Human body temperature compensation method, device and equipment based on monocular vision and medium

Abstract

The invention relates to the technical field of intelligent nursing and provides a human body temperature compensation method, device and equipment based on monocular vision and a medium, aiming at solving the problem that the existing temperature measurement technology is low in accuracy in body temperature detection of a nursed object. The method comprises the following steps: shooting at least one target heat source according to a preset distance sequence and a preset temperature range to obtain a thermal infrared temperature sequence; the thermal infrared temperature sequence is preprocessed, and the compensation relation between the temperature measurement value and the actual shooting distance is obtained; acquiring an actual target distance of the nursed object according to a preset visible light image and an actual visible light image of the nursed object; acquiring an actual body temperature value of the nursed object according to the actual thermal infrared image of the nursed object; according to the actual body temperature value, the actual target distance and the compensation relation, the corrected body temperature value of the nursed object is obtained. The body temperature detection accuracy of the nursed object can be improved, and intelligent nursing is achieved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent nursing technology, and in particular to a human body temperature compensation method, device, equipment and medium based on monocular vision. Background Art

[0002] Monitoring the body temperature of a cared-for person is crucial to their health and safety, including infants, adults, and the elderly. An elevated body temperature in a cared-for person is often an early symptom of infection or other health issues. For example, a fever may indicate a viral or bacterial infection, such as the flu, pneumonia, or a urinary tract infection. Regularly monitoring body temperature allows for early detection of abnormal temperatures and prompt medical intervention, reducing potential health risks and helping parents better care for their children. When a cared-for person experiences an abnormal temperature, parents can take appropriate action or seek medical assistance. Regularly measuring and recording body temperature helps establish a health record for the cared-for person, providing a reference for future medical decisions. Existing human body temperature measurement technologies primarily include infrared point temperature technology, visible light technology, and thermal imaging + blackbody technology. Infrared point temperature technology uses an infrared sensor to measure infrared radiation emitted from the human body and calculate the temperature, but it can only measure the temperature of a single point and is significantly affected by environmental factors. Visible light technology measures body temperature by capturing visible light images of the human body. However, due to spatial variations in the captured images, such as position and angle, obtaining accurate body temperatures can be challenging, especially for subjects in complex environments with frequent movements. Thermal imaging plus blackbody technology uses a thermal infrared camera to capture infrared radiation emitted by the human body or object, generating a temperature image. A blackbody is an idealized thermal radiation source with completely predictable radiation characteristics. In a thermal imaging system, a blackbody is placed within the field of view. The camera is calibrated by measuring the blackbody's known temperature and radiation intensity to improve and calibrate temperature measurements. The blackbody radiation source provides a stable and known amount of radiation, enabling precise calibration of the thermal imaging camera and ensuring accurate temperature measurements. However, while a blackbody can reduce environmental interference, changes in ambient temperature can still affect device stability and measurement results. Furthermore, thermal infrared images may reflect thermal radiation from the environment, affecting measurement accuracy.

[0003] Therefore, in the monitoring scenario, how to more accurately detect the body temperature of the person being cared for, provide technical support for the health monitoring of the person being cared for, and realize intelligent care is an urgent problem to be solved. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a method, apparatus, device, and medium for human body temperature compensation based on monocular vision, so as to solve the problem of low accuracy in temperature detection of a cared-for object in the prior art.

[0005] In a first aspect, an embodiment of the present invention provides a method for human body temperature compensation based on monocular vision, the method comprising:

[0006] photographing at least one target heat source according to a preset distance sequence and a preset temperature range to obtain a thermal infrared temperature sequence, wherein the thermal infrared temperature sequence includes temperature measurement values of the target heat source in a plurality of thermal infrared images, and the actual temperature and / or actual photographing distance of the target heat source in each of the thermal infrared images is different;

[0007] Preprocessing the thermal infrared temperature sequence to obtain a compensation relationship between the temperature measurement value and the actual shooting distance;

[0008] Obtaining an actual target distance of the object being cared for based on a preset visible light image and an actual visible light image of the object being cared for, wherein the preset visible light image is obtained at a predetermined distance between the object being cared for and the visible light vision module;

[0009] Obtaining the actual body temperature of the subject under care based on the actual thermal infrared image of the subject under care, wherein the actual body temperature of the subject under care is obtained at the actual shooting distance between the subject under care and the thermal infrared vision module;

[0010] A corrected body temperature value of the object being cared for is obtained according to the actual body temperature value, the actual target distance and the compensation relationship.

[0011] Preferably, photographing at least one target heat source according to a preset distance sequence and a preset temperature range to obtain a thermal infrared temperature sequence includes:

[0012] photographing the target heat source according to a preset distance sequence to obtain a thermal infrared image at each actual temperature;

[0013] The thermal infrared images are sorted by size according to a preset distance to obtain a thermal infrared temperature sequence.

[0014] Preferably, the preprocessing of the thermal infrared temperature sequence to obtain a compensation relationship between the temperature measurement value and the actual shooting distance includes:

[0015] Performing difference calculations on the temperature measurement values and actual temperatures of the target heat source at each preset distance in the preset distance sequence to obtain a first temperature difference sequence corresponding to each preset distance;

[0016] Processing each of the first temperature difference value sequences according to a least squares method or a nonlinear curve fitting method to obtain a relationship function between each preset distance and each temperature measurement value;

[0017] Polynomial fitting is performed on each of the relationship functions to obtain the compensation relationship.

[0018] Preferably, obtaining the actual target distance of the object being cared for according to the preset visible light image and the actual visible light image of the object being cared for comprises:

[0019] Acquire a preset visible light image and an actual visible light image;

[0020] Identify the object being cared for according to a preset neural network model, a preset visible light image, and an actual visible light image, and obtain a first target detection frame and a second target detection frame, wherein the preset neural network model is constructed based on YOLO;

[0021] An actual target distance is obtained according to the first target detection frame, the second target detection frame, and a first preset algorithm.

[0022] Preferably, obtaining the actual target distance according to the first target detection frame, the second target detection frame, and a first preset algorithm includes:

[0023] Acquire a first width and a first height of the first object detection frame according to the first object detection frame;

[0024] Acquire a second width and a second height of the second object detection frame according to the second object detection frame;

[0025] Calculating the first width and the first height to obtain an area of a first detection frame;

[0026] Calculate the second width and the second height to obtain an area of a second detection frame;

[0027] The actual target distance is obtained by calculating the area of the first detection frame and the area of the second detection frame.

[0028] Preferably, calculating the area of the first detection frame and the area of the second detection frame to obtain the actual target distance includes:

[0029] Inputting the actual visible light image into a pre-trained facial key point detection model to determine whether there are any key points missing in the actual visible light image;

[0030] When a key point is missing, calculating the area of the first detection frame and the area of the second detection frame to obtain an area ratio;

[0031] determining an initial distance according to the area ratio;

[0032] Identify missing key points in the actual visible light image, obtain the key point missing type, and obtain the dynamic compensation factor corresponding to the key point missing type;

[0033] The initial distance is corrected according to the dynamic compensation factor to obtain the actual target distance.

[0034] Preferably, before acquiring the actual target distance of the object being cared for based on the preset visible light image and the actual visible light image of the object being cared for, the method further includes:

[0035] Acquiring a predetermined distance between the object being cared for and the visible light vision module and an image of the object being cared for captured at the predetermined distance between the object being cared for and the visible light vision module;

[0036] Performing facial analysis on the image of the person being cared for according to the predetermined distance to obtain a facial analysis result, wherein the facial analysis includes facial key point detection and matching;

[0037] According to the facial analysis result, when the face of the person being cared for in the image of the person being cared for presents a complete frontal face state, using the image of the person being cared for as the preset visible light image;

[0038] When the face of the object being cared for in the image of the object being cared for presents an incomplete frontal face state, the target image is discarded and a new image of the object being cared for is recaptured, wherein the incomplete frontal face state includes the face being blocked, the side face, and the face not appearing.

[0039] In a second aspect, an embodiment of the present invention provides a device for detecting sleep of a cared-for object based on thermal infrared images, the device comprising:

[0040] a thermal infrared temperature sequence acquisition module, which photographs at least one target heat source according to a preset distance sequence and a preset temperature range to obtain a thermal infrared temperature sequence;

[0041] a preprocessing module, which preprocesses the thermal infrared temperature sequence to obtain a compensation relationship between the temperature measurement value and the actual shooting distance;

[0042] A distance estimation module, which obtains the actual measured distance of the object being cared for based on the preset visible light image and the actual visible light image of the object being cared for;

[0043] The actual body temperature acquisition module obtains the actual body temperature value of the object being cared for based on the actual thermal infrared image of the object being cared for;

[0044] The body temperature compensation module obtains a corrected body temperature value of the object being cared for according to the actual body temperature value, the actual target distance and the compensation relationship.

[0045] In a third aspect, an embodiment of the present invention provides an electronic device comprising: at least one processor, at least one memory, and computer program instructions stored in the memory, which, when executed by the processor, implement the method of the first aspect of the above-mentioned embodiment.

[0046] In a fourth aspect, an embodiment of the present invention provides a storage medium having computer program instructions stored thereon, which implements the method of the first aspect of the above-mentioned embodiment when the computer program instructions are executed by a processor.

[0047] In summary, the beneficial effects of the present invention are as follows:

[0048] The embodiment of the present invention provides a human body temperature compensation method, device, equipment and medium based on monocular vision, which shoots at least one target heat source according to a preset distance sequence and a preset temperature range to obtain a thermal infrared temperature sequence. The data collection performed at different distances and at different temperatures can help the system better adapt to various actual usage situations, and can more comprehensively understand and correct the measurement deviation of the thermal infrared imaging system; the thermal infrared temperature sequence is preprocessed to obtain a compensation relationship between the temperature measurement value and the actual shooting distance, and a compensation relationship between the temperature measurement value and the actual shooting distance is established by analyzing and processing the thermal infrared temperature sequence. This relationship can be used to correct the measurement error caused by the distance change, and reduce the impact of the error on the result in the actual measurement; the actual target distance of the object being cared for is obtained according to the preset visible light image and the actual visible light image of the object being cared for, and the actual target distance can enable the subsequent body temperature compensation algorithm to Further adjust the temperature measurement value to improve the accuracy of the overall body temperature measurement value of the cared object; obtain the actual body temperature value of the cared object according to the actual thermal infrared image of the cared object. The thermal infrared image is not affected by changes in the visible light environment and can stably obtain body temperature data under different lighting conditions and adapt to a variety of environments. At the same time, thermal infrared technology allows non-contact measurement, which is especially important for the cared object and can reduce interference and discomfort to the cared object; obtain the corrected body temperature value of the cared object according to the actual body temperature value, the actual target distance and the compensation relationship, and adjust the actual body temperature value by combining the actual body temperature value and the estimated distance and using the compensation relationship. The compensation relationship is used to correct the measurement error caused by different distances, and can correct the body temperature deviation caused by changes in the measurement distance, thereby reducing system errors, providing more accurate corrected body temperature values of the cared object, providing technical support for body temperature monitoring of the cared object, and realizing intelligent care. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work, and these are all within the scope of protection of the present invention.

[0050] Figure 1 This is a flow chart of a method for human body temperature compensation based on monocular vision according to an embodiment of the present invention;

[0051] Figure 2 This is a flow chart of a method for human body temperature compensation based on monocular vision according to an embodiment of the present invention;

[0052] Figure 3 This is another flow chart of a method for human body temperature compensation based on monocular vision according to an embodiment of the present invention;

[0053] Figure 4 This is another flow chart of a method for human body temperature compensation based on monocular vision according to an embodiment of the present invention;

[0054] Figure 5 This is another flow chart of a method for human body temperature compensation based on monocular vision according to an embodiment of the present invention;

[0055] Figure 6 1 is a schematic structural diagram of a monocular vision-based human body temperature compensation device according to an embodiment of the present invention;

[0056] Figure 7 Schematic diagram of the structure of the device according to the embodiment of the present invention. DETAILED DESCRIPTION

[0057] The features and exemplary embodiments of various aspects of the present invention will be described in detail below. In order to make the objects, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below in conjunction with the accompanying drawings and Examples. It should be understood that the specific embodiments described herein are only configured to explain the present invention and are not configured to limit the present invention. For those skilled in the art, the present invention can be implemented without the need for some of these specific details. The following description of the embodiments is merely to provide a better understanding of the present invention by illustrating examples of the present invention.

[0058] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, the elements defined by the phrase "comprising..." do not exclude the presence of other identical elements in the process, method, article, or device comprising the elements.

[0059] It should be noted that all actions of acquiring signals, information or data in the present invention are performed in compliance with the corresponding local data protection laws and policies and with authorization from the corresponding device owner.

[0060] Example 1

[0061] See Figure 1 The embodiment of the present invention provides a method, device, equipment and medium for human body temperature compensation based on monocular vision, the method comprising:

[0062] S1. photographing at least one target heat source according to a preset distance sequence and a preset temperature range to obtain a thermal infrared temperature sequence, wherein the thermal infrared temperature sequence includes temperature measurement values of the target heat source in a plurality of thermal infrared images, and the actual temperature and / or actual photographing distance of the target heat source in each thermal infrared image is different;

[0063] The preset distance sequence includes a series of different shooting distances set in advance when shooting thermal infrared images, such as multiple fixed distances from 1 meter, 2 meters to 5 meters. These distances are used to simulate the different distances between the camera and the target heat source in actual use, so as to collect temperature data at different distances; the preset temperature range includes the temperature range that the shooting object (target heat source) needs to cover during the collection process, for example, set to 20°C to 50°C. This range is used to ensure that the captured image can cover the temperature changes that may occur in the target heat source under different conditions. There may be errors in the response of the thermal infrared camera at different distances and temperatures. By shooting at different preset temperature ranges and distances, the temperature measurement accuracy of the thermal infrared system under different conditions can be calibrated, thereby improving the overall measurement accuracy.

[0064] Preferably, see Figure 2 , photographing at least one target heat source according to a preset distance sequence and a preset temperature range, and obtaining a thermal infrared temperature sequence includes:

[0065] S11, photographing the target heat source according to a preset distance sequence to obtain a thermal infrared image at each actual temperature;

[0066] Preset distance sequences can help calibrate and verify the performance of thermal infrared cameras, ensuring that they can provide reliable image data at various distances. By shooting at different distances and comparing images at different distances with standard or expected thermal distribution images, a more comprehensive understanding of the target's thermal characteristics can be achieved, improving data accuracy.

[0067] Specifically, a thermal infrared temperature image measured by a thermal infrared module is obtained by capturing each actual temperature under a preset distance sequence of a single heat source. The single heat source refers to a single heating black body, which is obtained by artificial constant temperature heating. The actual temperature mainly refers to the body temperature range of the object being cared for. Here, eight temperature values are selected, including integers T (35°C, 36°C, 37°C, 38°C, 39°C, 40°C, 41°C, and 42°C). The actual shooting distance is mainly obtained based on the actual safety distance monitored by the object being cared for. Here, it is set to five values: 0.5 meters, 0.8 meters, 1.1 meters, 1.4 meters, and 1.7 meters. The object being cared for refers to a person who needs to be continuously monitored or cared for, usually including infants, the elderly, patients, or people with mobility difficulties.

[0068] S12. Sort the thermal infrared images by size according to a preset distance sequence to obtain a thermal infrared temperature sequence;

[0069] Temperature sequences sorted by distance can help identify changes in the target's heat source at different distances and understand the target's thermal characteristics. At the same time, sorting and analyzing temperature sequences provides clear data comparison, helping to verify and calibrate the accuracy of thermal infrared imaging systems.

[0070] Specifically, the thermal infrared images are sorted by size according to a preset distance sequence, and there are 5*8=40 data in total. That is, for each actual shooting distance, the thermal infrared module measures 8 actual temperatures to obtain a thermal infrared temperature sequence R1.

[0071] S2. Preprocessing the thermal infrared temperature sequence to obtain a compensation relationship between the temperature measurement value and the actual shooting distance;

[0072] Temperature measurements from thermal infrared images can be affected by shooting distance. For example, when moving away from the target, the temperature resolution in the image may decrease, affecting measurement accuracy. By establishing a compensation relationship, temperature measurements at different distances can be standardized, facilitating comparison and analysis of data from different distances. Preprocessing the thermal infrared temperature series can effectively reduce measurement deviations caused by distance variations, thereby improving data reliability and validity.

[0073] Preferably, see Figure 3 , preprocessing the thermal infrared temperature sequence to obtain a compensation relationship between the temperature measurement value and the actual shooting distance includes:

[0074] S21. Acquire a first temperature difference sequence within the preset distance sequence based on the temperature measurement values of the target heat sources, wherein the first temperature difference sequence is a difference between the temperature measurement values of each target heat source and each preset temperature value within the preset distance sequence;

[0075] The first temperature difference sequence can be used to adjust and calibrate the thermal infrared imaging system. By understanding the measurement errors at different distances, the system can be properly corrected to improve the overall measurement accuracy. It is also possible to find a solution to optimize the measurement conditions to obtain more accurate results.

[0076] Specifically, for each temperature measurement value T(i), the difference ΔT(i) = R1(i) - T(i) between the temperature measurement value of the thermal infrared module at each preset distance and each of the preset temperature values is calculated. For each distance, there are 8 difference values, a total of 5*8=40 difference values, and a first temperature difference sequence is obtained.

[0077] S22. Processing each of the first temperature difference value sequences according to a least squares method or a nonlinear curve fitting method to obtain a relationship function between a preset distance and a temperature measurement value;

[0078] By obtaining the relationship function between the preset distances and the temperature measurement value, the temperature measurement characteristics of the target at different distances can be accurately described, the thermal infrared imaging system can be calibrated, and the system settings can be adjusted to reduce the impact of distance on the temperature measurement value, thereby improving measurement accuracy.

[0079] Specifically, the least squares method is a statistical analysis technique used to fit data by minimizing the squared difference between the observed values and the model's predicted values. It is particularly important in regression analysis, where it is used to determine the best fit line or curve so that the predicted values are as close as possible to the actual data. The least squares method is expressed as follows:

[0080] Objective function = ∑(theoretical value - actual value) 2

[0081] The theoretical value is the target function to be fitted, which is in the form of m samples with only one feature: (x i ,y i )(i=1,2,3...,m), the sample is fitted by a general polynomial with f(x) of degree n, a(α0,α1,α2...α n) is a parameter, the least squares method is to find a set of α0 such that Minimum, that is, Based on this, the present invention applies the least square method to perform nonlinear fitting on the ΔT sequence of each temperature to obtain the function G(T) that can best describe the relationship between the distance and the temperature difference at that temperature. i ,d j ), where T represents temperature and d represents distance.

[0082] Polynomial functions offer a high degree of flexibility and can capture complex nonlinear relationships. The order of the polynomial can be adjusted based on the actual data, enabling fitting of various data distributions. In measured data, there may be local fluctuations or noise. The polynomial function can smooth these fluctuations by adjusting the order of the polynomial, thereby better capturing the overall trend of the data. An important feature is the ability to balance overfitting and underfitting by adjusting the order. If the order is too low, the data may not fit well (underfitting); if the order is too high, the noise may be overfitted (overfitting). By selecting the optimal order through an optimization process, a balance can be found between the two, resulting in the best fitting effect. The following is a specific implementation:

[0083] Start with a low polynomial order n = 1 and gradually increase the order. For each temperature Ti, use the polynomial form Perform fitting and use the least squares method to calculate the fitting coefficients α0, α1, α2...α n The error after fitting is the mean squared error (MSE), which is used to evaluate the fitting effect. The goal is to minimize the error between the fitting function and the actual data. The MSE expression is as follows:

[0084]

[0085] The key to this process is selecting the optimal polynomial order. If the polynomial order is too low, the fit may be insufficient and the error may be large; if the order is too high, it may lead to overfitting, which will increase the error. Therefore, by calculating the errors of different orders and selecting the polynomial order with the minimum error, we can ensure that the compensation function fits the data well without losing its generalization ability due to overfitting, and thus ensure the reliability of the compensation function under different temperatures and distances.

[0086] The order of the polynomial is gradually increased, and the fitting process and error calculation are repeated. The fitting errors of different orders are compared, and the polynomial order n with the smallest error is recorded to obtain the relationship function between each of the preset distances and the temperature measurement value within the preset temperature range.

[0087] S23. Perform polynomial fitting processing on each of the relationship functions to obtain the compensation relationship.

[0088] According to the relationship function between each of the preset distances and the temperature measurement value The eight functions G(T1,d), G(T2,d), ...G(T8,d) corresponding to the eight temperature measurement values are integrated into a continuous temperature-distance compensation function F'(T,d) through a polynomial function fitting method to obtain the compensation relationship between the temperature measurement value and the actual shooting distance, thereby realizing accurate compensation prediction of distance changes at any temperature.

[0089] S3. Obtaining an actual target distance of the subject under care based on a preset visible light image and an actual visible light image of the subject under care, wherein the preset visible light image is obtained at a predetermined distance between the subject under care and the visible light vision module;

[0090] Specifically, in real-world monitoring scenarios, the location of the subject is not fixed; the distance between the subject and the camera may vary. Therefore, estimating the actual distance and adjusting the temperature measurement in real time can improve the stability and consistency of the measurement results. By obtaining the actual target distance, the temperature measurement system can maintain high accuracy and reliability. Accurate temperature monitoring is particularly important for special groups such as infants, as temperature data with minimal error can better reflect the infant's actual health status.

[0091] Preferably, before S3, the method further includes:

[0092] S301: Acquire a predetermined distance between the object being cared for and the visible light vision module and an image of the object being cared for captured at the predetermined distance between the object being cared for and the visible light vision module;

[0093] Specifically, the visible light vision module is controlled to capture images of the object being cared for at a set fixed distance, wherein the images of the object being cared for are used for subsequent key point detection and posture judgment.

[0094] S302: performing facial analysis on the image of the person being cared for according to the predetermined distance to obtain a facial analysis result, wherein the facial analysis includes facial key point detection and matching;

[0095] Specifically, based on the preset distance at which the image was captured in S301, a keypoint detection model adapted to that distance is invoked to extract the facial region and locate keypoints in the image of the person being cared for. Subsequently, a matching algorithm is used to compare the detected keypoints with a standard frontal face template to determine the integrity and frontal pose of the face in the current image. This step not only improves the robustness of keypoint detection but also avoids misjudgments of keypoints due to varying shooting angles, thus laying the foundation for selecting the optimal image.

[0096] S303: When, according to the facial analysis result, the face of the person being cared for in the image of the person being cared for shows a complete frontal face, using the image of the person being cared for as the preset visible light image;

[0097] Specifically, the analysis results from S302 determine whether a complete frontal face is detected in the current image. This means that the current image has a complete number of key points, a balanced distribution of key points, and a high degree of match with the frontal face template. If these conditions are met, the current image is considered high-quality and representative, and the system uses it as a standard visible light image for subsequent processing, such as modeling, comparison, or distance calibration. By selecting only the complete frontal face image as a reference, errors in subsequent temperature estimation can be effectively avoided, thereby improving the stability and reliability of the overall detection system.

[0098] S304: When the face of the object being cared for in the image of the object being cared for shows an incomplete frontal face state, the target image is removed and a new image of the object being cared for is recaptured, wherein the incomplete frontal face state includes a face that is blocked, a side face, and a face that does not appear.

[0099] Specifically, if the analysis result in step S302 indicates that the current image has an incomplete frontal face, the system will automatically determine that the image is an invalid image and remove it in this step. Specific incomplete states include serious missing facial key points (for example, eyes, nose or mouth are not detected), obvious side face posture (key points are distributed to one side) or the face area cannot be detected in the image. After removing the image, the system automatically triggers the image acquisition module to reshoot until a complete frontal face image that meets the standards is obtained. This strategy can prevent subsequent processing errors caused by poor image quality, help the system continuously output high-quality input data, and ensure the accuracy and consistency of modules such as face recognition, temperature fitting, and distance estimation.

[0100] Preferably, see Figure 4 , obtaining the actual target distance of the object under care according to the preset visible light image and the actual visible light image of the object under care includes:

[0101] S31, obtaining a preset visible light image and an actual visible light image;

[0102] The preset visible light image P1 is captured at a predetermined distance and records the subject's normal body temperature. This provides a fixed comparison baseline for subsequent compensation calculations in actual measurements. The actual visible light image P2, obtained during the actual measurement process, is captured under actual application conditions. The actual shooting distance may differ from the preset distance. By comparing P1 and P2, the actual target distance can be determined, allowing the necessary compensation to be applied to the subject's temperature measurement data.

[0103] Specifically, the preset visible light image P1 refers to the normal body temperature image of the cared object obtained by the user through the visible light vision module at a predetermined distance of 1m before use; the actual visible light image P2 refers to the normal body temperature image of the cared object taken by the user through the visible light vision module at the actual shooting distance before use.

[0104] S32. Identify the object being cared for according to a preset neural network model, a preset visible light image, and an actual visible light image, and obtain a first target detection frame and a second target detection frame, wherein the preset neural network model is constructed based on YOLO;

[0105] By using the preset neural network model YOLOV8s to detect the preset visible light image and the actual visible light image, the monitored object is identified. In the recognition result, the first target detection frame R1 detected in the preset visible light image and the second target detection frame R2 detected in the actual visible light image can achieve accurate target location and size comparison. The first target detection frame provides standard reference information, while the second target detection frame reflects the target position and size changes under actual measurement conditions. Integrating the target detection frame data to accurately adjust the compensation model improves system robustness.

[0106] Specifically, the preset visible light image P1 and the actual visible light image P2 are sent to the YOLOV8s model for detection, and the target of the cared object is identified. In the recognition result, the first target detection frame R1 (x, y, w, h) of the preset visible light image and the second target detection frame R2 (x, y, w, h) of the actual visible light image are obtained, where x represents the horizontal position of the upper left corner of the target frame in the image, y represents the vertical position of the upper left corner of the target frame in the image, w represents the width of the target frame, and h represents the height of the target frame.

[0107] S33. Obtaining an actual target distance based on the first target detection frame, the second target detection frame, and a first preset algorithm;

[0108] Preferably, the S33 includes:

[0109] S331: Acquire a first width and a first height of the first object detection frame according to the first object detection frame;

[0110] S332: Acquire a second width and a second height of the second object detection frame according to the second object detection frame;

[0111] S333: Calculate the first width and the first height to obtain an area of a first detection frame;

[0112] S334: Calculate the second width and the second height to obtain an area of a second detection frame;

[0113] S335: Calculate the first detection frame area and the second detection frame area to obtain the actual target distance.

[0114] The width w and height h of the target detection box will be different in the preset image and the actual image due to the change in distance. By comparing the two detection boxes, the actual target distance can be calculated.

[0115] Specifically, the first preset algorithm expression of the actual target distance is as follows:

[0116]

[0117] This estimation method uses the proportional change between the first target detection frame and the second target detection frame to infer the actual target distance as the basis for body temperature measurement compensation.

[0118] Preferably, the S335 includes:

[0119] S3351: Inputting the actual visible light image into a pre-trained facial key point detection model to determine whether there are any key points missing in the actual visible light image;

[0120] Specifically, by inputting the actual visible light image into a trained and highly robust facial key point detection model, multiple predefined standard key points in the facial area (such as the corners of the eyes, the tip of the nose, the corners of the mouth, the chin, etc.) are automatically detected. The detection results are compared with the standard key point template to determine whether there is a key point missing phenomenon, that is, the model fails to return the valid position information of certain key points. This step helps to identify the key point loss problem caused by occlusion (such as hats, hand occlusions, baby pacifiers, etc.) or posture changes (such as side face, pitch), thereby providing a judgment basis for subsequent distance correction and improving the robustness and adaptability of the system.

[0121] S3352: When a key point is missing, calculate the area of the first detection frame and the area of the second detection frame to obtain an area ratio;

[0122] Specifically, the area of the first detection frame in the reference image (i.e., the area of the standard face frame captured at a preset distance) and the area of the second detection frame in the current actual visible light image (i.e., the area of the currently detected face frame) are first calculated. Subsequently, the two area values are proportionally calculated to obtain an area ratio value, which serves as a quantitative basis for preliminarily estimating the change in the relative distance between the current face and the device. As a basic feature for distance estimation, the area ratio can provide a certain degree of distance estimation reference in the presence of occlusion, and is particularly suitable for situations with light occlusion or partial missing images.

[0123] S3353: Determine an initial distance based on the area ratio;

[0124] Specifically, based on the ratio of the areas of the first and second detection frames, combined with a preset reference distance (e.g., one meter when capturing the baseline image), an area proportionality formula is used to derive an initial distance estimate for the current image. This initial distance is a basic estimate in an uncorrected state. Although errors may exist when key points are missing, it serves as a baseline distance value before introducing compensation factors. This method is computationally simple and highly real-time, making it suitable for real-time execution in embedded or mobile systems, saving computing resources for subsequent compensation processing.

[0125] S3354: Identify missing key points in the actual visible light image, obtain a key point missing type, and obtain a dynamic compensation factor corresponding to the key point missing type;

[0126] Specifically, by analyzing the positions and areas of missing key points in the actual visible light image, the missing type is identified, such as missing eye key points, nose tip key points, mouth corner key points, or facial edge key points. Based on a preset mapping table of key point missing types and corresponding dynamic compensation factors, the system retrieves the most matching compensation factor value. The dynamic compensation factor has a numerical range of less than 1 and is used to reflect the degree of reduction in the detection frame area that may be caused by the missing key points, and is used for subsequent distance correction operations. This design takes into account the differences in estimation results caused by different types of occlusion, and improves the distance estimation accuracy of the system in complex shooting scenes.

[0127] S3355: Correct the initial distance according to the dynamic compensation factor to obtain the actual target distance.

[0128] Specifically, the initial distance obtained is used as a base estimate, and then combined with a dynamic compensation factor to correct the initial estimate. This correction method is to divide the initial distance by the compensation factor to obtain the actual target distance. This correction mechanism can effectively compensate for the face frame area error caused by missing key points, making the final estimated actual distance between the baby and the device closer to the actual situation, thereby further improving the accuracy and reliability of the subsequent body temperature compensation function calculation. In addition, in an optional solution, the distance value can be weighted and fused with the output of the monocular depth estimation model to achieve high-precision distance estimation through multi-source fusion.

[0129] S4. Acquire the actual body temperature of the subject under care based on the actual thermal infrared image of the subject under care, wherein the actual body temperature of the subject under care is acquired at an actual shooting distance between the subject under care and the thermal infrared vision module;

[0130] The actual body temperature value provides actual data support for subsequent body temperature compensation, which ensures that the algorithm can effectively cope with various measurement distances and environmental changes. During actual use, the actual body temperature value can be obtained in real time and compensated to obtain the corrected body temperature value, which improves the real-time and accuracy of the body temperature measurement system.

[0131] Specifically, the actual thermal infrared image of the object being cared for is acquired by shooting at an actual shooting distance using the thermal infrared module, thereby acquiring the actual body temperature value R2 of the object being cared for.

[0132] S5. Obtaining a corrected body temperature value of the object being cared for based on the actual body temperature value, the actual target distance, and the compensation relationship;

[0133] The actual body temperature value is corrected through the compensation relationship, the measurement error caused by the distance change is corrected, and the influence of the actual measurement conditions on the body temperature measurement results of the cared object is taken into account. After the compensation adjustment, the real body temperature of the cared object can be reflected more accurately.

[0134] Preferably, see Figure 5 Obtaining a corrected body temperature value of the object being cared for according to the actual body temperature value, the actual target distance, and the compensation relationship includes:

[0135] S51, obtaining a first temperature deviation according to the actual body temperature value, the actual target distance, and the compensation relationship;

[0136] According to the actual body temperature value R2 and the actual target distance Dis, R2 and Dis are substituted into the compensation relationship F'(T, d) to obtain the first temperature deviation ΔT expected =F'(T R2 ,Dis).

[0137] S52: The cared-for object compensates and adjusts the actual body temperature value according to the first temperature deviation to obtain a corrected body temperature value of the cared-for object.

[0138] According to the first temperature deviation ΔT expected The actual body temperature value R2 is compensated to obtain the corrected body temperature value T of the object being cared for. true , the compensation adjustment formula is as follows:

[0139] T true =R2+ΔT expected

[0140] R2 and ΔT expected The sum is the corrected body temperature of the person being cared for.

[0141] Example 2

[0142] See also Figure 6 The embodiment of the present invention provides a human body temperature compensation device based on monocular vision, the device comprising:

[0143] Specifically, a human body temperature compensation device based on monocular vision provided by an embodiment of the present invention is used, and the device includes: a thermal infrared temperature sequence acquisition module, which shoots at least one target heat source according to a preset distance sequence and a preset temperature range to obtain a thermal infrared temperature sequence; a preprocessing module, which preprocesses the thermal infrared temperature sequence to obtain a compensation relationship between the temperature measurement value and the actual shooting distance; a distance estimation module, which obtains the actual measured distance of the cared object according to a preset visible light image and an actual visible light image of the cared object; an actual body temperature acquisition module, which obtains the actual body temperature value of the cared object according to the actual thermal infrared image of the cared object; and a body temperature compensation module, which obtains the corrected body temperature value of the cared object according to the actual body temperature value, the actual target distance and the compensation relationship.

[0144] This device can collect data at varying distances and temperatures, helping the system better adapt to various practical scenarios and providing a more comprehensive understanding and correction of measurement errors in thermal infrared imaging systems. By analyzing and processing thermal infrared temperature sequences, a compensation relationship is established between temperature measurements and actual imaging distance. This relationship can be used to correct measurement errors caused by varying distances, minimizing the impact of these errors on actual measurement results. The actual target distance allows subsequent temperature compensation algorithms to further adjust temperature measurements, improving overall accuracy of the subject's temperature. Thermal infrared images are unaffected by changes in visible light conditions and can stably acquire temperature data under varying lighting conditions, adapting to a variety of environments. Thermal infrared technology also allows for non-contact measurement, which is particularly important for subjects, minimizing disturbance and discomfort. By combining actual temperature values with estimated distances and applying a compensation relationship to adjust the actual temperature values, the system can correct for temperature deviations caused by varying measurement distances, thereby reducing system errors and providing more accurate, corrected temperature values for the subject. This provides technical support for temperature monitoring and intelligent care.

[0145] It should be noted that the modules and units in the human body temperature compensation device based on monocular vision in this embodiment correspond one-to-one to the steps in the human body temperature compensation method based on monocular vision in the aforementioned embodiment. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned human body temperature compensation method based on monocular vision, and will not be repeated here.

[0146] Example 3

[0147] In addition, combined Figure 6 The human body temperature compensation method based on monocular vision of the embodiment of the present invention described above can be implemented by a human body temperature compensation device based on monocular vision, which is characterized by being used to implement the method as described in any one of claims 1-7. Figure 7 A schematic diagram of the hardware structure of a human body temperature compensation device based on monocular vision provided by an embodiment of the present invention is shown.

[0148] A human body temperature compensation device based on monocular vision may include a processor and a memory storing computer program instructions.

[0149] Specifically, the processor may include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits for implementing the embodiments of the present invention.

[0150] The memory may include a large capacity memory for data or instructions. By way of example and not limitation, the memory may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory may include a removable or non-removable (or fixed) medium. Where appropriate, the memory may be inside or outside the data processing device. In a specific embodiment, the memory is a non-volatile solid-state memory. In a specific embodiment, the memory includes a read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or a flash memory, or a combination of two or more of these.

[0151] The processor implements any one of the human body temperature compensation methods based on monocular vision in the above embodiments by reading and executing computer program instructions stored in the memory.

[0152] In one example, the human body temperature compensation device based on monocular vision may further include a communication interface and a bus. Figure 6 As shown, the processor 401 , the memory 402 , and the communication interface 403 are connected via a bus 410 and communicate with each other.

[0153] The communication interface is mainly used to implement communication between the modules, devices, units and / or equipment in the embodiments of the present invention.

[0154] Bus comprises hardware, software or both, couples the parts of electronic equipment to each other.For example, and not limitation, bus can comprise accelerated graphics port (AGP) or other graphics bus, enhanced industry standard architecture (EISA) bus, front side bus (FSB), hypertransport (HT) interconnection, industry standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations.In suitable cases, bus can comprise one or more buses.Although the embodiment of the present invention describes and shows specific bus, the present invention considers any suitable bus or interconnection.

[0155] Example 4

[0156] In addition, in conjunction with the monocular vision-based human body temperature compensation method in the above-mentioned embodiment, an embodiment of the present invention may provide a computer-readable storage medium for implementation. The computer-readable storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any of the monocular vision-based human body temperature compensation methods in the above-mentioned embodiment is implemented.

[0157] In summary, the embodiments of the present invention provide a method, device, equipment, and medium for monocular vision-based human body temperature compensation.

[0158] It should be understood that the present invention is not limited to the specific configurations and processes described above and illustrated in the figures. For the sake of brevity, a detailed description of known methods is omitted. In the above embodiments, several specific steps are described and illustrated as examples. However, the method of the present invention is not limited to the specific steps described and illustrated. Those skilled in the art may make various changes, modifications, and additions, or change the order of the steps after understanding the spirit of the present invention.

[0159] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in unit, a function card or the like. When implemented in software, the elements of the present invention are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROMs, flash memories, erasable ROMs (EROMs), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0160] It should also be noted that the exemplary embodiments described herein describe methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the steps described above. In other words, the steps may be performed in the order described in the embodiments, or in a different order, or several steps may be performed simultaneously.

[0161] The above description is only a specific embodiment of the present invention. Those skilled in the art will clearly understand that for the convenience and brevity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present invention is not limited to this. Any person skilled in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention.

Claims

1. A human body temperature compensation method based on monocular vision, characterized in that: The method comprises: photographing at least one target heat source according to a preset distance sequence and a preset temperature range to obtain a thermal infrared temperature sequence, wherein the thermal infrared temperature sequence includes temperature measurement values of the target heat source in a plurality of thermal infrared images, and the actual temperature and / or actual photographing distance of the target heat source in each of the thermal infrared images is different; Preprocessing the thermal infrared temperature sequence to obtain a compensation relationship between the temperature measurement value and the actual shooting distance; Obtaining an actual target distance of the object being cared for based on a preset visible light image and an actual visible light image of the object being cared for, wherein the preset visible light image is obtained at a predetermined distance between the object being cared for and the visible light vision module; Obtaining the actual body temperature of the subject under care based on the actual thermal infrared image of the subject under care, wherein the actual body temperature of the subject under care is obtained at the actual shooting distance between the subject under care and the thermal infrared vision module; A corrected body temperature value of the object being cared for is obtained according to the actual body temperature value, the actual target distance and the compensation relationship.

2. The method for human body temperature compensation based on monocular vision according to claim 1, characterized in that: The photographing of at least one target heat source according to a preset distance sequence and a preset temperature range to obtain a thermal infrared temperature sequence comprises: photographing the target heat source according to a preset distance sequence to obtain a thermal infrared image at each actual temperature; The thermal infrared images are sorted by size according to a preset distance to obtain a thermal infrared temperature sequence.

3. The method for human body temperature compensation based on monocular vision according to claim 1, characterized in that: The preprocessing of the thermal infrared temperature sequence to obtain a compensation relationship between the temperature measurement value and the actual shooting distance includes: Performing difference calculations on the temperature measurement values and actual temperatures of the target heat source at each preset distance in the preset distance sequence to obtain a first temperature difference sequence corresponding to each preset distance; Processing each of the first temperature difference value sequences according to a least squares method or a nonlinear curve fitting method to obtain a relationship function between each preset distance and each temperature measurement value; Polynomial fitting is performed on each of the relationship functions to obtain the compensation relationship.

4. The method for human body temperature compensation based on monocular vision according to claim 1, characterized in that: The obtaining of the actual target distance of the object under care according to the preset visible light image and the actual visible light image of the object under care includes: Acquire a preset visible light image and an actual visible light image; Identify the object being cared for according to a preset neural network model, a preset visible light image, and an actual visible light image, and obtain a first target detection frame and a second target detection frame, wherein the preset neural network model is constructed based on YOLO; An actual target distance is obtained according to the first target detection frame, the second target detection frame, and a first preset algorithm.

5. The method for human body temperature compensation based on monocular vision according to claim 4, characterized in that: The obtaining of the actual target distance according to the first target detection frame, the second target detection frame, and the first preset algorithm includes: Acquire a first width and a first height of the first object detection frame according to the first object detection frame; Acquire a second width and a second height of the second object detection frame according to the second object detection frame; Calculating the first width and the first height to obtain an area of a first detection frame; Calculate the second width and the second height to obtain an area of a second detection frame; The actual target distance is obtained by calculating the area of the first detection frame and the area of the second detection frame.

6. A method for human body temperature compensation based on monocular vision according to any one of claim 5, characterized in that: The calculating the first detection frame area and the second detection frame area to obtain the actual target distance includes: Inputting the actual visible light image into a pre-trained facial key point detection model to determine whether there are any key points missing in the actual visible light image; When a key point is missing, calculating the area of the first detection frame and the area of the second detection frame to obtain an area ratio; determining an initial distance according to the area ratio; Identify missing key points in the actual visible light image, obtain the key point missing type, and obtain the dynamic compensation factor corresponding to the key point missing type; The initial distance is corrected according to the dynamic compensation factor to obtain the actual target distance.

7. A method for human body temperature compensation based on monocular vision according to any one of claims 1 to 6, characterized in that: Before acquiring the actual target distance of the object under care according to the preset visible light image and the actual visible light image of the object under care, the method further includes: Acquiring a predetermined distance between the object being cared for and the visible light vision module and an image of the object being cared for captured at the predetermined distance between the object being cared for and the visible light vision module; Performing facial analysis on the image of the person being cared for according to the predetermined distance to obtain a facial analysis result, wherein the facial analysis includes facial key point detection and matching; According to the facial analysis result, when the face of the person being cared for in the image of the person being cared for presents a complete frontal face state, using the image of the person being cared for as the preset visible light image; When the face of the object being cared for in the image of the object being cared for presents an incomplete frontal face state, the target image is discarded and a new image of the object being cared for is recaptured, wherein the incomplete frontal face state includes the face being blocked, the side face, and the face not appearing.

8. A human body temperature compensation device based on monocular vision, characterized in that: The device comprises: a thermal infrared temperature sequence acquisition module, which photographs at least one target heat source according to a preset distance sequence and a preset temperature range to obtain a thermal infrared temperature sequence; a preprocessing module, which preprocesses the thermal infrared temperature sequence to obtain a compensation relationship between the temperature measurement value and the actual shooting distance; A distance estimation module, which obtains the actual measured distance of the object being cared for based on the preset visible light image and the actual visible light image of the object being cared for; The actual body temperature acquisition module obtains the actual body temperature value of the object being cared for based on the actual thermal infrared image of the object being cared for; The body temperature compensation module obtains a corrected body temperature value of the object being cared for according to the actual body temperature value, the actual target distance and the compensation relationship.

9. An electronic device, characterized in that: include: At least one processor, at least one memory, and computer program instructions stored in the memory, which implement the method according to any one of claims 1 to 7 when the computer program instructions are executed by the processor.

10. A storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images