A storage medium and an infrared thermal image processing system

Abstract

This application relates to the technical field of general image data processing or generation, and particularly relates to a storage medium and an infrared thermal image processing system. Instructions or programs are stored in the storage medium, and the instructions or programs are loaded and executed by a processor to implement the following steps: Obtain A, T B and T C ; If C is located in S B or C is not located in S B but d BC <d0 and T BC <T0, then obtain T AB =T 1 A -T 1 B , then output a second prompt message indicating T AB ; If C is not located in S B and d BC ≥d0 or T BC ≥T0, then output a first prompt message indicating to retake or re-obtain L. The present invention can accurately obtain the temperature of the symmetric position of a certain position of the human body in the infrared thermal image.

Description

Technical Field

[0001] The present invention relates to the technical field of general image data processing or generation, and particularly to a storage medium and an infrared thermal image processing system. Background Art

[0002] Infrared thermal imaging technology belongs to modern medical imaging technology, which is a functional imaging technology based on cell metabolism. An infrared camera can be used to collect the infrared thermal image of the human body. The temperature difference between the symmetric positions on the left and right sides of the human body in the infrared thermal image has high reference significance. However, when collecting the infrared thermal image of the human body, the human body may shake or tilt, or there may be deviations when the user determines the symmetry axis of the human body, or there may be deviations when the computer automatically identifies the symmetry axis. As a result, the method of obtaining the symmetric position of a certain position of the human body based on the symmetry axis of the human body is prone to deviations, and further the reliability of the obtained temperature difference is not high. How to accurately obtain the temperature of the symmetric position of a certain position of the human body in the infrared thermal image is an urgent problem to be solved. Summary of the Invention

[0003] The purpose of the present invention is to provide a storage medium and an infrared thermal image processing system, which can accurately obtain the temperature of the symmetric position of a certain position of the human body in the infrared thermal image.

[0004] According to a first aspect of the present invention, there is provided a non-transitory computer-readable storage medium, in which at least one instruction or at least one program segment is stored. The at least one instruction or the at least one program segment is characterized in that it is loaded and executed by a processor to implement the following steps:

[0005] S100, obtain A, where A is the position with the lowest temperature in the first target area S1 of the human body in the infrared thermal image F.

[0006] S200, obtain T B , T B is the temperature of B, where B is the position of the human body in F that is symmetric to A with respect to L, and L is the symmetry axis of the human body in F.

[0007] S300, obtain T C , T C is the temperature of C, where C is the position with the lowest temperature in the second target area S2 of the human body in F, and S2 is the area symmetric to S1 with respect to L.

[0008] S400, if C is located in S B then enter S600, S B is a region centered on B with a size of m*n, where m and n are both positive integers; if C is not located in S B then enter S500.

[0009] S500, if d BC < d0 and T BC < T0, then enter S600; if d BC ≥ d0 or T BC ≥ T0, then output the first prompt message indicating reshooting or re - obtaining L; d BC is the distance between B and C, T BC = T B - T C , d0 is the set distance, T0 is the set temperature, T0 > 0.

[0010] S600, obtain T AB = T 1 A - T 1 B , and output the second prompt message indicating T AB ; T A,j is the temperature at the j - th position in S A , S A is a region of size m * n centered on A, T B,k is the temperature at the k - th position in S B .

[0011] Compared with the prior art, the present invention has obvious beneficial effects. By means of the above - mentioned technical solutions, the storage medium and the infrared thermal image processing system provided by the present invention can achieve considerable technological progress and practicality, and have wide industrial utilization value. It has at least the following beneficial effects:

[0012] The present invention respectively obtains the position A with the lowest temperature in S1, the position B symmetric to A about L, and the position C with the lowest temperature in the region S2 symmetric to S1 about L. Based on the fact that C is located in the region of size m * n centered on B, it quickly determines that the temperature corresponding to B is the temperature of the symmetric position of accurate A, and when C is not located in the above - mentioned region, it further judges whether the distance between C and B is less than the set distance and whether the temperature difference between C and B is less than the set temperature, and only when both are less, it determines that the temperature corresponding to B is the temperature of the symmetric position of accurate A; on the premise that the temperature corresponding to B is the temperature of the symmetric position of accurate A, the present invention further obtains T AB , and outputs the second prompt message indicating T AB ; otherwise, output the first prompt message indicating reshooting or re - obtaining L. The present invention judges whether the temperature corresponding to B is the temperature of the symmetric position of accurate A by introducing C, achieving the purpose of accurately obtaining the temperature of the symmetric position of A. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0014] Figure 1 It is a flowchart of the infrared thermal image processing method provided by the embodiment of the present invention. Specific embodiments

[0015] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0016] According to the first aspect of the present invention, a non-transitory computer-readable storage medium is provided. At least one instruction or at least one program segment is stored in the storage medium, and the at least one instruction or the at least one program segment is loaded and executed by a processor to implement the infrared thermal image processing method. As Figure 1 shown, the infrared thermal image processing method includes the following steps:

[0017] S100, obtain A, where A is the position with the lowest temperature in the first target area S1 of the human body in the infrared thermal image F.

[0018] According to the present invention, the method for obtaining S1 includes:

[0019] S110, obtain the key points P=(p1, p2,..., p N ) on L, p r =(x p,r , y p,r ) is the r-th key point on L, x p,r and y p,r are the abscissa and ordinate of p r respectively, and the value range of r is from 1 to N, where N is the total number of key points on L.

[0020] According to the present invention, L is the axis of symmetry of the human body in F.

[0021] S120, obtain the edge points E=(e1, e2,..., e N ) of S1, e r =(x p,r + x' r , y p,r + y'r ),x' r and y' r are respectively the r horizontal coordinate offset and vertical coordinate offset of e r compared with p

[0022] According to the present invention, the position of the key point p r on L can be determined first. After the position of the key point p r on L is determined, the horizontal coordinate and vertical coordinate of e r can be obtained according to the pre-set x' r and y' r thereby obtaining the horizontal coordinate and vertical coordinate of e r and the position of e

[0023] in the infrared thermal image. r The advantage of the present invention in obtaining e r in this way is that the position of the key point on L is easier to accurately obtain, and the relative position relationship between the upper edge point of S1 and the corresponding key point is fixed, thereby improving the accuracy of obtaining e

[0024] S130, traverse E, connect e r-1 and e r+1 to e r respectively to obtain S1.

[0025] Optionally, in S110, the trained neural network is used to obtain P.

[0026] According to the present invention, the method for obtaining the trained neural network includes:

[0027] S111, obtain a set of infrared thermal image samples.

[0028] S112, perform key point annotation on each infrared thermal image sample on L to obtain a set of annotated infrared thermal image samples.

[0029] S113, use the set of annotated infrared thermal image samples to train the constructed neural network to obtain a trained neural network.

[0030] Those skilled in the art know that using any method for training a neural network in the prior art to obtain the trained neural network of the present invention falls within the protection scope of the present invention.

[0031] Optionally, S1 is the precordial area or the postcardiac area input by the user or automatically recognized by the computer.

[0032] S200, obtain T B , T BThe temperature of B, where B is the position of the human body in F that is symmetric to A with respect to L, and L is the axis of symmetry of the human body in F.

[0033] According to the present invention, the method for obtaining L is as follows: traverse P, and for p r-1 and p r+1 respectively connect with P r to obtain L.

[0034] Optionally, when S1 is the precordial region, L is the Conception Vessel of the human body, and P is the set of acupoint key points on the Conception Vessel; when S1 is the postcardiac region, L is the Governor Vessel of the human body, and P is the set of acupoint key points on the Governor Vessel. It should be understood that there are multiple acupoint key points on the Conception Vessel and the Governor Vessel of the human body respectively. In the process of training the neural network in the present invention, it is not necessary to label all acupoint key points, nor is it necessary to make the trained neural network have the function of recognizing all acupoint key points of the human body. It is only necessary to label the acupoint key points used to locate E, so that the trained neural network has the function of recognizing the acupoint key points of the human body used to locate E.

[0035] According to the present invention, when collecting the infrared thermal image of the human body, the human body may shake or tilt, or due to the deviation of L obtained in the above process, it may lead to the temperature T corresponding to B obtained in the present invention B not being the temperature of the symmetric position of the accurate A (according to the present invention, the obtained temperature T corresponding to B B may either be the temperature of the symmetric position of the accurate "A" or not be the temperature of the symmetric position of the accurate "A"), thus resulting in the calculation result of T in S600 AB having no reference significance. For this reason, the present invention then also needs to determine whether T B is the temperature of the symmetric position of the accurate A.

[0036] S300, obtain T C , T C is the temperature of C, where C is the position with the lowest temperature in the second target area S2 of the human body in F, and S2 is the area symmetric to S1 with respect to L.

[0037] According to the present invention, A belongs to S1, B is the position symmetric to A with respect to L, and S2 is the area symmetric to S1 with respect to L. Then B also belongs to S2. Therefore, C may coincide with B or may not coincide with B.

[0038] According to the present invention, the thermal energy radiated by the human body has symmetry. If B is the exact symmetric position of A and the temperature information of B is accurate, then the temperatures of B and A should be basically the same. If A is the position with the lowest temperature in S1, then B should also be the position with the lowest temperature in S2. Conversely, if B is not the exact symmetric position of A or the temperature information of B is inaccurate, then there will be a large temperature difference between B and the position with the lowest temperature in S2.

[0039] In order to achieve the judgment of whether the temperature at the symmetric position of A is accurate, the present invention also introduces the position C with the lowest temperature in S2. Based on the position and temperature of the introduced C, the present invention can determine whether the temperature of B is the temperature at the symmetric position of A, and obtain T only when the temperature of B is the temperature at the symmetric position of A. B In order to achieve the judgment of whether the temperature at the symmetric position of A is accurate, the present invention also introduces the position C with the lowest temperature in S2. Based on the position and temperature of the introduced C, the present invention can determine whether the temperature of B is the temperature at the symmetric position of A, and obtain T only when the temperature of B is the temperature at the symmetric position of A. AB , thereby ensuring the reference significance of T. AB of T.

[0040] S400, if C is located in S B , then enter S600, S B is a region of size m*n centered on B, where both m and n are positive integers; if C is not located in S B , then enter S500.

[0041] According to the present invention, the positions in S B are the positions in S2 that are relatively close to B. The purpose of the present invention to judge whether C is located in S B is to quickly judge whether C is very close to B. According to the present invention, when C is very close to B, the temperatures of C and B are similar. Therefore, the present invention can directly determine that B is the exact symmetric position of A and the temperature information of B is accurate when C is located in S B , without the need to judge through S500. Based on this, the present invention improves the efficiency of judging whether the temperature of B is the temperature at the symmetric position of A.

[0042] S500, if d BC <d0 and T BC <T0, then enter S600; if d BC ≥d0 or T BC ≥T0, then output the first prompt information indicating to reshoot or re-obtain L; d BC is the distance between B and C, T BC =T B -T C , d0 is the set distance, T0 is the set temperature, and T0>0.

[0043] According to the present invention, if d BC <d0 and T BC<T0 indicates that the distance and temperature difference between C and B are small, and B can be determined as the accurate symmetric position of A, and the temperature of B can be determined as the temperature of the accurate symmetric position of A.

[0044] According to the present invention, if d BC ≥ d0 or T BC ≥ T0, it indicates that the distance or temperature difference between C and B is large, and B cannot be determined as the accurate symmetric position of A, and the temperature of B cannot be determined as the temperature of the accurate symmetric position of A. The reason for this situation may be that the human body may shake or tilt when collecting the infrared thermal image of the human body, or there may be a deviation in the above process of obtaining L. Preferably, the present invention outputs a first prompt message indicating to re - shoot or re - obtain L in this case.

[0045] Optionally, x B and x C are the abscissas of B and C respectively, and y B and y C are the ordinates of B and C respectively.

[0046] S600, obtain T AB = T 1 A - T 1 B , and output a second prompt message indicating T AB ; T A,j is the temperature at the j - th position in S A , S A is a region of size m * n centered on A, T B,k is the temperature at the k - th position in S B .

[0047] According to the present invention, obtaining the average value of the temperatures of each position in the region of size m * n centered on A represents the temperature of A, and obtaining the average value of the temperatures of each position in the region of size m * n centered on B represents the temperature of B. The advantages of the present invention in obtaining T 1 A and T 1 B are: reducing the influence of inaccurate temperature information of a single position in the infrared thermal image on the analysis result, and improving the accuracy of the temperature difference between A and its symmetric position obtained.

[0048] Optionally, m = n. At this time, S A is a square region centered on A.

[0049] Preferably, m = n = 3. At this time, S AA-centered area of size 3*3, T 1 A Taking into account the influence of inaccurate temperature information at a single position in the infrared thermal image on the analysis result and T 1 A The similarity with the temperature of A, improving the accuracy of the obtained temperature difference between A and the symmetric position.

[0050] An embodiment of the present invention also provides an infrared thermal image processing system, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the following infrared thermal image processing method described in the embodiments of the present invention is implemented.

[0051] Although some specific embodiments of the present invention have been described in detail by way of examples, those skilled in the art should understand that the above examples are for illustrative purposes only and not for limiting the scope of the present invention. Those skilled in the art should also understand that various modifications can be made to the embodiments without departing from the scope and spirit of the present invention. The scope of the present invention is defined by the appended claims.

Claims

1. A non-transitory computer-readable storage medium storing at least one instruction or at least one program segment, characterized in that, The at least one instruction or the at least one program segment is loaded and executed by a processor to implement the following steps: S100, obtain A, where A is the position with the lowest temperature in the first target area S1 of the human body in the infrared thermal image F; S200, obtain T B , T B is the temperature of B, B is the position of the human body in F that is symmetric to A with respect to L, and L is the axis of symmetry of the human body in F; S300, obtain T C , T C is the temperature of C, where C is the position with the lowest temperature in the second target area S2 of the human body in F, and S2 is the area symmetric to S1 with respect to L; S400, if C is located in S B then enter S600, where S B is a region centered at B with a size of m*n, where both m and n are positive integers; if C is not located in S B then enter S500; S500, if d BC < d0 and T BC < T0, then enter S600; if d BC ≥ d0 or T BC ≥ T0, then output the first prompt message indicating reshooting or reacquiring L d BC is the distance between B and C, T BC = T B - T C , d0 is the set distance, T0 is the set temperature, T0 > 0; S600, obtain T AB = T 1 A -T 1 B , and output a second prompt message indicating T AB ; T A,j is the temperature at the j-th position in S A , where S A is a region of size m*n centered at A, T B,k is the temperature at the k-th position in S B .

2. The medium according to claim 1, wherein In S100, the method for obtaining S1 includes: S110, obtain the key point P = (p1, p2,..., p N ), p r = (x p,r , y p,r ) is the r-th key point on L, x p,r and y p,r are the abscissa and ordinate of p r respectively, and the value range of r is from 1 to N, where N is the total number of key points on L; S120, obtain the edge points E = (e1, e2,..., e N ), e r = (x p,r + x' r , y p,r + y' r ), where x' r and y' r are respectively the horizontal coordinate offset and the vertical coordinate offset of e r compared to p r ; S130, traverse E, and take e r-1 and e r+1 respectively connect with e r to obtain S1.

3. The medium according to claim 2, wherein In S110, use a trained neural network to obtain P.

4. The medium according to claim 3, wherein In S110, the method for obtaining the trained neural network includes: S111, obtain a set of infrared thermal image samples; S112, perform key point annotation on each infrared thermal image sample on L to obtain a set of annotated infrared thermal image samples; S113, use the set of annotated infrared thermal image samples to train the constructed neural network to obtain a trained neural network.

5. The medium according to claim 1, wherein In S600, m = n.

6. The medium according to claim 5, wherein In S600, m = n = 3.

7. The medium according to claim 1, wherein In S500, x B and x C are the abscissas of B and C respectively, and y B and y C are the ordinates of B and C respectively.

8. The medium according to claim 1, characterized in that, In S100, S1 is the precordial area or the postcardiac area input by the user or automatically recognized by the computer.

9. An infrared thermal image processing system, 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 computer program, the following steps are implemented: S100, obtain A, where A is the position with the lowest temperature in the first target area S1 of the human body in the infrared thermal image F; S200, obtain T B , T B is the temperature of B, B is the position of the human body in F that is symmetric to A with respect to L, and L is the axis of symmetry of the human body in F; S300, obtain T C , T C is the temperature of C, where C is the position with the lowest temperature in the second target area S2 of the human body in F, and S2 is the area symmetric to S1 with respect to L; S400, if C is located in S B then enter S600, where S B is a region of size m*n centered on B, and both m and n are positive integers; if C is not located in S B then enter S500; S500, if d BC < d0 and T BC < T0, then enter S600; if d BC ≥ d0 or T BC ≥ T0, then output the first prompt message indicating reshooting or re-acquiring L; d BC is the distance between B and C, T BC = T B - T C , d0 is the set distance, T0 is the set temperature, T0 > 0; S600, obtain T AB = T 1 A -T 1 B , and output a second prompt message indicating T AB ; T A,j is the temperature at the j-th position in S A ; S A is a region of size m*n centered on A, T B,k is the temperature at the k-th position in S B .

Images