CN113267258B - Infrared temperature measurement method, device, equipment, intelligent inspection robot and storage medium - Google Patents
Infrared temperature measurement method, device, equipment, intelligent inspection robot and storage medium Download PDFInfo
- Publication number
- CN113267258B CN113267258B CN202110541334.XA CN202110541334A CN113267258B CN 113267258 B CN113267258 B CN 113267258B CN 202110541334 A CN202110541334 A CN 202110541334A CN 113267258 B CN113267258 B CN 113267258B
- Authority
- CN
- China
- Prior art keywords
- temperature
- distance
- detection
- thermal imaging
- 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
- 238000000034 method Methods 0.000 title claims abstract description 66
- 238000009529 body temperature measurement Methods 0.000 title claims abstract description 45
- 238000007689 inspection Methods 0.000 title abstract description 11
- 238000001514 detection method Methods 0.000 claims abstract description 185
- 238000001931 thermography Methods 0.000 claims abstract description 88
- 238000012937 correction Methods 0.000 claims abstract description 74
- 238000012549 training Methods 0.000 claims description 34
- 239000000523 sample Substances 0.000 claims description 20
- 238000005259 measurement Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 9
- 230000004927 fusion Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000004861 thermometry Methods 0.000 claims description 4
- 230000002457 bidirectional effect Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 3
- 230000005457 Black-body radiation Effects 0.000 description 8
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000007613 environmental effect Effects 0.000 description 4
- 238000013178 mathematical model Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000036760 body temperature Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000004883 computer application Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000005670 electromagnetic radiation Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 230000000007 visual effect Effects 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
- G01J5/52—Radiation pyrometry, e.g. infrared or optical thermometry using comparison with reference sources, e.g. disappearing-filament pyrometer
-
- 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
- G01J5/52—Radiation pyrometry, e.g. infrared or optical thermometry using comparison with reference sources, e.g. disappearing-filament pyrometer
- G01J5/53—Reference sources, e.g. standard lamps; Black bodies
Abstract
The invention discloses an infrared temperature measurement method, which takes the influence of ambient temperature as the inherent characteristic of detection equipment output, corrects the output temperature according to the detection equipment and the ambient temperature, and eliminates the influence of the ambient temperature on the output temperature of different infrared thermal imaging detection equipment; meanwhile, the detection distance, the emissivity and the atmospheric humidity between the target device and the detection device are regarded as external influence factors, the detection distance and the atmospheric humidity influence on the first correction temperature are corrected according to the atmospheric humidity and the detection distance according to the established universal distance and humidity correction model, the influence of the detection distance and the atmospheric humidity on the first correction temperature is eliminated, the temperature value is measured according to object detection data with the influence of all aspects eliminated, and the temperature measurement accuracy can be remarkably improved. The invention also discloses an infrared temperature measuring device, infrared thermal imaging detection equipment, an intelligent inspection robot and a readable storage medium, and the infrared temperature measuring device, the infrared thermal imaging detection equipment, the intelligent inspection robot and the readable storage medium have corresponding technical effects.
Description
Technical Field
The invention relates to the technical field of intelligent temperature measurement, in particular to an infrared temperature measurement method and device, infrared thermal imaging detection equipment, an intelligent inspection robot and a readable storage medium.
Background
With the rapid development of the unattended intelligent transformer substation, the intelligent inspection robot of the transformer substation is widely applied. The power equipment in the transformer substation generates energy loss due to work or faults, so that the temperature of the power equipment per se rises, when the temperature is higher than a normal value, the service life of the power equipment is greatly shortened, potential safety hazards exist, accidents can be directly caused seriously, and the stability of a power grid is influenced. Therefore, infrared temperature measurement is the most basic and important step in the unattended intelligent substation.
However, the intelligent degree in the infrared temperature measurement of the existing intelligent inspection robot for the transformer substation is low, and parameters such as the emissivity e of a measured object and the distance d between the measured object and an infrared camera need to be manually input; and the temperature measurement precision is low, is difficult to satisfy the temperature acquisition precision demand of object, and then has greatly restricted the intelligent degree of robot, has hindered the application of robot in the intelligent patrol inspection of transformer substation.
To sum up, how to promote the temperature measurement precision, promote intelligent level simultaneously, optimize user experience is the technical problem that technical personnel in the field need to solve at present urgently.
Disclosure of Invention
The invention aims to provide an infrared temperature measurement method, an infrared temperature measurement device, infrared temperature measurement equipment and a readable storage medium, which can improve the temperature measurement accuracy.
In order to solve the technical problems, the invention provides the following technical scheme:
an infrared temperature measurement method comprises the following steps:
acquiring the ambient temperature, the atmospheric humidity, the detection distance, the emissivity and the output temperature of target equipment when the infrared thermal imaging detection equipment detects the temperature of the target equipment;
calling an environment temperature correction model to carry out detection equipment influence correction on the output temperature according to the environment temperature to obtain a first correction temperature;
calling a distance humidity correction model to correct the influence of the detection distance and the atmospheric humidity on the first corrected temperature according to the atmospheric humidity and the detection distance to obtain a second corrected temperature;
and calling an object temperature identification model to calculate the temperature of the target equipment according to the emissivity, the environment temperature and the second correction temperature.
Optionally, the method for obtaining the emissivity includes:
detecting target equipment, and determining the type and the position of the target equipment;
and determining the emissivity corresponding to the type according to the emissivity matching information of various types of objects, and taking the emissivity as the emissivity of the target equipment.
Optionally, the method for acquiring the detection distance includes:
and calling a ranging network to determine the distance between the infrared thermal imaging detection device and the target device as the detection distance.
Optionally, the invoking a ranging network to determine a distance between the infrared thermal imaging detection device and the target device includes:
and calling an infrared monocular distance measurement network with lightweight enhanced edge loss and multi-scale feature fusion to calculate the distance between the infrared thermal imaging detection equipment and the target equipment.
Optionally, the training method of the ambient temperature correction model includes:
determining infrared thermal imaging detection equipment to be calibrated as the equipment to be calibrated;
placing the equipment to be calibrated and blackbodies with different set temperatures in a step-in high-low temperature box; the distance difference between each device to be calibrated and each black body is not greater than a threshold value;
sequentially adjusting the temperature of the walk-in high-low temperature box to each preset temperature value, and respectively obtaining the temperature value of each black body acquired by each device to be calibrated as a detection temperature;
taking the detection data corresponding to each device to be calibrated as a training sample, and training a pre-built environment temperature correction model according to the training sample; the probe data includes: the detection temperature, the temperature of the walk-in high and low temperature box and the temperature of the black body.
Optionally, the training method of the distance humidity correction model includes:
determining an infrared thermal imaging detection device;
fixing black bodies with different set temperatures at preset positions;
respectively moving infrared thermal imaging detection equipment to a position away from the black body by a preset distance, and respectively acquiring first corrected temperatures generated by the infrared thermal imaging detection equipment as detection temperatures;
taking detection data corresponding to the infrared thermal imaging detection equipment as a training sample, and training a pre-built distance humidity correction model according to the training sample; the probe data includes: atmospheric humidity, the detection temperature, the preset distance and the temperature of the black body.
An infrared temperature measuring device, comprising:
the data acquisition unit is used for acquiring the ambient temperature, the atmospheric humidity, the detection distance, the emissivity and the output temperature of the target equipment when the infrared thermal imaging detection equipment detects the temperature of the target equipment;
the first correction unit is used for calling an environment temperature correction model to correct the influence of the detection equipment on the output temperature according to the environment temperature to obtain a first correction temperature;
the second correction unit is used for calling a distance humidity correction model to correct the influence of the detection distance and the atmospheric humidity on the first correction temperature according to the atmospheric humidity and the detection distance to obtain a second correction temperature;
and the temperature calculation unit is used for calling an object temperature identification model to calculate the temperature of the target equipment according to the emissivity, the environment temperature and the second correction temperature.
An infrared thermal imaging detection device comprising:
a memory for storing a computer program;
and the processor is used for realizing the steps of the infrared temperature measurement method when the computer program is executed.
An intelligent inspection robot, comprising: the infrared thermographic detection arrangement as described above.
A readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the above-mentioned infrared temperature measurement method.
According to the method provided by the embodiment of the invention, on the basis of a traditional machine learning model, the influence of the ambient temperature is regarded as the inherent characteristic of the output of the detection equipment, the output temperature is corrected according to different detection equipment and the ambient temperature, and the influence of the ambient temperature on the output temperature of different infrared thermal imaging detection equipment is eliminated; meanwhile, the detection distance, the emissivity and the atmospheric humidity between the target device and the detection device are regarded as external influence factors, the distance and humidity correction model is built according to the established general model, the distance and humidity correction model corrects the influence of the detection distance and the atmospheric humidity on the first correction temperature according to the atmospheric humidity and the detection distance, the influence of the detection distance and the atmospheric humidity on the first correction temperature is eliminated, the temperature value is measured and calculated according to object detection data after influences in all aspects are eliminated, and the temperature measurement accuracy can be remarkably improved.
Correspondingly, the embodiment of the invention also provides an infrared temperature measuring device, an infrared thermal imaging detection device, an intelligent inspection robot and a readable storage medium corresponding to the infrared temperature measuring method, which have the technical effects and are not described herein again.
Drawings
In order to more clearly illustrate the embodiments of the present invention or technical solutions in related arts, the drawings used in the description of the embodiments or related arts will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flowchart illustrating an exemplary method of infrared temperature measurement;
FIG. 2 is a schematic diagram illustrating an arrangement of a device to be calibrated and a black body in a walk-in high and low temperature chamber according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of the position of a blackbody and infrared thermal imaging detection device in distance and atmospheric humidity correction according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of an infrared temperature measuring device according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an infrared thermal imaging detection apparatus according to an embodiment of the present invention.
Detailed Description
The core of the invention is to provide an infrared temperature measurement method which can improve the temperature measurement accuracy.
In order that those skilled in the art will better understand the disclosure, the invention will be described in further detail with reference to the accompanying drawings and specific embodiments. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be obtained by a person skilled in the art without making any creative effort based on the embodiments in the present invention, belong to the protection scope of the present invention.
Referring to fig. 1, fig. 1 is a flowchart of an infrared temperature measurement method according to an embodiment of the present invention, the method includes the following steps:
s101, acquiring an ambient temperature, an atmospheric humidity, a detection distance, an emissivity of target equipment and an output temperature when infrared thermal imaging detection equipment detects the temperature of the target equipment;
the infrared thermal imaging detection device is used for detecting the temperature of the target device, outputting a detected temperature value (namely, an output temperature), and acquiring an ambient temperature t, an atmospheric humidity h, a detection distance d (namely, a distance between the infrared thermal imaging detection device and the target device), an emissivity e of the target device and an output temperature v after temperature detection in the temperature detection, so as to identify the temperature of the target device according to the data.
In this embodiment, the obtaining manners of the ambient temperature t, the atmospheric humidity h, the detection distance d, the emissivity e of the target device, and the output temperature v are not limited. The output temperature can directly obtain the temperature value output after the infrared thermal imaging detection equipment detects the temperature value; the ambient temperature and the atmospheric humidity can be obtained according to a traditional method by temperature and humidity values obtained by temperature and humidity sensors in infrared thermal imaging detection equipment (most of the infrared thermal imaging detection equipment is provided with the temperature and humidity sensors), and data acquisition can also be carried out on the ambient temperature and the atmospheric humidity through other equipment, which is not repeated herein.
At present, the emissivity of the target device needs to be manually input by a user, and certainly, in the method, the emissivity of the target device may also be obtained in a manner that the emissivity is manually input by the user, and in order to improve the intelligent degree of the infrared temperature measurement process and reduce user side operations, a method for automatically obtaining the emissivity of the target device is provided in this embodiment, which is specifically as follows:
(1) Detecting target equipment and determining the type and the position of the target equipment;
and detecting the target equipment through a general target detection algorithm, and identifying the type and the position of the target equipment. In this embodiment, the target detection algorithm is not limited, and reference may be made to the description of the related art.
(2) And determining emissivity corresponding to the types according to the emissivity matching information of various types of objects, and taking the emissivity as the emissivity of the target equipment.
Mapping matching information between various detected objects (namely target equipment) and emissivity in an application scene is pre-established, the types contained in the matching information are not limited, the matching information can be configured according to an actual application scene, for example, the matching information is applied to a transformer substation, and the matching information can include emissivity of power equipment such as a transformer and a voltage current transformer.
After the target equipment to be detected is determined, the emissivity corresponding to the target equipment can be determined according to the pre-established emissivity matching information of various objects, so that the emissivity can be automatically obtained.
In this embodiment, only the above mentioned emissivity obtaining method is taken as an example for description, and of course, other obtaining methods may also be adopted, which are all described in this embodiment and will not be described herein again.
At present, the detection distance between target device and the infrared thermal imaging detection device also needs user manual input, certainly, this method also can adopt user manual input detection distance's mode to acquire target device's detection distance, in order to promote the intelligent degree of infrared temperature measurement process, reduces user side operation, proposes a method of automatic acquisition detection distance in this embodiment, specifically does: and calling a ranging network to determine the distance between the infrared thermal imaging detection equipment and the target equipment as a detection distance.
In order to improve the accuracy of distance measurement, the process of determining the distance between the infrared thermal imaging detection device and the target device by using the ranging network may specifically be: and calling an infrared monocular distance measurement network with lightweight enhanced edge loss and multi-scale feature fusion to calculate the distance between the infrared thermal imaging detection equipment and the target equipment.
Distance measurement is an indispensable key technology in the fields of automatic driving, infrared thermal imaging accurate temperature measurement and the like, and compared with common laser radar and binocular distance measurement, unsupervised monocular vision distance measurement attracts the attention of numerous researchers due to the characteristics of low cost, convenience in deployment, low process requirement and the like. Although monocular visual ranging based on visible light has been a major development, visible light is not suitable in nighttime, foggy day, etc. scenes, and infrared thermal imaging is a beneficial complement. However, compared with the visible light image, the infrared thermal imaging image has the defects of low contrast, wide dynamic range, discontinuous image, low signal-to-noise ratio, low texture and the like, and the monocular vision distance measurement algorithm of the visible light is simply applied to the monocular vision distance measurement of the infrared thermal imaging, so that the problems of training collapse, low precision, blurred depth image edge and the like can be caused.
In order to solve these problems, the present embodiment designs a new loss function for the characteristics of low infrared image contrast, wide dynamic range, image discontinuity, low signal-to-noise ratio, and low texture: the edge loss function aims to reduce pixel mismatching when the image is re-projected. In addition, in the conventional unsupervised monocular distance measurement, the depth maps of four scales are simply up-sampled to the resolution of the original image to calculate the projection error, and the relevance among the scales and the contribution difference among different scales are ignored, so that the bidirectional feature pyramid network (BiFPN) is applied to the feature fusion of the multi-scale depth map, and the problem of edge blurring of the depth map is solved through the multi-scale feature fusion. In addition, the CSPNet can replace Resnet in the infrared monocular distance measuring network, so that the network complexity is reduced, the operation speed is increased, and the algorithm can be conveniently transplanted to a low-end AI processing chip.
In this embodiment, only the above-mentioned ranging network structure is taken as an example to describe the distance detection, and other distance detection means can refer to the description of this embodiment, which is not described herein again.
After obtaining ambient temperature, atmospheric humidity, detection distance, target device's emissivity and output temperature, present traditional temperature measurement process can directly be based on T = f (v, e, d, T, h) and calculate that models, and this kind of computational mode not only can lead to the process flow too complicated, and production efficiency is low, and the temperature value precision that actual computation obtained is lower moreover, is difficult to satisfy the user demand of high accurate temperature measurement.
In view of the above, the present application provides an accurate infrared temperature measurement model to achieve accurate target temperature measurement.
Firstly, through a plurality of experimental applicants, the output temperature v of different infrared thermal imaging detection devices can change along with the change of the ambient temperature t, and the inherent property of the infrared thermal imaging detection device is a main factor influencing the temperature measurement precision. In order to avoid the influence on the measurement accuracy caused by using different infrared thermal imaging detection devices, the method first calls an environment temperature correction model to eliminate the influence of the detection devices in the accurate infrared temperature measurement, and then executes step S102.
S102, calling an environment temperature correction model to perform detection equipment influence correction on the output temperature according to the environment temperature to obtain a first correction temperature;
the environment temperature correction model is pre-trained in the method and is used for calculating the blackbody radiation temperature T f Mathematical model (T) of the correlation between the output v of an infrared thermographic detection device and the ambient temperature T f = f (v, T), where T f To eliminate the blackbody radiation temperature affected by the ambient temperature t), the ambient temperature t and the output temperature v are input into the model, and then the temperature without the influence of the ambient temperature on the output temperatures of different infrared thermal imaging detection devices can be obtained as the first correction temperature.
In this embodiment, the specific network structure and the training method of the environment temperature correction model are not limited, and may be set according to actual use requirements.
In order to ensure the accuracy of eliminating the influence, the embodiment provides a training method of an environmental temperature correction model, which includes:
(1) Determining infrared thermal imaging detection equipment to be calibrated as the equipment to be calibrated;
because the infrared thermal imaging detection devices are different, the output temperature of the infrared thermal imaging detection devices has larger variation along with the change of the environmental temperature, and therefore, the whole infrared thermal imaging detection device needs to be calibrated and corrected when the whole infrared thermal imaging detection device leaves a factory. In this embodiment, the infrared thermal imaging detection device to be calibrated refers to an infrared thermal imaging detection device to be subjected to ambient temperature correction, and is referred to as a device to be calibrated for simplifying description. In this embodiment, the number of the devices to be calibrated is not limited, and may be one device or multiple devices, and the devices to be calibrated may be determined according to actual use requirements.
(2) Placing equipment to be calibrated and black bodies with different set temperatures in a step-in high-low temperature box;
the black body is an ideal object, which is capable of absorbing all external electromagnetic radiation and has no reflection or transmission, and is used as the object of infrared temperature detection research in this embodiment to exclude the influence of other factors (such as shape, material, etc.) besides temperature. Of course, other detection objects may also be selected, and this embodiment is not limited thereto. The black bodies should be provided in plural numbers and have different temperatures, and the number and the temperature of the black bodies are not limited in this embodiment, for example, 6 black bodies may be provided, and the temperatures of the 6 black bodies are set to-20 ℃, 0 ℃, 30 ℃, 70 ℃, 110 ℃ and 150 ℃.
The distance difference between each device to be calibrated and each black body is not greater than a threshold value, the distance between each device to be calibrated and each black body is kept as same as the distance between each device to be calibrated and each black body as far as possible, so that the influence of the distance between each device and each black body on temperature measurement is avoided, the distance between each black body and each device to be calibrated is not limited, and the distance can be set according to an empirical value, for example, the distance between each black body and each device to be calibrated is about 3 meters. The schematic layout of devices to be calibrated and black bodies in a walk-in high and low temperature chamber is shown in fig. 2, in this embodiment, only the devices to be calibrated are arranged at equal intervals, black bodies with different temperatures are described as an example of arc arrangement opposite to the calibration devices according to the sequence of temperature values, and other arrangement modes can refer to the description of this embodiment and are not described herein again.
(3) Sequentially adjusting the temperature of the walk-in high and low temperature box to each preset temperature value, and respectively collecting the temperature value of each black body collected by each device to be calibrated as a detection temperature;
starting the device to be calibrated, the black body and the step-in high-low temperature box, and sequentially adjusting the temperature of the step-in high-low temperature box to preset temperature values, such as-20 ℃ firstly, then 0 ℃, 20 ℃ and 50 ℃. Taking single acquisition as an example, after a system (a system composed of a device to be calibrated, a black body and a step-in high-low temperature box) reaches a thermal equilibrium state, recording the output temperature v of the device to be calibrated, the temperature T of the device to be calibrated (the temperature of the device to be calibrated can represent the ambient temperature) and the corresponding temperature T of each black body. Note that when collecting each blackbody data, the center of the optical lens of the device to be calibrated should be aligned with the center of the imaging spot as much as possible.
(4) Taking detection data corresponding to each device to be calibrated as a training sample, and training a pre-built environment temperature correction model according to the training sample; the probe data includes: the temperature is detected, the temperature of the step-in high-low temperature box and the temperature of the black body.
According to each detection data basis T f The blackbody radiation temperature T can be established and trained by = f (v, T) f And a mathematical model of the output v of the infrared thermal imaging detection device and the ambient temperature t is used as an ambient temperature correction model.
It should be noted that, in this embodiment, the above training process of the environmental temperature correction model (the temperature measurement range is-20 ℃ to 150 ℃, and the environmental temperature range is-20 ℃ to 50 ℃) is only used as an example for description, and other training manners can refer to the description of this embodiment and are not described herein again.
S103, calling a distance and humidity correction model to correct the detection distance and the influence of the atmosphere humidity on the first corrected temperature according to the atmosphere humidity and the detection distance to obtain a second corrected temperature;
the distance and humidity correction model is a pre-trained model for calculating blackbody radiation temperature T in the method d Mathematical model T relating to the distance v and the atmospheric humidity h d ＝f(T f D, h) in which T d F, modeling by using a traditional machine learning algorithm such as SVR (space vector regression) and ANN (artificial neural network) and correcting the first corrected temperature T to eliminate the blackbody radiation temperature after the influence of the ambient temperature T f After the detection distance d and the atmospheric humidity h are input into the model, the elimination detection distance d and the atmosphere can be obtainedThe influence of the humidity h on the first corrected temperature is used as the second corrected temperature from the data output from the model.
It should be noted that, the applicant researches and discovers that the detection distance d, the emissivity e of the measured object, the atmospheric humidity h and the like between each target device to be detected and the thermal imaging detection device belong to external influence factors and do not change along with the change of the infrared thermal imaging detection device, and in the method, a general model modeling T is established for the influence of the detection distance d and the emissivity e of the measured object on the detection temperature d ＝f(T f D, h) in which T d In order to eliminate the influence of the detection distance d and the atmospheric humidity h on the corrected blackbody radiation temperature, on the basis of the first correction temperature, the process flow is simplified, the production efficiency is improved, and the compensation of the detection distance and the humidity is realized.
In this embodiment, the specific network structure and the training method of the distance and humidity correction model are not limited, and may be set accordingly according to actual use requirements.
In order to ensure the accuracy of eliminating the influence, the embodiment provides a training method for a distance and humidity correction model, which includes the following steps:
(1) Determining an infrared thermal imaging detection device;
(2) Fixing black bodies with different set temperatures at preset positions;
the blackbody positions are fixed in an outdoor environment (an application environment can be selected according to an actual application scene, and only the outdoor environment is taken as an example in the embodiment), 6 blackbodies (the temperatures are respectively set to be-20 ℃, 0 ℃, 30 ℃, 70 ℃, 110 ℃ and 150 ℃) are arranged in an arc shape as shown in fig. 3, the distance between the blackbodies is not limited in the embodiment, and the blackbody positions can be set according to actual test requirements.
(3) Respectively moving the infrared thermal imaging detection equipment to a position away from a black body by a preset distance, and respectively acquiring first corrected temperatures generated by the infrared thermal imaging detection equipment as detection temperatures;
after the black body and the infrared thermal imaging detection device are in thermal equilibrium, data acquisition is started, and the infrared thermal imaging detection device is moved to enable the infrared thermal imaging detection device and the black body to have different distances, and the preset distance is not limited in this embodiment, for example, the infrared thermal imaging detection device can be moved to positions 3 meters, 9 meters, 18 meters and 30 meters away from the black body to perform repeated detection, as shown in fig. 3.
(4) Taking detection data corresponding to the infrared thermal imaging detection equipment as a training sample, and training a pre-built distance humidity correction model according to the training sample; the probe data includes: atmospheric humidity, detection temperature, preset spacing and black body temperature.
The collection is made of T at each interval f Black body radiation temperature T calculated by = f (v, T) f (first correction temperature), distance d, atmospheric humidity h and corresponding first correction temperature T to obtain a training sample (T) f ,d,h,T)。
According to an influence formula T of the training sample based on distance and atmospheric humidity on temperature acquisition d ＝f(T f D, h) the blackbody radiation temperature T can be established and trained d A mathematical model of the distance v and the atmospheric humidity h, and a distance humidity correction model.
It should be noted that in this embodiment, the description of the model training process is only performed by taking an example in which the maximum measurement distance is 30 meters and the temperature measurement range is-20 ℃ to 150 ℃, and other training manners can refer to the description of this embodiment, which is not described herein again.
And S104, calling the object temperature identification model to calculate the temperature of the target equipment according to the emissivity, the environment temperature and the second correction temperature.
The object temperature identification model refers to a model for performing temperature calculation according to parameters (emissivity e and ambient temperature T) of a detected target device, wherein the model takes the influence of the ambient temperature on the temperature of the target device into consideration, and uses T r ＝f 1 (T d E, T) based on a model (where T r To eliminate the real object temperature after emissivity effects, f 1 Universal emissivity and ambient temperature correction models in the industry) can be adopted, and specific model building and training modes can refer to the introduction of related technologies, which is not described herein again.
After the second corrected temperature, the emissivity and the environment temperature are input into the object temperature identification model, the model can automatically output a temperature value, and the temperature value is the real temperature value of the target device.
It should be noted that, the implementation subject of the method is not limited in the present application, and may be an infrared thermal imaging detection device, that is, the actual temperature calculation is performed on the output temperature detected by the infrared thermal imaging detection device immediately after the detection; the actual temperature may also be calculated for other devices, that is, for obtaining related data in the detection of the infrared thermal imaging detection device, which is not limited herein, and the setting of the execution main body may be performed according to the actual use requirement and the limitation of the calculation capability, which is not described herein again.
Based on the above description, in the technical scheme provided by the embodiment of the present invention, considering the conditions of the interaction and the interaction among several main factors, such as the detection distance, the emissivity of the target device, the ambient temperature, the atmospheric humidity, and the output temperature, which affect the accuracy of infrared temperature measurement, on the basis of the conventional machine learning model, the influence of the ambient temperature is regarded as the inherent characteristic of the output of the detection device, and the output temperature is corrected according to different detection devices and ambient temperatures, so as to eliminate the influence of the ambient temperature on the output temperatures of different infrared thermal imaging detection devices; meanwhile, the detection distance, the emissivity and the atmospheric humidity between the target device and the detection device are regarded as external influence factors, the distance and humidity correction model is built according to the established general model, the distance and humidity correction model corrects the influence of the detection distance and the atmospheric humidity on the first correction temperature according to the atmospheric humidity and the detection distance, the influence of the detection distance and the atmospheric humidity on the first correction temperature is eliminated, the temperature value is measured and calculated according to object detection data with the influence of all aspects eliminated, and the temperature measurement accuracy can be remarkably improved.
Corresponding to the above method embodiment, the embodiment of the present invention further provides an infrared temperature measuring device, and the infrared temperature measuring device described below and the infrared temperature measuring method described above may be referred to correspondingly.
Referring to fig. 4, the apparatus includes the following modules:
the data acquiring unit 110 is mainly used for acquiring an ambient temperature, an atmospheric humidity, a detection distance, an emissivity of the target device, and an output temperature when the infrared thermal imaging detection device detects a temperature of the target device;
the first correction unit 120 is mainly configured to invoke an ambient temperature correction model to perform detection device influence correction on the output temperature according to the ambient temperature, so as to obtain a first corrected temperature;
the second correcting unit 130 is mainly configured to invoke the range-humidity correcting model to correct the detection distance and the influence of the atmospheric humidity on the first corrected temperature according to the atmospheric humidity and the detection distance, so as to obtain a second corrected temperature;
the temperature calculation unit 140 is mainly configured to call the object temperature identification model to calculate the temperature of the target device according to the emissivity, the ambient temperature, and the second correction temperature.
Corresponding to the above method embodiment, an embodiment of the present invention further provides an infrared thermal imaging detection apparatus, and an infrared thermal imaging detection apparatus described below and an infrared temperature measurement method described above may be referred to correspondingly.
The infrared thermal imaging detection apparatus includes:
a memory for storing a computer program;
and the processor is used for realizing the steps of the infrared temperature measurement method of the embodiment of the method when executing the computer program.
Specifically, referring to fig. 5, a schematic diagram of a specific structure of an infrared thermal imaging detection apparatus provided in this embodiment is provided, where the infrared thermal imaging detection apparatus may generate a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 322 (e.g., one or more processors) and a memory 332, where the memory 332 stores one or more computer applications 342 or data 344. Memory 332 may be, among other things, transient storage or persistent storage. The program stored in memory 332 may include one or more modules (not shown), each of which may include a sequence of instructions operating on the data processing apparatus. Still further, the central processor 322 may be configured to communicate with the memory 332 to execute a series of instruction operations in the memory 332 on the infrared thermal imaging detection device 301.
The infrared thermal imaging detection apparatus 301 may also include one or more power supplies 326, one or more wired or wireless network interfaces 350, one or more input-output interfaces 358, and/or one or more operating systems 341.
The steps in the above-described infrared thermometry method may be implemented by the structure of an infrared thermal imaging detection apparatus.
Corresponding to the above device embodiment, the embodiment of the present invention further provides an intelligent inspection robot, in which the infrared thermal imaging detection device described in the above embodiment is disposed, and the infrared thermal imaging detection device and the above-described infrared temperature measurement method may be referred to correspondingly.
In this embodiment do not do the injecture to the mounted position of infrared thermal imaging detection equipment in the robot is patrolled and examined to intelligence, for avoiding other factors such as sheltering from and height to the unstable factor that the temperature measurement process brought, infrared thermal imaging detection equipment can set up in the intelligence and patrol and examine the outside of robot, and infrared thermal imaging detection equipment patrols and examines the position of robot portable at intelligence to guarantee to not co-altitude target device and infrared thermal imaging detection equipment keep the level.
Corresponding to the above method embodiment, the embodiment of the present invention further provides a readable storage medium, and a readable storage medium described below and an infrared temperature measurement method described above may be referred to correspondingly.
A readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of the infrared temperature measurement method of the above-mentioned method embodiments.
The readable storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and various other readable storage media capable of storing program codes.
Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the technical solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
Claims (8)
1. An infrared temperature measurement method is characterized by comprising the following steps:
acquiring the ambient temperature, the atmospheric humidity, the detection distance, the emissivity and the output temperature of target equipment when the infrared thermal imaging detection equipment detects the temperature of the target equipment;
calling an environment temperature correction model to perform detection equipment influence correction on the output temperature according to the environment temperature to obtain a first correction temperature;
calling a distance humidity correction model to correct the influence of the detection distance and the atmospheric humidity on the first corrected temperature according to the atmospheric humidity and the detection distance to obtain a second corrected temperature;
calling an object temperature identification model to calculate the temperature of the target equipment according to the emissivity, the environment temperature and the second correction temperature;
the method for acquiring the detection distance comprises the following steps:
calling a ranging network to determine the distance between the infrared thermal imaging detection device and the target device as the detection distance;
wherein the invoking of the ranging network to determine the distance between the infrared thermal imaging detection device and the target device comprises:
calling an infrared monocular distance measurement network with lightweight enhanced edge loss and multi-scale feature fusion to calculate the distance between the infrared thermal imaging detection equipment and the target equipment; the multi-scale feature fusion is the feature fusion that a bidirectional feature pyramid network is applied to a multi-scale depth map.
2. The infrared thermometry method of claim 1, wherein said emissivity obtaining method comprises:
detecting target equipment, and determining the type and the position of the target equipment;
and determining the emissivity corresponding to the type according to the emissivity matching information of various types of objects, and taking the emissivity as the emissivity of the target equipment.
3. The infrared temperature measurement method of claim 1, wherein the training method of the environment temperature correction model comprises:
determining infrared thermal imaging detection equipment to be calibrated as the equipment to be calibrated;
placing the equipment to be calibrated and blackbodies with different set temperatures in a step-in high-low temperature box; the distance difference between each device to be calibrated and each black body is not greater than a threshold value;
sequentially adjusting the temperature of the walk-in high-low temperature box to each preset temperature value, and respectively obtaining the temperature value of each black body acquired by each device to be calibrated as a detection temperature;
taking the detection data corresponding to each device to be calibrated as a training sample, and training a pre-built environment temperature correction model according to the training sample; the probe data includes: the detection temperature, the temperature of the walk-in high and low temperature box and the temperature of the black body.
4. The infrared temperature measurement method of claim 1, wherein the training method of the range-humidity correction model comprises:
determining an infrared thermal imaging detection device;
fixing black bodies with different set temperatures at preset positions;
respectively moving infrared thermal imaging detection equipment to a position away from the black body by a preset distance, and respectively acquiring first corrected temperatures generated by the infrared thermal imaging detection equipment as detection temperatures;
taking detection data corresponding to the infrared thermal imaging detection equipment as a training sample, and training a pre-built distance humidity correction model according to the training sample; the probe data includes: atmospheric humidity, the detection temperature, the preset distance and the temperature of the black body.
5. An infrared temperature measuring device, comprising:
the data acquisition unit is used for acquiring the ambient temperature, the atmospheric humidity, the detection distance, the emissivity of the target equipment and the output temperature when the infrared thermal imaging detection equipment detects the temperature of the target equipment;
the first correction unit is used for calling an environment temperature correction model to perform detection equipment influence correction on the output temperature according to the environment temperature to obtain a first correction temperature;
the second correction unit is used for calling a distance and humidity correction model to correct the detection distance and the influence of the atmosphere humidity on the first correction temperature according to the atmosphere humidity and the detection distance to obtain a second correction temperature;
the temperature calculation unit is used for calling an object temperature identification model to calculate the temperature of the target equipment according to the emissivity, the environment temperature and the second correction temperature;
the data acquisition unit is further used for calling a ranging network to determine the distance between the infrared thermal imaging detection device and the target device as the detection distance;
the data acquisition unit is further used for calling a lightweight enhanced edge loss and multiscale feature fused infrared monocular distance measurement network to calculate the distance between the infrared thermal imaging detection equipment and the target equipment; the multi-scale feature fusion is a feature fusion applying a bidirectional feature pyramid network to a multi-scale depth map.
6. An infrared thermal imaging detection device, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the infrared thermometry method of any one of claims 1 to 4 when executing the computer program.
7. The utility model provides a robot is patrolled and examined to intelligence which characterized in that includes: the infrared thermal imaging detection device of claim 6.
8. A readable storage medium, characterized in that the readable storage medium has stored thereon a computer program which, when being executed by a processor, carries out the steps of the infrared thermometry method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110541334.XA CN113267258B (en) | 2021-05-18 | 2021-05-18 | Infrared temperature measurement method, device, equipment, intelligent inspection robot and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110541334.XA CN113267258B (en) | 2021-05-18 | 2021-05-18 | Infrared temperature measurement method, device, equipment, intelligent inspection robot and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113267258A CN113267258A (en) | 2021-08-17 |
| CN113267258B true CN113267258B (en) | 2023-02-17 |
Family
ID=77231489
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110541334.XA Active CN113267258B (en) | 2021-05-18 | 2021-05-18 | Infrared temperature measurement method, device, equipment, intelligent inspection robot and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113267258B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113916384B (en) * | 2021-09-30 | 2024-03-19 | 云南电网有限责任公司电力科学研究院 | Method for controlling temperature of blackbody radiation source based on multivariate statistical analysis modeling |
| CN114199384B (en) * | 2021-11-02 | 2023-06-20 | 武汉钢铁有限公司 | Infrared temperature measurement method and system |
| CN114264373A (en) * | 2021-12-27 | 2022-04-01 | 淮阴工学院 | Method and system for temperature compensation and measured distance enhancement of infrared thermometer |
| CN115736844B (en) * | 2022-11-16 | 2023-10-24 | 吉林省科英医疗激光有限责任公司 | Real-time body surface temperature detection system and detection method |
| CN115876334B (en) * | 2023-02-22 | 2023-05-30 | 瑞纳智能设备股份有限公司 | Infrared thermal image indoor temperature measurement method, system and computer readable storage medium |
| CN116448250A (en) * | 2023-06-14 | 2023-07-18 | 国网山西省电力公司超高压变电分公司 | Auxiliary positioning device and auxiliary positioning method for infrared thermal imaging of power equipment |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102809434A (en) * | 2011-05-30 | 2012-12-05 | 安讯士有限公司 | Methods and apparatus for thermographic measurements |
| CN107941348A (en) * | 2017-11-24 | 2018-04-20 | 广东电网有限责任公司电力科学研究院 | A kind of infrared measurement of temperature Calibration Method |
| CN108991905A (en) * | 2017-06-06 | 2018-12-14 | 佛山市顺德区美的电热电器制造有限公司 | Infrared measurement of temperature method, system and cooking apparatus for cooking apparatus |
| CN109357766A (en) * | 2018-09-26 | 2019-02-19 | 国网福建省电力有限公司 | Defect of transformer equipment detection method and defect detecting system based on infrared measurement of temperature |
| 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 |
| CN110530432A (en) * | 2019-09-30 | 2019-12-03 | 国网山东省电力公司电力科学研究院 | A kind of grid equipment electrification detection system, thermal infrared imager and method |
| CN110910383A (en) * | 2019-12-04 | 2020-03-24 | 江苏方天电力技术有限公司 | Phase modulator fault monitoring method and system based on infrared image recognition |
| CN111412992A (en) * | 2020-04-03 | 2020-07-14 | 华为技术有限公司 | Method for measuring temperature and electronic equipment |
| CN111751003A (en) * | 2020-06-10 | 2020-10-09 | 四川省东宇信息技术有限责任公司 | Thermal imager temperature correction system and method and thermal imager |
| CN112050948A (en) * | 2020-08-05 | 2020-12-08 | 沈阳上博智像科技有限公司 | Non-barrier infrared temperature measurement method based on detector temperature drift model |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112393808B (en) * | 2020-11-23 | 2021-12-17 | 南通嘉骏信息科技有限公司 | Temperature compensation method and system for thermal camera |
-
2021
- 2021-05-18 CN CN202110541334.XA patent/CN113267258B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102809434A (en) * | 2011-05-30 | 2012-12-05 | 安讯士有限公司 | Methods and apparatus for thermographic measurements |
| CN108991905A (en) * | 2017-06-06 | 2018-12-14 | 佛山市顺德区美的电热电器制造有限公司 | Infrared measurement of temperature method, system and cooking apparatus for cooking apparatus |
| CN107941348A (en) * | 2017-11-24 | 2018-04-20 | 广东电网有限责任公司电力科学研究院 | A kind of infrared measurement of temperature Calibration Method |
| CN109357766A (en) * | 2018-09-26 | 2019-02-19 | 国网福建省电力有限公司 | Defect of transformer equipment detection method and defect detecting system based on infrared measurement of temperature |
| 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 |
| CN110530432A (en) * | 2019-09-30 | 2019-12-03 | 国网山东省电力公司电力科学研究院 | A kind of grid equipment electrification detection system, thermal infrared imager and method |
| CN110910383A (en) * | 2019-12-04 | 2020-03-24 | 江苏方天电力技术有限公司 | Phase modulator fault monitoring method and system based on infrared image recognition |
| CN111412992A (en) * | 2020-04-03 | 2020-07-14 | 华为技术有限公司 | Method for measuring temperature and electronic equipment |
| CN111751003A (en) * | 2020-06-10 | 2020-10-09 | 四川省东宇信息技术有限责任公司 | Thermal imager temperature correction system and method and thermal imager |
| CN112050948A (en) * | 2020-08-05 | 2020-12-08 | 沈阳上博智像科技有限公司 | Non-barrier infrared temperature measurement method based on detector temperature drift model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113267258A (en) | 2021-08-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113267258B (en) | Infrared temperature measurement method, device, equipment, intelligent inspection robot and storage medium | |
| CN109977813B (en) | Inspection robot target positioning method based on deep learning framework | |
| CN110599541B (en) | Method and device for calibrating multiple sensors and storage medium | |
| CN110826549A (en) | Inspection robot instrument image identification method and system based on computer vision | |
| CN111931565A (en) | Photovoltaic power station UAV-based autonomous inspection and hot spot identification method and system | |
| CN102800096B (en) | Robustness estimation algorithm of camera parameter | |
| CN102768762B (en) | Digital camera calibration method targeted to shield tunnel defect digital radiography detection and device thereof | |
| CN111191625A (en) | Object identification and positioning method based on laser-monocular vision fusion | |
| CN108871373B (en) | Star sensor calibration method based on pitching rolling table and nonlinear optimization | |
| CN109711400A (en) | A kind of electric inspection process method and apparatus identifying simulated pointer formula meter reading | |
| CN111473755B (en) | Remote distance measurement method and device | |
| CN107607091A (en) | A kind of method for measuring unmanned plane during flying flight path | |
| CN111968048A (en) | Method and system for enhancing image data of few samples in power inspection | |
| CN109799073A (en) | A kind of optical distortion measuring device and method, image processing system, electronic equipment and display equipment | |
| CN113358231B (en) | Infrared temperature measurement method, device and equipment | |
| CN115376030A (en) | Steel structure monitoring method based on BIM and unmanned aerial vehicle technology | |
| CN113237633B (en) | Photoelectric platform stability and precision detection method based on image processing | |
| CN103176349B (en) | Lens detection device and method | |
| CN116563841B (en) | Detection method and detection device for power distribution network equipment identification plate and electronic equipment | |
| CN112504156A (en) | Structural surface strain measurement system and measurement method based on foreground grid | |
| CN112419402A (en) | Positioning method and system based on multispectral image and laser point cloud | |
| CN113077518B (en) | Camera parameter calibration method, device and storage medium | |
| CN115861407A (en) | Safe distance detection method and system based on deep learning | |
| CN116381726A (en) | Unmanned aerial vehicle laser point cloud precision self-evaluation method based on data | |
| RU2692970C2 (en) | Method of calibration of video sensors of the multispectral system of technical vision |
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 |