CN111189545B - High-precision wide-area intelligent infrared body temperature screening method and system - Google Patents
High-precision wide-area intelligent infrared body temperature screening method and system Download PDFInfo
- Publication number
- CN111189545B CN111189545B CN202010107712.9A CN202010107712A CN111189545B CN 111189545 B CN111189545 B CN 111189545B CN 202010107712 A CN202010107712 A CN 202010107712A CN 111189545 B CN111189545 B CN 111189545B
- Authority
- CN
- China
- Prior art keywords
- temperature
- target
- calibration
- detected
- infrared
- 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
- 230000036760 body temperature Effects 0.000 title claims abstract description 60
- 238000012216 screening Methods 0.000 title claims abstract description 56
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000013507 mapping Methods 0.000 claims abstract description 91
- 230000000007 visual effect Effects 0.000 claims abstract description 34
- 230000005855 radiation Effects 0.000 claims abstract description 21
- 238000000605 extraction Methods 0.000 claims abstract description 7
- 230000003044 adaptive effect Effects 0.000 claims description 34
- 238000012545 processing Methods 0.000 claims description 25
- 230000002159 abnormal effect Effects 0.000 claims description 16
- 238000005315 distribution function Methods 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 10
- 238000009529 body temperature measurement Methods 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 7
- 230000003287 optical effect Effects 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 230000010365 information processing Effects 0.000 claims description 2
- 238000001514 detection method Methods 0.000 abstract description 2
- 230000000875 corresponding effect Effects 0.000 description 15
- 238000010586 diagram Methods 0.000 description 8
- 238000005259 measurement Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000010276 construction Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 206010037660 Pyrexia Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000002834 transmittance Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/0022—Radiation pyrometry, e.g. infrared or optical thermometry for sensing the radiation of moving bodies
- G01J5/0025—Living bodies
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/80—Calibration
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01K—MEASURING TEMPERATURE; MEASURING QUANTITY OF HEAT; THERMALLY-SENSITIVE ELEMENTS NOT OTHERWISE PROVIDED FOR
- G01K13/00—Thermometers specially adapted for specific purposes
- G01K13/20—Clinical contact thermometers for use with humans or animals
- G01K13/223—Infrared clinical thermometers, e.g. tympanic
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Radiation Pyrometers (AREA)
Abstract
A high-precision wide-area intelligent infrared body temperature screening method and a system thereof are provided, wherein the method comprises the following steps: step 1: visible light feature recognition and extraction are carried out on the target to be detected, and visible light view field space-time position information of the target to be detected is obtained; step 2: converting the visible light view field space-time position information into infrared light view field space-time position information according to a space-time position mapping algorithm; and step 3: according to the time-space position information of the infrared light visual field, directional infrared radiation characteristic collection is carried out on the target to be detected, and the infrared radiation characteristic information is converted into a corresponding gray value; and 4, step 4: obtaining the temperature absolute value of the target to be measured according to the gray value information by using a self-adaptive temperature mapping calibration algorithm; and 5: and performing temperature compensation on the absolute value of the temperature of the target to be measured by using the intelligent temperature self-calibration compensation algorithm to obtain the final value of the temperature of the target to be measured. The invention can realize the high-precision body temperature detection of the infrared body temperature screening in the outdoor complex environment, and the precision can reach +/-0.1 ℃.
Description
Technical Field
The invention relates to the technical field of infrared sensing and screening, in particular to a high-precision wide-area intelligent infrared body temperature screening method and system.
Background
The body temperature screening technology based on infrared radiation perception has the advantages of being rapid and non-contact, and is widely applied to airports, railway stations, subways, shopping malls, schools and other public places with dense people streams. However, in the working process of infrared temperature measurement, infrared radiation of a measured object is collected at a certain distance, and the self emissivity, the measurement distance, the atmospheric transmittance, the self radiation of infrared temperature measurement equipment and the like of the measured object all have influences, so that the temperature measurement precision is difficult to improve for a long time, and particularly, large errors occur in long-distance temperature measurement in cold outdoor environments in winter in the north.
Disclosure of Invention
In view of the above, the present invention provides a high-precision wide-area intelligent infrared body temperature screening method and system thereof, so as to at least partially solve at least one of the above-mentioned technical problems.
The invention provides a high-precision wide-area intelligent infrared body temperature screening method, which comprises the following steps:
step 1: visible light feature recognition and extraction are carried out on the target to be detected, and visible light view field space-time position information of the target to be detected is obtained;
step 2: converting the visible light view field space-time position information into infrared light view field space-time position information according to a space-time position mapping algorithm;
and step 3: according to the time-space position information of the infrared light visual field, directional infrared radiation characteristic collection is carried out on the target to be detected, and the infrared radiation characteristic information is converted into a corresponding gray value;
and 4, step 4: obtaining the temperature absolute value of the target to be measured according to the gray value information by using a self-adaptive temperature mapping calibration algorithm;
and 5: performing temperature compensation on the absolute value of the temperature of the target to be measured by using the intelligent temperature self-calibration compensation algorithm to obtain a final value of the temperature of the target to be measured;
step 6: and screening the temperature of the target to be detected by using the intelligent temperature self-calibration compensation algorithm, and judging whether the body temperature of the target to be detected is normal or not.
As another aspect of the present invention, there is also provided a high-precision wide-area intelligent infrared body temperature screening system for implementing the above-mentioned high-precision wide-area intelligent infrared body temperature screening method, including a visible light module, an infrared light module and an intelligent processing terminal module, wherein:
the visible light module is used for carrying out visible light feature recognition and extraction on the target to be detected through a visible light field, and transmitting the acquired visible light field space-time position information of the target to be detected to the intelligent processing terminal module;
the infrared optical module is used for carrying out directional infrared radiation characteristic collection on the target to be detected through the space-time position information of the infrared visual field, converting the infrared radiation characteristic information into gray value information and transmitting the gray value information to the intelligent processing terminal module;
the intelligent processing terminal module is used for carrying out mutual mapping conversion on the visible light view field space-time position information and the infrared light view field space-time position information by utilizing the space-time position mapping algorithm; transmitting the infrared light view field time-space position information to the infrared light module; obtaining the temperature absolute value of the target to be detected according to the gray value information transmitted by the infrared light module by using a self-adaptive temperature mapping calibration algorithm; and performing temperature compensation on the absolute temperature value of the target to be detected by using an intelligent temperature self-calibration compensation algorithm to obtain a final temperature value of the target to be detected, performing temperature screening on the target to be detected, and judging whether the body temperature of the target to be detected is normal or not.
Based on the technical scheme, compared with the prior art, the invention has at least one or part of the following beneficial effects:
(1) the invention carries out the conversion of the space position of the same target to be measured with different view fields based on the space-time position mapping algorithm, thereby improving the positioning matching precision; comparing the gray value information of the target to be detected with the gray value of the calibration black body based on a self-adaptive temperature mapping calibration algorithm to obtain a corresponding temperature absolute value; based on an intelligent temperature self-calibration compensation algorithm, the error between the temperature absolute value and the actual temperature is calculated, the temperature absolute value is compensated, and the human body temperature screening precision in a complex environment is comprehensively improved;
(2) the self-adaptive temperature mapping calibration model is constructed, the temperature of the calibration black body is controlled to change continuously under the condition that the background environment changes continuously, the initial calibration gray value is optimized, self-adaptive learning can be automatically carried out according to the change of the external environment, an optimized self-adaptive temperature mapping calibration function is obtained, and the measurement precision of the absolute temperature is improved;
(3) a crowd temperature characteristic distribution model is constructed, interference targets in the environment can be automatically eliminated, meanwhile, offset compensation is carried out on absolute temperature, and the human body temperature screening precision in the complex environment is further improved.
Drawings
FIG. 1 is a flowchart of a high-precision wide-area intelligent infrared body temperature screening method according to embodiments 1 and 2 of the present invention;
FIG. 2 is a schematic flow chart of a spatiotemporal position mapping algorithm in embodiment 1 of the present invention;
FIG. 3 is a schematic flow chart of the adaptive temperature mapping calibration algorithm of embodiments 1 and 2 of the present invention;
FIG. 4 is a schematic flow chart of the intelligent temperature self-calibration compensation algorithm of embodiments 1 and 2 of the present invention;
FIG. 5 is a block diagram of the construction of spatio-temporal location mapping models according to embodiments 1 and 2 of the present invention;
FIG. 6 is a block diagram of a calibration model for constructing an adaptive temperature map according to embodiments 1 and 2 of the present invention;
FIG. 7 is a block diagram of a population temperature profile model constructed according to embodiments 1 and 2 of the present invention;
fig. 8 is a schematic diagram of a high-precision wide-area intelligent infrared body temperature screening system according to embodiment 3 of the present invention.
Detailed Description
The invention breaks through the problem of inaccurate human body temperature monitoring in outdoor complex environment, ensures that temperature screening is not limited to absolute temperature accurate measurement any more, and greatly improves the probability of screening the heating individuals in the population.
In order that the objects, technical solutions and advantages of the present invention will become more apparent, the present invention will be further described in detail with reference to the accompanying drawings in conjunction with the following specific embodiments.
In a first exemplary embodiment of the present invention, fig. 1 is a flowchart of a high-precision wide-area intelligent infrared body temperature screening method according to embodiments 1 and 2 of the present invention; as shown in FIG. 1, the invention provides a high-precision wide-area intelligent infrared body temperature screening method, which comprises the following steps:
step 1: visible light feature recognition and extraction are carried out on the target to be detected, and visible light view field space-time position information of the target to be detected is obtained;
step 2: converting the visible light view field space-time position information into infrared light view field space-time position information according to a space-time position mapping algorithm;
and step 3: according to the time-space position information of the infrared light visual field, directional infrared radiation characteristic collection is carried out on the target to be detected, and the infrared radiation characteristic information is converted into a corresponding gray value;
wherein, in the embodiment of the present invention, fig. 2 is a schematic flow chart of the spatio-temporal position mapping algorithm in embodiment 1 of the present invention; FIG. 5 is a block diagram of the construction of a spatiotemporal position mutual mapping model according to embodiment 1 of the present invention; it should be noted that the modules for constructing the space-time position mutual mapping model include a visible light module, an infrared light module and an intelligent processing terminal module, and the functions of the modules are specifically described in other embodiments and are not described herein again.
The following will specifically describe step 1 to step 3 with reference to fig. 2 and 5:
firstly, a visible light module finds a target to be measured, and determines the visible light field space-time position of a point to be measured after visible light characteristic recognition and extraction are carried out; then, the visible light visual field space-time position information is transmitted to an intelligent processing terminal module, and is converted into infrared light visual field space-time position information according to a space-time position mapping model after being processed by a space-time position mapping algorithm embedded in the intelligent processing terminal module; and finally, the infrared light module carries out directional infrared radiation characteristic receiving on the point to be measured at the position, converts the infrared radiation characteristic information into a corresponding gray value, and transmits the gray value information to the intelligent processing terminal module for processing.
More specifically, in the embodiment of the present invention, the spatio-temporal position mapping algorithm includes a spatio-temporal position mapping model, that is, the core of the spatio-temporal position mapping model is a spatio-temporal position mapping model;
the high-precision wide-area intelligent infrared body temperature screening method further comprises the step of constructing a space-time position mapping model, and specifically comprises the following steps:
establishing a space-time reference expression W ═ phi (X, Y, Z, t) respectively) And the space-time position expression W of the infrared light visual field1＝φ(X1,Y1,Z1T) and visible light field space-time position expression W2＝φ(X2,Y2,Z2,t)；
Respectively mapping the space-time position expression of the infrared visual field and the space-time position expression of the visible visual field to obtain a space-time reference expression W of the infrared visual field1F (W) and the visible field spatiotemporal reference expression W2＝G(W)；
Correspondence F using infrared view field space-time reference expression and visible light view field space-time reference expression-1(W1)＝G-1(W2) Obtaining a space-time position mapping model between the infrared visual field and the visible visual field;
wherein, X, Y, Z are the coordinate of three-dimensional space respectively, t is time, and lower corner marks 1 and 2 represent infrared visual field and visible visual field respectively.
It is worth mentioning that the positioning matching precision is improved by positioning the target to be detected based on the space-time position mapping algorithm, and the improvement of the human body temperature screening precision in a complex environment is facilitated; the method for constructing the space-time position mapping model based on the coordinates is small in difficulty, high in precision and wide in application scene.
And 4, step 4: obtaining the temperature absolute value of the target to be measured according to the gray value information by using a self-adaptive temperature mapping calibration algorithm;
in an embodiment of the invention, the adaptive temperature mapping calibration algorithm comprises an adaptive temperature mapping calibration model;
the high-precision wide-area intelligent infrared body temperature screening method further comprises the step of constructing a self-adaptive temperature mapping calibration model, and specifically comprises the following steps:
under the condition that the background environment is not changed, controlling the temperature of the calibration black body to change;
taking the calibration black body as a target to be measured, and obtaining a gray value corresponding to the temperature by using the steps 1 to 3 as an initial calibration gray value;
fitting an adaptive temperature mapping calibration function according to each initial calibration gray value and the corresponding temperature value to obtain an initial adaptive temperature mapping calibration model;
under the condition that the background environment is constantly changed, the temperature of the calibration black body is controlled to be constantly changed;
and (3) taking the calibration black body as a target to be measured, obtaining a corresponding actual gray value by using the steps 1 to 3, optimizing the initial calibration gray value by using the actual gray value, updating the initial calibration gray value, realizing adaptive learning, and obtaining a calibration gray value and an adaptive temperature mapping calibration model.
FIG. 3 is a schematic flow chart of the adaptive temperature mapping calibration algorithm of embodiments 1 and 2 of the present invention; FIG. 6 is a block diagram of a calibration model for constructing an adaptive temperature map according to embodiments 1 and 2 of the present invention; it should be noted that the module for constructing the adaptive temperature mapping calibration model includes a visible light module, an infrared light module, an intelligent processing terminal module and a calibration black body, and the functions of the modules will be specifically described in other embodiments, which are not described herein again.
The following describes the construction of the adaptive temperature mapping calibration model in detail with reference to fig. 3 and 6:
firstly, it needs to be pointed out that the core of the adaptive temperature mapping calibration algorithm is an adaptive temperature mapping calibration model, the core of the adaptive temperature mapping calibration model is an adaptive temperature mapping calibration function, and the adaptive temperature mapping calibration function reflects the relationship between the temperature and the calibration gray value. And calibrating gray scale values, which reflect the imaging gray scale information of the black body temperature on the infrared light detector of the infrared light module at different distances, different angles and different environmental temperatures. And (3) changing parameters such as temperature, angle, distance and environment temperature of the calibration black body to train the self-adaptive temperature mapping calibration model, and determining each parameter value in the self-adaptive temperature mapping calibration function as an initial state. However, in the actual use process, the position of the calibration black body is fixed, so the angle and the distance are not changed. However, there are many factors affecting the outdoor environment including the ambient temperature, and these influences are ultimately reflected in the difference between the set temperature of the calibration black body and the temperature received by the infrared light module.
Therefore, firstly, under a certain specific condition, that is, under the condition that parameters such as the angle, the distance, the background environment and the like of the calibration black body are not changed, the temperature of the calibration black body is controlled to be changed continuously by using the intelligent processing terminal module, corresponding different gray values are obtained according to the infrared radiation characteristics received by the infrared light equipment and are used as initial calibration gray values, and then a corresponding initial adaptive temperature mapping calibration model is obtained.
Then, under an outdoor complex environment, namely a state that a background environment changes continuously, the dynamic change of the calibration black body is controlled by the intelligent processing terminal module, the initial calibration gray value is continuously updated by the initial adaptive temperature mapping calibration model, adaptive self-learning is realized, and the calibration gray value and the adaptive temperature mapping calibration model are obtained.
And finally, converting the infrared radiation characteristics of the target to be detected received by the infrared optical module into corresponding gray values, comparing the gray values with the calibration gray values, and obtaining corresponding absolute temperature values by using the adaptive temperature mapping calibration function curve.
And 5: carrying out temperature compensation on the absolute value of the temperature of the target to be measured by using an intelligent temperature self-calibration compensation algorithm to obtain a final value of the temperature of the target to be measured;
firstly, it needs to be introduced that, in the embodiment of the present invention, the intelligent temperature self-calibration compensation algorithm includes a crowd temperature characteristic distribution model;
the high-precision wide-area intelligent infrared body temperature screening method further comprises the step of constructing a population temperature characteristic distribution model, and specifically comprises the following steps:
measuring the temperature of a plurality of known targets with normal body temperature by using the steps 1 to 3, obtaining the initial calibration temperature of the plurality of known targets based on the initial adaptive temperature mapping calibration model, and fitting to obtain an initial calibration crowd temperature normal distribution function and an initial calibration temperature expected value;
measuring the temperature of the known target with the initial calibration temperature expected value by using the steps 1 to 4 to obtain the corresponding calibration temperature expected value;
and obtaining a crowd temperature normal distribution function, a temperature expected value and a standard deviation sigma by using the initial calibration temperature expected value, the corresponding calibration temperature expected value and the initial calibration crowd temperature normal distribution function, and further obtaining a crowd temperature characteristic distribution model.
FIG. 4 is a schematic flow chart of the intelligent temperature self-calibration compensation algorithm of embodiments 1 and 2 of the present invention; FIG. 7 is a block diagram of a population temperature profile model constructed according to embodiments 1 and 2 of the present invention; it should be noted that the module for constructing the adaptive temperature mapping calibration model includes a visible light module, an infrared light module, an intelligent processing terminal module and a calibration black body, and the functions of the modules will be specifically described in other embodiments, which are not described herein again.
The process of constructing the population temperature characteristic distribution model is described in detail below with reference to fig. 4 and 7:
the infrared optical module locks the space position of a training crowd (namely a known target) through the visible optical module, wherein the training crowd consists of a certain number of normal temperature people. The method comprises the steps that an infrared module is used for measuring the temperature of a plurality of known targets, initial calibration temperatures of the plurality of known targets are obtained based on an initial adaptive temperature mapping calibration model, and an initial calibration crowd temperature normal distribution function and an initial calibration temperature expected value are obtained through fitting;
then, carrying out temperature measurement on the known target of the initial calibration temperature expected value by using the steps 1 to 4, and obtaining a corresponding calibration temperature expected value based on the adaptive temperature mapping calibration model;
and finally, obtaining a crowd temperature normal distribution function, a temperature expected value and a standard deviation sigma by using the initial calibration temperature expected value, the corresponding calibration temperature expected value and the initial calibration crowd temperature normal distribution function, and further obtaining a crowd temperature characteristic distribution model. It is worth noting that the more people trained, i.e. the more abundant the features of the sample, the more accurate the model will be fitted.
The model can be used for compensating the absolute value of the temperature to obtain the final value of the temperature, and the measurement precision of the infrared human body temperature measurement is further improved. If the calibrated black body is calibrated in real time, the closer the population temperature normal distribution function curve is to the reality, and the closer the measured temperature absolute value is to the final temperature value; if the environment changes violently and the calibration black body cannot be calibrated in real time, the absolute value of the temperature is supplemented by the offset, so that the accuracy of actual measurement is improved.
Thus, in an embodiment of the present invention, step 5 comprises the following sub-steps:
substep 5.1: measuring the temperature of the target to be measured by using the steps 1 to 3, and obtaining an initial calibration temperature value of the target to be measured based on the initial adaptive temperature mapping calibration model;
substep 5.2: calculating the difference value between the initial calibration temperature value of the target to be measured and the initial calibration temperature expected value, and recording the difference value as an offset;
substep 5.3: measuring the temperature of the target to be measured by using the steps 1 to 4 to obtain the absolute value of the temperature of the target to be measured;
substep 5.4: and adding the offset to the absolute value of the temperature of the target to be measured to obtain the final value of the temperature of the target to be measured.
Optionally, after the step 5 and before the step 6, the method further includes an interference target determining step:
comparing the obtained temperature final value of the target to be detected with a temperature threshold, and directly rejecting the target to be detected if the temperature final value of the target to be detected is not within the temperature threshold range according to the condition that the target to be detected is an interference target; for example, in a normal environment, the temperature of a vehicle in starting is high, and when the target to be measured is the vehicle, the final temperature value is high and exceeds the maximum value of the temperature threshold range, the target to be measured is the interference target, and the interference target is directly rejected.
And if the final temperature value of the target to be detected is within the temperature threshold range, judging whether the body temperature of the target to be detected is normal or not in the step 6.
The temperature threshold is drawn according to the obtained crowd temperature characteristic distribution model and is drawn up according to the crowd temperature characteristic distribution 3 sigma principle, and the temperature threshold is (mu-3 sigma, mu +3 sigma), wherein mu is an expected value, and sigma is a standard deviation; the temperature threshold comprises an abnormal temperature threshold interval and a normal temperature threshold interval;
step 6: and (4) screening the temperature of the target to be detected by using an intelligent temperature self-calibration compensation algorithm, and judging whether the body temperature of the target to be detected is normal or not.
In the embodiment of the present invention, step 6 specifically includes comparing the obtained temperature final value of the target to be measured with a temperature threshold, and if the temperature final value of the target to be measured is within an abnormal temperature threshold interval, considering the target to be measured as an abnormal target; and if the final temperature value of the target to be detected is within the normal temperature threshold range, the target to be detected is considered as a normal target.
For example, when the body temperature of the human body exceeds 37.3 ℃, the medical definition is a low fever state, the abnormal temperature threshold interval is (37.3, μ +3 σ), and the normal temperature threshold interval is (μ -3 σ, 37.3);
if the final temperature value of the target to be detected is higher than 37.3 ℃, the target to be detected is regarded as an abnormal target; and if the final temperature value of the target to be detected is lower than 37.3 ℃, the target to be detected is regarded as a normal target.
In the embodiment of the invention, if the target to be tested is a normal target, the test data is used as effective data to enter the crowd temperature characteristic distribution model, and the accuracy is further optimized.
In the embodiment of the present invention, if the target to be measured is an abnormal target, step 6 is followed by step 7, where step 7 specifically includes:
grabbing the target to be detected according to the visible light empty position information of the target to be detected; and displaying the final temperature value of the target to be measured in real time, marking red and alarming. Wherein the alarm mode can be, but is not limited to, ringing.
It should be noted that the above three algorithms are not operated in isolation, but are fused and correlated with each other. And the model is continuously trained in real time so as to improve the precision of body temperature screening. The temperature value of any point in the space is obtained after the three algorithms are comprehensively processed and calculated. Based on three algorithms, the invention can realize high-precision body temperature detection of infrared body temperature screening in outdoor complex environment, and the precision can reach +/-0.1 ℃.
Thus, the first exemplary embodiment of the present invention has been described.
In the second exemplary embodiment of the present invention, the difference from the first exemplary embodiment of the present invention is that the step of constructing the spatio-temporal position mapping model specifically includes:
extracting visible light field image characteristics of a target to be detected;
extracting the infrared light field image characteristics of the target to be detected;
and carrying out mutual mapping matching on the visible light visual field image characteristics and the infrared visual field image characteristics to obtain a space-time position mapping model between the infrared visual field and the visible light visual field.
It is worth mentioning that two methods for constructing the spatio-temporal position mapping model, the method in the first exemplary embodiment has less difficulty, higher precision and wider use scenario.
Thus, the second exemplary embodiment of the present invention has been described.
In a third exemplary embodiment of the present invention, fig. 8 is a schematic diagram of a high-precision wide-area intelligent infrared body temperature screening system according to embodiment 3 of the present invention. As shown in fig. 8, the present invention provides a high-precision wide-area intelligent infrared body temperature screening system for implementing the high-precision wide-area intelligent infrared body temperature screening method, which includes a visible light module, an infrared light module and an intelligent processing terminal module, wherein:
the visible light module is used for identifying and extracting visible light characteristics of the target to be detected through a visible light field and transmitting the acquired visible light field space-time position information of the target to be detected to the intelligent processing terminal module;
the infrared optical module is used for carrying out directional infrared radiation characteristic collection on the target to be detected through the infrared light view field space-time position information, converting the infrared radiation characteristic information into gray value information and transmitting the gray value information to the intelligent processing terminal module;
the intelligent processing terminal module is used for carrying out mutual mapping conversion on the visible light view field space-time position information and the infrared light view field space-time position information by utilizing a space-time position mapping algorithm; transmitting the time-space position information of the infrared light visual field to an infrared light module; obtaining the temperature absolute value of the target to be measured according to the gray value information transmitted by the infrared light module by using a self-adaptive temperature mapping calibration algorithm; and performing temperature compensation on the absolute temperature value of the target to be detected by using an intelligent temperature self-calibration compensation algorithm to obtain a final temperature value of the target to be detected, performing temperature screening on the target to be detected, and judging whether the body temperature of the target to be detected is normal or not.
In the embodiment of the invention, the intelligent processing terminal module comprises an intelligent information processing unit, a time-space position mapping model, a self-adaptive temperature mapping calibration model and an intelligent temperature self-calibration compensation model; judging whether the temperature of the target to be detected is abnormal or not;
the high-precision wide-area intelligent infrared body temperature screening system also comprises a calibration black body, the temperature change can be controlled by the intelligent processing terminal module, and an initial calibration gray value for constructing a self-adaptive temperature mapping calibration model is obtained through the infrared optical module;
the high-precision wide-area intelligent infrared body temperature screening system also comprises a display, a display and a display, wherein the display is used for displaying the absolute value of the temperature of the abnormal target and marking red;
the high-precision wide-area intelligent infrared body temperature screening system further comprises an alarm for alarming when abnormal targets are screened out.
It is worth mentioning that each functional module in the system supplements each other, and is absent. The calibration black body needs to be placed in a view field in the direction of the target to be measured. The target to be detected does not need to be stopped during screening, and the screening efficiency is improved.
Thus, the third exemplary embodiment of the present invention has been described.
It should also be noted that the algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. Moreover, the present invention is not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functionality of some or all of the components in the associated system according to embodiments of the invention. The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
All modules of embodiments of the present invention may be hardware structures, physical implementations of which include, but are not limited to, physical devices including, but not limited to, transistors, memristors, DNA computers.
Those skilled in the art will appreciate that the modules in the system in an embodiment may be adaptively changed and placed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise. Also in the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention and are not intended to limit the present invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. A high-precision wide-area intelligent infrared body temperature screening method is characterized by comprising the following steps:
step 1: visible light feature recognition and extraction are carried out on the target to be detected, and visible light view field space-time position information of the target to be detected is obtained;
step 2: converting the visible light view field space-time position information into infrared light view field space-time position information according to a space-time position mapping algorithm;
and step 3: according to the time-space position information of the infrared light visual field, directional infrared radiation characteristic collection is carried out on the target to be detected, and the infrared radiation characteristic information is converted into a corresponding gray value;
and 4, step 4: obtaining the temperature absolute value of the target to be measured according to the gray value information by using a self-adaptive temperature mapping calibration algorithm;
and 5: performing temperature compensation on the absolute value of the temperature of the target to be measured by using the intelligent temperature self-calibration compensation algorithm to obtain a final value of the temperature of the target to be measured;
step 6: screening the temperature of the target to be detected by using the intelligent temperature self-calibration compensation algorithm, and judging whether the body temperature of the target to be detected is normal or not;
wherein the adaptive temperature mapping calibration algorithm comprises an adaptive temperature mapping calibration model;
the high-precision wide-area intelligent infrared body temperature screening method further comprises the step of constructing a self-adaptive temperature mapping calibration model, and specifically comprises the following steps:
under the condition that the background environment is not changed, controlling the temperature of the calibration black body to change;
taking the calibration black body as a target to be measured, and obtaining a gray value corresponding to the temperature by utilizing the steps 1 to 3, wherein the gray value is taken as an initial calibration gray value;
fitting an adaptive temperature mapping calibration function according to each initial calibration gray value and the corresponding temperature value to obtain an initial adaptive temperature mapping calibration model;
under the condition that the background environment is constantly changed, the temperature of the calibration black body is controlled to be constantly changed;
and (3) taking the calibration black body as a target to be measured, obtaining a corresponding actual gray value by utilizing the steps 1 to 3, optimizing the initial calibration gray value by utilizing the actual gray value, updating the initial calibration gray value, realizing self-adaptive learning, and obtaining the calibration gray value and the self-adaptive temperature mapping calibration model.
2. The high-precision wide-area intelligent infrared body temperature screening method of claim 1, wherein the spatiotemporal position mapping algorithm comprises a spatiotemporal position mapping model;
the high-precision wide-area intelligent infrared body temperature screening method further comprises the step of constructing a space-time position mapping model, and specifically comprises the following steps:
respectively establishing a space-time reference expression W ═ phi (X, Y, Z, t) and an infrared light visual field space-time position expression W1＝φ(X1，Y1，Z1T) and visible light field space-time position expression W2＝φ(X2，Y2，Z2，t)；
Respectively mapping the infrared visual field space-time position expression and the visible visual field space-time position expression to obtain a space-time reference expression W of the infrared visual field1F (W) and the visible field spatiotemporal reference expression W2＝G(W)；
Space-time reference expression using infrared visual field andcorrespondence F of space-time reference expression in visible light field-1(W1)＝G-1(W2) Obtaining a space-time position mapping model between the infrared visual field and the visible visual field;
wherein, X, Y, Z are the coordinate of three-dimensional space respectively, t is time, and lower corner marks 1 and 2 represent infrared visual field and visible visual field respectively.
3. The high-precision wide-area intelligent infrared body temperature screening method of claim 1, wherein the spatiotemporal position mapping algorithm comprises a spatiotemporal position mapping model;
the high-precision wide-area intelligent infrared body temperature screening method further comprises the step of constructing a space-time position mapping model, and specifically comprises the following steps:
extracting visible light field image characteristics of a target to be detected;
extracting the infrared light field image characteristics of the target to be detected;
and carrying out mutual mapping matching on the visible light visual field image characteristics and the infrared light visual field image characteristics to obtain a space-time position mapping model between the infrared light visual field and the visible light visual field.
4. The high-precision wide-area intelligent infrared body temperature screening method of claim 1, wherein the intelligent temperature self-calibration compensation algorithm comprises a population temperature characteristic distribution model;
the high-precision wide-area intelligent infrared body temperature screening method further comprises the step of constructing a population temperature characteristic distribution model, and specifically comprises the following steps:
measuring the temperatures of a plurality of known targets with normal body temperatures by utilizing the steps 1 to 3, obtaining the initial calibration temperatures of the plurality of known targets based on the initial adaptive temperature mapping calibration model, and fitting to obtain an initial calibration crowd temperature normal distribution function and an initial calibration temperature expected value;
carrying out temperature measurement on the known target with the initial calibration temperature expected value by utilizing the steps 1 to 4 to obtain a corresponding calibration temperature expected value;
and obtaining a crowd temperature normal distribution function, a temperature expected value and a standard deviation sigma by using the initial calibration temperature expected value, the corresponding calibration temperature expected value and the initial calibration crowd temperature normal distribution function, and further obtaining a crowd temperature characteristic distribution model.
5. The high-precision wide-area intelligent infrared body temperature screening method of claim 4,
the step 5 comprises the following substeps:
substep 5.1: measuring the temperature of the target to be measured by utilizing the steps 1 to 3, and obtaining an initial calibration temperature value of the target to be measured based on the initial adaptive temperature mapping calibration model;
substep 5.2: calculating the difference value between the initial calibration temperature value of the target to be measured and the initial calibration temperature expected value, and recording the difference value as an offset;
substep 5.3: measuring the temperature of the target to be measured by utilizing the steps 1 to 4 to obtain the absolute value of the temperature of the target to be measured;
substep 5.4: and adding the offset to the absolute value of the temperature of the target to be measured to obtain a final value of the temperature of the target to be measured.
6. The method for high-precision wide-area intelligent infrared body temperature screening as claimed in claim 5, further comprising an interference target determination step before the step 6:
comparing the obtained final temperature value of the target to be detected with the temperature threshold, and if the final temperature value of the target to be detected is not within the temperature threshold range, directly rejecting the target to be detected as an interference target;
if the final temperature value of the target to be detected is within the temperature threshold range, judging whether the body temperature of the target to be detected is normal;
the temperature threshold is drawn up according to a crowd temperature characteristic distribution model and following the crowd temperature characteristic distribution 3 sigma principle, and is (mu-3 sigma, mu +3 sigma), wherein mu is an expected value, and sigma is a standard deviation; the temperature threshold comprises an abnormal temperature threshold interval and a normal temperature threshold interval;
the step 6 specifically includes:
comparing the obtained temperature final value of the target to be detected with the temperature threshold, and if the temperature final value of the target to be detected is in an abnormal temperature threshold interval, considering the target to be detected as an abnormal target; and if the final temperature value of the target to be detected is within the normal temperature threshold range, the target to be detected is considered as a normal target.
7. The high-precision wide-area intelligent infrared body temperature screening method of claim 6, wherein if the target to be detected is an abnormal target, the method further comprises a step 7 after the step 6, and the step 7 specifically comprises:
grabbing the target to be detected according to the visible light empty position information of the target to be detected; and displaying the final temperature value of the target to be detected in real time, marking red and alarming.
8. A high-precision wide-area intelligent infrared body temperature screening system for realizing the high-precision wide-area intelligent infrared body temperature screening method as claimed in any one of claims 1 to 7, which is characterized by comprising a visible light module, an infrared light module and an intelligent processing terminal module, wherein:
the visible light module is used for carrying out visible light feature recognition and extraction on the target to be detected through a visible light field, and transmitting the acquired visible light field space-time position information of the target to be detected to the intelligent processing terminal module;
the infrared optical module is used for carrying out directional infrared radiation characteristic collection on the target to be detected through the space-time position information of the infrared visual field, converting the infrared radiation characteristic information into gray value information and transmitting the gray value information to the intelligent processing terminal module;
the intelligent processing terminal module is used for carrying out mutual mapping conversion on the visible light view field space-time position information and the infrared light view field space-time position information by utilizing the space-time position mapping algorithm; transmitting the infrared light view field time-space position information to the infrared light module; obtaining the temperature absolute value of the target to be detected according to the gray value information transmitted by the infrared light module by using a self-adaptive temperature mapping calibration algorithm; and performing temperature compensation on the absolute temperature value of the target to be detected by using an intelligent temperature self-calibration compensation algorithm to obtain a final temperature value of the target to be detected, performing temperature screening on the target to be detected, and judging whether the body temperature of the target to be detected is normal or not.
9. The high-precision wide-area intelligent infrared body temperature screening system of claim 8, wherein the intelligent processing terminal module comprises an intelligent information processing unit for constructing the spatiotemporal position mapping model, the adaptive temperature mapping calibration model and the intelligent temperature self-calibration compensation model; judging whether the temperature of the target to be detected is abnormal or not;
the high-precision wide-area intelligent infrared body temperature screening system further comprises a calibration black body, the temperature change can be controlled by the intelligent processing terminal module, and an initial calibration gray value for constructing the self-adaptive temperature mapping calibration model is obtained through the infrared light module;
the high-precision wide-area intelligent infrared body temperature screening system further comprises a display, wherein the display is used for displaying the absolute value of the temperature of the abnormal target;
the high-precision wide-area intelligent infrared body temperature screening system further comprises an alarm for alarming when abnormal targets are screened out.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010107712.9A CN111189545B (en) | 2020-02-21 | 2020-02-21 | High-precision wide-area intelligent infrared body temperature screening method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010107712.9A CN111189545B (en) | 2020-02-21 | 2020-02-21 | High-precision wide-area intelligent infrared body temperature screening method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111189545A CN111189545A (en) | 2020-05-22 |
| CN111189545B true CN111189545B (en) | 2021-05-18 |
Family
ID=70708334
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010107712.9A Active CN111189545B (en) | 2020-02-21 | 2020-02-21 | High-precision wide-area intelligent infrared body temperature screening method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111189545B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111657881A (en) * | 2020-06-19 | 2020-09-15 | 中国电子科技集团公司第十一研究所 | Wide-area body temperature screening equipment |
| CN111879414A (en) * | 2020-08-04 | 2020-11-03 | 银河水滴科技（北京）有限公司 | Infrared temperature measurement method and device, computer equipment and medium |
| JP7492211B2 (en) | 2020-10-15 | 2024-05-29 | 株式会社スペクトラ | Non-contact body temperature measuring device, method and program |
| CN113465743A (en) * | 2020-11-19 | 2021-10-01 | 中国传媒大学 | Infrared non-contact body temperature measurement system and method based on normal distribution characteristics |
| CN114659646A (en) * | 2020-12-07 | 2022-06-24 | 华为技术有限公司 | Temperature measurement method, device, equipment and system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101369371A (en) * | 2007-08-16 | 2009-02-18 | 公安部上海消防研究所 | Large spacing fire disaster detection system with fire disaster coordinate setting and fire disaster temperature real-time analysis ability |
| JP2013185234A (en) * | 2012-03-09 | 2013-09-19 | Nippon Steel & Sumitomo Metal Corp | Method and apparatus for observing condition of blast furnace tuyere |
| CN103335724A (en) * | 2013-06-20 | 2013-10-02 | 重庆邮电大学 | Calibration-based scene self-adaption IRFPA heterogeneity correction method |
| CN105852819A (en) * | 2016-03-23 | 2016-08-17 | 深圳云天励飞技术有限公司 | Body temperature monitoring method and device |
| JP2018084512A (en) * | 2016-11-24 | 2018-05-31 | 凸版印刷株式会社 | Three-dimensional shape heat measurement device, method for measuring three-dimensional shape heat, and program |
| CN109655162A (en) * | 2018-11-30 | 2019-04-19 | 诺仪器（中国）有限公司 | Thermal infrared imager temperature measurement correction system and method |
| CN109846463A (en) * | 2019-03-04 | 2019-06-07 | 武汉迅检科技有限公司 | Infrared face temp measuring method, system, equipment and storage medium |
| CN110411605A (en) * | 2019-08-02 | 2019-11-05 | 武汉高德智感科技有限公司 | A kind of infrared survey human body temperature modification method |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102011076680A1 (en) * | 2011-05-30 | 2012-12-06 | Hilti Aktiengesellschaft | Imaging measuring system and measuring method for measuring a heat emission at a target object |
-
2020
- 2020-02-21 CN CN202010107712.9A patent/CN111189545B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101369371A (en) * | 2007-08-16 | 2009-02-18 | 公安部上海消防研究所 | Large spacing fire disaster detection system with fire disaster coordinate setting and fire disaster temperature real-time analysis ability |
| JP2013185234A (en) * | 2012-03-09 | 2013-09-19 | Nippon Steel & Sumitomo Metal Corp | Method and apparatus for observing condition of blast furnace tuyere |
| CN103335724A (en) * | 2013-06-20 | 2013-10-02 | 重庆邮电大学 | Calibration-based scene self-adaption IRFPA heterogeneity correction method |
| CN105852819A (en) * | 2016-03-23 | 2016-08-17 | 深圳云天励飞技术有限公司 | Body temperature monitoring method and device |
| JP2018084512A (en) * | 2016-11-24 | 2018-05-31 | 凸版印刷株式会社 | Three-dimensional shape heat measurement device, method for measuring three-dimensional shape heat, and program |
| CN109655162A (en) * | 2018-11-30 | 2019-04-19 | 诺仪器（中国）有限公司 | Thermal infrared imager temperature measurement correction system and method |
| CN109846463A (en) * | 2019-03-04 | 2019-06-07 | 武汉迅检科技有限公司 | Infrared face temp measuring method, system, equipment and storage medium |
| CN110411605A (en) * | 2019-08-02 | 2019-11-05 | 武汉高德智感科技有限公司 | A kind of infrared survey human body temperature modification method |
Non-Patent Citations (3)
| Title |
|---|
| Chenna, Yedukondala Narendra Dwith.Free-Form Deformation Approach for Registration of Visible and Infrared Facial Images in Fever Screening.《SENSORS》.2018, * |
| Ma, Chao.Adapting Local Features for Face Detection in Thermal Image.《SENSORS》.2017, * |
| 田鹰.一种基于红外和可见光的快速体温测量与告警系统.《中国安防》.2013, * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111189545A (en) | 2020-05-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111189545B (en) | High-precision wide-area intelligent infrared body temperature screening method and system | |
| EP2992355B1 (en) | Scalable real-time location detection based on overlapping neural networks | |
| CN110456320B (en) | Ultra-wideband radar identity recognition method based on free space gait time sequence characteristics | |
| CN110136186B (en) | Detection target matching method for mobile robot target ranging | |
| CN113777600A (en) | Multi-millimeter-wave radar cooperative positioning tracking method | |
| CN112462368A (en) | Obstacle detection method and device, vehicle and storage medium | |
| CN114037972A (en) | Target detection method, device, equipment and readable storage medium | |
| CN111289111B (en) | Self-calibration infrared body temperature rapid detection method and detection device | |
| CN113988228B (en) | Indoor monitoring method and system based on RFID and vision fusion | |
| CN111856445B (en) | Target detection method, device, equipment and system | |
| CN111340884B (en) | Dual-target positioning and identity identification method for binocular heterogeneous camera and RFID | |
| CN117113284A (en) | Multi-sensor fusion data processing method and device and multi-sensor fusion method | |
| CN116340736A (en) | Heterogeneous sensor information fusion method and device | |
| CN116385866B (en) | SAR image-based railway line color steel house change detection method and device | |
| JP2021154935A (en) | Vehicle simulation system, vehicle simulation method and computer program | |
| CN116243303A (en) | Indoor personnel target feature extraction method based on millimeter wave radar | |
| CN113405664B (en) | Temperature measurement method, temperature measurement equipment and machine-readable storage medium | |
| CN113239922B (en) | Virtual reality space positioning feature point recognition system and recognition method | |
| CN112633143B (en) | Image processing system, method, head-mounted device, processing device, and storage medium | |
| CN114814810A (en) | Pedestrian detection method | |
| CN110895701B (en) | Forest fire online identification method and device based on CN and FHOG | |
| CN113673105A (en) | Design method of true value comparison strategy | |
| CN112598738A (en) | Figure positioning method based on deep learning | |
| CN113804332A (en) | Temperature sensing element array fault diagnosis method based on ultrasonic imaging system and application thereof | |
| CN114487004B (en) | Method, equipment and medium for penetrating type measurement of heat conductivity coefficient |
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 |