the width of the side target region, wherein the target region is the waist, includes: identifying key points of the shoulders and hips on the overall outer contour of the human body in the front image, and calculating the vertical distance between the shoulders and hips; determining the waist feature measurement layer according to a preset human anatomical ratio; extracting the coordinates of the left and right boundary points along the horizontal direction on the waist feature measurement layer to obtain the front waist width; and performing a horizontal boundary search on the side infrared image at the same waist measurement height as the front image to extract the front and rear boundary points of the side contour to obtain the side waist width.

[0010] Preferably, the acquisition of the frontal and side infrared thermal images of the subject simultaneously includes: continuously acquiring multiple frames of frontal and side infrared thermal images using an infrared thermal imager; and obtaining a stable infrared thermal image with a high signal-to-noise ratio through time-domain mean filtering or weighted fusion processing.

[0011] On the other hand, a human body parameter measurement device based on infrared thermal imaging is also provided, preferably comprising: an infrared thermal imager for acquiring frontal and side infrared thermal images of the subject; and a data processing and control unit, communicatively connected to the infrared thermal imager, for executing the human body parameter measurement method based on infrared thermal imaging as described above.

[0012] Preferably, the infrared thermal imager comprises two units, which are used to simultaneously acquire frontal and side infrared thermal images of the subject, respectively; it also includes: a fixed bracket and a positioning platform, used to fix the infrared thermal imager to maintain a constant shooting height, angle and distance, and to provide a standardized standing area for the subject; and a standard-size calibration plate, set in the measurement area of ​​the positioning platform, used to establish the mapping relationship between image pixels and physical length.

[0013] Preferably, it further includes: an auxiliary structural component, the auxiliary structural component including a light-shielding structure, used to reduce ambient light and temperature interference, and reduce background noise.

[0014] On another front, a health monitoring system is provided, characterized in that it includes the human body parameter measurement device based on infrared thermal imaging as described above, and the system further includes a risk assessment module, which is used to receive the human body parameter data output by the data processing and control unit, and to assess the central obesity level and health risk of the subject based on the human body parameter data.

[0015] In another aspect, a computer-readable storage medium is also provided, on which a computer program is stored, characterized in that, when the computer program is executed by a processor, it implements the steps of the human body parameter measurement method based on infrared thermal imaging as described above.

[0016] Compared to existing technologies, the advantages of this invention are as follows: Utilizing infrared thermal imaging technology, it only collects human body thermal radiation information, physically filtering out sensitive visual features such as faces, thus greatly protecting user privacy. Simultaneously, due to the natural temperature difference between the human body and the background, infrared images exhibit extremely high contrast in complex backgrounds and low-light environments. Combined with adaptive threshold segmentation and model fitting, it can effectively penetrate some thin clothing or eliminate visual interference from the edges of loose clothing, significantly improving the accuracy and robustness of parameter measurements. Furthermore, this system employs passive infrared reception, producing no electromagnetic radiation, making it safe and harmless to the human body, and suitable for various health monitoring scenarios. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating a human body parameter measurement method based on infrared thermal imaging according to an embodiment of this application. Figure 2 This is a schematic diagram of a human body parameter measurement device based on infrared thermal imaging according to an embodiment of this application; Figure 3 This is a functional block diagram of a health monitoring system according to an embodiment of this application.

[0018] In the picture, 1. Infrared thermal imager; 2. Standard size calibration plate; 3. Fix the bracket; 31. Positioning platform; 4. Data processing and control unit; 10. A device for measuring human waist circumference parameters based on infrared thermal imaging; 20. Risk Assessment Module; 100, Health Monitoring System. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0020] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of this application are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indication will also change accordingly.

[0021] Furthermore, the use of terms such as "first" and "second" in this application is for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. Additionally, the technical solutions of the various embodiments can be combined with each other, but only on the basis of being achievable by those skilled in the art. When the combination of technical solutions is contradictory or impossible to implement, such a combination of technical solutions should be considered non-existent and not within the scope of protection claimed in this application.

[0022] Example 1: refer to Figure 1 A method for measuring human body parameters based on infrared thermal imaging includes the following steps: S1. Acquire infrared images of the standard-sized calibration plate; Using the known physical length of the standard-size calibration plate and the corresponding pixel length in the image, calculate the pixel-to-physical-length ratio conversion factor; One of the most critical challenges in using infrared thermal images for geometric dimension measurement is converting the pixel coordinate system in the image into a physical coordinate system in the real world. This invention describes in detail the system calibration process, which is a core prerequisite for ensuring measurement accuracy at the millimeter level.

[0023] During initial device deployment or routine maintenance, calibration using a standard-sized calibration plate is required. This calibration plate possesses unique physical properties that allow it to display clear, high-contrast geometric patterns under infrared light. For example, the calibration plate surface can be made with a high-emissivity material (such as a special matte varnish) as the substrate, with low-emissivity metal foil embedded to form a checkerboard pattern or dot array. When the calibration plate is placed in the measurement area, the data processing and control unit acquires its image. Since the actual physical spacing of each feature point on the calibration plate is known, the processor can calculate the pixel-to-physical-length ratio conversion factor k using a perspective projection model or a simple linear mapping model.

[0024] S2. Acquire the frontal and side infrared thermal images of the subject simultaneously. Multiple frames of frontal and side infrared thermal images are continuously acquired; stable infrared thermal images with high signal-to-noise ratio are obtained through time-domain mean filtering or weighted fusion processing.

[0025] S3. Based on the difference between the human body surface temperature and the ambient background temperature, extract the overall outer contour of the human body from the front infrared thermal image and the side infrared thermal image. S31. Calculate the average temperature and standard deviation of the infrared thermal image, and generate an adaptive segmentation threshold; Calculate the average gray value of all pixels in the image ( ) and standard deviation ( Using these statistics, the system generates an adaptive segmentation threshold. . ,in It is an adaptive adjustment dynamic coefficient obtained from experimental calibration.

[0026] S32. The infrared thermal image is binarized according to the adaptive segmentation threshold to generate an initial binary image; Binarizing the image using this threshold will separate pixels with values ​​higher than a certain threshold. The region is set to 1 (representing a possible human body region), below which... The area is set to 0 (representing the background). .

[0027] S33. Perform morphological opening and closing operations on the initial binary image in sequence, and retain the largest connected region through connected component analysis to extract the smooth overall outer contour of the human body.

[0028] Binary images after initial segmentation often contain noise points. The background may contain small, high-temperature interference sources, while the interior of the human body may show internal voids due to clothing materials (such as thermal underwear with a metallic coating) or accessories. To address this issue, the data processing and control unit performs morphological operations on the binary image. First, a morphological opening operation (erosion followed by dilation) is performed, which effectively severs small connections and eliminates isolated noise points. Next, a morphological closing operation (dilation followed by erosion) is performed, which fills in small voids inside the human body and connects adjacent fractured areas.

[0029] Finally, the system uses connected component analysis to mark and calculate the area of ​​all white connected regions in the image. Based on the prior assumption that "the human body occupies the largest proportion in the field of view," the algorithm retains only the largest connected regions and completely filters out other interfering blocks. After this series of complex pixel-level operations, the system is able to extract a smooth, continuous, and realistic overall human body contour. This accurate contour extraction is fundamental to subsequent waist localization and width calculation.

[0030] S4. Locate the waist area on the overall outer contour of the human body, and extract the front waist width and the side waist width respectively; S41. Identify key points of the shoulders and hips on the overall outer contour of the human body in the frontal image, and calculate the vertical distance between the shoulders and hips. S42. Determine the lumbar feature measurement layer according to the preset human anatomical proportions; S43. On the waist feature measurement layer, extract the coordinates of the left and right boundary points along the horizontal direction to obtain the front waist pixel width, and calculate the actual front waist width by combining it with the ratio conversion coefficient. ; S44. At the same waist measurement height as the frontal image, perform a lateral boundary search on the side infrared image to extract the front and rear boundary points of the side contour to obtain the pixel width of the side waist. Combine this with a scaling conversion factor to calculate the actual side waist width. .

[0031] S5. Using the front waist width and the side waist width as the major axis and minor axis of the ellipse model respectively, calculate the human waist circumference parameters.

[0032] Traditional manual measurement with a measuring tape directly obtains the perimeter of a closed curve, while infrared imaging obtains the projected width. In order to reconstruct the three-dimensional perimeter information from the two-dimensional projected data, this embodiment employs a scientific elliptical geometric fitting model.

[0033] Studies have shown that the cross-section of an adult's waist is statistically highly approximately elliptical. Within the algorithmic framework of this invention, the extracted frontal physical width... Consider it as the major axis of an ellipse, and the physical width of the side. Consider it as the minor axis of an ellipse. At this point, the calculation of the waist circumference parameter is transformed into a classic geometric problem: calculating the circumference of an ellipse given the lengths of its major and minor semi-axes.

[0034] The formula for calculating the waist circumference parameter L can be expressed as: .

[0035] This formula is extremely accurate when the difference between the major and minor axes is small, and it can fully meet the requirements of clinical medicine and daily fitness for waist circumference measurement.

[0036] Furthermore, to further improve computational stability, the data processing and control unit can introduce a multi-layer weighted averaging mechanism. Multiple frames of frontal and side infrared thermal images are continuously acquired; through time-domain mean filtering or weighted fusion processing, stable infrared thermal images with high signal-to-noise ratio are obtained. In addition, the system not only calculates the perimeter of a single measurement layer, but also continuously extracts the major and minor axis data of multiple cross-sections within a certain range (e.g., ±2 cm) around a defined waist position, and calculates a set of perimeter values. By applying a Gaussian weighted average to these values, random fluctuations caused by skin folds, respiratory movements, or minor standing deviations can be effectively reduced. The final output waist circumference parameter value is a robust result obtained through multi-dimensional geometric fitting and statistical optimization, accurately reflecting the body shape characteristics of the subject.

[0037] It should be noted that step S1, acquiring an infrared image of a standard-sized calibration plate and obtaining the pixel-to-physical-length ratio conversion coefficient, does not need to be performed before measuring the waist circumference of each subject. This step only needs to be performed during initial measurement or after system adjustment and calibration.

[0038] Example 2: Overall Architecture and Core Principle of Human Waist Circumference Measurement Device Based on Infrared Thermal Imaging refer to Figure 2 This invention discloses a human waist circumference parameter measurement device based on infrared thermal imaging. This device, serving as the physical hardware carrier of the entire measurement system, is designed with the core concept of utilizing non-contact infrared sensing technology combined with high-precision data processing capabilities to achieve automated and objective measurement of human waist circumference parameters. In the field of modern biomedicine and health monitoring, the accurate acquisition of human morphological parameters is of paramount importance. The waist circumference parameter measurement device mainly consists of an infrared thermal imager, a data processing unit, and a mechanical support structure.

[0039] The human waist circumference parameter measurement device based on infrared thermal imaging includes two infrared thermal imagers 1, a standard size calibration plate 2, a fixed bracket 3, and a data processing and control unit 4.

[0040] The core of the waist circumference measurement device lies in its at least two infrared thermal imagers 1. These two thermal imagers are cleverly positioned at a specific angle, typically orthogonal at 90 degrees to each other, to simultaneously acquire frontal and side infrared thermal images of the subject. The infrared thermal imagers employ uncooled focal plane array detectors, whose operating wavelength is mainly concentrated in the far-infrared band of 8 to 14 micrometers. This infrared thermal imager can convert minute differences in thermal radiation on the human body surface into high-contrast digital images. In other embodiments, a single infrared thermal imager can be used, rotating around the perimeter of the body, to similarly acquire frontal and side infrared thermal images of the subject. Compared to using two infrared thermal imagers, this method saves costs, but the time difference between acquiring the frontal and side infrared thermal images will increase.

[0041] To ensure measurement accuracy and consistency, the waist circumference measurement device not only includes sensors but also integrates a crucial data processing and control unit 4. This unit acts as the "brain" of the entire device, seamlessly connecting to the infrared thermal imager via a high-speed communication interface (such as Gigabit Ethernet, USB 3.0, or industrial-grade wireless protocols). The data processing and control unit 4 is responsible for receiving raw infrared thermal images from the imager, as well as handling complex control command issuance, image synchronization triggering, real-time algorithm execution, and external data transmission. In actual operation, this unit ensures that the two thermal imagers can trigger the shutter with millisecond-level synchronization accuracy, thus guaranteeing that the frontal and side images correspond to the subject's respiratory phase and standing posture at the same instant.

[0042] During initial device deployment or routine maintenance, calibration is required using a standard-sized calibration plate 2. This calibration plate possesses unique physical properties that allow it to display clear, high-contrast geometric patterns under infrared viewing. For example, the calibration plate surface can be made with a high-emissivity material (such as a special matte varnish) as the substrate, with low-emissivity metal foil embedded to form a checkerboard pattern or dot array. When the calibration plate is placed in the measurement area, the data processing and control unit acquires its image. Since the actual physical spacing of each feature point on the calibration plate is known, the processor can calculate the pixel-to-physical-length ratio conversion factor k using a perspective projection model or a simple linear mapping model.

[0043] In addition, the waist circumference measurement device typically includes a fixed support 3 to house all the aforementioned components. This frame, through scientific industrial design, ensures unobstructed optical path and stable device operation. The device is also equipped with a positioning platform 31 to standardize the subject's standing position.

[0044] Example 3: Internal Logic and Hardware Configuration of the Data Processing and Control Unit The "Data Processing and Control Unit" is the core hardware implementation of the human waist circumference parameter measurement method described in this invention. This unit is not a simple signal converter, but an embedded computing system or general-purpose computer system with high-performance computing capabilities, large-scale data buffering capabilities, and multiple communication interfaces.

[0045] From a hardware perspective, the data processing and control unit typically includes one or more high-performance processors, such as multi-core system-on-a-chip (SoC) based on the ARM architecture, digital signal processors with high-performance floating-point arithmetic capabilities, or field-programmable gate arrays (FPGAs) and graphics processing units (GPUs) that offer significant advantages when processing large-scale image matrices. To store intermediate image data, algorithm weight parameters, and final measurement results during operation, the unit is also equipped with high-bandwidth random access memory (RAM) and large-capacity flash memory or solid-state drives.

[0046] The data processing and control unit operates as follows: First, it sends a synchronous acquisition command to both infrared thermal imagers via a control interface. After the thermal imagers complete exposure and convert infrared radiation into electrical signals, the data processing and control unit receives raw frame data in real time via a dedicated image acquisition card or communication bus. This raw data is typically a grayscale image representing the temperature distribution. Subsequently, the firmware or operating system kernel running within the unit schedules pre-written software modules, i.e., "computer programs," to process the image pixel by pixel.

[0047] Furthermore, the data processing and control unit also possesses comprehensive self-diagnostic capabilities. Before each measurement is initiated, it checks the connection status of the infrared thermal imager, the remaining space in the storage medium, and the operating temperature of the processor to ensure the safety and reliability of the measurement process. This highly integrated and intelligent design makes the measuring device of this invention not merely a passive sensing tool, but a closed-loop system capable of independently completing the entire process from sensing to decision-making, and from calculation to feedback.

[0048] In the actual waist circumference measurement process, after the system extracts the frontal pixel width Wp and side pixel width Dp of the human waist, it does not perform direct calculations. Instead, it first calls the calibration matrix stored in non-volatile memory. Through coordinate transformation, the pixels in different areas of the image are converted to a standard physical plane, and then multiplied by a coefficient k. This method takes into account the perspective scaling effect that may occur when the human body is at different depths within the shooting area. This rigorous calibration mechanism is an important technical feature that distinguishes the device of this invention from ordinary consumer-grade photographic equipment.

[0049] Example 4: Adaptive Infrared Image Segmentation and Human Body Full Contour Extraction Technology The quality of infrared thermal images is greatly affected by the ambient thermal background. In order to accurately extract the human body contour from a complex background, this embodiment describes in detail an adaptive segmentation algorithm based on statistical properties.

[0050] As warm-blooded animals, the human body typically maintains a skin temperature between 31 and 34 degrees Celsius, while most indoor environments range from 20 to 26 degrees Celsius. Although this temperature difference exists, in real-world scenarios, there may be heat-generating appliances, radiators, or reflected human body heat in the background. Therefore, fixed threshold segmentation is often insufficient to adapt to varying measurement environments. The data processing and control unit analyzes the grayscale histogram of the entire infrared thermal image in real time by running specific algorithmic logic.

[0051] First, calculate the average grayscale value of all pixels in the image ( ) and standard deviation ( Using these statistics, the system generates an adaptive segmentation threshold. . ,in It is an adaptive adjustment dynamic coefficient obtained through experimental calibration. This threshold is used to binarize the image, separating pixels with values ​​higher than a certain threshold. The region is set to 1 (representing a possible human body region), and the region below T is set to 0 (representing the background). .

[0052] However, the binary images after initial segmentation often contain noise. Small, high-temperature interference sources may exist in the background, while internal voids may appear inside the human body due to clothing materials (such as thermal underwear with a metallic coating) or accessories. To address this issue, the data processing and control unit performs morphological operations on the binary image. First, a morphological opening operation (erosion followed by dilation) is performed, which effectively severs small connections and eliminates isolated noise points. Next, a morphological closing operation (dilation followed by erosion) is performed, which fills in small voids inside the human body and connects adjacent fractured areas.

[0053] Finally, the system uses connected component analysis to mark and calculate the area of ​​all white connected regions in the image. Based on the prior assumption that "the human body occupies the largest proportion in the field of view," the algorithm retains only the largest connected regions and completely filters out other interfering blocks. After this series of complex pixel-level operations, the system is able to extract a smooth, continuous, and realistic overall human body contour. This accurate contour extraction is fundamental to subsequent waist localization and width calculation.

[0054] Example 5: Waist region localization and feature point extraction based on anatomical proportions After obtaining the complete external outline of the human body, the core challenge of the measurement method of this invention is how to accurately locate the "waist" on the outline. Human body shapes vary, and traditional fixed-height measurement methods often cannot accurately correspond to the actual waist of individuals of different heights and body types.

[0055] This embodiment introduces a dynamic positioning model based on human anatomical proportions. Within the contour of a frontal infrared thermal image, the data processing and control unit first identifies a series of key anatomical reference points. By analyzing the curvature and width variation rates of the contour edges, the system can locate the highest and outermost points of the shoulders, as well as the widest point of the hips. The shoulders typically exhibit a significant abrupt change in width in the upper region of the contour, while the hips correspond to the local widest point of the lower body.

[0056] Once the longitudinal positions of the shoulders and hips are determined, the system calculates the vertical distance between them. According to general statistical principles of anthropometry, the waist is typically located within a specific proportional range along the line connecting the shoulders and hips, for example, slightly below the midpoint. The data processing and control unit performs a fine horizontal scan within this candidate longitudinal range. By comparing the lateral width of each row of pixels, the system finds the section with the smallest width, or combines this with the degree of abdominal protrusion in the side profile, to comprehensively determine the final "waist feature measurement layer."

[0057] On the defined measurement layer, the system extracts key geometric parameters from the front and side images respectively. In the front image, the pixel coordinate difference between the left and right boundary points of the contour at this height is extracted to obtain the front pixel width. In the side image, the pixel coordinates of the front and rear edges of the human contour are located using the same vertical coordinate positioning to obtain the side pixel width. Since the side image captures the front and back thickness information of the human body, this dimension is crucial for accurately describing the waist cross-section.

[0058] This dynamic search method based on anatomical proportions gives the measurement system extremely high robustness. Whether for adults of different heights and builds, or for adolescents in their growth and development period, the system can autonomously find the most representative waist position for sampling, thus avoiding errors caused by deviations in the placement of the measuring tape in traditional manual measurements.

[0059] Example 6: Risk Assessment and Data Closed Loop in Health Monitoring Systems refer to Figure 3 The health monitoring system 100 elevates the waist circumference parameter measuring device of this invention from a simple measuring tool into a comprehensive health management platform. This system uses waist circumference parameter data as its starting point to construct a closed-loop system encompassing data acquisition, storage, analysis, and early warning.

[0060] The health monitoring system 100 includes the human waist circumference parameter measuring device 10 based on infrared thermal imaging as described above, and the risk assessment module 20.

[0061] The system's risk assessment module 20 is the core of its intelligent features. This module integrates a vast health standards database, covering the World Health Organization's and various national and ethnic definitions of central obesity. When the waist circumference measurement device outputs a specific value (e.g., 95 cm), the risk assessment module immediately retrieves background parameters such as the subject's gender, age, and ethnicity for multi-dimensional matching analysis.

[0062] The assessment logic focuses not only on current absolute values ​​but also on dynamic trends. The system automatically retrieves the subject's historical measurement records and generates a waist circumference parameter change curve. If the system detects a significant increase in the subject's waist circumference within a short period, even if it has not yet exceeded the standard threshold, it will issue an early warning. This trend analysis has extremely high medical value for the early prevention of metabolic diseases such as type 2 diabetes, hypertension, and fatty liver.

[0063] Furthermore, the risk assessment module can calculate relevant derivative indicators based on waist circumference parameter data. For example, combined with the height information input by the test subject, the system can calculate the waist-to-height ratio (WHtR). Studies have shown that WHtR is more sensitive than body mass index (BMI) alone in predicting cardiovascular risk. Based on these calculation results, the system generates a richly illustrated electronic health report, which is pushed to the user's mobile app or cloud account via the communication interface between the waist circumference parameter measurement device's data processing and control unit. The report not only includes measurement results but also targeted dietary plans, exercise programs, and advice on whether medical attention is needed. This in-depth health data mining allows this invention to truly integrate into the ecosystem of modern preventive medicine.

[0064] Example 7: Anti-interference optimization of infrared thermal imaging under different environments To ensure the stable operation of the waist circumference measurement device in various complex real-world environments, this invention further explores anti-interference hardware and software optimization strategies in its detailed description. Infrared measurement is highly sensitive to environmental heat sources; therefore, auxiliary structural components are incorporated into the device design.

[0065] On a physical level, auxiliary structural components include specially designed light-shielding structures (such as light shields made of special materials). These structures not only block visible light, but more importantly, they effectively reduce external long-wave infrared radiation. For example, in office environments near windows, the infrared component of sunlight can cause severe reflection interference in thermal imaging. By scattering and absorbing incident infrared radiation, the light-shielding structure ensures that the thermal imager receives almost entirely the thermal radiation emitted by the human body itself. Furthermore, the surface of the positioning platform can be covered with a low-reflectivity, temperature-controlled material to reduce the impact of ground heat reflection on the foot contours.

[0066] At the algorithm level, the computer program running the data processing and control unit includes robust noise suppression logic. The system periodically acquires "idle" images, i.e., background heatmaps when there is no subject present. Background subtraction techniques eliminate interference from fixed heat sources in the environment (such as computer hosts and power adapters) on human contour extraction. Simultaneously, to address edge blurring caused by subtle human movements, the program employs multi-frame fusion technology. Within a few seconds of measurement time, dozens of images are continuously acquired, and time-domain weighted filtering preserves stable contour information while filtering out occasional interference signals.

[0067] Furthermore, since human skin humidity also affects infrared emissivity, the system can also acquire environmental parameters through integrated temperature and humidity sensors to make subtle compensations to the proportional conversion coefficient k. This multi-dimensional optimization from the physical layer to the algorithm layer enables the waist circumference parameter measurement device of this invention to have all-weather, multi-scene adaptability, ensuring the reliability of the output results regardless of drought or humidity, or extreme cold or heat.

[0068] Example 8: The Social Value and Privacy Advantages of Infrared Thermal Imaging Technology While describing the technical implementation of the present invention in detail, it is necessary to emphasize its significant advantages in privacy protection. Traditional visible light camera measurement methods inevitably capture the facial features and skin details of the subject, which often causes users to feel strong resistance and insecurity when measuring sensitive areas such as the waist and buttocks.

[0069] The infrared thermal imaging technology of this invention solves this problem from a physical perspective. Infrared images record temperature distribution, presenting an abstract, "thermal map"-like visual effect. In such images, facial features are highly blurred, and due to the relatively uniform heat distribution on the human surface, the image primarily shows geometric contours rather than textural details. After the data processing and control unit extracts the contour coordinates, the original thermal image can be immediately physically destroyed or completely erased; only the irreversible geometric parameters and values ​​are stored in the system.

[0070] This inherent privacy feature makes the parameter measurement device of this invention particularly suitable for deployment in semi-open settings such as public gyms, community pharmacies, and health corners in enterprises and institutions. Users do not need to worry about privacy leaks during measurement, experiencing minimal psychological pressure, which will greatly enhance public participation in health monitoring. Simultaneously, the non-contact measurement method completely eliminates the risk of cross-infection, offering significant advantages in public health management. This integration of technology and humanistic care is a crucial component of the core competitiveness of this invention.

[0071] Example 9: On the long-term operational stability and automatic calibration mechanism of the device The waist circumference measurement device described in this invention is designed to support long-term automated operation without frequent manual intervention. To achieve this, the data processing and control unit incorporates a sophisticated automatic calibration mechanism.

[0072] Because infrared thermal imagers' detectors exhibit a physical property of response drift over time (drift effect), the device performs periodic non-uniformity corrections during internal shutter operation. The data processing and control unit analyzes the temperature uniformity of the shutter baffle and adjusts the gain and offset parameters of each pixel in real time to ensure the image background remains flat.

[0073] Furthermore, to address camera pose changes caused by slight deformation or vibration of the support during long-term operation, the system establishes permanent reference calibration points on the positioning platform. These calibration points possess constant temperature characteristics (maintained, for example, by miniature heating elements). Whenever the device is started or idle, the computer program automatically detects the position of these reference points in the image. If a positional offset is detected to exceed a preset threshold, the system automatically initiates a recalibration procedure to update the pixel physical conversion coefficient k.

[0074] This automated maintenance mechanism significantly reduces equipment ownership costs. Operators do not need specialized infrared optics knowledge to ensure the equipment is always in a high-precision measurement state. Combined with a robust mechanical support structure and a highly efficient data processing unit, the waist circumference parameter measurement device of this invention exhibits extremely high industrial robustness, capable of meeting the needs of high-frequency, large-scale population screening.

[0075] Example 10: Installation, Commissioning, and Long-Term Performance Monitoring of the Device To ensure the long-term performance of the device after deployment, this embodiment also details the standard operating procedures during the installation and commissioning phases. These procedures are automatically guided by the bootloader in the data processing and control unit.

[0076] After the physical installation is completed, technicians connect to the display terminal via the data processing unit and enter the "viewpoint optimization mode". In this mode, the system overlays auxiliary lines in real time to guide technicians to fine-tune the angle of the infrared thermal imager, so that the overall outline of the subject perfectly fits within the optimal imaging area.

[0077] The commissioning phase also includes an important "environmental stress test." The data processing and control unit continuously monitors ambient temperature fluctuations over 24 hours. If the ambient temperature change is detected to be too drastic and exceeds the automatic compensation range of the thermal imager, the system will recommend that the user install a temperature-controlled backplate or a light-shielding structure from the auxiliary structural components.

[0078] After the equipment is put into operation, the system records changes in the number of blind elements and the noise equivalent temperature difference of the thermal imager detector. If a decline in hardware performance is detected that impairs contour extraction accuracy, the computer will automatically send an early warning request to the maintenance backend via the network. This full lifecycle performance management ensures that the invention maintains a high level of technical reliability in practical applications over a long period of time.

[0079] In summary, this invention, through deep integration and optimization of the "waist circumference parameter measurement device," "data processing and control unit," and "computer program," has successfully developed an efficient, accurate, and privacy-respecting solution for measuring human waist circumference parameters. This solution not only considers multi-dimensional imaging and anti-interference requirements in its hardware design, but also integrates human anatomy, statistics, and modern geometric fitting techniques in its software algorithms.

[0080] It should be noted that the above embodiments focus on waist circumference measurement. Using the same principle, this can be further extended to measuring parameters of various parts of the human body, such as hip circumference, neck circumference, thigh circumference, chest circumference, and height. With further reductions in the cost of infrared detectors and continuous improvements in edge computing capabilities, the technology involved in this invention is expected to be applied in a wider range of fields. In the future, through continuous upgrades to the computer program, the device may even achieve preliminary estimations of body composition (such as the proportion of visceral fat).

[0081] This invention not only solves the problems of human error and inconvenience in traditional parameter measurement, but also provides a digital and scientific means for health management in modern society. Its technical protection scope covers the entire chain from basic physical detection to top-level business applications, possessing extremely high technical barriers and broad application prospects.

[0082] The above embodiments are merely preferred embodiments of the present invention and should not be construed as limiting the scope of protection of the present invention. Any non-substantial changes and substitutions made by those skilled in the art based on the present invention shall fall within the scope of protection claimed by the present invention.

Claims

1. A method for measuring human body parameters based on infrared thermal imaging, characterized in that, include: Acquire frontal and side infrared thermal images of the subject; Based on the difference between the human body surface temperature and the ambient background temperature, the overall outer contour of the human body is extracted from the front infrared thermal image and the side infrared thermal image; target areas are located on the overall outer contour of the human body, and the widths of the front target areas and the side target areas are extracted respectively; the widths of the front target areas and the side target areas are used as the major axis and minor axis of the model respectively to calculate the human body shape parameters.

2. The method for measuring human body parameters based on infrared thermal imaging according to claim 1, characterized in that, Before acquiring the infrared thermal image of the subject, the system calibration step is also included: acquiring the infrared image of a standard-sized calibration plate; using the known physical length of the standard-sized calibration plate and the corresponding pixel length in the image, calculating the pixel-to-physical-length ratio conversion factor; the extraction of the width of the front target area and the width of the side target area includes: acquiring the pixel width of the front target area and the pixel width of the side target area, and converting them into the actual width of the front target area and the width of the side target area by combining the ratio conversion factor.

3. The method for measuring human body parameters based on infrared thermal imaging according to claim 1, characterized in that, The step of extracting the overall human body contour from the frontal infrared thermal image and the side infrared thermal image includes: calculating the average temperature and standard deviation of the infrared thermal image to generate an adaptive segmentation threshold; performing binarization processing on the infrared thermal image according to the adaptive segmentation threshold to generate an initial binary image; performing morphological opening and closing operations on the initial binary image in sequence, and retaining the largest connected region through connected component analysis to extract a smooth overall human body contour.

4. The method for measuring human body parameters based on infrared thermal imaging according to claim 1, characterized in that, The process of locating the target region on the overall outer contour of the human body, and extracting the width of the frontal target region and the width of the side target region, wherein the target region is the waist, includes: identifying key points of the shoulders and hips on the overall outer contour of the human body in the frontal image, and calculating the vertical distance between the shoulders and hips; determining the waist feature measurement layer according to a preset human anatomical ratio; extracting the coordinates of the left and right boundary points along the horizontal direction on the waist feature measurement layer to obtain the frontal waist width; and performing a horizontal boundary search on the side infrared image at the same waist measurement height as the frontal image to extract the front and rear boundary points of the side contour to obtain the side waist width.

5. The method for measuring human body parameters based on infrared thermal imaging according to claim 1, characterized in that, The acquisition of the frontal and side infrared thermal images of the subject simultaneously includes: continuously acquiring multiple frames of frontal and side infrared thermal images using an infrared thermal imager; and obtaining a stable infrared thermal image with a high signal-to-noise ratio through time-domain mean filtering or weighted fusion processing.

6. A human body parameter measurement device based on infrared thermal imaging, characterized in that, include: Infrared thermal imagers are used to acquire frontal and side infrared thermal images of the subject. A data processing and control unit, communicatively connected to the infrared thermal imager, is used to execute the human body parameter measurement method based on infrared thermal imaging as described in any one of claims 1 to 5.

7. The human body parameter measurement device based on infrared thermal imaging according to claim 6, characterized in that, The infrared thermal imager consists of two units, which are used to simultaneously acquire frontal and side infrared thermal images of the subject, respectively. It also includes: a fixed bracket and positioning platform for fixing the infrared thermal imager to maintain constant shooting height, angle, and distance, and to provide a standardized standing area for the subject; and a standard-sized calibration plate, set within the measurement area of ​​the positioning platform, for establishing a mapping relationship between image pixels and physical length.

8. The human body parameter measurement device based on infrared thermal imaging according to claim 7, characterized in that, Also includes: An auxiliary structural component, including a light-shielding structure, is used to reduce ambient light and temperature interference and decrease background noise.

9. A health monitoring system, characterized in that, The system includes the human body parameter measurement device based on infrared thermal imaging as described in claim 6, and further includes a risk assessment module, which is used to receive human body parameter data output by the data processing and control unit, and to assess the central obesity level and health risks of the subject based on the human body parameter data.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the human body parameter measurement method based on infrared thermal imaging as described in any one of claims 1-5.

Images