Intelligent positioning system for acupuncture points of children with tic disorders based on infrared images

Abstract

The application relates to an infrared image-based intelligent positioning system for acupuncture points of children's tic disorders. The system comprises a calculation module, which calculates a constant temperature coefficient according to the temperature standard deviation and temperature change slope of each grid in a reference frame; a calibration module, which calibrates the temperature of each pixel point according to the average temperature and constant temperature coefficient of multiple constant temperature grids to obtain a target temperature; a determination module, which determines a confidence weight according to the distance between the centroid and multiple candidate acupuncture points of the face; a clustering module, which clusters multiple variable temperature zones according to the centroid distance between the multiple variable temperature zones to obtain multiple clusters, obtains the fluctuation amplitude of the temperature change curve of each central variable temperature zone, the effective duration, the similarity between the temperature change curve and a preset model, and the confidence weight, and determines a high-confidence variable temperature zone; and a positioning module, which determines a target confidence degree according to the confidence weight and fluctuation degree of the variable temperature zone to position the acupuncture points of the face. The application can improve the accuracy of acupuncture point recognition.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to an intelligent acupuncture point positioning system for children with tic disorders based on infrared images. Background Technology

[0002] Acupoint recognition technology based on infrared thermal imaging and computer vision has demonstrated non-invasive, dynamic, and objective advantages in the auxiliary diagnosis and treatment of pediatric tic disorders, providing a new path for the visualization and quantification of TCM "syndrome differentiation and acupoint selection," and promoting the intelligent and precise development of pediatric acupuncture. However, its clinical application faces key challenges: the rapid head and facial movements caused by tic episodes easily lead to blurred thermal images and regional shifts, while the local thermal response signal of acupoints is weak and often mixed with non-specific temperature changes such as sweat evaporation and environmental interference; at the same time, children have large individual developmental differences, and standard acupoint atlases are difficult to universally match children of different ages and body types, and there is a lack of high-quality labeled time-series infrared datasets to support model generalization. These factors seriously restrict the stability and clinical credibility of this technology in multi-center, real-world application scenarios. Summary of the Invention

[0003] To address the aforementioned technical problems, the purpose of this application is to provide an intelligent acupuncture point positioning system for children with tic disorders based on infrared images. The specific technical solution adopted is as follows: In a first aspect, an intelligent acupuncture point positioning system for children with tic disorders based on infrared images is provided, the system comprising: The calculation module is used to calculate the isothermal coefficient of each grid in the reference frame of the infrared image sequence based on the temperature standard deviation and temperature change slope of each grid within a preset time period. The calibration module is used to perform temperature calibration on each pixel in each frame of infrared image based on the average temperature and isothermal coefficient of multiple isothermal grids in the isothermal region in the infrared image sequence, so as to obtain the target temperature of each pixel; the isothermal region is selected from multiple grids based on the isothermal coefficient. The determination module is used to determine the confidence weight of each temperature-changing zone based on the distance between the centroid of each temperature-changing zone and multiple candidate acupoints on the face; each temperature-changing zone consists of multiple temperature-changing points, which indicate pixels where the difference between the target temperature and the initial temperature is greater than a preset temperature. The clustering module is used to cluster multiple temperature-changing zones located in the same anatomical region with a built-in confidence weight greater than a preset weight, based on the centroid distance between multiple temperature-changing zones, to obtain multiple clusters. It obtains the fluctuation amplitude, effective duration, similarity between the temperature change curve and the preset model, and confidence weight of the temperature-changing zone in the infrared image sequence for each central temperature-changing zone, and determines the high-confidence temperature-changing zone. The central temperature-changing zone indicates the temperature-changing zone with the largest confidence weight in each cluster. The positioning module is used to determine the target confidence of each high-confidence target point based on the confidence weight of the temperature change zone to which it belongs and the fluctuation degree of the temperature change curve of the corresponding temperature change zone, so as to locate acupoints on the face according to the target confidence; the high-confidence target point indicates the centroid of the high-confidence temperature change zone.

[0004] Optionally, the calculation module is also used for: Acquire infrared image sequences and corresponding visible light images of a child's face; Multiple anatomical landmarks are extracted from visible light images, and multiple anatomical regions are constructed based on these landmarks; Based on anatomical landmarks, a pre-defined standard pediatric facial acupoint atlas is registered to the spatial coordinate system of the visible light image to obtain multiple candidate acupoints in the visible light image; Visible light images are registered with infrared image sequences to obtain multiple candidate acupoints and multiple anatomical regions in the infrared image sequence.

[0005] Optionally, the calculation module is also used for: Calculate the average displacement velocity of each anatomical landmark in a series of consecutive infrared images. If the average displacement velocity is lower than a preset static threshold, then the middle frame of the series of consecutive infrared images is determined as the reference frame. Multiple anatomical regions in the infrared image sequence are divided into grids to obtain multiple grids; Calculate the absolute values ​​of the temperature standard deviation and temperature change slope for each grid in the reference frame within a preset time period; The isothermal coefficient of each grid is determined based on the absolute value of the temperature standard deviation and the slope of temperature change within a preset time period; the isothermal coefficient is negatively correlated with the temperature standard deviation and negatively correlated with the absolute value of the slope of temperature change.

[0006] Optionally, the calibration module is also used for: In response to the grid having a isothermal coefficient greater than a preset isothermal threshold, the grid is defined as an isothermal grid. Clustering multiple adjacent isothermal grids yields at least one connected region, which is then defined as the isothermal region. The calibration coefficient of the isothermal region in each frame of infrared image is calculated by multiplying the isothermal coefficient of multiple isothermal grids in the isothermal region by the average temperature of the grid in the infrared image sequence. Based on the ratio of the sum of the product to the sum of the isothermal coefficients of multiple isothermal grids, the calibration coefficient of the isothermal region in the frame of infrared image is determined. The average calibration coefficient of multiple isothermal regions in the frame of infrared image is calculated to obtain the calibration coefficient of the frame of infrared image. Based on the calibration coefficients of each frame of the infrared image and the calibration coefficients of the reference frame, temperature calibration is performed on each pixel in the infrared image to obtain the target temperature of each pixel in the infrared image.

[0007] Optionally, the calibration module is also used for: The target calibration coefficient of the infrared image frame is determined based on the difference between the calibration coefficient of each frame and the calibration coefficient of the reference frame. The target temperature of each pixel is obtained by calculating the difference between the temperature of each pixel in each frame of infrared image and the target calibration coefficient of that frame of infrared image.

[0008] Optionally, the determining module is also used for: If the difference between the target temperature of a pixel and the temperature of the corresponding pixel in the reference frame is greater than the preset temperature, the pixel is identified as a temperature change point; the initial temperature indicates the temperature of the corresponding pixel in the reference frame for each pixel; Using temperature change points as seeds, region growth is performed based on temperature similarity to obtain multiple connected regions. The minimum convex polygon bounding box of each connected region is calculated to obtain the temperature change region. Calculate the Euclidean distance between the centroid of each temperature-changing zone and multiple candidate acupoints on the face, and determine the minimum Euclidean distance as the deviation of that temperature-changing zone; The confidence weight of each temperature-varying zone is determined by the negative of the ratio of the square of the spatial deviation to the square of a preset distance scale parameter.

[0009] Optionally, the clustering module is also used for: Based on the centroid distance between multiple temperature zones, multiple temperature zones located in the same anatomical region with a built-in confidence weight greater than a preset weight are clustered to obtain multiple clusters. The temperature zone with the largest confidence weight in each cluster is determined as the central temperature zone of the cluster. The first average temperature of the central temperature-variable zone is obtained by averaging the target temperature of multiple pixels in the central temperature-variable zone of each frame of infrared image. The second average temperature value of the central temperature-variable zone is obtained by averaging the temperatures of multiple pixels in the central temperature-variable zone of the reference frame. The average first temperature of the central temperature-changing zone in the infrared image sequence is calculated, and the average first temperature is curve-fitted to obtain the temperature change curve. The fluctuation range of the temperature change curve can be obtained by the difference between the maximum and minimum values ​​in the temperature change curve. Identify all continuous time segments from the temperature change curve that satisfy the condition that the temperature difference is greater than the preset temperature difference, and determine the duration of the longest continuous time segment as the effective duration of the central temperature change zone; the temperature difference indicates the absolute difference between the first temperature mean and the second temperature mean of the central temperature change zone; The amplitude threshold of each central temperature-changing zone is calculated based on the product of the confidence weight of each zone and the preset first adjustment coefficient. The duration threshold of each central temperature-changing zone is calculated based on the product of the confidence weight of each zone and the preset second adjustment coefficient. High-confidence temperature change zones are determined based on the fluctuation amplitude, effective duration, amplitude threshold, duration threshold, and similarity between the temperature change curve and the preset model of each central temperature change zone.

[0010] Optionally, the clustering module is also used for: If the fluctuation amplitude of the central temperature change zone is greater than the amplitude threshold of the central temperature change zone, and the effective duration of the central temperature change zone is greater than the duration threshold of the central temperature change zone, and the Pearson correlation coefficient between the temperature change curve and the preset model is greater than the preset coefficient threshold, then the central temperature change zone is determined as a high-confidence temperature change zone.

[0011] Optionally, the positioning module is also used for: The centroid of each high-confidence temperature variation region is determined as the high-confidence target point of that high-confidence temperature variation region. Calculate the product of the confidence weight of the high-confidence temperature-varying region to which each high-confidence target belongs and the preset balance parameter to obtain the confidence product of the high-confidence target. The functional confidence of the high-confidence target is calculated based on the fluctuation amplitude of the temperature change curve in the variable temperature zone to which the high-confidence target belongs, the effective duration, and the Pearson correlation coefficient between the temperature change curve and the preset model. Based on the functional confidence and confidence product of each high-confidence target, the target confidence of that high-confidence target is determined, so as to locate acupoints on the face according to the target confidence.

[0012] Optionally, the positioning module is also used for: If the target confidence of a high-confidence target is greater than or equal to the preset confidence, then the candidate acupoint associated with the high-confidence target is determined as the target acupoint on the face.

[0013] Based on common knowledge in the field, the above-mentioned preferred conditions can be combined arbitrarily to obtain various preferred embodiments of this application.

[0014] This application has the following beneficial effects: The calculation module quantifies the thermal stability of each grid in the reference frame based on the temperature standard deviation and temperature change slope within a preset time period, generating an isothermal coefficient. The calibration module performs dynamic temperature calibration on each pixel in the entire infrared image sequence based on the isothermal region formed by the selection of high isothermal coefficient grids, effectively eliminating environmental drift and system noise, and obtaining an accurate target temperature. The determination module identifies pixels whose target temperature differs from the initial temperature by more than a preset temperature as temperature change points, and aggregates them into temperature change zones. Based on the spatial distance between the centroid of each temperature change zone and multiple candidate acupoints on the face, its confidence weight is calculated. The clustering module further clusters multiple temperature change zones located within the same anatomical region and with confidence weights greater than the preset weights into clusters based on the distance between their centroids. Taking the central temperature change zone with the largest confidence weight in each cluster as a representative, the fluctuation amplitude, effective duration, and similarity to the preset model of its temperature change curve are extracted to comprehensively determine high-confidence temperature change zones. The localization module combines the confidence weights of the high-confidence temperature-varying zone with the fluctuation degree of its temperature change curve to calculate the target confidence of the corresponding high-confidence target point. Only when the target confidence meets the clinical criteria is the standard acupoint associated with that target point output as the final localization result. This achieves an end-to-end reliable mapping from the original infrared sequence to the standard acupoint, effectively suppressing mislocalization caused by sweat evaporation, micro-motion artifacts, and environmental interference. It significantly improves the specificity and robustness of acupoint recognition, providing objective and quantitative auxiliary decision-making basis for precise acupuncture treatment of tic disorders. Attached Figure Description

[0015] To more clearly illustrate the technical solutions and advantages in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a schematic diagram of the structure of an intelligent acupuncture point positioning system for pediatric tic disorders based on infrared images in one embodiment. Figure 2 This is a flowchart of an intelligent acupuncture point localization method for childhood tic disorders based on infrared images, as described in one embodiment. Figure 3 This is a schematic diagram of the structure of an electronic device in one embodiment. Detailed Implementation

[0017] To further illustrate the technical means and effects adopted by this application to achieve the intended purpose of the invention, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of an intelligent acupuncture point positioning system for children's tic disorders based on infrared images, as proposed in this application. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains.

[0019] The following description, in conjunction with the accompanying drawings, details the specific scheme of the intelligent acupuncture point positioning system for children's tic disorders based on infrared images provided in this application. For example... Figure 1 As shown, the system includes: The calculation module 11 is used to calculate the isothermal coefficient of the grid based on the temperature standard deviation and temperature change slope of each grid in the reference frame of the infrared image sequence within a preset time period.

[0020] In one embodiment, the computing module is further configured to: Acquire infrared image sequences and corresponding visible light images of a child's face; Multiple anatomical landmarks are extracted from visible light images, and multiple anatomical regions are constructed based on these landmarks; Based on anatomical landmarks, a pre-defined standard pediatric facial acupoint atlas is registered to the spatial coordinate system of the visible light image to obtain multiple candidate acupoints in the visible light image; Visible light images are registered with infrared image sequences to obtain multiple candidate acupoints and multiple anatomical regions in the infrared image sequence.

[0021] Since children's acupoints have a fixed anatomical distribution pattern on the head and face, and the temperature changes caused by tic disorders have local and dynamic characteristics, in order to accurately capture the specific temperature changes of acupoints and distinguish them from normal tissues, it is necessary to fuse and register the collected visible light and infrared images to ensure that there is a unified quantitative reference for subsequent use.

[0022] Simultaneously acquire visible light images and infrared thermal imaging sequences of the child's head and face. Utilize the texture information of the visible light images or the emissivity anomalies of the infrared images to generate a non-skin interference mask using a semantic segmentation model or threshold-morphology method. This mask is used to mark areas that are not physically exposed skin, such as large areas covered solely by hair (excluding eyebrows), areas covered by glasses or jewelry, and external obstructions like medical tape. When subsequently screening constant-temperature areas, areas marked by the non-skin interference mask are excluded to avoid thermal radiation interference with the establishment of the reference benchmark. When locating acupoints based on confidence levels, if a candidate acupoint (such as Zanzhu in the eyebrow area) partially falls within the non-skin interference mask, its confidence weight is reduced based on the proportion of obstruction, rather than being directly eliminated, allowing physicians to make a final judgment based on clinical experience.

[0023] Using a deep learning-based 68-point facial landmark detection model, stable anatomical landmarks such as the pupil center, nose tip, corner of mouth, and tragus are accurately located on visible light images, and multiple anatomical regions are constructed based on these landmarks. Building upon this, an affine transformation is used to proportionally align the national standard pediatric facial acupoint atlas with the visible light images of the affected children, establishing a unified global coordinate system.

[0024] Using key points such as the center of the eyes, the tip of the nose, and the corners of the mouth as references, the face is divided into several anatomical functional areas, such as the forehead area, the periorbital area, the cheek area, and the perioral area. Each area corresponds to a common acupoint cluster area (such as the periorbital area corresponding to Jingming, Zanzhu, and Tongziliao, etc.) to obtain multiple candidate acupoints in the visible light image. The visible light image is then registered with the infrared image sequence to obtain multiple candidate acupoints and multiple anatomical regions in the infrared image sequence.

[0025] In one embodiment, the computing module is further configured to: Calculate the average displacement velocity of each anatomical landmark in a series of consecutive infrared images. If the average displacement velocity is lower than a preset static threshold, then the middle frame of the series of consecutive infrared images is determined as the reference frame. Multiple anatomical regions in the infrared image sequence are divided into grids to obtain multiple grids; Calculate the absolute values ​​of the temperature standard deviation and temperature change slope for each grid in the reference frame within a preset time period; The isothermal coefficient of each grid is determined based on the absolute value of the temperature standard deviation and the slope of temperature change within a preset time period; the isothermal coefficient is negatively correlated with the temperature standard deviation and negatively correlated with the absolute value of the slope of temperature change.

[0026] Within each anatomical region, a uniformly sized grid matrix is ​​further subdivided. The grid size is set according to the image resolution, preferably 1 / 20 to 1 / 30 of the total pixel size of the facial region, to ensure that it can cover the potential influence range of a single acupoint (such as Jingming acupoint). All grids are uniquely coded in the format [region code_row and column number], for example, the left periorbital region is numbered […]. ,...].

[0027] It should be noted that the grid size, distance scale parameters and other parameters used in this system are all proportional values ​​relative to the currently detected face size rather than fixed pixel values. Since the differences in children's facial size are reflected in the number of pixels, and the above proportional parameters have scale invariance, they can be applied to children of different ages and different facial sizes.

[0028] The entire temporal infrared sequence is defined as containing F frames of images, with frame indices as follows: To ensure a stable and reliable reference temperature, the average displacement velocity of all key points within multiple consecutive frames (e.g., 10 frames) is calculated. If the average velocity is lower than a preset static threshold (e.g., 2 pixels / frame), the middle frame of that segment is selected as the reference frame. Otherwise, continue waiting until a static segment that meets the conditions is detected; any frame in the sequence is called the current frame t. All subsequent calculations involving single-frame operations are performed on the current frame t; all time-series analysis is performed on the frame from... The time period up to t or the entire sequence.

[0029] Stable anatomical landmarks such as the pupil center, nasal apex, and tragus point are extracted, and their grid numbers and global coordinates are recorded as invariant references for subsequent multi-temporal image matching. In preparation for subsequent temporal analysis, the geometric center of each secondary grid is preset as a dynamic functional candidate point, and its coordinates are recorded to track the dynamic temperature changes in that local area.

[0030] In facial infrared images, areas outside acupoints that do not experience significant temperature changes compared to acupoint areas are considered relatively isothermal regions. To eliminate individual differences and environmental interference, an isothermal reference region for calibration needs to be quantized and selected within the effective skin mask. This is done in the initial reference frame. In the middle, perform the following operations: Calculate the average temperature standard deviation for each grid cell over a preset time period (e.g., 1 second before the twitching occurs). The isothermal coefficient is obtained by considering the slope k of the average temperature change. The isothermal coefficient for each grid cell is... The calculation formula is: in, Temperature standard deviation for each grid, The slope of the temperature change in this grid.

[0031] The calibration module 12 is used to perform temperature calibration on each pixel in each frame of infrared image based on the average temperature and isothermal coefficient of multiple isothermal grids in the isothermal region in the infrared image sequence, so as to obtain the target temperature of each pixel.

[0032] The constant temperature region is selected from multiple grids based on the constant temperature coefficient.

[0033] In one embodiment, the calibration module is also used for: In response to the grid having a isothermal coefficient greater than a preset isothermal threshold, the grid is defined as an isothermal grid. Clustering multiple adjacent isothermal grids yields at least one connected region, which is then defined as the isothermal region. The calibration coefficient of the infrared image frame is determined by summing the products of the isothermal coefficients of multiple isothermal grids in the isothermal region of each frame of infrared image and the average temperature of the grid in the infrared image sequence, and by the ratio of the sum of the products to the sum of the isothermal coefficients of multiple isothermal grids. Based on the calibration coefficients of each frame of the infrared image and the calibration coefficients of the reference frame, temperature calibration is performed on each pixel in the infrared image to obtain the target temperature of each pixel in the infrared image.

[0034] Specifically, the calibration module is also used for: The target calibration coefficient of the infrared image frame is determined based on the difference between the calibration coefficient of each frame and the calibration coefficient of the reference frame. The target temperature of each pixel is obtained by calculating the difference between the temperature of each pixel in each frame of infrared image and the target calibration coefficient of that frame of infrared image.

[0035] The constant temperature threshold can be set according to the actual situation, for example, 0.8.

[0036] In response to a grid having a isothermal coefficient greater than a preset isothermal threshold, the grid is designated as an isothermal grid. Multiple adjacent isothermal grids are clustered to obtain at least one connected region, which is then designated as an isothermal region. All information generated in the above steps (standard coordinates, multi-level grids, anatomical landmarks, candidate acupoints, and isothermal grids) is mapped to a unified global coordinate system, providing a precise spatial and data foundation for dynamic feature extraction and selection.

[0037] In actual childhood tics, they are characterized by involuntary, repetitive, and rapid movements, often starting in the head and face (approximately 80% of cases begin with the eyes or face). The movements are stereotyped and frequent (several to dozens of times per minute). This process causes changes in the patient's posture. Based on this, feature extraction and analysis are performed on changes in infrared images over time to observe the trends in tissue changes within constant-temperature and temperature-varying regions, thereby identifying and locating specific acupoints.

[0038] To address head and facial movements caused by tics, firstly, based on the fixed anatomical feature points (such as pupils and nasal alae) in step one, inter-frame affine or thin plate spline (TPS) transformations are performed on multiple visible light images. Since the visible light images and infrared images have already been spatially registered, the transformation relationship of the visible light images can be applied to the corresponding infrared images, thereby solving the problem of positional shift of the same anatomical point in consecutive infrared frames.

[0039] Based on extracted anatomical landmarks, inter-frame displacement velocities are calculated in real time. When the displacement velocity of a key point exceeds the tic attack threshold (e.g., 5 pixels / frame), a tic attack is identified. The extracted anatomical landmarks are used to calculate the transformation matrix (e.g., affine or homography transformation) between the current frame and the reference frame in the visible light image. Geometric correction (motion compensation) is then performed on the current frame's infrared image. Since the visible light and infrared images are spatially registered, the transformation matrix can be directly applied to the corresponding infrared image, ensuring the correspondence between pixels and anatomical positions remains unchanged. Corrected temperature data is continuously collected, generating a continuous temperature change curve. The system continuously collects temperature data throughout the entire tic attack process (resting phase → attack phase → recovery phase). Once the displacement velocity falls below the resting threshold (e.g., 2 pixels / frame) and enters the recovery phase, the recovery phase temperature T1 is collected, and the relative temperature is calculated. , Reference frame The temperature.

[0040] For the isothermal region identified in the preceding steps, its average temperature value in each frame is tracked throughout the entire time series. This yields a system reference temperature curve for all frames. This curve is used to eliminate systematic interferences such as ambient temperature drift. The calibration coefficient for each isothermal region in the t-th frame infrared image is also shown. The calculation formula is: ; Where i represents the i-th isothermal grid, and n represents the number of isothermal grids in the isothermal region of each frame of infrared image. Let be the isothermal coefficient of the i-th isothermal grid. Let be the average temperature of the i-th isothermal grid in the t-th frame of the infrared image.

[0041] The target temperature of the p-th pixel in the t-th frame of the infrared image. The calculation formula is: ; in, Let p be the temperature value of the p-th pixel in the t-th frame of the infrared image. Let be the calibration coefficients for the t-th frame of the infrared image. Reference frame The calibration coefficient.

[0042] The determination module 13 is used to determine the confidence weight of the temperature-changing zone based on the distance between the centroid of each temperature-changing zone and multiple candidate acupoints on the face.

[0043] Each temperature-changing zone consists of multiple temperature-changing points, which indicate pixels where the difference between the target temperature and the initial temperature is greater than the preset temperature.

[0044] In one embodiment, the determining module is further configured to: If the difference between the target temperature of a pixel and the temperature of the corresponding pixel in the reference frame is greater than the preset temperature, the pixel is identified as a temperature change point; the initial temperature indicates the temperature of the corresponding pixel in the reference frame for each pixel; Using temperature change points as seeds, region growth is performed based on temperature similarity to obtain multiple connected regions. The minimum convex polygon bounding box of each connected region is calculated to obtain the temperature change region. Calculate the Euclidean distance between the centroid of each temperature-changing zone and multiple candidate acupoints on the face, and determine the minimum Euclidean distance as the deviation of that temperature-changing zone; The confidence weight of each temperature-varying zone is determined by the negative of the ratio of the square of the spatial deviation to the square of a preset distance scale parameter.

[0045] In each frame of calibrated infrared image, calculate the p-th pixel of the t-th frame infrared image and its relationship with the reference frame. temperature difference .Will greater than the preset temperature (e.g., 0.3) The pixels marked with significant temperature changes are used as seeds. Region growing is performed based on temperature similarity to obtain multiple connected regions. The minimum convex polygon bounding box of each connected region is calculated to obtain the temperature-changing region. .

[0046] For each temperature-changing zone Calculate its average temperature change intensity Space area In addition, the geometric centroid of the temperature-changing region is extracted in each frame to form its temporal motion trajectory, which is used to evaluate the region's stability performance.

[0047] For each temperature-changing zone Calculate the local region where it is located in the reference frame. isothermal coefficient ,like If the area is unstable before the twitching (such as a sweaty area), then its temperature change is judged as noise and should be removed or downweighted.

[0048] The retained temperature-changing zones are associated with the standard acupoint distribution from the above steps. For each temperature-changing zone... Calculate the Euclidean distance from its centroid to all candidate acupoints, and take the minimum value. As a deviation, the confidence weight is calculated. Define the preset distance scale parameters The value is 1 / 20 of the width of the currently detected face bounding box (if the face width is 300 pixels, then...). The value is approximately 15 pixels, used to control the attenuation range of spatial weights; adjusted based on the density of acupoint distribution.

[0049] Variable temperature zone Confidence weight The calculation formula is: ; in, It is an exponential function. Variable temperature zone The square of the deviation, These are the preset distance scale parameters.

[0050] Clustering module 14 is used to cluster multiple temperature-changing zones located in the same anatomical region with a built-in confidence weight greater than a preset weight based on the centroid distance between multiple temperature-changing zones, to obtain multiple clusters, and to obtain the fluctuation amplitude, effective duration, similarity between the temperature change curve and the preset model, and confidence weight of the temperature-changing zone of each central temperature-changing zone in the infrared image sequence, so as to determine the high-confidence temperature-changing zone.

[0051] The central variable temperature zone indicates the variable temperature zone with the highest confidence weight in each cluster.

[0052] In one embodiment, the clustering module is also used for: Based on the centroid distance between multiple temperature zones, multiple temperature zones located in the same anatomical region with a built-in confidence weight greater than a preset weight are clustered to obtain multiple clusters. The temperature zone with the largest confidence weight in each cluster is determined as the central temperature zone of the cluster. The first average temperature of the central temperature-variable zone is obtained by averaging the target temperature of multiple pixels in the central temperature-variable zone of each frame of infrared image. The second average temperature value of the central temperature-variable zone is obtained by averaging the temperatures of multiple pixels in the central temperature-variable zone of the reference frame. The average first temperature of the central temperature-changing zone in the infrared image sequence is calculated, and the average first temperature is curve-fitted to obtain the temperature change curve. The fluctuation range of the temperature change curve can be obtained by the difference between the maximum and minimum values ​​in the temperature change curve. Identify all continuous time segments from the temperature change curve that satisfy the condition that the temperature difference is greater than the preset temperature difference, and determine the duration of the longest continuous time segment as the effective duration of the central temperature change zone; the temperature difference indicates the absolute difference between the first temperature mean and the second temperature mean of the central temperature change zone; The amplitude threshold of each central temperature-changing zone is calculated based on the product of the confidence weight of each zone and the preset first adjustment coefficient. The duration threshold of each central temperature-changing zone is calculated based on the product of the confidence weight of each zone and the preset second adjustment coefficient. High-confidence temperature change zones are determined based on the fluctuation amplitude, effective duration, amplitude threshold, duration threshold, and similarity between the temperature change curve and the preset model of each central temperature change zone.

[0053] Specifically, the clustering module is also used for: If the fluctuation amplitude of the central temperature change zone is greater than the amplitude threshold of the central temperature change zone, and the effective duration of the central temperature change zone is greater than the duration threshold of the central temperature change zone, and the Pearson correlation coefficient between the temperature change curve and the preset model is greater than the preset coefficient threshold, then the central temperature change zone is determined as a high-confidence temperature change zone.

[0054] The threshold values ​​in this embodiment can be adaptively adjusted based on the sensitivity (NETD) of the infrared thermal imager and the ambient temperature. For example, the isothermal threshold can be set to a value representing a percentage of the standard deviation of the average temperature across the entire image. times.

[0055] Based on the above-described primary anatomical region grid (such as the periorbital region and the frontal region), regions within the same anatomical region and with confidence weights are classified. In the variable-temperature region, nearest-neighbor clustering is performed based on the Euclidean distance between their centroids, with 2-3 clusters per group (3 for dense regions, 2 for sparse regions, and isolated holes can be grouped separately), resulting in clusters. The temperature variation region with the highest confidence weight in each cluster is determined as the central temperature variation region of that cluster. The preset weight is used to screen temperature-changing zones that closely match the standard acupoint locations. Here, a value of 0.6 is preferred, and this value can be adjusted within the range [0.5, 0.8] according to the device resolution or clinical needs.

[0056] For each cluster Using the central temperature-changing region as a representative, the average target temperature of multiple pixels in the central temperature-changing region of each cluster in the t-th frame infrared image is extracted. The average first temperature of the central temperature-changing zone in the infrared image sequence is calculated, and curve fitting is performed on the average first temperature to obtain the temperature change curve. The fluctuation amplitude of the temperature change curve is then calculated. : , This is the maximum value in the temperature curve. This is the minimum value in the temperature curve. Based on the average temperature of multiple pixels in the central temperature-changing zone of the reference frame, a second average temperature value for that central temperature-changing zone is obtained, and its effective duration is [not specified]. From Find all conditions that satisfy the following conditions during the entire time interval until the end of the sequence. For consecutive time periods exceeding a preset temperature difference (e.g., 0.5℃), the length of the longest consecutive segment is taken as the [length of the segment]. The value is used to identify all time segments where the temperature difference is greater than a preset temperature difference. If the interval between two adjacent segments that meet the condition is less than a preset tolerance time (e.g., 0.5 seconds), they are merged into a single continuous segment. The longest duration of the merged segment is calculated as the effective duration, where... It is the absolute difference between the first and second average temperatures in the central temperature-varying zone.

[0057] Define the ideal pathological response model as follows: This template is generated based on clinical observation data of infrared thermal imaging of acupoints on the head and face of healthy children. It simulates the three-stage normal thermophysiological process of rest → congestion → deterioration, and includes 11 data points at equal time intervals. The values ​​in the template are relative changes, with a peak value of 1.0 corresponding to the maximum temperature change amplitude during the congestion period of acupoints in healthy children, which is used for subsequent correlation comparison with the temperature change curves of sick children.

[0058] The extracted variable-length temperature variation sequence is resampled by linear interpolation to make the number of data points consistent with the ideal template vector length (11 points), ensuring that the sequence length for calculating the Pearson correlation coefficient matches.

[0059] Response Mode Score The Pearson correlation coefficient is obtained by calculating the temperature change curve of the central temperature variation zone and the preset model. Before calculating the Pearson correlation coefficient, the collected temperature change curve is time-warped or resampled to ensure its length matches the preset model. The preset model is only an exemplary feature template; in practical applications, the peak value and duration parameters can be adjusted according to individual differences (such as age and physical condition). The preset model is a standardized three-stage time series curve, representing the slow temperature rise (approximately 0.5 seconds) before the twitching. The attack peaks rapidly during the seizure (approximately 0.3 seconds). The typical thermophysiological response pattern is a slow decline during the remission period (approximately 1.0 s).

[0060] For fluctuation range Its basic threshold At this time, its amplitude threshold Then it is: ; in, The preset first adjustment coefficient can be 0.5. Variable temperature zone The confidence weight.

[0061] For effective duration Its basic threshold At this point, its duration threshold Then it is: ; in, The preset second adjustment coefficient can be 0.5. Variable temperature zone The confidence weight.

[0062] like ; ; If the temperature change zone is located within the effective skin mask, then the central temperature change zone is identified as a high-confidence temperature change zone. The coefficient threshold is used for this purpose. The preferred value is 0.7, which can be adjusted within the range [0.6, 0.85] based on the device sampling rate or the child's age.

[0063] The positioning module 15 is used to determine the target confidence of the high confidence target point based on the confidence weight of the variable temperature zone to which each high confidence target point belongs and the fluctuation degree of the temperature change curve of the corresponding variable temperature zone, so as to locate the acupoints on the face according to the target confidence.

[0064] Among them, the high-confidence target point indicates the centroid of the high-confidence temperature-varying region.

[0065] In one embodiment, the positioning module is further configured to: The centroid of each high-confidence temperature variation region is determined as the high-confidence target point of that high-confidence temperature variation region. Calculate the product of the confidence weight of the high-confidence temperature-varying region to which each high-confidence target belongs and the preset balance parameter to obtain the confidence product of the high-confidence target. The functional confidence of the high-confidence target is calculated based on the fluctuation amplitude of the temperature change curve in the variable temperature zone to which the high-confidence target belongs, the effective duration, and the Pearson correlation coefficient between the temperature change curve and the preset model. Based on the functional confidence and confidence product of each high-confidence target, the target confidence of that high-confidence target is determined, so as to locate acupoints on the face according to the target confidence.

[0066] Specifically, if the target confidence of a high-confidence target is greater than or equal to the preset confidence, then the candidate acupoint associated with the high-confidence target is determined as the target acupoint on the face.

[0067] If the central temperature variation region is a high-confidence temperature variation region, then the centroid of the central temperature variation region is identified as a high-confidence target point. Otherwise, mark it as a low-confidence candidate point and do not output it.

[0068] Calculate the target confidence for each high-confidence target. The formula for calculating the target confidence level is: ; in, This is a balance parameter used for adjustment. and Contribution ratio to the target confidence level The value range is [0.5, 0.8]. The specific values ​​are determined based on clinical validation data using a grid search method, that is, using the marked actual acupoint locations as the standard, and traversing the validation set. Candidate values ​​were selected to achieve the highest accuracy in acupoint location. The value serves as a balancing parameter in initial scenarios where validation data is insufficient. 0.6 is acceptable. High-confidence target The confidence weight of the high-confidence temperature variation region. High-confidence target Functional confidence, , That is, the reference value for the maximum temperature change range. As a reference value for the longest effective duration, the weight coefficients for each feature are a=b=c=1.0; this weight setting is suitable for the benchmark validation scenario of this embodiment; after accumulating multi-center clinical data, the weight coefficients can be dynamically adjusted through multivariate regression analysis or other algorithms to improve the accuracy of target identification. High-confidence target The fluctuation range within the high-confidence temperature variation zone. High-confidence target The effective duration of the high-confidence temperature variation zone.

[0069] High-confidence targets Match the acupoints with standard acupoint charts to identify their corresponding acupoint names and associated meridians. Based on clinical guidelines for childhood tic disorders, establish a priority set of acupoints (e.g., Jingming, Zanzhu, Sizhukong, Sibai, Taiyang, etc.). If a matched acupoint does not belong to this set, it is downgraded.

[0070] Establish final judgment rules: target point An acupoint is identified as a positive acupoint if and only if: Such as (pre-set reliability) If the matched acupoint belongs to the clinical priority set and is located within the effective skin mask, then the point is the location of the acupoint.

[0071] Output results: The acupoint locations are marked on the original infrared image, with different colors distinguishing the confidence level, and the interference mask area is semi-transparently displayed. The output is structured data containing information such as acupoint name, meridian, comprehensive confidence level, maximum temperature change range, and coordinates. Combined with professional physician clinical diagnosis, it is convenient for review and further feedback correction, so as to obtain accurate and correct acupoint identification results.

[0072] Those skilled in the art should understand that, although there are individual differences in facial size among children, the confidence weight, fluctuation amplitude threshold, and effective duration threshold used in this system are all designed with dynamic adaptive mechanisms. These mechanisms can tolerate spatial positioning deviations caused by differences in facial size to a certain extent. The acupoint positioning accuracy in the children population using the above fixed parameters reaches a clinically acceptable level.

[0073] The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this application according to actual needs.

[0074] This application also provides a method for intelligent localization of acupuncture points for tic disorders in children based on infrared images, such as... Figure 2 As shown, the method includes: S21. Calculate the isothermal coefficient of each grid in the reference frame of the infrared image sequence based on the temperature standard deviation and temperature change slope within a preset time period. S22. Based on the average temperature and isothermal coefficient of multiple isothermal grids in the infrared image sequence, perform temperature calibration on each pixel in each frame of the infrared image to obtain the target temperature of each pixel; the isothermal region is selected from multiple grids based on the isothermal coefficient. S23. Determine the confidence weight of each temperature-changing zone based on the distance between the centroid of each temperature-changing zone and multiple candidate acupoints on the face; each temperature-changing zone consists of multiple temperature-changing points, which indicate pixels where the difference between the target temperature and the initial temperature is greater than the preset temperature. S24. Based on the centroid distance between multiple temperature-changing zones, cluster multiple temperature-changing zones located in the same anatomical region with a confidence weight greater than a preset weight to obtain multiple clusters. Obtain the fluctuation amplitude, effective duration, similarity between the temperature change curve and the preset model, and confidence weight of the central temperature-changing zone in the infrared image sequence for each central temperature-changing zone to determine the high-confidence temperature-changing zone. The central temperature-changing zone indicates the temperature-changing zone with the largest confidence weight in each cluster. S25. Based on the confidence weight of the temperature change zone to which each high-confidence target point belongs and the fluctuation degree of the corresponding temperature change curve, determine the target confidence of the high-confidence target point, so as to locate the acupoints on the face according to the target confidence; the high-confidence target point indicates the centroid of the high-confidence temperature change zone.

[0075] For the method embodiments, since they are basically corresponding to the system embodiments, the relevant parts can be referred to in the description of the system embodiments.

[0076] It should be understood that, although Figure 2 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order in which these steps are executed, and they can be performed in other orders. Furthermore, Figure 2 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0077] Figure 3 This is a schematic diagram of the structure of an electronic device according to an example embodiment of this application. The electronic device includes a memory, a processor, and a computer program stored in the memory and used to run on the processor. When the processor executes the computer program, it implements the method described in any of the above embodiments. Figure 3 The electronic device 30 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0078] like Figure 3As shown, the electronic device 30 can be manifested as a general-purpose computing device, such as a server device. The components of the electronic device 30 may include, but are not limited to: at least one processor 31, at least one memory 32, and a bus 33 connecting different system components (including memory 32 and processor 31).

[0079] Bus 33 includes a data bus, an address bus, and a control bus.

[0080] The memory 32 may include volatile memory, such as random access memory (RAM) 321 and / or cache memory 322, and may further include read-only memory (ROM) 323.

[0081] The memory 32 may also include a program tool 325 (or utility) having a set (at least one) program module 324, such program module 324 including but not limited to: an operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0082] The processor 31 executes various functional applications and data processing, such as the methods provided in any of the above embodiments, by running computer programs stored in the memory 32.

[0083] Electronic device 30 can also communicate with one or more external devices 34 (e.g., keyboard, pointing device, etc.). This communication can be performed via input / output (I / O) interface 35. Furthermore, electronic device 30 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public network, such as the Internet) via network adapter 36. As shown, network adapter 36 communicates with other modules of electronic device 30 via bus 33. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in conjunction with electronic device 30, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems.

[0084] It should be noted that although several units / modules or sub-units / modules of the electronic device have been mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to the embodiments of this application, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided and embodied by multiple units / modules.

[0085] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method provided in any of the above embodiments.

[0086] The readable storage medium may be more specifically adopted, including but not limited to: portable disk, hard disk, random access memory, read-only memory, erasable programmable read-only memory, optical storage device, magnetic storage device, or any suitable combination thereof.

[0087] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0088] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the method described in any of the above embodiments.

[0089] The program code for executing the computer program product of this application can be written in any combination of one or more programming languages. The program code can be executed entirely on the user device, partially on the user device, as a standalone software package, partially on the user device and partially on a remote device, or entirely on a remote device.

[0090] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0091] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these modifications and improvements all fall within the protection scope of this application.

[0092] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A smart acupuncture point positioning system for children with tic disorders based on infrared images, characterized in that, The system includes: The calculation module is used to calculate the isothermal coefficient of each grid in the reference frame of the infrared image sequence based on the temperature standard deviation and temperature change slope of each grid within a preset time period. The calibration module is used to perform temperature calibration on each pixel in each frame of infrared image based on the average temperature and isothermal coefficient of multiple isothermal grids in the isothermal region in the infrared image sequence, so as to obtain the target temperature of each pixel; the isothermal region is selected from multiple grids based on the isothermal coefficient. The determination module is used to determine the confidence weight of each temperature-changing zone based on the distance between the centroid of each temperature-changing zone and multiple candidate acupoints on the face; each temperature-changing zone consists of multiple temperature-changing points, which indicate pixels where the difference between the target temperature and the initial temperature is greater than a preset temperature. The clustering module is used to cluster multiple temperature-changing zones located in the same anatomical region with a built-in confidence weight greater than a preset weight, based on the centroid distance between multiple temperature-changing zones, to obtain multiple clusters. It obtains the fluctuation amplitude, effective duration, similarity between the temperature change curve and the preset model, and confidence weight of the temperature-changing zone in the infrared image sequence for each central temperature-changing zone, and determines the high-confidence temperature-changing zone. The central temperature-changing zone indicates the temperature-changing zone with the largest confidence weight in each cluster. The positioning module is used to determine the target confidence of each high-confidence target point based on the confidence weight of the temperature change zone to which it belongs and the fluctuation degree of the temperature change curve of the corresponding temperature change zone, so as to locate acupoints on the face according to the target confidence; the high-confidence target point indicates the centroid of the high-confidence temperature change zone.

2. The intelligent acupuncture point positioning system for children's tic disorders based on infrared images as described in claim 1, characterized in that, The computing module is also used for: Acquire infrared image sequences and corresponding visible light images of a child's face; Multiple anatomical landmarks are extracted from visible light images, and multiple anatomical regions are constructed based on these landmarks; Based on anatomical landmarks, a pre-defined standard pediatric facial acupoint atlas is registered to the spatial coordinate system of the visible light image to obtain multiple candidate acupoints in the visible light image; Visible light images are registered with infrared image sequences to obtain multiple candidate acupoints and multiple anatomical regions in the infrared image sequence.

3. The intelligent acupuncture point positioning system for children's tic disorders based on infrared images as described in claim 2, characterized in that, The computing module is also used for: Calculate the average displacement velocity of each anatomical landmark in a series of consecutive infrared images. If the average displacement velocity is lower than a preset static threshold, then the middle frame of the series of consecutive infrared images is determined as the reference frame. Multiple anatomical regions in the infrared image sequence are divided into grids to obtain multiple grids; Calculate the absolute values ​​of the temperature standard deviation and temperature change slope for each grid in the reference frame within a preset time period; The isothermal coefficient of each grid is determined based on the absolute value of the temperature standard deviation and the slope of temperature change within a preset time period; the isothermal coefficient is negatively correlated with the temperature standard deviation and negatively correlated with the absolute value of the slope of temperature change.

4. The intelligent acupuncture point positioning system for children's tic disorders based on infrared images as described in claim 1, characterized in that, The calibration module is also used for: In response to the grid having a isothermal coefficient greater than a preset isothermal threshold, the grid is defined as an isothermal grid. Clustering multiple adjacent isothermal grids yields at least one connected region, which is then defined as the isothermal region. The calibration coefficient of the isothermal region in each frame of infrared image is calculated by multiplying the isothermal coefficient of multiple isothermal grids in the isothermal region by the average temperature of the grid in the infrared image sequence. Based on the ratio of the sum of the product to the sum of the isothermal coefficients of multiple isothermal grids, the calibration coefficient of the isothermal region in the frame of infrared image is determined. The average calibration coefficient of multiple isothermal regions in the frame of infrared image is calculated to obtain the calibration coefficient of the frame of infrared image. Based on the calibration coefficients of each frame of the infrared image and the calibration coefficients of the reference frame, temperature calibration is performed on each pixel in the infrared image to obtain the target temperature of each pixel in the infrared image.

5. The intelligent acupuncture point positioning system for children's tic disorders based on infrared images as described in claim 4, characterized in that, The calibration module is also used for: The target calibration coefficient of the infrared image frame is determined based on the difference between the calibration coefficient of each frame and the calibration coefficient of the reference frame. The target temperature of each pixel is obtained by calculating the difference between the temperature of each pixel in each frame of infrared image and the target calibration coefficient of that frame of infrared image.

6. The intelligent acupuncture point positioning system for children's tic disorders based on infrared images as described in claim 1, characterized in that, The determining module is also used for: If the difference between the target temperature of a pixel and the temperature of the corresponding pixel in the reference frame is greater than the preset temperature, the pixel is identified as a temperature change point; the initial temperature indicates the temperature of the corresponding pixel in the reference frame for each pixel; Using temperature change points as seeds, region growth is performed based on temperature similarity to obtain multiple connected regions. The minimum convex polygon bounding box of each connected region is calculated to obtain the temperature change region. Calculate the Euclidean distance between the centroid of each temperature-changing zone and multiple candidate acupoints on the face, and determine the minimum Euclidean distance as the deviation of that temperature-changing zone; The confidence weight of each temperature-varying zone is determined by the negative of the ratio of the square of the spatial deviation to the square of a preset distance scale parameter.

7. The intelligent acupuncture point positioning system for children's tic disorders based on infrared images as described in claim 1, characterized in that, The clustering module is also used for: Based on the centroid distance between multiple temperature zones, multiple temperature zones located in the same anatomical region with a built-in confidence weight greater than a preset weight are clustered to obtain multiple clusters. The temperature zone with the largest confidence weight in each cluster is determined as the central temperature zone of the cluster. The first average temperature of the central temperature-variable zone is obtained by averaging the target temperature of multiple pixels in the central temperature-variable zone of each frame of infrared image. The second average temperature value of the central temperature-variable zone is obtained by averaging the temperatures of multiple pixels in the central temperature-variable zone of the reference frame. The average first temperature of the central temperature-changing zone in the infrared image sequence is calculated, and the average first temperature is curve-fitted to obtain the temperature change curve. The fluctuation range of the temperature change curve can be obtained by the difference between the maximum and minimum values ​​in the temperature change curve. Identify all continuous time segments from the temperature change curve that satisfy the condition that the temperature difference is greater than the preset temperature difference, and determine the duration of the longest continuous time segment as the effective duration of the central temperature change zone. The temperature difference indicates the absolute difference between the first and second average temperatures in the central temperature-varying zone; The amplitude threshold of each central temperature-changing zone is calculated based on the product of the confidence weight of each zone and the preset first adjustment coefficient. The duration threshold of each central temperature-changing zone is calculated based on the product of the confidence weight of each zone and the preset second adjustment coefficient. High-confidence temperature change zones are determined based on the fluctuation amplitude, effective duration, amplitude threshold, duration threshold, and similarity between the temperature change curve and the preset model of each central temperature change zone.

8. The intelligent acupuncture point positioning system for pediatric tic disorders based on infrared images as described in claim 7, characterized in that, The clustering module is also used for: If the fluctuation amplitude of the central temperature change zone is greater than the amplitude threshold of the central temperature change zone, and the effective duration of the central temperature change zone is greater than the duration threshold of the central temperature change zone, and the Pearson correlation coefficient between the temperature change curve and the preset model is greater than the preset coefficient threshold, then the central temperature change zone is determined as a high-confidence temperature change zone.

9. The intelligent acupuncture point positioning system for children's tic disorders based on infrared images as described in claim 2, characterized in that, The positioning module is also used for: The centroid of each high-confidence temperature variation region is determined as the high-confidence target point of that high-confidence temperature variation region. Calculate the product of the confidence weight of the high-confidence temperature-varying region to which each high-confidence target belongs and the preset balance parameter to obtain the confidence product of the high-confidence target. The functional confidence of the high-confidence target is calculated based on the fluctuation amplitude of the temperature change curve in the variable temperature zone to which the high-confidence target belongs, the effective duration, and the Pearson correlation coefficient between the temperature change curve and the preset model. Based on the functional confidence and confidence product of each high-confidence target, the target confidence of that high-confidence target is determined, so as to locate acupoints on the face according to the target confidence.

10. The intelligent acupuncture point positioning system for children's tic disorders based on infrared images as described in claim 9, characterized in that, The positioning module is also used for: If the target confidence of a high-confidence target is greater than or equal to the preset confidence, then the candidate acupoint associated with the high-confidence target is determined as the target acupoint on the face.

Images