Human body temperature sequence objective evaluation method based on infrared thermal imaging technology

Abstract

The invention relates to the technical field of thermal infrared image evaluation in image data processing, and discloses a human body temperature sequential objective evaluation method based on an infrared thermal imaging technology, which comprises the following steps: acquiring a thermal infrared image of a normal crowd to obtain an average temperature data set of a plurality of regions of interest of the normal crowd, screening out at least two significant regions of interest with statistical difference from the plurality of regions of interest, arranging and ranking the significant regions of interest according to the average temperature representation value to obtain the temperature sequence representation of the normal population, and comparing the temperature sequence representation of the person to be tested with the temperature sequence representation of the normal population to obtain the temperature sequence representation of the person to be tested. The obtained temperature sequence of the to-be-tested person represents the degree of deviation from the normal crowd. According to the method, the normal sequence of different ROI temperatures can be obtained, the temperature deviation degree of the to-be-tested person relative to the body part of a normal crowd is objectively and quantitatively described through a sequence comparison result, and a doctor is assisted in diagnosing whether the to-be-tested person is abnormal in metabolism or not.

Description

Technical Field

[0001] The present invention relates to the technical field of thermal infrared image evaluation in image data processing, and in particular to an objective evaluation method for human body temperature sequence based on infrared thermal imaging technology. Background Art

[0002] "Synopsis of Prescriptions of the Golden Chamber - Chapter on Disorders of Spasm, Dampness and Fever": "A patient with fever in the body and cold feet, stiffness and tightness in the neck, aversion to cold, sometimes fever in the head, red face and red eyes, involuntary shaking of the head alone, sudden lockjaw, and opisthotonos is suffering from spasm disorder." "Synopsis of Prescriptions of the Golden Chamber - Chapter on Disorders of Spasm, Dampness and Fever":

[0003] "If there is a coating on the tongue like fetal fur, it indicates that there is heat in the dantian and cold in the chest. Thirsty and wanting to drink but unable to do so, then there is dryness and restlessness." The ancients began to use the temperature difference between different regions of the body to identify and diagnose diseases very early.

[0004] However, there is currently no objective method for evaluating the surface temperature order of multiple body regions of the human body. Currently, when evaluating the surface temperature difference of different body regions, it is often judged by visually observing pseudo - colors to determine the temperature level, or described by using the method of relative thermal state difference. When trying to describe the temperature differences of multiple parts of the human body simultaneously, it is likely to appear less objective or not intuitive enough.

[0005] Therefore, there is an urgent need for a new type of objective evaluation method for human body temperature sequence. Summary of the Invention

[0006] The present invention provides an objective evaluation method for human body temperature sequence based on infrared thermal imaging technology to solve the defect of lacking a method for objectively evaluating the surface temperature order of multiple body regions of the human body.

[0007] The present invention provides an objective evaluation method for human body temperature sequence based on infrared thermal imaging technology, including:

[0008] Obtaining thermal infrared images of a normal population, where the normal population is a male normal population or a female normal population;

[0009] Based on the thermal infrared images of the normal population, obtaining an average temperature data set of multiple regions of interest (ROIs, region of interest) of the normal population;

[0010] Based on the average temperature data set of multiple regions of interest of the normal population, inferring whether the data distribution of the average temperature data set of multiple regions of interest comes from the same overall distribution through hypothesis testing, so as to screen out multiple significantly interesting regions with statistical differences between each pair from multiple regions of interest;

[0011] Based on the data distribution of the average temperature datasets of multiple significantly interested regions, obtain the average temperature representation values of the average temperature datasets of multiple significantly interested regions. Sort and rank the multiple significantly interested regions of the normal population according to the magnitudes of the average temperature representation values of the average temperature datasets of multiple significantly interested regions, so as to obtain the temperature sequence representation of the normal population in multiple significantly interested regions.

[0012] According to the present invention, there is provided a method for objectively evaluating the human body temperature sequence based on infrared thermal imaging technology. The method for obtaining the average temperature datasets of multiple interested regions of the normal population according to the thermal infrared images of the normal population includes:

[0013] According to the thermal infrared images of the normal population, obtain the temperature datasets of each individual in multiple interested regions of the normal population;

[0014] According to the temperature datasets of each individual in multiple interested regions, obtain the average temperature data of each individual in multiple interested regions, and form the average temperature datasets of the normal population in this interested region from the average temperature data of each individual in the same interested region, so as to obtain the average temperature datasets of the normal population in multiple interested regions.

[0015] According to the present invention, there is provided a method for objectively evaluating the human body temperature sequence based on infrared thermal imaging technology. The method for screening out multiple significantly interested regions with statistical differences between each pair from multiple interested regions by hypothesis testing according to the average temperature datasets of multiple interested regions of the normal population includes:

[0016] When the data distribution of the average temperature datasets of multiple interested regions of the normal population simultaneously satisfies the conditions of normal distribution and homogeneity of variance, use the analysis of variance of randomized block design to infer whether the means of the average temperature datasets of multiple interested regions are the same. When the data distribution of the average temperature datasets of multiple interested regions of the normal population cannot fully satisfy the conditions of normal distribution and homogeneity of variance, use the Friedman test of randomized block design to infer whether the data distributions of the average temperature datasets of multiple interested regions are the same;

[0017] When the inference result does not reject the hypothesis that the data distribution of the average temperature datasets of multiple interested regions comes from the same population distribution, it means that there is no exact sequence in this multiple interested regions, and other interested regions need to be reselected;

[0018] When the inference result rejects the hypothesis that the data distributions of the average temperature datasets of multiple regions of interest come from the same population distribution, multiple comparisons are performed on the average temperature datasets of multiple regions of interest through a loop, and the region of interest with the smallest statistical difference from the remaining regions of interest is recursively eliminated until the data distributions of the average temperature datasets of the remaining regions of interest are all different from each other pairwise. The remaining regions of interest are used as the significant regions of interest.

[0019] According to the present invention, a method for objectively evaluating the human body temperature sequence based on infrared thermal imaging technology is provided. According to the data distributions of the average temperature datasets of multiple significant regions of interest, the average temperature representation values of the average temperature datasets of multiple significant regions of interest are obtained, and the multiple significant regions of interest of the normal population are sorted and ranked according to the magnitudes of the average temperature representation values of the average temperature datasets of multiple significant regions of interest, so as to obtain the temperature sequence representation of the normal population in multiple significant regions of interest, including:

[0020] When the data distributions of the average temperature datasets of multiple significant regions of interest of the normal population simultaneously satisfy the conditions of normal distribution and homogeneity of variance, the mean of the average temperature dataset of each significant region of interest is used as the average temperature representation value of this significant region of interest, and the multiple significant regions of interest of the normal population are sorted and ranked according to the magnitudes of the average temperature representation values of each significant region of interest, so as to obtain the first temperature sequence representation of the normal population in multiple significant regions of interest, denoted as A′(A′1, A′2,... A′ i ... A′ n ), A′ i = i (1 ≤ i ≤ n));

[0021] When the data distributions of the average temperature datasets of multiple significant regions of interest of the normal population cannot simultaneously satisfy the conditions of normal distribution and homogeneity of variance, the median of the average temperature dataset of each significant region of interest is used as the average temperature representation value of this significant region of interest, and the multiple significant regions of interest of the normal population are sorted and ranked according to the magnitudes of the average temperature representation values of each significant region of interest, so as to obtain the second temperature sequence representation of the normal population in multiple significant regions of interest, denoted as A″(A″1, A″2,... A″ i ... A″ n ), A″ i = i (1 ≤ 1 ≤ n)).

[0022] The present invention also provides a method for objectively evaluating the human body temperature sequence based on infrared thermal imaging technology, including:

[0023] Receiving the thermal infrared image of the person to be measured, where the person to be measured is a male person to be measured or a female person to be measured;

[0024] Based on the thermal infrared image of the person to be tested, obtain the average temperature data of multiple significantly interesting regions selected by the above-mentioned objective evaluation method for human body temperature sequence based on infrared thermal imaging technology for the person to be tested;

[0025] Arrange the average temperature data of multiple significantly interesting regions of the person to be tested in the arrangement order of multiple significantly interesting regions in the temperature sequence representation of the normal population obtained by the above-mentioned objective evaluation method for human body temperature sequence based on infrared thermal imaging technology, and rank the multiple significantly interesting regions of the person to be tested according to the magnitudes of the average temperature data of the multiple significantly interesting regions of the person to be tested, so as to obtain the temperature sequence representation of the person to be tested in multiple significantly interesting regions, denoted as B(B1, B2,... B i ...,B n ), (1≤i≤n);

[0026] Compare the temperature sequence representation of the person to be tested with the temperature sequence representation of the normal population obtained by the above-mentioned objective evaluation method for human body temperature sequence based on infrared thermal imaging technology, so as to obtain the deviation degree between the temperature sequence representation of the person to be tested and the temperature sequence representation of the normal population. Among them, when the person to be tested is male, the temperature sequence representation of the normal population is the temperature sequence representation of the male normal population, and when the person to be tested is female, the temperature sequence representation of the normal population is the temperature sequence representation of the female normal population.

[0027] According to an objective evaluation method for human body temperature sequence based on infrared thermal imaging technology provided by the present invention, the comparing the temperature sequence representation of the person to be tested with the temperature sequence representation of the normal population obtained by the above-mentioned objective evaluation method for human body temperature sequence based on infrared thermal imaging technology to obtain the deviation degree between the temperature sequence representation of the person to be tested and the temperature sequence representation of the normal population includes:

[0028] According to the sequence expression, calculate the distance between the temperature sequence representation of the person to be tested and the temperature sequence representation of the normal population obtained by the above-mentioned objective evaluation method for human body temperature sequence based on infrared thermal imaging technology and perform normalization processing to obtain a sequence comparison result, where the sequence comparison result is within the interval [0, 1];

[0029] According to the sequence comparison result, the deviation degree of the temperature sequence representation of the person to be tested from the temperature sequence representation of the normal population is obtained. Among them, when the sequence comparison result is closer to 1, it indicates that the temperature sequence representation of the person to be tested is more deviated from the temperature sequence representation of the normal population. When the sequence comparison result is 1, it indicates that the temperature sequence representation of the person to be tested and the temperature sequence representation of the normal population are in a completely reverse order, that is, the temperature sequence representation of the person to be tested is completely opposite to the temperature sequence representation of the normal population. When the sequence comparison result is 0, it indicates that the temperature sequence representation of the person to be tested is the same as the temperature sequence representation of the normal population, that is, the temperature sequence representation of the person to be tested is not deviated from the temperature sequence representation of the normal population.

[0030] According to an objective evaluation method for the sequence of human body temperature based on infrared thermal imaging technology provided by the present invention, the sequence expression is:

[0031]

[0032] A i = i,

[0033] In the sequence expression, d represents the distance between the temperature sequence representation of the person to be tested and the temperature sequence representation of the normal population, d max represents the maximum value of the distance between the temperature sequence representation of the person to be tested and the temperature sequence representation of the normal population, d min represents the minimum value of the distance between the temperature sequence representation of the person to be tested and the temperature sequence representation of the normal population, d min is always equal to 0, n represents the number of significantly interested regions, A i represents the rank of the i-th significantly interested region in the temperature sequence representation of the normal population, B i represents the rank of the i-th significantly interested region in the temperature sequence representation of the person to be tested.

[0034] The present invention also provides one based on infrared thermal imaging technology, including:

[0035] A data acquisition module, configured to: acquire the thermal infrared images of the normal population, where the normal population is the male normal population or the female normal population;

[0036] A first data processing module, configured to: obtain the average temperature data set of multiple interested regions of the normal population according to the thermal infrared images of the normal population, where the interested regions represent the human body regions;

[0037] An interested region screening module, configured to: infer whether the data distribution of the average temperature data set of multiple interested regions comes from the same overall distribution through hypothesis testing according to the average temperature data set of multiple interested regions of the normal population, so as to screen out multiple significantly interested regions with statistical differences between each other from multiple interested regions;

[0038] A sequence representation module, configured to: obtain an average temperature representation value of the average temperature datasets of multiple significantly interested regions according to the data distribution of the average temperature datasets of multiple significantly interested regions, sort and rank the multiple significantly interested regions of the normal population according to the magnitude of the average temperature representation value of the average temperature datasets of multiple significantly interested regions, so as to obtain a temperature sequence representation of the normal population in the multiple significantly interested regions.

[0039] The present invention also provides a human body metabolic abnormality evaluation system based on infrared thermal imaging technology, including:

[0040] A data receiving module, configured to: receive the thermal infrared image of the person to be tested, where the person to be tested is a male person to be tested or a female person to be tested;

[0041] A second data processing module, configured to: obtain the average temperature data of the multiple significantly interested regions screened by the above-mentioned objective evaluation method for the human body temperature sequence based on infrared thermal imaging technology according to the thermal infrared image of the person to be tested;

[0042] A sorting and ranking module, configured to: sort and rank the multiple significantly interested regions of the person to be tested according to the magnitude of the average temperature data of the multiple significantly interested regions of the person to be tested, so as to obtain a temperature sequence representation of the person to be tested in the multiple significantly interested regions, denoted as B(B1, B2,...B i ...,B n ), (1≤i≤n);

[0043] A comparison module, configured to: compare the temperature sequence representation of the person to be tested with the temperature sequence representation of the normal population obtained by the above-mentioned objective evaluation method for the human body temperature sequence based on infrared thermal imaging technology, so as to obtain the deviation degree between the temperature sequence representation of the person to be tested and the temperature sequence representation of the normal population. When the deviation degree between the temperature sequence representation of the person to be tested and the temperature sequence representation of the normal population is greater than a preset degree threshold, a comparison result of metabolic abnormality of the person to be tested is obtained, where when the person to be tested is male, the temperature sequence representation of the normal population is the temperature sequence representation of the male normal population, and when the person to be tested is female, the temperature sequence representation of the normal population is the temperature sequence representation of the female normal population.

[0044] The present invention also provides an electronic device, including a processor and a memory storing a computer program, and when the processor executes the computer program, the above-mentioned objective evaluation method for the human body temperature sequence based on infrared thermal imaging technology is implemented.

[0045] The present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned objective evaluation method for the human body temperature sequence based on infrared thermal imaging technology is implemented.

[0046] The present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute any one of the above-mentioned objective evaluation methods for human body temperature sequence based on infrared thermal imaging technology.

[0047] An objective evaluation method for human body temperature sequence based on infrared thermal imaging technology provided by the present invention screens out significantly interesting regions with statistical differences based on thermal infrared images, and ranks and numbers the significantly interesting regions using human body temperature data, so as to obtain a temperature sequence representation of the normal population, that is, the normal order of the temperature levels of different ROIs. It is also possible to compare the temperature sequence representation of the person to be tested with the temperature sequence representation of the normal population, and objectively and quantitatively describe the deviation degree of the temperature sequence representation of the person to be tested from the temperature sequence representation of the normal population through the sequence comparison result, which can promote the development of medical research to a certain extent and effectively assist doctors in judging whether the person to be tested has metabolic abnormalities. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0049] Figure 1 It is one of the flow diagrams of an objective evaluation method for human body temperature sequence based on infrared thermal imaging technology provided by the present invention.

[0050] Figure 2 It is another flow diagram of an objective evaluation method for human body temperature sequence based on infrared thermal imaging technology provided by the present invention.

[0051] Figure 3 It shows the process of comparing the temperature sequence representation of the person to be tested with the temperature sequence representation of the normal population.

[0052] Figure 4 It is the structural diagram of an objective evaluation system for human body temperature sequence based on infrared thermal imaging technology and a human body metabolic abnormality evaluation system based on infrared thermal imaging technology provided by the present invention.

[0053] Figure 5 It is the structural diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0054] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention with reference to the accompanying drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention, and they should not be construed as limiting the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present invention without creative efforts fall within the scope of protection of the present invention. In the description of the present invention, it should be understood that the terms used are only for the purpose of description and cannot be construed as indicating or implying relative importance.

[0055] After extensive exploration by the research team, it was found that there is symmetry in the thermal infrared images of the normal population between the left and right sides of the body, and there is a temperature directionality in different body parts (hereinafter referred to as temperature sequence, abbreviated as sequence), for example, T head and face > T both palms > T both dorsa of feet. In people with abnormal metabolism, the thermal image characteristics of increased temperature at the extremities and decreased temperature in the trunk will appear, which is different from the sequence of the normal population. Currently, there is no objective method to evaluate the order of the body surface temperature in multiple body regions of the human body.

[0056] The following will combine Figures 1-5 to describe the objective evaluation method and system for the human body temperature sequence based on infrared thermal imaging technology provided by the present invention.

[0057] Figures 1-2 is a schematic flowchart of the objective evaluation method for the human body temperature sequence based on infrared thermal imaging technology provided by the present invention. Referring to Figure 1 , an objective evaluation method for the human body temperature sequence based on infrared thermal imaging technology provided by the present invention may include:

[0058] Step S110: Obtain thermal infrared images of the normal population, where the normal population is male normal population or female normal population. Specifically, thermal infrared images of healthy patients can be obtained from the hospital system as the thermal infrared images of the normal population. Then, the thermal infrared images of the male normal population are used as a set of thermal infrared images, and the thermal infrared images of the female normal population are used as another set of thermal infrared images for studying males and females respectively.

[0059] Step S120: According to the thermal infrared images of the normal population, obtain the average temperature data set of multiple regions of interest (ROIs) in the normal population, where the region of interest represents the human body region, and the number and location of the regions of interest can be flexibly set according to the actual situation.

[0060] Specifically, in step S120, based on the thermal infrared images of the normal population, a temperature data set of each individual in multiple regions of interest in the normal population can be obtained (the temperature data set is composed of data points in the corresponding regions of interest on the thermal infrared image of the person); then, based on the temperature data sets of each individual in multiple regions of interest, the average temperature data of each individual in multiple regions of interest can be obtained (that is, the mean value of the data in the temperature data set is taken as the average temperature data), and moreover, the average temperature data of each individual in the same region of interest constitutes the average temperature data set of the normal population in this region of interest, so as to obtain the average temperature data sets of the normal population in each region of interest.

[0061] The present invention believes that the region of interest is the body region that can sensitively reflect disease changes in the thermal infrared image. The correct selection of the region of interest is of great significance. It can be said that the selection of the ROI determines the diagnostic value of the sequence. The region of interest represents the human body region; in terms of metabolic diseases, its thermal map changes are complex and involve the whole body. ROIs such as the front of the neck, the head and face, the back torso, the calves, the palms, etc. that can better reflect metabolic changes can be selected as the research objects. Step S130: According to the data distribution of the average temperature data sets of multiple significantly interested regions, through hypothesis testing, it is inferred whether the data distributions of the average temperature data sets of multiple significantly interested regions come from the same population distribution. If they do not come from the same population distribution, then the data distributions of the average temperature data sets of multiple ROIs are repeatedly compared, and the ROIs with insignificant statistical differences are recursively excluded, and the significantly interested regions with statistical differences between each pair are screened out from multiple regions of interest for the objective evaluation of the average temperature data set of the average temperature data set. Among them, the number of regions of interest is N, and the number of significantly interested regions is n, (2 ≤ n ≤ N).

[0062] When performing statistical inference, when the data follows a normal distribution and the variances of each group of data are homogeneous, analysis of variance with a randomized block design is used for hypothesis testing, and the paired-sample t-test method is used for comparison between groups. The Bonferroni method is used to correct the P value to control the occurrence probability of type I error; when the data does not follow a normal distribution or the variance homogeneity, Friedman is used for hypothesis testing, and the Wilcoxon method is used for comparison between groups. The Bonferroni method is used to correct the P value to control the occurrence probability of type I error. If the overall values of the body surface temperatures of multiple ROIs are not completely the same, but the pairwise comparisons between groups are not completely statistically different, then by means of recursion, each time the ROI with the smallest average significance in the N - 1 pairwise comparisons between a certain ROI and the remaining N - 1 ROIs is excluded, and then the hypothesis testing is performed on the overall values of the body surface temperatures of the remaining N - 1 ROIs, and the above process is cycled until n (n ≤ N) ROIs with statistical differences between each pair are screened out.

[0063] In one embodiment, step S130 may include:

[0064] When the data distributions of the average temperature data sets of multiple regions of interest of the normal population simultaneously satisfy the normal distribution and the homogeneity of variance conditions, the analysis of variance of the randomized block design is used to infer whether the means of the average temperature data sets of multiple regions of interest are the same. When the data distributions of the average temperature data sets of multiple regions of interest of the normal population do not fully satisfy the normal distribution and the homogeneity of variance conditions, the Friedman test of the randomized block design is used to infer whether the data distributions of the average temperature data sets of multiple regions of interest are the same;

[0065] When the inference result does not reject the hypothesis that the data distributions of the average temperature data sets of multiple regions of interest come from the same population distribution, it means that there is no exact sequence in these multiple regions of interest;

[0066] When the inference result rejects the hypothesis that the data distributions of the average temperature data sets of multiple regions of interest come from the same population distribution, multiple comparisons are performed on the average temperature data sets of multiple regions of interest by looping, and the region of interest with the smallest statistical difference from the remaining regions of interest is recursively eliminated until the data distributions of the average temperature data sets of the remaining regions of interest are different from each other pairwise, and the remaining regions of interest are used as the significant regions of interest.

[0067] Step S140: According to the data distributions of the average temperature data sets of multiple significant regions of interest, obtain the average temperature representation values of the average temperature data sets of multiple significant regions of interest, and rank and number the multiple significant regions of interest of the normal population according to the magnitudes of the average temperature representation values of the average temperature data sets of multiple significant regions of interest, so as to obtain the temperature sequence representation of the normal population in multiple significant regions of interest.

[0068] In one embodiment, step S140 may include:

[0069] When the data distributions of the average temperature data sets of multiple significant regions of interest of the normal population simultaneously satisfy the normal distribution and the homogeneity of variance conditions, the mean of the average temperature data set of each significant region of interest is used as the average temperature representation value of this significant region of interest, and the multiple significant regions of interest of the normal population are ranked and numbered according to the magnitudes of the average temperature representation values of each significant region of interest, so as to obtain the first temperature sequence representation of the normal population in multiple significant regions of interest, denoted as A′(A′1, A′2,... A′ i ... A′ n ), A′ i = i (1 ≤ i ≤ n));

[0070] When the data distributions of the average temperature datasets of multiple significantly interested regions of the normal population cannot simultaneously satisfy the conditions of normal distribution and homogeneity of variance, the median of the average temperature dataset of each significantly interested region is used as the representative value of the average temperature of that significantly interested region. The multiple significantly interested regions of the normal population are sorted and ranked according to the magnitudes of the representative values of the average temperatures of each significantly interested region, obtaining the second temperature sequence representation of the normal population in multiple significantly interested regions, denoted as A″(A″1, A″2,... A″ i ... A″ n ), where A″ i = i (1 ≤ i ≤ n)).

[0071] In this embodiment, the left palm, left calf, back torso, head and face, and front neck are five significantly interested regions obtained through statistical inference and screening. When the average temperature data of these five significantly interested regions of the male / female normal population cannot simultaneously satisfy the conditions of normal distribution and homogeneity of variance, the median of the average temperature data of each significantly interested region is used to represent the representative value of the average temperature of that significantly interested region, and the multiple significantly interested regions are sorted from high to low according to the representative values of the average temperatures and ranked in sequence according to the serial numbers, obtaining: (left palm, 1) < (left calf, 2) < (back torso, 3) < (head and face, 4) < (front neck, 5). After step S140 arranges and ranks the significantly interested regions of the normal population according to the representative values of the average temperatures, the sequence of multiple significantly interested regions of the normal population is obtained (ROI1 < ROI2 < … < ROI i < … < ROI n ), and the corresponding rank order of the significantly interested regions is the normal sequence of the temperature data of the normal population in multiple significantly interested regions, denoted as A(A1, A2,... A i ... A n ). In this embodiment, the normal arrangement of the five significantly interested regions is (left palm < left calf < … < back torso < head and face < front neck), and the temperature sequence is represented as A = (1, 2, 3, 4, 5).

[0072] Through steps S110 - S140, significantly interested regions with statistical differences can be automatically screened out, and the normal order of the temperature levels of different significantly interested regions can be obtained.

[0073] Step S150: Obtain the thermal infrared image of the subject to be measured, where the subject to be measured is a male subject or a female subject.

[0074] Step S160: Obtain the average temperature data of the significantly interested regions selected by the above-mentioned objective evaluation method for human body temperature sequence based on infrared thermal imaging technology from the thermal infrared image of the person to be tested. In this embodiment, that is, obtain the average temperature data of the person to be tested on the left palm, left calf, back torso, head and face, and front neck from the thermal infrared image of the person to be tested.

[0075] Step S170: According to the order of the significantly interested regions arranged by the normal population obtained by the above-mentioned objective evaluation method for human body temperature sequence based on infrared thermal imaging technology, arrange the average temperature data of the significantly interested regions of the person to be tested in the order of the significantly interested regions of the normal population, and rank them in ascending order according to the magnitudes of the average temperature data of multiple significantly interested regions. The obtained ranking represents the temperature sequence of the person to be tested (the rank sequence is the temperature sequence of the person to be tested), denoted as B (B1, B2,... B i ...,B n ), (1 ≤ i ≤ n).

[0076] Specifically, when ranking the multiple significantly interested regions of the person to be tested in ascending order according to the average temperature data, if there are several pairs of identical average temperature data, it means that the ranks of each pair of significantly interested regions are the same. Then, take the average of the original ranks of this pair of significantly interested regions as the rank order.

[0077] Step S180: Compare the temperature sequence representation of the person to be tested with the temperature sequence representation of the normal population obtained above to obtain the deviation degree between the temperature sequence representation of the person to be tested and the temperature sequence representation of the normal population. Among them, when the person to be tested is male, the temperature sequence representation of the normal population is the temperature sequence representation of the male normal population; when the person to be tested is female, the temperature sequence representation of the normal population is the temperature sequence representation of the female normal population.

[0078] In this embodiment, step S180 may include:

[0079] According to the sequence expression, calculate the distance between the temperature sequence representation of the person to be tested and the temperature sequence representation of the normal population obtained by the above-mentioned objective evaluation method for human body temperature sequence based on infrared thermal imaging technology and perform normalization processing to obtain a sequence comparison result, where the sequence comparison result is within the interval [0, 1];

[0080] According to the sequence comparison result, the degree of deviation between the temperature sequence representation of the person to be tested and the temperature sequence representation of the normal population is obtained. Among them, when the sequence comparison result is closer to 1, it indicates that the temperature sequence representation of the person to be tested is more deviated from the temperature sequence representation of the normal population. When the sequence comparison result is 1, it means that the temperature sequence representation of the person to be tested and the temperature sequence representation of the normal population are in completely reverse order, that is, the temperature sequence representation of the person to be tested is completely opposite to the temperature sequence representation of the normal population. When the sequence comparison result is 0, it means that the temperature sequence representation of the person to be tested is the same as the temperature sequence representation of the normal population, that is, the temperature sequence representation of the person to be tested does not deviate from the temperature sequence representation of the normal population.

[0081] In one embodiment, when comparing the temperature sequence representation of the person to be tested with the temperature sequence representation of the normal population obtained by the above objective evaluation method of human body temperature sequence based on infrared thermal imaging technology, the Euclidean distance between sequence A and sequence B can be calculated first to obtain the deviation distance d, and then divided by the maximum Euclidean distance d between sequence B and sequence A in n significantly interesting regions max , and normalization is performed. It can be proved that when and only when sequence B and sequence A are in completely reverse order, d can be obtained max .

[0082] The verification process is as follows:

[0083] (x1, x2,...x i ,...x j ...xn) is a permutation of (1, 2...i...j,...n) (j > i).

[0084] d0 2 =(x1 - 1) 2 +(x2 - 2) 2 +...+(x i -i) 2 +(x j -j) 2 +(x n -n) 2

[0085] For any 1 ≤ i < j ≤ n

[0086] d1 2 =(x1 - 1) 2 +(x2 - 2) 2 +...+(x j -i) 2 +(x i -j) 2 +(x n -n) 2

[0087] d12 -d0 2 =(d1 + d0)×(d1 - d0)

[0088] =[(x j -i) 2 +(x i -j) 2 -[(x i -i) 2 +(x j -j) 2

[0089] =(x j +x i -2i)×(x j -x i )+(x j +x i -2j)×(x i -x j )

[0090] =2(j - i)×(x j -x i )

[0091] Since j > i, d1 + d0 > 0, if xi > xi, d1 - d2 > 0

[0092] It can be obtained that: In any permutation of [1, 2...i...j,...n], if the larger of the two values is moved forward, the Euclidean distance from the normal sequence A will be greater than the original permutation, and the maximum Euclidean distance d from the sequence A is obtained when it is completely reversed max , if the smaller of the two values is moved forward, the Euclidean distance from the normal sequence A will be less than the original permutation, and the minimum Euclidean distance d from the sequence A is obtained when it is identical to the permutation of sequence A min -0. And by calculation, when there are n regions of significant interest, the general term formula of d max is:

[0093]

[0094] The calculated sequence expression is:

[0095]

[0096] Since A i = i, the above formula can be further simplified to:

[0097]

[0098] ​In the sequential expression, d represents the distance between the temperature sequence representation of the person to be tested and the temperature sequence representation of the normal population, and d max represents the maximum value of the distance between the temperature sequence representation of the person to be tested and the temperature sequence representation of the normal population, n represents the number of significantly interested regions, and A i represents the ranking of the i-th significantly interested region in the temperature sequence representation of the normal population, and B i represents the ranking of the i-th significantly interested region in the temperature sequence representation of the person to be tested.

[0099] See Figure 3 , in this embodiment, the temperature sequence representations of three female persons to be tested are compared with the temperature sequence representations of the normal population. Among them, the significantly interested regions are the left palm, left calf, back torso, head and face, and front neck. And in the normal population, the sorting of the average temperature representation values between multiple significantly interested regions is: left palm < left calf < back torso < head and face < front neck, that is

[0100] SortO = [left dorsal foot, left palm, left calf, back torso, head and face, front neck], and the temperature sequence representation is A(A1, A2,... A i ... A n ) = (1, 2, 3, 4, 5). The average temperature data of the female persons to be tested in the left palm, left calf, back torso, head and face, and front neck are arranged in the order of the significantly interested regions of Sort0, and then the ranking process is performed on the significantly interested regions of the female persons to be tested in ascending order of the average temperature data of each significantly interested region. The temperature sequence representation of female person to be tested A is B 甲 = [1, 2, 3, 4, 5], the temperature sequence representation of female person to be tested B is B 乙 = [1, 2, 4, 3, 5], the temperature sequence representation of female person to be tested C is B 丙 = [5, 3, 1, 4, 2]. Then, the sequential comparison results of the temperature sequence representations B of the three female persons to be tested and the temperature sequence representation A of the female normal population are obtained through the sequential expression. The temperature sequence representation B of female person to be tested A 甲 and the temperature sequence representation A of the female normal population has a sequence of 0, that is, the temperature sequence representation of female person to be tested A is the same as the temperature sequence representation of the normal population, and the temperature sequence representation of the person to be tested does not deviate from the temperature sequence representation of the normal population. The temperature sequence representation B of female person to be tested B 乙 and the temperature sequence representation A of the female normal population has a sequence of 0.2236, that is, the temperature sequence representation of female person to be tested B is slightly deviated from the temperature sequence representation of the normal population. The temperature sequence representation B of female person to be tested C 丙The sequence similarity between the temperature sequence representation A of the female normal population and that of the female subject C is 0.8660, that is, the temperature sequence representation of the female subject C deviates significantly from that of the normal population, and the deviation degree of the female subject C is greater than that of the female subject B. When comparing the temperature sequence representation of the female subject with that of the normal population, if the deviation degree between the temperature sequence representation of the subject and that of the normal population is greater than the preset degree threshold (the preset degree threshold can be set according to the actual situation), it indicates that the subject has abnormal metabolism.

[0101] By evaluating the temperature differences between the subject and the normal population at various body parts, it is beneficial for medical staff to promptly detect patients with abnormal metabolism or potential diseases and flexibly formulate appropriate interrogation decisions.

[0102] Based on the thermal infrared images, the regions of interest with statistical differences are screened out, and the surface temperature data is used to sort and rank the regions of interest, so as to obtain the temperature sequence representation of the normal population, that is, the normal order of the temperature levels of different ROIs. The temperature sequence representation of the subject can also be compared with that of the normal population, and the deviation degree between the temperature sequence representation of the subject and that of the normal population can be objectively and quantitatively described through the sequence similarity comparison result, which can promote the development of medical research to a certain extent.

[0103] The following describes the objective evaluation system for the sequence similarity of human body temperature based on infrared thermal imaging technology provided by the present invention. The objective evaluation system for the sequence similarity of human body temperature based on infrared thermal imaging technology described below can be mutually referred to the objective evaluation method for the sequence similarity of human body temperature based on infrared thermal imaging technology described above.

[0104] Refer to Figure 4 , an objective evaluation system for the sequence similarity of human body temperature based on infrared thermal imaging technology provided by the present invention may include:

[0105] A data acquisition module, configured to: acquire thermal infrared images of the normal population, where the normal population is the male normal population or the female normal population;

[0106] A first data processing module, configured to: obtain the average temperature data set of multiple regions of interest (ROI, region of interest) of the normal population according to the thermal infrared images of the normal population;

[0107] A region of interest screening module, configured to: infer whether the data distribution of the average temperature data set of multiple regions of interest comes from the same overall distribution through hypothesis testing according to the average temperature data set of multiple regions of interest of the normal population, so as to screen out multiple significant regions of interest with statistical differences between each other from multiple regions of interest;

[0108] A sequence representation module, configured to: obtain an average temperature representation value of the average temperature datasets of multiple significantly interested regions according to the data distribution of the average temperature datasets of the multiple significantly interested regions, and sort and rank the multiple significantly interested regions of the normal population according to the magnitudes of the average temperature representation values of the average temperature datasets of the multiple significantly interested regions, so as to obtain a temperature sequence representation of the normal population in the multiple significantly interested regions.

[0109] According to a human body temperature sequence objective evaluation system based on infrared thermal imaging technology provided by the present invention, the first data processing module may include:

[0110] A first data acquisition sub-module, configured to: obtain temperature datasets of each individual in multiple interested regions of the normal population according to the thermal infrared images of the normal population;

[0111] A first data processing sub-module, configured to: obtain the average temperature data of each individual in the multiple interested regions according to the temperature datasets of each individual in the multiple interested regions, and form an average temperature dataset of the normal population in the interested region from the average temperature data of each individual in the same interested region, so as to obtain the average temperature datasets of the normal population in the multiple interested regions.

[0112] According to a human body temperature sequence objective evaluation system based on infrared thermal imaging technology provided by the present invention, the interested region screening module may include:

[0113] A first screening sub-module, configured to: when the data distribution of the average temperature datasets of the multiple interested regions of the normal population simultaneously satisfies the normal distribution and the homogeneity of variance conditions, use the analysis of variance of the randomized block design to infer whether the means of the average temperature datasets of the multiple interested regions are the same, and when the data distribution of the average temperature datasets of the multiple interested regions of the normal population does not fully satisfy the normal distribution and the homogeneity of variance conditions, use the Friedman test of the randomized block design to infer whether the data distributions of the average temperature datasets of the multiple interested regions are the same;

[0114] A second screening sub-module, configured to: when the inference result does not reject the hypothesis that the data distributions of the average temperature datasets of the multiple interested regions come from the same population distribution, it represents that there is no exact sequence in the multiple interested regions;

[0115] The third screening sub-module is used to: when the inference result rejects the hypothesis that the data distributions of the average temperature datasets of multiple regions of interest come from the same population distribution, perform multiple comparisons on the average temperature datasets of multiple regions of interest through a loop, recursively eliminate the region of interest with the smallest statistical difference from the remaining regions of interest until the data distributions of the average temperature datasets of the remaining regions of interest are all different from each other pairwise, and use the remaining regions of interest as the significant regions of interest.

[0116] According to a human body temperature sequence objective evaluation system based on infrared thermal imaging technology provided by the present invention, the sequence representation module may include:

[0117] The first sorting and ranking sub-module is used to: when the data distributions of the average temperature datasets of multiple significant regions of interest of the normal population simultaneously satisfy the normal distribution and the homogeneity of variance conditions, use the mean of the average temperature dataset of each significant region of interest as the average temperature representation value of the significant region of interest, sort and rank the multiple significant regions of interest of the normal population according to the size of the average temperature representation value of each significant region of interest, and obtain the first temperature sequence representation of the normal population in multiple significant regions of interest, denoted as A′(A′1, A′2,...A′ i ...,A′ n ),A′ i =i(1≤i≤n));

[0118] The second sorting and ranking sub-module is used to: when the data distributions of the average temperature datasets of multiple significant regions of interest of the normal population cannot simultaneously satisfy the normal distribution and the homogeneity of variance conditions, use the median of the average temperature dataset of each significant region of interest as the average temperature representation value of the significant region of interest, sort and rank the multiple significant regions of interest of the normal population according to the size of the average temperature representation value of each significant region of interest, and obtain the second temperature sequence representation of the normal population in multiple significant regions of interest, denoted as A″(A″1, A″2,...A″ i ...,A″ n ),A″ i =i(1≤i≤n))

[0119] Referring to Figure 4 , a human body metabolic abnormality evaluation system based on infrared thermal imaging technology provided by the present invention may include:

[0120] The data receiving module is used to: receive the thermal infrared image of the person to be tested, and the person to be tested is a male person to be tested or a female person to be tested;

[0121] A second data processing module, configured to: obtain, according to the thermal infrared image of the person to be tested, the average temperature data of multiple significantly interested regions screened by the above-mentioned objective evaluation method for the human body temperature sequence based on the infrared thermal imaging technology for the person to be tested;

[0122] A sorting and ranking module, configured to: sort the average temperature data of multiple significantly interested regions of the person to be tested according to the arrangement order of multiple significantly interested regions in the temperature sequence representation of the normal population obtained by the above-mentioned objective evaluation method for the human body temperature sequence based on the infrared thermal imaging technology, and rank the multiple significantly interested regions of the person to be tested according to the magnitudes of the average temperature data of the multiple significantly interested regions of the person to be tested, so as to obtain the temperature sequence representation of the person to be tested in the multiple significantly interested regions, denoted as B(B1, B2,...B i ...,B n ), (1≤i≤n);

[0123] A comparison module, configured to: compare the temperature sequence representation of the person to be tested with the temperature sequence representation of the normal population obtained by the above-mentioned objective evaluation method for the human body temperature sequence based on the infrared thermal imaging technology, so as to obtain the deviation degree between the temperature sequence representation of the person to be tested and the temperature sequence representation of the normal population. When the deviation degree between the temperature sequence representation of the person to be tested and the temperature sequence representation of the normal population is greater than a preset degree threshold, a comparison result of metabolic abnormality of the person to be tested is obtained, wherein when the person to be tested is male, the temperature sequence representation of the normal population is the temperature sequence representation of the male normal population, and when the person to be tested is female, the temperature sequence representation of the normal population is the temperature sequence representation of the female normal population.

[0124] According to a human metabolic abnormality evaluation system based on the infrared thermal imaging technology provided by the present invention, the comparison module may include:

[0125] A first comparison sub-module, configured to: calculate the distance between the temperature sequence representation of the person to be tested and the temperature sequence representation of the normal population obtained by the above-mentioned objective evaluation method for the human body temperature sequence based on the infrared thermal imaging technology according to a sequence expression and perform normalization processing, so as to obtain a sequence comparison result, wherein the sequence comparison result is within the interval [0, 1];

[0126] The second comparison sub-module is used to: obtain the deviation degree between the temperature sequence representation of the person to be tested and the temperature sequence representation of the normal population according to the sequence comparison result. Among them, when the sequence comparison result is closer to 1, it indicates that the temperature sequence representation of the person to be tested deviates more from the temperature sequence representation of the normal population. When the sequence comparison result is 1, it indicates that the temperature sequence representation of the person to be tested and the temperature sequence representation of the normal population are in a completely reverse order, that is, the temperature sequence representation of the person to be tested is completely opposite to the temperature sequence representation of the normal population. When the sequence comparison result is 0, it indicates that the temperature sequence representation of the person to be tested is the same as the temperature sequence representation of the normal population, that is, the temperature sequence representation of the person to be tested does not deviate from the temperature sequence representation of the normal population. When the deviation degree between the temperature sequence representation of the person to be tested and the temperature sequence representation of the normal population is greater than the preset degree threshold, obtain the comparison result of metabolic abnormality of the person to be tested.

[0127] Figure 5 An example of a schematic physical structure diagram of an electronic device is shown as Figure 5 shown. The electronic device may include: a processor 810, a communication interface 820, a memory 830, and a communication bus 840. Among them, the processor 810, the communication interface 820, and the memory 830 complete communication with each other through the communication bus 840. The processor 810 can call the logical instructions in the memory 830 to execute an objective evaluation method for the sequence of human body temperatures based on infrared thermal imaging technology. The method includes:

[0128] Receiving the thermal infrared image of the person to be tested, where the person to be tested is a male or female person to be tested;

[0129] According to the thermal infrared image of the person to be tested, obtain the average temperature data of multiple significantly interested regions selected by the above objective evaluation method for the sequence of human body temperatures based on infrared thermal imaging technology;

[0130] Arrange the average temperature data of multiple significantly interested regions of the person to be tested in the arrangement order of multiple significantly interested regions in the temperature sequence representation of the normal population obtained by the above objective evaluation method for the sequence of human body temperatures based on infrared thermal imaging technology, and rank the multiple significantly interested regions of the person to be tested according to the size of the average temperature data of the multiple significantly interested regions of the person to be tested, to obtain the temperature sequence representation of the person to be tested in multiple significantly interested regions, denoted as B(B1, B2,...B i ...,B n ), (1 ≤ i ≤ n);

[0131] Compare the temperature sequence representation of the person to be tested with the temperature sequence representation of the normal population obtained by the above-mentioned objective evaluation method for human body temperature sequence based on infrared thermal imaging technology, to obtain the deviation degree between the temperature sequence representation of the person to be tested and the temperature sequence representation of the normal population. When the deviation degree between the temperature sequence representation of the person to be tested and the temperature sequence representation of the normal population is greater than the preset degree threshold, obtain the comparison result of metabolic abnormality of the person to be tested. Among them, when the person to be tested is male, the temperature sequence representation of the normal population is the temperature sequence representation of the male normal population; when the person to be tested is female, the temperature sequence representation of the normal population is the temperature sequence representation of the female normal population.

[0132] Alternatively, the processor 810 may call the logical instructions in the memory 830 to execute another objective evaluation method for human body temperature sequence based on infrared thermal imaging technology, and the method includes:

[0133] Receive the thermal infrared image of the person to be tested, where the person to be tested is a male or a female;

[0134] According to the thermal infrared image of the person to be tested, obtain the average temperature data of multiple significantly interested regions screened by the above-mentioned objective evaluation method for human body temperature sequence based on infrared thermal imaging technology;

[0135] Arrange the average temperature data of multiple significantly interested regions of the person to be tested in the arrangement order of multiple significantly interested regions in the temperature sequence representation of the normal population obtained by the above-mentioned objective evaluation method for human body temperature sequence based on infrared thermal imaging technology, and rank the multiple significantly interested regions of the person to be tested according to the magnitude of the average temperature data of the multiple significantly interested regions of the person to be tested, to obtain the temperature sequence representation of the person to be tested in multiple significantly interested regions, denoted as B(B1, B2,...B i ...,B n ), (1≤i≤n);

[0136] Compare the temperature sequence representation of the person to be tested with the temperature sequence representation of the normal population obtained by the above-mentioned objective evaluation method for human body temperature sequence based on infrared thermal imaging technology, to obtain the deviation degree between the temperature sequence representation of the person to be tested and the temperature sequence representation of the normal population. When the deviation degree between the temperature sequence representation of the person to be tested and the temperature sequence representation of the normal population is greater than the preset degree threshold, obtain the comparison result of metabolic abnormality of the person to be tested. Among them, when the person to be tested is male, the temperature sequence representation of the normal population is the temperature sequence representation of the male normal population; when the person to be tested is female, the temperature sequence representation of the normal population is the temperature sequence representation of the female normal population.

[0137] In addition, when the logical instructions in the above-mentioned memory 830 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0138] On the other hand, the present invention also provides a computer program product. The computer program product includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute an objective evaluation method for the human body temperature sequence based on infrared thermal imaging technology provided by the above-mentioned various methods. The method includes:

[0139] Receiving a thermal infrared image of a person to be tested, where the person to be tested is a male person to be tested or a female person to be tested;

[0140] According to the thermal infrared image of the person to be tested, obtaining the average temperature data of multiple significantly interesting regions screened by the above-mentioned objective evaluation method for the human body temperature sequence based on infrared thermal imaging technology for the person to be tested;

[0141] Arranging the average temperature data of multiple significantly interesting regions of the person to be tested in the arrangement order of multiple significantly interesting regions in the temperature sequence representation of the normal population obtained by the above-mentioned objective evaluation method for the human body temperature sequence based on infrared thermal imaging technology, and ranking the multiple significantly interesting regions of the person to be tested according to the magnitude of the average temperature data of the multiple significantly interesting regions of the person to be tested, to obtain the temperature sequence representation of the person to be tested in multiple significantly interesting regions, denoted as B(B1, B2,...B i ...,B n ), (1 ≤ i ≤ n);

[0142] Compare the temperature sequence representation of the person to be tested with the temperature sequence representation of the normal population obtained by the above-mentioned objective evaluation method for the human body temperature sequence based on infrared thermal imaging technology to obtain the deviation degree between the temperature sequence representation of the person to be tested and the temperature sequence representation of the normal population. When the deviation degree between the temperature sequence representation of the person to be tested and the temperature sequence representation of the normal population is greater than the preset degree threshold, a comparison result of metabolic abnormality of the person to be tested is obtained. Among them, when the person to be tested is male, the temperature sequence representation of the normal population is the temperature sequence representation of the male normal population, and when the person to be tested is female, the temperature sequence representation of the normal population is the temperature sequence representation of the female normal population.

[0143] In another aspect, the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is implemented to execute an objective evaluation method for the human body temperature sequence based on infrared thermal imaging technology provided by the above-mentioned various methods. The method includes:

[0144] Receive the thermal infrared image of the person to be tested, where the person to be tested is a male person to be tested or a female person to be tested;

[0145] According to the thermal infrared image of the person to be tested, obtain the average temperature data of multiple significantly interested regions selected by the above-mentioned objective evaluation method for the human body temperature sequence based on infrared thermal imaging technology for the person to be tested;

[0146] Arrange the average temperature data of multiple significantly interested regions of the person to be tested in the arrangement order of multiple significantly interested regions in the temperature sequence representation of the normal population obtained by the above-mentioned objective evaluation method for the human body temperature sequence based on infrared thermal imaging technology, and rank the multiple significantly interested regions of the person to be tested according to the size of the average temperature data of the multiple significantly interested regions of the person to be tested, to obtain the temperature sequence representation of the person to be tested in multiple significantly interested regions, denoted as B(B1, B2,...B i ...,B n ), (1≤i≤n);

[0147] Compare the temperature sequence representation of the person to be tested with the temperature sequence representation of the normal population obtained by the above-mentioned objective evaluation method for the human body temperature sequence based on infrared thermal imaging technology to obtain the deviation degree between the temperature sequence representation of the person to be tested and the temperature sequence representation of the normal population. When the deviation degree between the temperature sequence representation of the person to be tested and the temperature sequence representation of the normal population is greater than the preset degree threshold, a comparison result of metabolic abnormality of the person to be tested is obtained. Among them, when the person to be tested is male, the temperature sequence representation of the normal population is the temperature sequence representation of the male normal population, and when the person to be tested is female, the temperature sequence representation of the normal population is the temperature sequence representation of the female normal population.

[0148] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative effort.

[0149] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0150] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. These modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An objective evaluation method for human body temperature sequence based on infrared thermal imaging technology, characterized in that, Including: Obtaining thermal infrared images of a normal population, where the normal population is a male normal population or a female normal population; Based on the thermal infrared images of the normal population, obtaining an average temperature data set of multiple regions of interest of the normal population, where the regions of interest represent human body regions; Based on the average temperature data set of multiple regions of interest of the normal population, inferring whether the data distributions of the average temperature data sets of multiple regions of interest come from the same overall distribution through hypothesis testing, so as to screen out multiple significantly interesting regions with statistical differences between each pair from multiple regions of interest; Based on the data distribution of the average temperature data set of multiple significantly interesting regions, obtaining the average temperature representation values of the average temperature data set of multiple significantly interesting regions, sorting and ranking the multiple significantly interesting regions of the normal population according to the size of the average temperature representation values of the average temperature data set of multiple significantly interesting regions, and obtaining the temperature sequence representation of the normal population in multiple significantly interesting regions.

2. The objective evaluation method for the human body temperature sequence based on the infrared thermal imaging technology according to claim 1, wherein The obtaining an average temperature data set of multiple regions of interest of the normal population based on the thermal infrared images of the normal population includes: Based on the thermal infrared images of the normal population, obtaining the temperature data set of each individual in multiple regions of interest of the normal population; Based on the temperature data set of each individual in multiple regions of interest, obtaining the average temperature data of each individual in multiple regions of interest, and forming the average temperature data set of the normal population in this region of interest from the average temperature data of each individual in the same region of interest, so as to obtain the average temperature data set of the normal population in multiple regions of interest.

3. The objective evaluation method for human body temperature sequence based on infrared thermal imaging technology according to claim 2, characterized in that The inferring whether the data distributions of the average temperature data sets of multiple regions of interest come from the same overall distribution through hypothesis testing, so as to screen out multiple significantly interesting regions with statistical differences between each pair from multiple regions of interest based on the average temperature data set of multiple regions of interest of the normal population includes: When the data distributions of the average temperature data sets of multiple regions of interest of the normal population simultaneously satisfy the conditions of normal distribution and homogeneity of variance, using analysis of variance with randomized block design to infer whether the means of the average temperature data sets of multiple regions of interest are the same. When the data distributions of the average temperature data sets of multiple regions of interest of the normal population cannot fully satisfy the conditions of normal distribution and homogeneity of variance, using the Friedman test with randomized block design to infer whether the data distributions of the average temperature data sets of multiple regions of interest are the same; When the inference result rejects the hypothesis that the data distributions of the average temperature data sets of multiple regions of interest come from the same overall distribution, performing multiple comparisons on the average temperature data sets of multiple regions of interest through a loop, recursively eliminating the region of interest with the smallest statistical difference from the remaining regions of interest until the data distributions of the remaining regions of interest are all different between each pair, and using the remaining regions of interest as significantly interesting regions.

4. The objective evaluation method for human body temperature sequence based on infrared thermal imaging technology according to claim 3, characterized in that Based on the data distribution of the average temperature datasets of multiple significantly interested regions, obtain the average temperature representation values of the average temperature datasets of multiple significantly interested regions, and sort and rank the multiple significantly interested regions of the normal population according to the magnitudes of the average temperature representation values of the average temperature datasets of multiple significantly interested regions, to obtain the temperature sequence representation of the normal population in multiple significantly interested regions, including: When the data distributions of the average temperature datasets of multiple significantly interesting regions in the normal population simultaneously satisfy the conditions of normal distribution and homogeneity of variance, the mean of the average temperature dataset of each significantly interesting region is used as the numerical value representing the average temperature of that significantly interesting region. The multiple significantly interesting regions of the normal population are sorted and ranked according to the magnitude of the numerical values representing the average temperature of each significantly interesting region, and the first temperature sequence representation of the normal population in multiple significantly interesting regions is obtained, denoted as A′(A′1, A′2,... A′ i ... A′ n ), A′ i = i (1 ≤ i ≤ n)); When the data distribution of the average temperature datasets of multiple significantly interesting regions in the normal population cannot simultaneously satisfy the conditions of normal distribution and homogeneity of variance, the median of the average temperature dataset of each significantly interesting region is used as the representative value of the average temperature of that significantly interesting region. The multiple significantly interesting regions of the normal population are sorted and ranked according to the magnitudes of the representative values of the average temperatures of each significantly interesting region, and the second temperature sequence representation of the normal population in the multiple significantly interesting regions is obtained, denoted as A″(A″1, A″2,... A″ i ... A″ n ), A″ i = i (1 ≤ i ≤ n)).

5. An objective evaluation method for human body temperature sequence based on infrared thermal imaging technology, characterized in that, including: Receive the thermal infrared image of the subject to be tested, where the subject to be tested is a male subject or a female subject; Based on the thermal infrared image of the subject to be tested, obtain the average temperature data of the significantly interested regions screened by the objective evaluation method for human body temperature sequence based on infrared thermal imaging technology according to any one of claims 1 to 4; Arrange the average temperature data of multiple significantly interested regions of the person to be tested in the arrangement order of multiple significantly interested regions in the temperature sequence representation of the normal population obtained by the objective evaluation method of human body temperature sequence based on infrared thermal imaging technology according to any one of claims 1 to 4, and rank the multiple significantly interested regions of the person to be tested according to the magnitudes of the average temperature data of the multiple significantly interested regions of the person to be tested, so as to obtain the temperature sequence representation of the person to be tested in the multiple significantly interested regions, denoted as B(B1, B2,... B i ...,B n ), (1 ≤ i ≤ n); Compare the temperature sequence representation of the subject to be tested with the temperature sequence representation of the normal population obtained by the objective evaluation method for human body temperature sequence based on infrared thermal imaging technology according to any one of claims 1 to 4, to obtain the deviation degree between the temperature sequence representation of the subject to be tested and the temperature sequence representation of the normal population. Among them, when the subject to be tested is male, the temperature sequence representation of the normal population is the temperature sequence representation of the male normal population, and when the subject to be tested is female, the temperature sequence representation of the normal population is the temperature sequence representation of the female normal population.

6. The objective evaluation method for human body temperature sequence based on infrared thermal imaging technology according to claim 5, wherein The step of comparing the temperature sequence representation of the subject to be tested with the temperature sequence representation of the normal population obtained by the objective evaluation method for human body temperature sequence based on infrared thermal imaging technology according to any one of claims 1 to 4, to obtain the deviation degree between the temperature sequence representation of the subject to be tested and the temperature sequence representation of the normal population, includes: According to the sequence expression, obtain the distance between the temperature sequence representation of the subject to be tested and the temperature sequence representation of the normal population obtained by the objective evaluation method for human body temperature sequence based on infrared thermal imaging technology according to any one of claims 1 to 4 and perform normalization processing to obtain the sequence comparison result, where the sequence comparison result is within the interval [0, 1]; According to the sequence comparison result, obtain the deviation degree between the temperature sequence representation of the subject to be tested and the temperature sequence representation of the normal population. Among them, when the sequence comparison result is closer to 1, it indicates that the temperature sequence representation of the subject to be tested is more deviated from the temperature sequence representation of the normal population. When the sequence comparison result is 1, it indicates that the temperature sequence representation of the subject to be tested and the temperature sequence representation of the normal population are in a completely reverse order, that is, the temperature sequence representation of the subject to be tested is completely opposite to the temperature sequence representation of the normal population. When the sequence comparison result is 0, it indicates that the temperature sequence representation of the subject to be tested is the same as the temperature sequence representation of the normal population, that is, the temperature sequence representation of the subject to be tested is not deviated from the temperature sequence representation of the normal population; Preferably, the sequence expression is: A i = i, In the sequential expression, d represents the distance between the temperature sequence representation of the person to be tested and the temperature sequence representation of the normal population, d max represents the maximum value of the distance between the temperature sequence representation of the person to be tested and the temperature sequence representation of the normal population, d min represents the minimum value of the distance between the temperature sequence representation of the person to be tested and the temperature sequence representation of the normal population, d min The value is always equal to 0, m represents the number of significantly interesting regions, A i represents the rank of the i-th significantly interesting region in the temperature sequence representation of the normal population, B i represents the rank of the i-th significantly interesting region in the temperature sequence representation of the person to be tested.

7. An objective evaluation system for human body temperature sequence based on infrared thermal imaging technology, characterized in that, including: A data acquisition module, configured to: acquire the thermal infrared image of the normal population, where the normal population is the male normal population or the female normal population; A first data processing module, configured to: based on the thermal infrared image of the normal population, obtain the average temperature datasets of multiple interested regions of the normal population, where the interested regions represent the human body regions; The region of interest screening module is used for: according to the average temperature data set of multiple regions of interest of normal people, inferring whether the data distributions of the average temperature data sets of multiple regions of interest come from the same population distribution through hypothesis testing, so as to screen out multiple significantly interesting regions with statistical differences between each other from multiple regions of interest; The sequence representation module is used for: according to the data distributions of the average temperature data sets of multiple significantly interesting regions, obtaining the average temperature representation values of the average temperature data sets of multiple significantly interesting regions, sorting and ranking multiple significantly interesting regions of normal people according to the magnitudes of the average temperature representation values of the average temperature data sets of multiple significantly interesting regions, and obtaining the temperature sequence representation of normal people in multiple significantly interesting regions.

8. A human body metabolic abnormality evaluation system based on infrared thermal imaging technology, characterized in that, It includes: The data receiving module is used for: receiving the thermal infrared image of the subject to be measured, and the subject to be measured is a male subject or a female subject; The second data processing module is used for: according to the thermal infrared image of the subject to be measured, obtaining the average temperature data of the significantly interesting regions screened by the objective evaluation method for human body temperature sequence based on infrared thermal imaging technology described in any one of claims 1 to 4; A sorting and ranking module, configured to: sort the average temperature data of multiple significantly interested regions of a person to be measured in accordance with the arrangement order of multiple significantly interested regions in the temperature sequence representation of the normal population obtained by the human body temperature sequential objective evaluation method based on infrared thermal imaging technology according to any one of claims 1 to 4, and rank the multiple significantly interested regions of the person to be measured according to the magnitudes of the average temperature data of the multiple significantly interested regions of the person to be measured, so as to obtain a temperature sequence representation of the person to be measured in the multiple significantly interested regions, denoted as B(B1, B2,... B i ...,B n ), (1 ≤ i ≤ n); The comparison module is used for: comparing the temperature sequence representation of the subject to be measured with the temperature sequence representation of normal people obtained by the objective evaluation method for human body temperature sequence based on infrared thermal imaging technology described in any one of claims 1 to 4, obtaining the deviation degree between the temperature sequence representation of the subject to be measured and the temperature sequence representation of normal people, and when the deviation degree between the temperature sequence representation of the subject to be measured and the temperature sequence representation of normal people is greater than the preset degree threshold, obtaining the comparison result of metabolic abnormality of the subject to be measured, wherein, when the subject to be measured is male, the temperature sequence representation of normal people is the temperature sequence representation of male normal people, and when the subject to be measured is female, the temperature sequence representation of normal people is the temperature sequence representation of female normal people.

9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the objective evaluation method for human body temperature sequence based on infrared thermal imaging technology described in any one of claims 1 to 6.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the objective evaluation method for human body temperature sequence based on infrared thermal imaging technology described in any one of claims 1 to 6.

Images