CN117297551B - Data processing system based on infrared image - Google Patents
Data processing system based on infrared image Download PDFInfo
- Publication number
- CN117297551B CN117297551B CN202311424530.4A CN202311424530A CN117297551B CN 117297551 B CN117297551 B CN 117297551B CN 202311424530 A CN202311424530 A CN 202311424530A CN 117297551 B CN117297551 B CN 117297551B
- Authority
- CN
- China
- Prior art keywords
- temperature
- area
- region
- infrared image
- sub
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000008186 active pharmaceutical agent Substances 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims 1
- 230000000875 corresponding effect Effects 0.000 description 37
- 208000026106 cerebrovascular disease Diseases 0.000 description 12
- 238000001514 detection method Methods 0.000 description 7
- 238000003745 diagnosis Methods 0.000 description 5
- 210000004204 blood vessel Anatomy 0.000 description 4
- 238000000034 method Methods 0.000 description 4
- 230000002490 cerebral effect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000003331 infrared imaging Methods 0.000 description 2
- 206010008190 Cerebrovascular accident Diseases 0.000 description 1
- 241000282412 Homo Species 0.000 description 1
- 208000006011 Stroke Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 230000004630 mental health Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0033—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0033—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room
- A61B5/004—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room adapted for image acquisition of a particular organ or body part
- A61B5/0042—Features or image-related aspects of imaging apparatus classified in A61B5/00, e.g. for MRI, optical tomography or impedance tomography apparatus; arrangements of imaging apparatus in a room adapted for image acquisition of a particular organ or body part for the brain
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Radiology & Medical Imaging (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Neurology (AREA)
- Radiation Pyrometers (AREA)
Abstract
The invention provides a data processing system based on infrared images, which comprises: a processor and an infrared image capturing device; the infrared image shooting device is used for acquiring an infrared image of the target. The processor is used for: acquiring a target area in a target infrared image, wherein the target area comprises a first area and a second area which are symmetrical relative to a vertical axis; acquiring temperature information in the first area and the second area, judging whether the temperatures in the first area and the second area have symmetry or not based on the acquired temperature information, and obtaining corresponding judgment results; acquiring a temperature fluctuation coefficient of temperature information on a set length on the vertical axis, and comparing the acquired temperature fluctuation coefficient with the set temperature fluctuation coefficient to obtain a corresponding comparison result; and assigning corresponding labels to the target infrared images based on the judging result and the comparing result. The invention can objectively and accurately analyze the image.
Description
Technical Field
The invention relates to the field of image processing, in particular to a data processing system based on infrared images.
Background
With the advancement of medical technology, humans are gradually walking into the elderly society. With the advent of the aged society, physical and mental health of the aged has become an important social problem, and particularly, detection of cerebrovascular diseases such as cerebral apoplexy, which pose a great threat to life, has become a major concern. For such diseases, common detection methods include comprehensive judgment based on medical history, detection using medical images such as magnetic resonance blood vessel images and cerebral blood vessel CTA, etc., however, detection based on medical history may have a problem of inaccurate detection, detection based on medical images may have a certain radiation, detection based on cerebral blood vessel CTA may have a problem of being unable to display lesions of small blood vessel branches. In recent years, infrared imaging technology has been widely used in the field of traditional Chinese medicine, and by observing the temperature distribution, shape distribution, and the like of infrared images, the physical function of the human body can be known in an assisted manner. Currently, related studies for assisting diagnosis of cerebrovascular diseases based on infrared images have been conducted. In the prior art, the interpretation of infrared images is performed by manual reading and manual analysis. However, in view of the complexity of the temperature distribution of the infrared image, the manner of manually reading the infrared image is seriously dependent on the experience of medical staff, and when the experience of the medical staff is insufficient, a large diagnosis error is brought, so that the auxiliary diagnosis of the infrared image is meaningless.
Disclosure of Invention
Aiming at the technical problems, the invention adopts the following technical scheme:
The embodiment of the invention provides a data processing system based on infrared images, which comprises: the processor is in communication connection with the infrared image shooting device; the infrared image shooting device is used for shooting an infrared image of a target object to obtain a target infrared image;
the processor is configured to execute a computer program to implement the steps of:
S10, acquiring a target area in a target infrared image, wherein the target area comprises a first area and a second area which are symmetrical relative to a vertical axis.
S12, temperature information in the first area and temperature information in the second area are respectively acquired, whether symmetry exists in the temperatures in the first area and the second area or not is judged based on the acquired temperature information, and corresponding judgment results are obtained.
S14, acquiring a temperature fluctuation coefficient of the temperature information on the set length on the vertical axis, and comparing the acquired temperature fluctuation coefficient with the set temperature fluctuation coefficient to obtain a corresponding comparison result.
And S16, giving corresponding labels to the target infrared image based on the judging result and the comparing result, wherein if the temperature in the first area and the second area are symmetrical and the comparing result is a first result, the labels of the target infrared image are set as first labels, otherwise, the labels of the target infrared image are set as second labels, and the first result is a result that the temperature fluctuation coefficient of the temperature information representing the set length is smaller than the set temperature fluctuation coefficient.
Embodiments of the present invention also provide a non-transitory computer readable storage medium having stored therein at least one instruction or at least one program, wherein the at least one instruction or the at least one program is loaded and executed by a processor to implement a method as described above.
The embodiment of the invention also provides an electronic device comprising a processor and the non-transitory computer readable storage medium.
The invention has at least the following beneficial effects:
The data processing system based on the infrared image provided by the embodiment of the invention can automatically analyze the temperature in the target infrared image based on the temperature information required by the actual application scene such as the cerebrovascular disease, so as to obtain the corresponding analysis result, and can improve the analysis speed and accuracy. The invention can objectively and accurately output the auxiliary information of the cerebrovascular diseases and improve the accuracy of the diagnosis of the cerebrovascular diseases.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a data processing system based on infrared images according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to fall within the scope of the invention.
The embodiment of the invention provides a data processing system based on infrared images, which comprises a processor and an infrared image shooting device which are in communication connection; the infrared image shooting device is used for shooting an infrared image of a target object to obtain a target infrared image.
In the embodiment of the invention, the infrared image capturing device can be an existing product. The target infrared image may be an image captured by the infrared imaging device when the human body makes a corresponding action based on a behavior gesture set in an actual application scene, for example, may be an image including a head and a neck, or may be an overall image of the human body.
Further, in an embodiment of the present invention, the processor is configured to execute a computer program to implement the steps shown in fig. 1:
S10, acquiring a target area in the target infrared image, wherein the target area comprises a first area and a second area which are symmetrical relative to a vertical axis, namely the target area is a symmetrical area.
In this embodiment, the target infrared image vertical axis refers to the vertical axis of the body.
In this embodiment, the target region may be acquired from the target infrared image based on existing methods. In the case where the target infrared image is entirely symmetrical with respect to the vertical axis, the target area may be the entire infrared image.
S12, temperature information in the first area and temperature information in the second area are respectively acquired, whether symmetry exists in the temperatures in the first area and the second area or not is judged based on the acquired temperature information, and corresponding judgment results are obtained.
S14, acquiring a temperature fluctuation coefficient of the temperature information on the set length on the vertical axis, and comparing the acquired temperature fluctuation coefficient with the set temperature fluctuation coefficient to obtain a corresponding comparison result.
In the embodiment of the invention, the set length can be determined based on the actual application scene and is the length section needing to be focused. In a specific application scenario, the set length may be a length corresponding to a brain.
S16, corresponding labels are given to the target infrared images based on the judging result and the comparing result. And if the temperature in the first area and the second area have symmetry and the comparison result is a first result, setting the label of the target infrared image as a first label, otherwise, setting the label of the target infrared image as a second label, wherein the first result is a result that the temperature fluctuation coefficient of the temperature information on the set length is smaller than the set temperature fluctuation coefficient.
In embodiments of the present invention, the first tag and the second tag may be represented by different identifications. In one specific application scenario, the first label represents a label in the absence of a cerebrovascular disease, and the second label represents a label in the presence of a possible cerebrovascular disease.
The data processing system based on the infrared image provided by the embodiment of the invention can automatically analyze the temperature in the target infrared image based on the temperature information required by the actual application scene such as the cerebrovascular disease, so as to obtain the corresponding analysis result, and can improve the analysis speed and accuracy. The invention can objectively and accurately output the auxiliary information of the cerebrovascular diseases and improve the accuracy of the diagnosis of the cerebrovascular diseases.
Further, in an embodiment of the present invention, the first region includes m sub-regions A1 1,A12,…,A1i,…,A1m, the second region includes m sub-regions a13, A2 2,…,A2i,…,A2m, and the i-th sub-region A1 i in the first region and the i-th sub-region A2 i in the second region are two sub-regions symmetrical with respect to the vertical axis. In this embodiment, the sub-regions may be set based on actual needs. In one example, the sub-region may be an expert-specified sub-region. In another example, the sub-region may be a region that is automatically acquired by a trained AI model, and the specific manner of acquisition may be prior art.
In this embodiment, S12 may specifically include:
S123, acquiring the temperature corresponding to n (i) pixel points in any sub-area A1 i, obtaining temperature information T1 i＝(T1i1,T1i2,…,T1ir,…,T1in(i) corresponding to A1 i, and acquiring the temperature corresponding to n (i) pixel points in sub-area A2 i corresponding to any sub-area A1 i, obtaining temperature information T2 i＝(T2i1,T2i2,…,T2ir,…,T2in(i) corresponding to A2 i), wherein T1 ir is the temperature corresponding to the r-th pixel point in A1 i, T2 ir is the temperature corresponding to the r-th pixel point symmetrical to the r-th pixel point in A1 i in A2 i, and the value of r is 1 to n (i).
Those skilled in the art know that any method for obtaining the temperature corresponding to the pixel point in any sub-area falls within the protection scope of the present invention.
S122, obtaining the temperature similarity D i between the A1 i and the A2 i; if D i > D0, execute S123; otherwise, S124 is performed; d0 is a set similarity threshold.
In this embodiment, D i may be obtained using an existing similarity algorithm, for example, euclidean distance, mahalanobis distance, cosine distance, or the like. D0 can be set based on actual needs, preferably D0.gtoreq.0.8, more preferably D0.gtoreq.0.9.
S123, setting c1=c1+1; s124 is performed. C1 is a counter and the initial value may be 0.
S124, setting i=i+1, if i is less than or equal to n (i), executing S123; otherwise, S125 is performed.
S125, if C1 is more than or equal to K m, judging that the temperature in the first area and the temperature in the second area are symmetrical; otherwise, judging that the temperature in the first area and the temperature in the second area are not symmetrical; k is a set coefficient, and K can be set based on actual needs, and in one exemplary embodiment, K is more than or equal to 0.8 and less than or equal to 1.
Further, in another embodiment of the present invention, the first area may include n sub-areas C1 1,C12,…,C1j,…,C1n, the second area includes n sub-areas C2 1,C22,…,C2j,…,C2n,C1j, where C2 j is an area acquired in the first area based on the j-th set temperature interval RT j, C2 j is an area acquired in the second area based on the j-th set temperature interval RT j, j has a value of 1 to n, and n is the number of set temperature intervals.
In one embodiment of the invention, RT j may be divided based on experience. The temperature interval may be the same for each temperature interval, i.e. the step size is the same for each temperature interval. For example, the temperature range in the target infrared image may be equally divided into n temperature sections according to a set temperature step.
In another embodiment of the present invention, RT j satisfies the following conditions simultaneously:
condition 1: r1 j＞B1,R2j is less than B2; wherein the first symmetrical proportion NP1 1 oj is the number of pixels in the sub-region C1 1 oj acquired in the corresponding first region in the o-th one of the set M first infrared images based on RT j, NP2 1 oj is the number of pixels in the sub-region C2 1 oj acquired in the corresponding second region in the o-th one of the set M first infrared images based on RT j, NP 1 oj is the number of symmetrical pixels in C1 oj and C2 oj; second symmetry ratio/>NP1 2 oj is the number of pixels in the sub-region C1 2 oj acquired in the corresponding first region in the o-th one of the set M second infrared images based on RT j, NP2 2 oj is the number of pixels in the sub-region C2 2 oj acquired in the corresponding second region in the o-th one of the set M first infrared images based on RT j, NP 2 oj is the number of symmetrical pixels in C1 2 oj and C2 2 oj; the first infrared image is a human body infrared image of a first object with a body state in a first set state, and the second infrared image is a human body infrared image of a second object with a body state in a second set state. B1 is a first set threshold, e.g., B2.gtoreq.0.8, and B2 is a second set threshold, which may be an empirical value, e.g., B2.gtoreq.0.4.
In an embodiment of the present invention, the first set state is a physical state without cerebrovascular disease, and the second set state is a physical state with cerebrovascular disease.
Condition 2: r1 jF＜R1j, R1 jB-R1j)/R1j < R0, wherein R1 jF is a first symmetrical proportion corresponding to a temperature interval (min (RT j),max(RTj) - [ delta ] T), R1 jB is a first symmetrical proportion corresponding to a temperature interval (min (RT j),max(RTj) + [ delta ] T), min (RT j) is a minimum value in R1 j, max (RT j) is a maximum value in RT j, and [ delta ] T is a set temperature step, can be set based on actual needs, and can be 0.02-0.05 DEG, preferably 0.05 DEG, R0 is a set value, such as 0.1-0.2.
Those skilled in the art will recognize that the start point (i.e., minimum) of any one temperature interval is the end point (i.e., maximum) of the previous temperature interval.
In a specific implementation, RT j can be obtained by the following steps:
Step 1, min (RT j) is obtained. Those skilled in the art will appreciate that the minimum value of the first temperature interval is a set starting temperature, for example, the lowest average temperature of the human body.
Step 2, setting max q(RTj)＝min(RTj) +q Δt, and obtaining a first symmetrical proportion R1 jq and a second symmetrical proportion R2 jq corresponding to a temperature interval (min (RT j),maxq(RTj)), if R1 jq＞B1,R2jq < B2, and the first symmetrical proportion RF jq＜R1jq corresponding to the temperature interval (min (RT j),maxq(RTj) -. DELTA.t), and the first symmetrical proportion RB jq and R1 jq corresponding to the temperature interval (min (RT j),maxq(RTj) +DELTA T) satisfy (RB jq-R1jq)/R1jq < R0), then (min (RT j),maxq(RTj) ] is taken as RT j, otherwise, step 3 is executed, and q is the current step number.
Step 3, setting q=q+1, and executing step 2. In this embodiment, since each temperature section is determined based on the above two conditions, the divided temperature sections can be made more accurate.
In this embodiment, S12 may specifically include:
S221, obtaining pixel points in any sub-region C1 j to obtain pixel point information P1 j＝(P1j1,P12,…,P1js,…,P1jf1(j) corresponding to C1 j), and obtaining pixel points in any sub-region C2 j to obtain pixel point information P2 j＝(P2j1,P2j2,…,P2jt,…,P2jf2(j) corresponding to C2 j), wherein P1 js is the S-th pixel point in C1 j, the value of S is 1 to f1 (j), and f1 (j) is the number of pixel points in C1 j; p2 jt is the t-th pixel point in C2 j, the value of t is 1 to f2 (j), and f2 (j) is the number of pixels in C2 j.
S222, obtaining symmetrical pixel points in C1 j and C2 j to obtain corresponding symmetrical pixel point information PS1 j＝(PS1j1,
PS1 j2,…,PS1ju,…,PS1jh(j)) and PS2 j＝(PS2j1,PS2j2,…,PS2ju,…,PS2jh(j)),PS1ju and PS2 ju
The u-th symmetrical pixel points in PS1 j and PS2 j are respectively, PS1 ju and PS2 ju are symmetrical relative to the vertical axis, the value of u is 1 to h (j), and h (j) is the number of symmetrical pixel points in C1 j and C2 j.
S223, if 2*h (j)/(f 1 (j) +f2 (j)) > a, executing S224, otherwise executing S225; a is a first set coefficient, and may be an empirical value, for example, 0.8.ltoreq.a.ltoreq.1.
S224, c2=c2+1 is set; s225 is performed. C2 is a counter and the initial value may be 0.
S225, setting j=j+1, and executing S221 if j is less than or equal to n; otherwise, S226 is performed.
S226, if C2.gtoreq.b.n, judging that the temperature in the first area and the second area have symmetry, otherwise, judging that the temperature in the first area and the second area have no symmetry, wherein b is a second set coefficient, and can be an empirical value, for example, 0.8.ltoreq.b.ltoreq.1.
Further, in the embodiment of the present invention, the following steps are further included between S222 and S223:
S21, acquiring temperature information TS1 j＝(TS1j1,TS1j2,…,TS1ju,…,TS1jh(j) corresponding to PS1 j) and acquiring temperature information TS2 j＝(TS2j1,TS2j2,…,TS2ju,…,TS2jh(j));TS1ju and TS2 ju corresponding to PS2 j are temperatures corresponding to PS1 j and PS2 j, respectively.
S22, acquiring the temperature similarity DS j.DSj between TS1 j and TS2 j can be achieved by adopting the existing similarity algorithm, such as Euclidean distance, mahalanobis distance, cosine distance and the like.
S223 is replaced with:
S23, if 2*h (j)/(f 1 (j) +f2 (j)) > a, and DS j > D0, executing S224, otherwise, executing S225; a is a first set coefficient, and may be an empirical value, for example, 0.8.ltoreq.a.ltoreq.1.
The technical effects of S21 to S23 are that, only if the proportion of the symmetrical pixel points in any two corresponding sub-areas in the first area and the second area reaches a certain proportion, and the temperature values in the any two sub-areas are relatively close, the symmetry of the first area and the second area is judged, and compared with the foregoing embodiments, the accuracy of judgment can be improved.
Further, in the embodiment of the present invention, S14 may specifically include:
S1401, obtaining pixel point information px= (PX 1,PX2,…,PXv,…,PXG),PXv is the v-th pixel point in PX, the value of v is 1 to G, and G is the number of pixel points in PX.
S1402, temperature information tx= (TX 1,TX2,…,TXv,…,TXG),TXv is the temperature corresponding to PX v) corresponding to PX is obtained.
S1403, obtaining the temperature fluctuation coefficient of TXIf FX > h F0, obtaining a first result, otherwise, obtaining a second result; avgTX = (TX 1+TX2+…+TXv+…+TXG)/G, h×f0 is a set fluctuation coefficient, h is a set value, h is equal to or greater than 1, preferably h=1.1.
In the embodiment of the present invention, f0=max (FX 1,FX2,…,FXd,…,FXE),TX dv is the v pixel point of the d infrared image in the E infrared images on the set length of the vertical axis, wherein the E infrared images are the human body infrared images of E objects with the body states in the set states, and the d has a value of 1 to E; avgTX d＝(TXd1+TXd2+…+TXdv+…+TXdG)/G. The setting state is the aforementioned first setting state.
Further, in the embodiment of the present invention, after S14, the method further includes:
s15, acquiring the deviation degree between the temperature information on the set length and the set temperature information.
In the embodiment of the present invention, the set temperature information may be TCX＝(TCX1,TCX2,…,TCXd,…,TCXE),TCXd＝Avg(TXd1,TXd2,…,TXdv,…,TXdG),TXdv a v-th pixel point of a set length of a d-th infrared image in the set E infrared images on a vertical axis.
In the embodiment of the present invention, the deviation between the temperature information on the set length and the set temperature information is the deviation distance between the temperature curves formed by the two, that is, whether the variation trend is consistent, may be obtained based on the prior art, for example, the covariance between the two is obtained, if the covariance is positive and is greater than the set threshold, the smaller the deviation between the two is, which indicates that the variation trend between the two is more similar.
S16 is replaced with:
and S18, giving corresponding labels to the target infrared image based on the judging result, the comparing result and the deviation degree, wherein if the temperature in the first area and the second area has symmetry and the comparing result is a first result and the deviation degree is smaller than a preset deviation degree, the labels of the target infrared image are set as first labels, otherwise, the labels of the target infrared image are set as second labels, and the first result is a result that the temperature fluctuation coefficient of the temperature information on the set length is smaller than the set temperature fluctuation coefficient.
In the embodiment of the present invention, the preset deviation may be an empirical value.
The technical effects of S15 and S16 are that the tag of the target infrared image is determined to be the first tag only when there is symmetry in the temperatures in the first area and the second area, the temperature fluctuation coefficient of the temperature information over the set length is smaller than the set temperature fluctuation coefficient, and the degree of deviation between the temperature information over the set length and the set temperature information is smaller than the preset degree of deviation, and the judgment accuracy can be further improved compared with the foregoing embodiments.
Further, in an embodiment of the present invention, a display is further included. The processor is further configured to execute a computer program to perform the steps of:
and visually displaying the target infrared image on the display based on the temperature distribution information in the target area.
In one exemplary embodiment, the temperature information on the vertical axis and the temperature information on the horizontal axis perpendicular to the vertical axis may be displayed in a curved form, respectively, so that the temperature distribution on the vertical axis and the horizontal axis is intuitively known to the relevant person.
In another exemplary embodiment, the temperature information on the target infrared image may be displayed in a 3D model, where the location of the region of high temperature in the model is high, and vice versa, so that the relevant person can more intuitively know the temperature information in the image.
While certain specific embodiments of the invention have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the invention. Those skilled in the art will also appreciate that many modifications may be made to the embodiments without departing from the scope and spirit of the invention. The scope of the present disclosure is defined by the appended claims.
Claims (7)
1. A data processing system based on infrared images, comprising: the processor is in communication connection with the infrared image shooting device; the infrared image shooting device is used for shooting an infrared image of a target object to obtain a target infrared image;
the processor is configured to execute a computer program to implement the steps of:
S10, acquiring a target area in a target infrared image, wherein the target area comprises a first area and a second area which are symmetrical relative to a vertical axis;
S12, respectively acquiring temperature information in the first area and the second area, judging whether symmetry exists between the temperature in the first area and the temperature in the second area based on the acquired temperature information, and obtaining a corresponding judgment result;
S14, acquiring a temperature fluctuation coefficient of temperature information on a set length on the vertical axis, and comparing the acquired temperature fluctuation coefficient with the set temperature fluctuation coefficient to obtain a corresponding comparison result;
S15, acquiring the deviation degree between the temperature information on the set length and the set temperature information;
s18, giving corresponding labels to the target infrared image based on the judging result, the comparing result and the deviation degree, wherein if the temperature in the first area and the second area are symmetrical and the comparing result is a first result and the deviation degree is smaller than a preset deviation degree, the labels of the target infrared image are set as first labels, otherwise, the labels of the target infrared image are set as second labels, and the first result is a result that the temperature fluctuation coefficient of the temperature information on the set length is smaller than the set temperature fluctuation coefficient;
s14 specifically comprises the following steps:
s1401, acquiring pixel point information px= (PX 1,PX2,…,PXv,…,PXG),PXv is the v-th pixel point in PX, the value of v is 1 to G, and G is the number of pixel points in PX;
S1402, acquiring temperature information tx= (TX 1,TX2,…,TXv,…,TXG),TXv is the temperature corresponding to PX v;
s1403, obtaining the temperature fluctuation coefficient of TX If FX > h F0, obtaining a first result, otherwise, obtaining a second result; avgTX = (TX 1+TX2+…+TXv+…+TXG)/G, h is F0 which is a set fluctuation coefficient, h is a set value, and h is more than or equal to 1;
The set temperature information is TCX＝(TCX1,TCX2,…,TCXd,…,TCXE),TCXd＝Avg(TXd1,TXd2,…,TXdv,…,TXdG),TXdv is a v pixel point of a d infrared image in the E set infrared images on a set length on a vertical axis, the E infrared images are human body infrared images of E objects with body states in the set states, and d has a value of 1 to E;
wherein f0=max (FX 1,FX2,…,FXd,…,FXE), TX dv is the v pixel point of the d infrared image in the E infrared images on the set length of the vertical axis, the E infrared images are the human body infrared images of E objects with the body states in the set states, and the values of d are 1 to E.
2. The system of claim 1, wherein the first region comprises m sub-regions A1 1,A12,…,A1i,…,A1m, the second region comprises m sub-regions A2 1,A22,…,A2i,…,A2m, and an i-th sub-region A1 i in the first region and an i-th sub-region A2 i in the second region are two sub-regions that are symmetrical about the vertical axis;
S12 specifically comprises the following steps:
S121, acquiring temperatures corresponding to n (i) pixel points in any sub-region A1 i, acquiring temperature information T1 i＝(T1i1,T1i2,…,T1ir,…,T1in(i) corresponding to A1 i, and acquiring temperatures corresponding to n (i) pixel points in sub-region A2 i corresponding to any sub-region A1 i, acquiring temperature information T2 i＝(T2i1,T2i2,…,T2ir,…,T2in(i) corresponding to A2 i), wherein T1 ir is the temperature corresponding to the r-th pixel point in A1 i, T2 ir is the temperature corresponding to the r-th pixel point symmetrical to the r-th pixel point in A1 i in A2 i, and the value of r is 1 to n (i);
s122, obtaining the temperature similarity D i between the A1 i and the A2 i; if D i > D0, execute S123; otherwise, S124 is performed; d0 is a set temperature similarity threshold;
s123, setting a counter c1=c1+1; s124 is executed;
s124, setting i=i+1, if i is less than or equal to n (i), executing S123; otherwise, S125 is performed;
s125, if C1 is more than or equal to K m, judging that the temperature in the first area and the temperature in the second area are symmetrical; otherwise, judging that the temperature in the first area and the temperature in the second area are not symmetrical; k is a set coefficient.
3. The system of claim 1, wherein the first region comprises n sub-regions C1 1,C12,…,C1j,…,C1n, the second region comprises n sub-regions C2 1,C22,…,C2j,…,C2n,C1j being regions acquired in the first region based on a j-th set temperature interval RT j, C2 j being regions acquired in the second region based on a j-th set temperature interval RT j, j having a value of 1 to n, n being the number of set temperature intervals;
S12 specifically comprises the following steps:
S221, obtaining pixel points in any sub-region C1 j to obtain pixel point information P1 j＝(P1j1,P12,…,P1js,…,P1jf1(j) corresponding to C1 j), and obtaining pixel points in any sub-region C2 j to obtain pixel point information P2 j＝(P2j1,P2j2,…,P2jt,…,P2jf2(j) corresponding to C2 j), wherein P1 js is the S-th pixel point in C1 j, the value of S is 1 to f1 (j), and f1 (j) is the number of pixel points in C1 j; p2 jt is the t pixel point in C2 j, the value of t is 1 to f2 (j), and f2 (j) is the number of pixels in C2 j;
s222, obtaining symmetric pixel points in C1 j and C2 j to obtain corresponding symmetric pixel point information PS1 j＝(PS1j1,PS1j2,…,PS1ju,…,PS1jh(j)) and corresponding symmetric pixel points in PS2 j＝(PS2j1,PS2j2,…,PS2ju,…,PS2jh(j)),PS1ju and PS2 ju which are the u-th symmetric pixel points in PS1 j and PS2 j respectively, wherein the PS1 ju and PS2 ju are symmetric relative to the vertical axis, the u value is 1 to h (j), and the h (j) is the number of the symmetric pixel points in C1 j and C2 j;
s223, if 2*h (j)/(f 1 (j) +f2 (j)) > a, executing S224, otherwise executing S225; a is a first set coefficient;
S224, a counter c2=c2+1 is set; s225 is executed;
s225, setting j=j+1, and executing S221 if j is less than or equal to n; otherwise, S226 is performed;
S226, if C2 is larger than or equal to b, judging that the temperature in the first area and the second area has symmetry, otherwise, judging that the temperature in the first area and the second area has no symmetry, and b is a second set coefficient.
4. A system according to claim 3, further comprising the steps between S222 and S223 of:
S21, acquiring temperature information TS1 j＝(TS1j1,TS1j2,…,TS1ju,…,TS1jh(j) corresponding to PS1 j) and acquiring temperature information TS2 j＝(TS2j1,TS2j2,…,TS2ju,…,TS2jh(j));TS1ju and TS2 ju corresponding to PS2 j, wherein the temperatures are corresponding to PS1 j and PS2 j respectively;
S22, obtaining a temperature similarity DS j between TS1 j and TS2 j;
S223 is replaced with:
S23, if 2*h (j)/(f 1 (j) +f2 (j)) > a, and DS j > D0, executing S224, otherwise, executing S225; a is a first set coefficient; d0 is a set temperature similarity threshold.
5. A system according to claim 3, wherein RT j satisfies the following conditions simultaneously:
condition 1: r1 j＞B1,R2j is less than B2; wherein the first symmetrical proportion NP1 1 oj is the number of pixels in the sub-region C1 1 oj acquired in the corresponding first region in the o-th one of the set M first infrared images based on RT j, NP2 1 oj is the number of pixels in the sub-region C2 1 oj acquired in the corresponding second region in the o-th one of the set M first infrared images based on RT j, NP 1 oj is the number of symmetrical pixels in C1 oj and C2 oj; second symmetry ratio/>NP1 2 oj is the number of pixels in the sub-region C1 2 oj acquired in the corresponding first region in the o-th one of the set M second infrared images based on RT j, NP2 2 oj is the number of pixels in the sub-region C2 2 oj acquired in the corresponding second region in the o-th one of the set M first infrared images based on RT j, NP 2 oj is the number of symmetrical pixels in C1 2 oj and C2 2 oj; the first infrared image is a human body infrared image of a first object with a body state in a first set state, and the second infrared image is a human body infrared image of a second object with a body state in a second set state; b1 is a first set threshold, and B2 is a second set threshold;
Condition 2: r1 jF＜R1j, and (R1 jB-R1j)/R1j < R0), wherein R1 jF is a first symmetrical proportion corresponding to a temperature interval (min (RT j),max(RTj) -. DELTA.T), R1 jB is a first symmetrical proportion corresponding to a temperature interval (min (RT j),max(RTj) +DELTA.T), min (RT j) is a minimum value in R1 j, max (RT j) is a maximum value in RT j, DELTA.T is a minimum value in a set temperature step min (RT j) is RT j, max (RT j) is a maximum value in RT j, DELTA.T is a set temperature step, and R0 is a set value.
6. The system of claim 1, further comprising a display; the processor is further configured to execute a computer program to perform the steps of: and visually displaying the target infrared image on the display based on the temperature distribution information in the target area.
7. The system of claim 6, wherein the visual display comprises a 3D display.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311424530.4A CN117297551B (en) | 2023-10-30 | 2023-10-30 | Data processing system based on infrared image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311424530.4A CN117297551B (en) | 2023-10-30 | 2023-10-30 | Data processing system based on infrared image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117297551A CN117297551A (en) | 2023-12-29 |
| CN117297551B true CN117297551B (en) | 2024-04-19 |
Family
ID=89249890
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311424530.4A Active CN117297551B (en) | 2023-10-30 | 2023-10-30 | Data processing system based on infrared image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117297551B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018158504A1 (en) * | 2017-03-01 | 2018-09-07 | Thermidas Oy | Multimodal medical imaging and analyzing system, method and server |
| CN115761212A (en) * | 2022-11-02 | 2023-03-07 | 北京鹰之眼智能健康科技有限公司 | Human body state early warning system based on infrared image |
| CN116407093A (en) * | 2023-03-23 | 2023-07-11 | 北京鹰之眼智能健康科技有限公司 | Automatic acquisition system for infrared image temperature |
| CN116452554A (en) * | 2023-04-23 | 2023-07-18 | 广州中大医疗器械有限公司 | Method and device for processing and analyzing human infrared image |
| CN116664966A (en) * | 2023-03-27 | 2023-08-29 | 北京鹰之眼智能健康科技有限公司 | Infrared image processing system |
-
2023
- 2023-10-30 CN CN202311424530.4A patent/CN117297551B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018158504A1 (en) * | 2017-03-01 | 2018-09-07 | Thermidas Oy | Multimodal medical imaging and analyzing system, method and server |
| CN115761212A (en) * | 2022-11-02 | 2023-03-07 | 北京鹰之眼智能健康科技有限公司 | Human body state early warning system based on infrared image |
| CN116407093A (en) * | 2023-03-23 | 2023-07-11 | 北京鹰之眼智能健康科技有限公司 | Automatic acquisition system for infrared image temperature |
| CN116664966A (en) * | 2023-03-27 | 2023-08-29 | 北京鹰之眼智能健康科技有限公司 | Infrared image processing system |
| CN116452554A (en) * | 2023-04-23 | 2023-07-18 | 广州中大医疗器械有限公司 | Method and device for processing and analyzing human infrared image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117297551A (en) | 2023-12-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Şevik et al. | Identification of suitable fundus images using automated quality assessment methods | |
| Ji et al. | Eye and mouth state detection algorithm based on contour feature extraction | |
| Cazzato et al. | When i look into your eyes: A survey on computer vision contributions for human gaze estimation and tracking | |
| US20180300540A1 (en) | Person identification systems and methods | |
| Roth et al. | Deep convolutional networks for automated detection of posterior-element fractures on spine CT | |
| CN115761212B (en) | Human body state early warning system based on infrared image | |
| Tam et al. | Automated delineation of organs-at-risk in head and neck CT images using multi-output support vector regression | |
| CN115690400B (en) | Infrared image display method | |
| CN115588099B (en) | Region of interest display method, electronic device and storage medium | |
| CN115497123B (en) | Method for acquiring state parameters of region of interest | |
| Abas et al. | Acne image analysis: lesion localization and classification | |
| Speidel et al. | Image-based tracking of the suturing needle during laparoscopic interventions | |
| Guo et al. | Robust fovea localization based on symmetry measure | |
| Shanker et al. | Brain tumor segmentation of normal and lesion tissues using hybrid clustering and hierarchical centroid shape descriptor | |
| Deng et al. | Automatic segmentation of corneal ulcer area based on ocular staining images | |
| CN117297551B (en) | Data processing system based on infrared image | |
| CN117297550B (en) | Information processing system | |
| Fotiadou et al. | Video-based facial discomfort analysis for infants | |
| CN117877691A (en) | Intelligent wound information acquisition system based on image recognition | |
| Liaghatdar et al. | Pupil localizing in video images the first step toward eye monitoring | |
| Tao et al. | Real-time driver fatigue detection based on face alignment | |
| Matsuyama | A novel method for automated lung region segmentation in chest X-ray images | |
| CN117462086A (en) | Infrared image processing system, electronic device, and storage medium | |
| Petridis et al. | Unobtrusive low cost pupil size measurements using web cameras | |
| Yu et al. | A fovea localization scheme using vessel origin-based parabolic model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |