Human body core-periphery temperature difference monitoring system and method

Abstract

The invention provides a human body core-periphery temperature difference monitoring system and method.The monitoring system comprises an image obtaining device and an information processing device connected with the image obtaining device, the image obtaining device is provided with an infrared imaging sensor, and the infrared imaging sensor is connected with the information processing device; the thermal imaging module is used for acquiring a thermal imaging image of the whole human body by using the infrared imaging sensor or the fusion sensor; and the information processing device is used for acquiring the thermal imaging image and processing the thermal imaging image to obtain a temperature difference value between the core area and the peripheral area of the human body. According to the monitoring system and method, the thermal imaging image of the surface of the human body is captured through the infrared thermal imaging technology, the temperature difference between the core and the periphery of the human body is obtained based on the thermal imaging image, the monitoring system is convenient to maintain, comprehensive monitoring data can be provided, and the monitoring efficiency and the data accuracy are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical monitoring, and particularly relates to a monitoring system and method for the core-peripheral temperature difference of the human body. Background Art

[0002] The core-peripheral temperature difference (CPTD) of the human body is an important physiological index of hemodynamic status, especially of great clinical significance for premature infants and critically ill neonates. CPTD refers to the temperature difference between the core area (such as the chest or abdomen) and the peripheral area (such as the hand or foot), which can reflect the blood circulation status of the neonate.

[0003] Currently, an infrared spot thermometer and a contact temperature patch are generally used as the main tools to monitor the core-peripheral temperature difference of the human body. However, this method requires manual operation, so continuous temperature monitoring cannot be achieved, and thus it is impossible to respond promptly to acute disease changes. Moreover, the infrared spot thermometer can only measure the temperature at a certain point, lacking the temperature distribution information of the whole body and unable to obtain the temperature distribution information of the entire human body. Therefore, it is not suitable for complex clinical scenarios. So the above method not only has a low degree of automation, but also the data integrity cannot meet the requirements.

[0004] Therefore, the prior art needs to be further improved. Summary of the Invention

[0005] In view of the above deficiencies in the prior art, the purpose of the present invention is to provide a monitoring system and method for the core-peripheral temperature difference of the human body, to solve the defects in the prior art that the monitoring of the core-peripheral temperature difference of the human body cannot be fully automated and the data integrity is low.

[0006] In a first aspect, the present application discloses a monitoring system for the core-peripheral temperature difference of the human body, which includes: an image acquisition device and an information processing device connected to the image acquisition device;

[0007] The image acquisition device is used to obtain a thermal imaging image of the whole human body by using an infrared imaging sensor or a fusion sensor;

[0008] The information processing device is used to obtain the thermal imaging image, identify the target core area and the peripheral area in the thermal imaging image, respectively obtain the temperature value of the target core area and the temperature value of the peripheral area, and determine the temperature difference between the core area and the peripheral area of the human body according to the temperature value of the target core area and the temperature value of the peripheral area.

[0009] Optionally, the image acquisition device is: an infrared thermal imaging camera;

[0010] The infrared thermal imaging camera is used to continuously capture the temperature distribution of the human body surface by using an infrared imaging sensor according to a preset working frequency, and generate a thermal imaging image of the whole human body.

[0011] Optionally, the image acquisition device includes an infrared thermal imaging camera and an auxiliary device; a plurality of different types of auxiliary sensors are installed on the auxiliary device, and the different types of auxiliary sensors include one or more of a visible light sensor, a position sensor, and an environmental sensor;

[0012] The image acquisition device is used to continuously capture the temperature distribution of the human body surface by using an infrared imaging sensor according to a preset working frequency, and obtain the body shape information of the human body by using a visible light sensor, obtain the body position information of the human body by using a position sensor, or obtain the environmental information of the location where the human body is located by using an environmental sensor, and fuse the temperature distribution of the human body surface with the body shape information, body position information, or environmental information of the location where the human body is located to generate a thermal imaging image of the whole human body.

[0013] Optionally, the information processing device includes: a deep learning processing module and a data processing and analysis module;

[0014] The deep learning processing module is used to input the received thermal imaging image into a trained region recognition model to obtain the target core region and peripheral region of the human body recognized by the region recognition model; wherein, the structure of the region recognition model is a Transformer model;

[0015] The data processing and analysis module is used to respectively perform temperature recognition on the recognized target core region and peripheral region of the human body to obtain a first temperature value of the target core region and a second temperature value of the peripheral region, and calculate the core-peripheral temperature difference of the human body according to the first temperature value and the second temperature value.

[0016] Optionally, the data processing and analysis module includes: a data preprocessing unit;

[0017] The data preprocessing unit is used to judge whether the temperature values of the recognized target core region and peripheral region of the human body are outliers, and delete the outliers to obtain the preprocessed first temperature value and second temperature value, wherein the recognition method of the outliers is the temperature value exceeding the preset target range.

[0018] Optionally, the data processing and analysis module further includes: a data correction unit;

[0019] The data correction unit is used to correct the first temperature value and the second temperature value after deleting the outliers by using the interpolation method to obtain the corrected first temperature value and second temperature value.

[0020] Optionally, the data processing and analysis module further includes: a data analysis unit;

[0021] The data analysis unit is configured to calculate the relative difference or absolute difference between the first temperature value and the second temperature value by using a difference algorithm, so as to obtain the temperature difference between the human body core region and the peripheral region.

[0022] In a second aspect, the present application discloses a method for monitoring the human body core-peripheral temperature difference, which is applied to the core-peripheral temperature monitoring system described above. The monitoring method includes:

[0023] Obtaining a thermal imaging image of the whole human body by using an infrared imaging sensor or a fusion sensor;

[0024] Processing the thermal imaging image to identify the target core region and the peripheral region in the thermal imaging image, respectively obtaining the temperature value of the target core region and the temperature value of the peripheral region, and determining the temperature difference between the human body core region and the peripheral region according to the temperature value of the target core region and the temperature value of the peripheral region.

[0025] Optionally, the step of obtaining a thermal imaging image of the whole human body by using a fusion sensor includes:

[0026] Continuously capturing the temperature distribution on the human body surface by using an infrared imaging sensor according to a preset working frequency;

[0027] Obtaining the body shape information of the human body by using a visible light sensor, and obtaining the body position information of the human body by using a position sensor or obtaining the environmental information of the location where the human body is located by using an environmental sensor;

[0028] Fusing the temperature distribution on the human body surface with the body shape information, the body position information of the human body or the environmental information of the location where the human body is located to generate a thermal imaging image of the whole human body.

[0029] Optionally, the step of processing the thermal imaging image to obtain the human body core-peripheral temperature difference includes:

[0030] Inputting the received thermal imaging image into a trained region recognition model to obtain the target core region and the peripheral region of the human body recognized by the region recognition model;

[0031] Judging whether the temperature values of the recognized target core region and peripheral region of the human body are abnormal values, and deleting the abnormal values to obtain the preprocessed first temperature value and second temperature value;

[0032] Calculating the temperature difference between the human body core region and the peripheral region according to the first temperature value and the second temperature value.

[0033] Beneficial effects:

[0034] The present invention provides a monitoring system and method for the core-peripheral temperature difference of the human body. The monitoring system includes an image acquisition device and an information processing device connected to the image acquisition device. Among them, the image acquisition device is provided with an infrared imaging sensor for obtaining a thermal imaging image of the whole human body by using the infrared imaging sensor or a fusion sensor; the information processing device is used to obtain the thermal imaging image and process the thermal imaging image to obtain the temperature difference between the core area and the peripheral area of the human body. The monitoring system and method disclosed in the embodiments of the present invention use infrared thermal imaging technology to capture the temperature distribution image of the human body surface, and obtain the core-peripheral temperature difference of the human body based on the temperature distribution image, so as to realize the automatic and real-time monitoring of the human body temperature. The non-contact monitoring disclosed in the present invention can avoid contact with the human body, is suitable for occasions in a sterile environment, and the monitoring system is easy to maintain, can provide comprehensive monitoring data, and improve the monitoring efficiency and data accuracy. Description of the Drawings

[0035] Figure 1 is a schematic structural diagram of the monitoring system for the core-peripheral temperature difference of the human body provided by the present invention;

[0036] Figure 2 is a monitoring effect diagram of the monitoring system provided by the present invention;

[0037] Figure 3 is a step flow chart of the method for the monitoring system of the core-peripheral temperature difference of the human body provided by the present invention. Detailed Embodiments

[0038] To make the objectives, technical solutions and advantages of the present invention clearer and more definite, the following further describes the present invention in detail with reference to the accompanying drawings and by way of examples. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0039] The core-peripheral temperature difference reflects the blood circulation status of the human body. The fluctuation of the core-peripheral temperature difference is an important indicator for early detection of abnormal human circulatory function. Therefore, the monitoring accuracy and timeliness of the core-peripheral temperature difference are of great significance for monitoring the condition.

[0040] Currently, infrared spot thermometers are a common way to monitor core-peripheral temperature difference (CPTD). Nursing staff use infrared spot thermometers to measure the temperatures of the core part (such as the chest) and the peripheral part (such as the hands and feet) of newborns respectively, and then calculate the difference. This method has significant limitations. First, this method relies on manual operation and cannot achieve real-time continuous monitoring, resulting in insufficient timeliness in monitoring acute changes in the condition. Second, manually measuring the temperatures of different parts requires repeated operations, which is time-consuming and cumbersome, increasing the burden on medical resources. In addition, infrared spot thermometers can only measure the temperature of a certain point and lack information on the temperature distribution of the whole body, which is particularly disadvantageous in complex clinical scenarios.

[0041] Another common CPTD monitoring method is to use contact temperature patches. Multiple temperature sensors are attached to different parts of the newborn's body (such as the core part and the peripheral part) to monitor the temperature. Although this method can achieve continuous CPTD monitoring, since the patch is contact-type, it is likely to cause skin discomfort or allergies in newborns, especially in premature or critically ill newborns. In addition, the installation and replacement of patch monitoring also require the time and energy of nursing staff, and the patch is prone to loosening or falling off during long-term use, resulting in inaccurate measurement data.

[0042] To overcome the above defects, this embodiment provides a monitoring system and method for human core-peripheral temperature difference. An infrared imaging sensor or a fusion sensor is used to obtain a thermal imaging image of the whole body of a human, and then the thermal imaging image is processed to obtain the temperature difference between the core area and the peripheral area of the human body. The monitoring system and method disclosed in the embodiments of the present invention use non-contact infrared thermal imaging technology to capture the temperature distribution image on the human body surface, and then identify the temperature distribution image to obtain the temperature difference between the target core area and the peripheral area, so as to realize automatic and real-time monitoring of the human body temperature. The method of this embodiment can not only provide comprehensive monitoring data, but also improve the monitoring efficiency and data accuracy through continuous temperature monitoring.

[0043] The following further describes in more detail a monitoring system and method for human core-peripheral temperature difference provided in this embodiment with reference to the accompanying drawings.

[0044] In the first aspect, the present application discloses a monitoring system for human core-peripheral temperature difference, as Figure 1 shown, including: an image acquisition device 110 and an information processing device 130 connected to the image acquisition device. Among them, the image acquisition device 130 is provided with an infrared imaging sensor or a fusion sensor obtained by fusing an infrared imaging sensor with multiple auxiliary sensors.

[0045] The image acquisition device 110 is configured to acquire a thermal imaging image of the whole body of a human using the infrared imaging sensor or a fusion sensor.

[0046] The information processing device 130 is configured to acquire the thermal imaging image, identify the target core area and the peripheral area in the thermal imaging image, respectively obtain the temperature value of the target core area and the temperature value of the peripheral area, and determine the temperature difference between the human core area and the peripheral area based on the temperature value of the target core area and the temperature value of the peripheral area.

[0047] As Figure 1 shown is a schematic diagram of automatically monitoring the core-peripheral temperature difference of a newborn using the monitoring system provided in this embodiment. Figure 1 In the figure, the newborn 140 is placed in the incubator 150, and the image acquisition device 110 is arranged above the newborn to acquire a thermal imaging image of the whole body of the newborn. The thermal imaging image of the whole body of the newborn acquired by the image acquisition device 110 is transmitted to the information processing device 130. The information processing device can be connected to the image acquisition device in a wired or wireless manner. To adjust the height and position of the image acquisition device, the image acquisition device 110 can be arranged on the pushchair bracket 120, and the height and position of the image acquisition device 110 can be adjusted by adjusting the height and position of the pushchair bracket 120.

[0048] In the image acquisition device proposed in this step, an infrared imaging sensor or a fusion sensor in which the infrared imaging sensor is fused with other types of sensors is provided. Therefore, the image acquisition device can capture the surface temperature of an object in front of it using the infrared imaging sensor and obtain the temperature distribution image of the front object surface. Moreover, non-contact continuous temperature measurement can be achieved using the infrared imaging sensor, continuous real-time monitoring data can be obtained, and it is applicable to complex clinical scenarios. And non-contact temperature measurement avoids the contact between the measuring instrument and the human body and reduces the risk of human infection. Especially in occasions that require a strictly aseptic environment.

[0049] Furthermore, in order to achieve more accurate measurement of the human body temperature, the human body can also be measured using a fusion sensor that fuses multiple sensors to obtain a thermal imaging image of the whole body of the human. The fusion sensor automatically analyzes and synthesizes the information and data from multiple sensors to obtain an accurate thermal imaging image of the whole body of the human. The fusion sensor contains an infrared imaging sensor and other auxiliary sensors, and the other auxiliary sensors can be used to further verify the temperature value measured by the infrared imaging sensor or to improve the measurement accuracy and clarity of the infrared imaging sensor.

[0050] Specifically, the image acquisition device is an infrared thermal imaging camera; the infrared thermal imaging camera is used to continuously capture the temperature distribution on the human body surface according to a preset working frequency by using an infrared imaging sensor, and generate a thermal imaging image of the whole human body.

[0051] The infrared thermal imaging camera is placed above the human body and is used to continuously capture the temperature distribution on the human body surface according to a preset working frequency, and generate a thermal imaging image of the whole human body. The infrared thermal imaging camera captures the invisible infrared radiation emitted by an object through a lens and an infrared imaging sensor. After steps such as photoelectric conversion and signal processing, these infrared radiations are converted into a visual thermal image, thereby showing the temperature distribution on the human body surface.

[0052] Further, in addition to the infrared thermal imaging camera, the image acquisition device may further include a plurality of auxiliary devices; a plurality of different types of auxiliary sensors are all installed on the auxiliary devices. In specific implementation, different types of auxiliary sensors may include one or more of a visible light sensor, a position sensor, and an environmental sensor. Among them, the visible light sensor can be used to capture the morphological information of the human body, and superimpose and compare it with the thermal imaging image to provide more comprehensive information. The position sensor and the environmental sensor can record the environmental conditions during the acquisition of the thermal imaging image, which helps data analysis and interpretation.

[0053] Therefore, in this step, the image acquisition device can also be used to continuously capture the temperature distribution on the human body surface according to a preset working frequency by using an infrared imaging sensor, and use the visible light sensor to obtain the morphological information of the human body, use the position sensor to obtain the body position information of the human body, or use the environmental sensor to obtain the environmental information of the location where the human body is located, and fuse the temperature distribution on the human body surface with the morphological information of the human body, the body position information, or the environmental information of the location where the human body is located to generate a thermal imaging image of the whole human body.

[0054] Specifically, the step of fusing the temperature distribution on the human body surface with the morphological information of the human body, the body position information, or the environmental information of the location where the human body is located to generate a thermal imaging image of the whole human body can use a data fusion algorithm to fuse the above-mentioned morphological information, body position information, and environmental information to obtain a composite image containing the above information. Further process and analyze the fused composite image to extract useful information. For example: the composite image can be processed such as position analysis and temperature anomaly detection to identify whether there is an anomaly in the location where the human body is located or the temperature anomaly area on the human body surface.

[0055] Further, after the image acquisition device obtains a thermal imaging image of the whole human body, the thermal imaging image is input into an information processing device, and the information processing device analyzes the thermal imaging image to obtain the temperature difference between the target core area and the periphery.

[0056] In one implementation, the information processing device includes: a deep learning processing module and a data processing and analysis module.

[0057] The deep learning processing module is configured to input the received thermal imaging image into a trained region recognition model to obtain the target core region and the peripheral region of the human body recognized by the region recognition model; wherein, the structure of the region recognition model is a Transformer model.

[0058] Before inputting the thermal imaging image into the trained region recognition model, in order to make the input thermal imaging image meet the model input requirements, it is necessary to preprocess the thermal imaging image, and the preprocessing includes: adjusting the image size, normalization operation, etc., to ensure that the image quality meets the model input requirements. The thermal imaging image is also converted into a format that the region recognition model can process, such as a grayscale image or a specific color space.

[0059] Furthermore, the region recognition model is a trained model that can recognize the human body region in the thermal imaging image and divide it into a target core region and a peripheral region. When training the region recognition model, thermal imaging images labeled with the human body core region and the peripheral region are used for training to learn the characteristics of different regions.

[0060] To more accurately use the region recognition model to recognize the human body region in the thermal imaging image, region recognition models applicable to different populations can be trained according to the population distribution of different ages. For example: in order to more accurately recognize the target core region and the peripheral region in the thermal imaging image of a newborn, when training the region recognition model applicable to a newborn, first collect a large number of thermal imaging images of newborns, and manually label the collected thermal imaging images of newborns. Clearly mark the core region (e.g., chest or abdomen) and the peripheral region (e.g., limbs and hands and feet) of the human body in the image. The annotation can use different shapes to accurately represent different regions of the human body. In order to increase the diversity and robustness of the training data, the annotated images can be enhanced, and common enhancement methods include rotation, flipping, and adding noise, etc., to generate more training samples and improve the generalization ability of the trained region recognition model.

[0061] When training the region recognition model, in order to accurately recognize each region in the thermal imaging image, a model architecture applicable to image recognition and classification tasks can be selected, such as: a convolutional neural network (CNN) and a Transformer model.

[0062] By inputting the labeled training sample data into a convolutional neural network or a Transformer model, the convolutional neural network or the Transformer model is trained, and finally a trained region recognition model is obtained. During the model training process, the convolutional neural network or the Transformer model continuously learns the features of the core region and the peripheral region of the human body target, and continuously optimizes the model parameters, and finally obtains a trained region recognition model.

[0063] After the region recognition model is trained, the obtained thermal imaging image is input into the region recognition model to obtain the core region and the peripheral region of the target recognized by the region recognition model.

[0064] The data processing and analysis module is used to respectively perform temperature recognition on the recognized core region and peripheral region of the human body to obtain the first temperature value of the core region and the second temperature value of the peripheral region, and calculate the core-peripheral temperature difference of the human body according to the first temperature value and the second temperature value.

[0065] When the deep learning processing module recognizes the core region and the peripheral region in the thermal imaging image, the temperatures in these two regions are recognized, and the temperature difference between the core region and the peripheral region is calculated. The temperature value of the core region is defined as the first temperature value, and the temperature value of the peripheral region is defined as the second temperature value, and the core-peripheral temperature difference is calculated.

[0066] Further, in order to improve the accuracy of temperature detection, the data processing and analysis module includes: a data preprocessing unit, which uses the data preprocessing unit to recognize the recognized temperature value and remove outliers.

[0067] The data preprocessing unit is used to determine whether the temperature values of the recognized core region and peripheral region of the human body are outliers, and delete the outliers to obtain the preprocessed first temperature value and second temperature value. The method for identifying outliers is a temperature value that exceeds the preset target range.

[0068] When extracting the temperature values of different regions, data errors may occur due to single measurement fluctuations. Therefore, in order to improve the accuracy of the extracted temperature, the identification and removal of outliers are also adopted in this step.

[0069] In one implementation, the definition of outliers is based on three-layer criteria: (1) temperatures exceeding the physiological range of 32 - 42 °C, (2) mutation values with a temperature change exceeding 2 °C between consecutive measurements, and (3) temperature values that significantly deviate from the local average in a 30-point sliding window. Specifically, temperatures that deviate from the window average by three standard deviations (i.e., outside the range of the average ± 3 times the standard deviation) are classified as outliers.

[0070] Furthermore, the data processing and analysis module further includes: a data correction unit;

[0071] The data correction unit is configured to correct the first temperature value and the second temperature value after removing outliers by using the interpolation method, so as to obtain the corrected first temperature value and the second temperature value.

[0072] In one implementation, the cubic spline interpolation method is used to replace these outliers to ensure data continuity and facilitate subsequent analysis. The cubic spline interpolation method is a method of generating a smooth curve through a system of given discrete points. This curve is a cubic polynomial on each small interval and is continuous and smooth over the entire interval. Specifically, according to the temperature values after removing outliers, cubic polynomials on each set temperature value interval are constructed, and these polynomials are made continuous and smooth at the interval connection points, and finally a smooth curve passing through all given points is obtained.

[0073] Specifically, the data processing and analysis module further includes: a data analysis unit;

[0074] The data analysis unit is configured to calculate the relative difference or absolute difference between the first temperature value and the second temperature value by using the difference algorithm, so as to obtain the temperature difference between the human body core region and the peripheral region.

[0075] Since there can be multiple target core regions, such as: the heart position, the abdomen or the chest, etc., after determining the above target core regions, the average value of the temperatures within the above target core regions is calculated as the first temperature value. The peripheral region includes the regions where the limbs are located, and similarly, the second temperature value can be determined by calculating the average value of the temperature values corresponding to the limb regions. In order to reduce the calculation, in one implementation, the highest value of the temperatures within the target core region can also be selected as the first temperature value, and the average value of the temperature values of the limb regions is selected as the second temperature value to calculate the core-peripheral temperature difference.

[0076] When calculating the temperature difference between the first temperature value and the second temperature value, it can be the relative difference or the absolute difference. The absolute difference is equal to the absolute value of the difference between the first temperature value and the second temperature value, and the relative difference is equal to the quotient obtained by dividing the absolute difference between the first temperature value and the second temperature value by the first temperature value and then multiplying by 100%.

[0077] The data processing and analysis module uses the difference calculation technology to obtain the relative temperature difference between the target core region and the peripheral region, reduces the influence of environmental temperature fluctuations and the absolute temperature measurement error of the imaging device, and ensures the stability and reliability of the system.

[0078] In one implementation, in order to reduce the reliance on absolute temperature, a differential calculation method based on core-peripheral temperature is adopted. By calculating the relative temperature change between the first temperature value and the second temperature value rather than the absolute value, the influence that may be caused by inaccurate calibration is effectively avoided. In addition, the system of this embodiment can automatically realize the identification of the core-peripheral temperature difference, thereby significantly reducing the need for manual intervention and realizing continuous and real-time monitoring. The system of this embodiment can not only improve the efficiency of core-peripheral temperature difference monitoring, but also provide more timely and accurate reference for early health warning of the human body, especially newborns.

[0079] The system of this embodiment realizes the automation, continuity and high precision of non-contact monitoring of core-peripheral temperature difference, overcomes many deficiencies in the prior art, provides a more effective clinical monitoring method for the hemodynamic status of newborns, especially premature infants, and significantly improves the clinical early warning and treatment response capabilities.

[0080] Combination Figure 2 As shown in the figure, it is a core-peripheral temperature monitoring effect diagram based on infrared thermal imaging provided by this embodiment, which shows the thermal imaging images of 5 newborns and the change of core-peripheral temperature difference over time, where the blue curve represents the change trend of temperature difference at different times, and the red horizontal line represents the clinical reference value of core-peripheral temperature. Based on the temperature difference change obtained by real-time monitoring, the change of newborn body temperature can be timely understood, so as to obtain a more accurate condition status.

[0081] The present embodiment provides a human core-peripheral temperature difference monitoring system, which overcomes the defects of the prior art that manual operation is required and continuous monitoring cannot be achieved by automatically identifying and monitoring the human core-peripheral temperature difference. It can also continuously and in real time capture small changes in human body temperature, thereby achieving early warning of body temperature. In addition, infrared imaging technology can achieve non-contact temperature monitoring, avoiding contact with traditional patch sensors or handheld devices, reducing the risk of human infection, and is particularly suitable for newborns and occasions that require a strict sterile environment.

[0082] In a second aspect, the present application discloses a method for monitoring the core-peripheral temperature difference of a human body, such as Figure 3 As shown, the monitoring system applied to the core-peripheral temperature, the monitoring method includes:

[0083] Step S1: using an infrared imaging sensor or a fusion sensor to obtain a thermal imaging image of the entire human body.

[0084] Step S2: Process the thermal imaging image, identify the target core area and the peripheral area in the thermal imaging image, obtain the temperature value of the target core area and the temperature value of the peripheral area respectively, and determine the temperature difference between the human core area and the peripheral area according to the temperature value of the target core area and the temperature value of the peripheral area.

[0085] Further, the step of obtaining the thermal imaging image of the whole human body by using the fusion sensor includes:

[0086] Use the infrared imaging sensor to continuously capture the temperature distribution on the human body surface according to the preset working frequency;

[0087] Use the visible light sensor to obtain the body shape information of the human body, and use the position sensor to obtain the body position information of the human body or use the environment sensor to obtain the environmental information of the location where the human body is located;

[0088] Fuse the temperature distribution on the human body surface with the body shape information, body position information of the human body or the environmental information of the location where the human body is located to generate a thermal imaging image of the whole human body.

[0089] Further, the step of processing the thermal imaging image to obtain the core-peripheral temperature difference of the human body includes:

[0090] Input the received thermal imaging image into the trained region recognition model to obtain the target core area and the peripheral area of the human body recognized by the region recognition model; judge whether the temperature values of the recognized target core area and the peripheral area of the human body are abnormal values, and delete the abnormal values to obtain the preprocessed first temperature value and second temperature value; calculate the temperature difference between the human core area and the peripheral area according to the first temperature value and the second temperature value.

[0091] The monitoring system and method disclosed in the embodiments of the present invention use infrared thermal imaging technology to capture the temperature distribution image on the human body surface, and obtain the core-peripheral temperature difference of the human body based on the temperature distribution image, so as to realize the automatic and real-time monitoring of the human body temperature. The system and method disclosed in this embodiment adopt full automation, non-contact, continuous real-time monitoring, temperature distribution spatial information, intelligent recognition of deep learning models, etc., to achieve high efficiency, high precision, strong stability and good clinical practicability in the monitoring of human core-peripheral temperature, and overcome the defects of complex operation, low efficiency, low precision and poor stability in the prior art.

[0092] Other embodiments of the present invention will be readily apparent to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. The present invention is intended to cover any variations, uses, or adaptations of the invention, which follow the general principles of the present invention and include known common knowledge or conventional technical means in the technical field not disclosed in this application. The specification and examples are only illustrative, and the true scope and spirit of the present invention are pointed out by the following claims.

[0093] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of this application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0094] It can be understood that the above embodiments are exemplary and should not be construed as limiting this application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A monitoring system for the core-peripheral temperature difference of the human body, characterized in that, Including: An image acquisition device and an information processing device connected to the image acquisition device; The image acquisition device is configured to obtain a thermal imaging image of the whole human body by using an infrared imaging sensor or a fusion sensor; The information processing device is configured to obtain the thermal imaging image, identify a target core region and a peripheral region in the thermal imaging image, respectively obtain a temperature value of the target core region and a temperature value of the peripheral region, and determine a temperature difference between the human core region and the peripheral region according to the temperature value of the target core region and the temperature value of the peripheral region.

2. The monitoring system for the core-peripheral temperature difference of the human body according to claim 1, characterized in that, The image acquisition device is an infrared thermal imaging camera; The infrared thermal imaging camera is configured to continuously capture the body surface temperature distribution of a human body at a preset working frequency by using an infrared imaging sensor and generate a thermal imaging image of the whole human body.

3. The monitoring system for the core-peripheral body temperature difference according to claim 1, characterized in that, The image acquisition device includes an infrared thermal imaging camera and an auxiliary device; a plurality of different types of auxiliary sensors are installed on the auxiliary device, and the different types of auxiliary sensors include one or more of a visible light sensor, a position sensor, and an environmental sensor; The image acquisition device is configured to continuously capture the body surface temperature distribution of a human body at a preset working frequency by using an infrared imaging sensor, and obtain the body shape information of the human body by using a visible light sensor, obtain the body position information of the human body by using a position sensor, or obtain the environmental information of the location where the human body is located by using an environmental sensor, and fuse the body surface temperature distribution with the body shape information, body position information, or environmental information of the location where the human body is located to generate a thermal imaging image of the whole human body.

4. The monitoring system for the core-peripheral temperature difference of the human body according to claim 1, characterized in that, The information processing device includes: a deep learning processing module and a data processing and analysis module; The deep learning processing module is configured to input the received thermal imaging image into a trained region recognition model to obtain a target core region and a peripheral region of the human body recognized by the region recognition model; wherein, the structure of the region recognition model is a Transformer model; The data processing and analysis module is configured to respectively perform temperature recognition on the recognized target core region and peripheral region of the human body to obtain a first temperature value of the target core region and a second temperature value of the peripheral region, and calculate a core-peripheral temperature difference of the human body according to the first temperature value and the second temperature value.

5. The monitoring system for the core-peripheral body temperature difference according to claim 4, characterized in that, The data processing and analysis module includes: a data preprocessing unit; The data preprocessing unit is configured to determine whether the temperature values of the recognized target core region and peripheral region of the human body are outliers, and delete the outliers to obtain preprocessed first and second temperature values, wherein the method for identifying outliers is a temperature value exceeding a preset target range.

6. The monitoring system for the core-peripheral temperature difference of the human body according to claim 5, wherein The data processing and analysis module further includes: a data correction unit; The data correction unit is configured to correct the first and second temperature values after deleting the outliers by using an interpolation method to obtain corrected first and second temperature values.

7. The monitoring system for the core-peripheral temperature difference of the human body according to claim 5 or 6, characterized in that, The data processing and analysis module further includes: a data analysis unit; The data analysis unit is configured to calculate the relative difference or absolute difference between the first temperature value and the second temperature value by using a difference algorithm, so as to obtain the temperature difference between the human body core region and the peripheral region.

8. A method for monitoring the core-peripheral body temperature difference, characterized in that, Applied to the core-peripheral temperature monitoring system according to any one of claims 1-7, the monitoring method includes: Obtaining a thermal imaging image of the whole human body by using an infrared imaging sensor or a fusion sensor; Processing the thermal imaging image to identify the target core region and the peripheral region in the thermal imaging image, respectively obtaining the temperature value of the target core region and the temperature value of the peripheral region, and determining the temperature difference between the human body core region and the peripheral region according to the temperature value of the target core region and the temperature value of the peripheral region.

9. The method for monitoring the core-peripheral temperature difference of the human body according to claim 8, wherein, The step of obtaining a thermal imaging image of the whole human body by using a fusion sensor includes: Continuously capturing the temperature distribution on the human body surface by using an infrared imaging sensor according to a preset working frequency; Obtaining the body shape information of the human body by using a visible light sensor, and obtaining the body position information of the human body by using a position sensor or obtaining the environmental information of the location where the human body is located by using an environmental sensor; Fusing the temperature distribution on the human body surface with the body shape information, the body position information of the human body or the environmental information of the location where the human body is located to generate a thermal imaging image of the whole human body.

10. The method for monitoring the core-peripheral body temperature difference according to claim 9, wherein, The step of processing the thermal imaging image to obtain the core-peripheral temperature difference of the human body includes: Inputting the received thermal imaging image into a trained region recognition model to obtain the target core region and the peripheral region of the human body recognized by the region recognition model; Judging whether the temperature values of the identified target core region and the peripheral region of the human body are abnormal values, and deleting the abnormal values to obtain the preprocessed first temperature value and second temperature value; Calculating the temperature difference between the human body core region and the peripheral region according to the first temperature value and the second temperature value.

Images