CN112414558A - Temperature detection method and device based on visible light image and thermal imaging image - Google Patents
Temperature detection method and device based on visible light image and thermal imaging image Download PDFInfo
- Publication number
- CN112414558A CN112414558A CN202110093688.2A CN202110093688A CN112414558A CN 112414558 A CN112414558 A CN 112414558A CN 202110093688 A CN202110093688 A CN 202110093688A CN 112414558 A CN112414558 A CN 112414558A
- Authority
- CN
- China
- Prior art keywords
- visible light
- user
- thermal imaging
- image
- light image
- 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.)
- Granted
Links
- 238000001931 thermography Methods 0.000 title claims abstract description 150
- 238000001514 detection method Methods 0.000 title claims abstract description 54
- 210000001061 forehead Anatomy 0.000 claims abstract description 103
- 238000009529 body temperature measurement Methods 0.000 claims abstract description 41
- 238000006243 chemical reaction Methods 0.000 claims abstract description 7
- 238000000034 method Methods 0.000 claims description 28
- 238000001914 filtration Methods 0.000 claims description 17
- 238000012549 training Methods 0.000 claims description 16
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 9
- 238000013527 convolutional neural network Methods 0.000 claims description 8
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 230000036760 body temperature Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static 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
- G01J5/0022—Radiation pyrometry, e.g. infrared or optical thermometry for sensing the radiation of moving bodies
- G01J5/0025—Living bodies
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/002—Measuring arrangements characterised by the use of optical techniques for measuring two or more coordinates
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
Abstract
The application relates to the technical field of artificial intelligence, and provides a temperature detection method and a temperature detection device based on a visible light image and a thermal imaging image, wherein the temperature detection method and the temperature detection device comprise the steps of collecting the visible light image of a user based on a visible light camera and collecting the thermal imaging image of the user based on a thermal imaging camera; detecting the coordinates of the forehead of the user in the visible light image; detecting the distance from a user to a visible light camera based on the visible light image; calculating the coordinates of the forehead of the user in the thermal imaging image based on the coordinates of the forehead of the user in the visible light image and the distance between the user and the visible light camera; and acquiring the thermal imaging temperature of the coordinate position of the forehead of the user in the thermal imaging image as a temperature detection result of the user. This application calculates the coordinate of user's forehead in the thermal imaging image with the coordinate conversion of user's forehead in visible light image, and simultaneously, this application is to carrying out the temperature measurement to the forehead position for the temperature measurement result is more accurate.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to a temperature detection method and device based on a visible light image and a thermal imaging image.
Background
At present, on temperature measurement equipment such as temperature measurement face identification all-in-one, camera preview picture and people's face frame position suggestion are indispensable user experience, especially on temperature measurement face identification all-in-one, because of temperature measurement module is fixed position and visual scope, when the face frame is not at the intermediate position of previewing the picture, can lead to the inaccurate problem of temperature measurement. Meanwhile, the visible light camera and the thermal imaging camera on the temperature measurement equipment cannot be overlapped, a certain horizontal distance must be provided, namely, images collected by the visible light camera and the thermal imaging camera cannot be completely overlapped, and inaccurate temperature measurement must be caused if the coordinate position of the visible light image face is directly adopted for temperature measurement.
Disclosure of Invention
The application mainly aims to provide a temperature detection method and device based on a visible light image and a thermal imaging image, and aims to overcome the defect that the temperature of the existing temperature measurement equipment is inaccurate.
In order to achieve the above object, the present application provides a temperature detection method based on a visible light image and a thermal imaging image, which is applied to a temperature measurement device, wherein the temperature measurement device includes a visible light camera and a thermal imaging camera, and includes the following steps:
collecting a visible light image of a user based on the visible light camera and collecting a thermal imaging image of the user based on the thermal imaging camera;
detecting the coordinates of the forehead of the user in the visible light image;
detecting the distance from the user to the visible light camera based on the visible light image;
calculating the coordinates of the forehead of the user in the thermal imaging image based on the coordinates of the forehead of the user in the visible light image and the distance of the user from the visible light camera;
and acquiring the thermal imaging temperature of the coordinate position of the forehead of the user in the thermal imaging image as a temperature detection result of the user.
Further, before the step of detecting the coordinates of the forehead of the user in the visible light image, the method further includes:
detecting a face frame of a user in the visible light image;
detecting the coordinates of the upper left corner and the upper right corner of the face frame, and acquiring the width of the visible light image;
acquiring a first margin between the upper left corner of the face frame and the leftmost side of the visible light image according to the upper left corner coordinate of the face frame;
calculating a second edge distance from the upper right corner of the face frame to the rightmost side of the visible light image according to the width of the visible light image and the upper right corner coordinate of the face frame;
calculating a margin difference value of the first margin and the second margin, and filtering the margin difference value based on a filter to obtain a filtering margin difference value;
judging whether the filtering edge distance difference value is within a first preset range or not, and judging whether a vertical coordinate in an upper left corner coordinate or an upper right corner coordinate of the face frame is within a second preset range or not;
if the filtering edge distance difference value is within a first preset range and the ordinate is within a second preset range, judging that the face of the user is centered;
and if the filtering edge distance difference value is not in a first preset range and/or the ordinate is not in a second preset range, judging that the face of the user is not centered, and sending out prompt information for prompting the user to be centered.
Further, the step of obtaining the coordinates of the forehead of the user in the thermal imaging image based on the coordinates of the forehead of the user in the visible light image and the distance of the user from the visible light camera comprises:
acquiring the size of a thermal imaging pixel and the size of a visible light pixel;
acquiring a thermal imaging focal length and a visible light focal length;
calculating an geometric scaling factor based on the thermal imaging focal length, the visible light focal length, the thermal imaging pixel size and the visible light pixel size;
acquiring a coordinate of a central area in a display picture of the temperature measuring equipment;
acquiring the horizontal distance between the visible light camera and the thermal imaging camera;
detecting a horizontal rotation angle, a pitch angle and an inclination angle of the face of the user in the visible light image;
calculating the offset of the visible light image relative to the thermal imaging image based on the horizontal rotation angle, the pitch angle and the tilt angle of the user face, the geometric scaling factor, the centered area coordinate, the horizontal distance, the thermal imaging pixel size, the thermal imaging focal length, the coordinate of the user forehead in the visible light image and the distance from the user to the visible light camera;
calculating the coordinates of the user's forehead in the thermal imaging image based on the offset and the coordinates of the user's forehead in the visible light image.
Further, the calculation formula for calculating the geometric scaling factor is as follows:
wherein k is an equal scaling coefficient,in order to achieve the thermal imaging focal length,the focal length of the visible light is set,for the size of the thermal imaging pixel,is the visible pixel size.
Further, the calculation formula for calculating the offset of the visible light image relative to the thermal imaging image is as follows:
where δ is the offset and the centered area coordinate is,Is the thermal imaging focal length, D is the horizontal distance, k is the geometric scaling factor, D is the distance of the user from the visible camera,for the size of the thermal imaging pixel, α, θ and Ω are the horizontal rotation angle, the pitch angle and the tilt angle of the user face, respectively, and γ and A, B, C are estimation coefficients, respectively.
Further, the step of detecting the coordinates of the forehead of the user in the visible-light image includes:
inputting the visible light image into a preset forehead detection network model, and detecting to obtain the coordinates of the forehead of the user in the visible light image;
wherein the training step of the preset forehead detection network model comprises the following steps:
acquiring a face frame in a training sample;
taking the upper left corner and the upper right corner of the face frame in the training sample as reference points, and acquiring an image of a preset area above the face frame as a forehead key point feature image;
inputting the forehead key point feature image into a convolutional neural network for regression operation, correcting deviation by adopting least square regression, and training on the basis of a gradient descent algorithm and a back propagation algorithm to obtain a global minimum value or a local minimum value of a loss function so as to train to obtain the forehead detection network model; wherein the loss function of the convolutional neural network is a cross entropy loss function.
Further, the step of detecting the distance from the user to the visible light camera based on the visible light image includes:
detecting the width of the face of the user in the visible light image;
detecting a horizontal corner of a user face in the visible light image;
calculating the distance between the user and the visible light camera based on the width of the user face in the visible light image and the horizontal rotation angle of the user face in the visible light image;
wherein the calculation formula for calculating the distance from the user to the visible light camera is as follows:
D=λ*(1-βCosα)* W;
d is the distance between the user and the visible light camera, W is the width of the user face in the visible light image, alpha is the horizontal rotation angle of the user face in the visible light image, and beta and lambda are distance conversion coefficients.
Further, before the step of calculating the distance from the user to the visible light camera based on the width of the user's face in the visible light image and the horizontal rotation angle of the user's face in the visible light image, the method includes:
acquiring a plurality of first sample data; each piece of first sample data comprises a sample distance from a sample face to a visible light camera, a horizontal rotation angle of the sample face in a corresponding visible light image, and a width of the sample face in the corresponding visible light image;
and inputting each first sample data into a preset depth network model for iterative training to obtain the distance conversion coefficient.
The application also provides a temperature-detecting device based on visible light image and thermal imaging image, is applied to temperature measurement equipment on, temperature measurement equipment includes visible light camera and thermal imaging camera, temperature-detecting device based on visible light image and thermal imaging image includes:
the acquisition unit is used for acquiring a visible light image of a user based on the visible light camera and acquiring a thermal imaging image of the user based on the thermal imaging camera;
a first coordinate detection unit, configured to detect a coordinate of the forehead of the user in the visible light image;
a distance detection unit for detecting a distance from the user to the visible light camera based on the visible light image;
a second coordinate detection unit, configured to calculate coordinates of the forehead of the user in the thermal imaging image based on the coordinates of the forehead of the user in the visible light image and a distance from the user to the visible light camera;
and the temperature detection unit is used for acquiring the thermal imaging temperature of the coordinate position of the forehead of the user in the thermal imaging image as the temperature detection result of the user.
The present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.
The temperature detection method, the temperature detection device and the computer equipment based on the visible light image and the thermal imaging image comprise the steps of collecting the visible light image of a user based on the visible light camera and collecting the thermal imaging image of the user based on the thermal imaging camera; detecting the coordinates of the forehead of the user in the visible light image; detecting the distance from the user to the visible light camera based on the visible light image; calculating the coordinates of the forehead of the user in the thermal imaging image based on the coordinates of the forehead of the user in the visible light image and the distance of the user from the visible light camera; and acquiring the thermal imaging temperature of the coordinate position of the forehead of the user in the thermal imaging image as a temperature detection result of the user. According to the method and the device, the coordinate of the forehead of the user in the visible light image is converted and calculated to obtain the coordinate of the forehead of the user in the thermal imaging image, and then temperature measurement is carried out, so that the temperature measurement result is more accurate; simultaneously, this application is to carrying out the temperature measurement to the forehead position, also can promote the degree of accuracy of temperature measurement.
Drawings
FIG. 1 is a schematic diagram illustrating the steps of a temperature detection method based on visible light images and thermal imaging images according to an embodiment of the present disclosure;
FIG. 2 is a block diagram of a temperature detection device based on visible light images and thermal imaging images according to an embodiment of the present disclosure;
fig. 3 is a block diagram illustrating a structure of a computer device according to an embodiment of the present application.
The implementation, functional features and advantages of the objectives of the present application will be further explained with reference to the accompanying drawings.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
Referring to fig. 1, an embodiment of the present application provides a temperature detection method based on a visible light image and a thermal imaging image, which is applied to a temperature measurement device, where the temperature measurement device includes a visible light camera and a thermal imaging camera, and includes the following steps:
step S1, collecting a visible light image of a user based on the visible light camera, and collecting a thermal imaging image of the user based on the thermal imaging camera;
step S2, detecting the coordinates of the forehead of the user in the visible light image;
step S3, detecting a distance from the user to the visible light camera based on the visible light image;
step S4, calculating the coordinates of the forehead of the user in the thermal imaging image based on the coordinates of the forehead of the user in the visible light image and the distance between the user and the visible light camera;
step S5, acquiring a thermal imaging temperature of the coordinate position of the forehead in the thermal imaging image as a temperature detection result for the user.
In this embodiment, the temperature measurement equipment is a temperature measurement face recognition all-in-one machine, which can realize face recognition and measure temperature, and the temperature measurement equipment is provided with a visible light camera and a thermal imaging camera, and the visible light camera and the thermal imaging camera are generally arranged on the same vertical plane and located on the same horizontal plane.
As described in the step S1, the visible light camera is configured to collect a visible light image of a user, and the thermal imaging camera is configured to collect a thermal imaging image of the user, where the visible light image is used for face recognition, and a face frame may be displayed in the visible light image during the face recognition. In this embodiment, in order to improve the accuracy of temperature measurement, the forehead temperature of the user is used as a result of measuring the body temperature of the user, and therefore, the forehead position of the user needs to be obtained from the thermal imaging image.
As described in step S2, the forehead position of the user cannot be normally obtained directly from the thermal imaging image, but since the distances between the visible light camera and the thermal imaging camera and the user are the same and are located on the same horizontal plane, the visible light image and the thermal imaging image can be subjected to offset calculation, and the coordinates of the forehead of the user in the thermal imaging image can be obtained based on the coordinates of the forehead of the user in the visible light image. Therefore, it is necessary to detect the coordinates of the forehead of the user from the visible light image.
As described in the above steps S3-S4, if the distances between the visible light camera and the thermal imaging camera and the user are the same and the visible light camera and the thermal imaging camera are located on the same horizontal plane, the visible light image and the thermal imaging image can be aligned in the vertical direction, but the visible light image and the thermal imaging image have a certain offset distance in the horizontal direction due to the horizontal distance between the visible light camera and the thermal imaging camera in the horizontal direction. Accordingly, the coordinates of the forehead of the user in the thermal imaging image can be calculated from the coordinates of the forehead of the user in the visible light image.
As described in step S5, when the coordinate position of the forehead in the thermal imaging image is obtained, the thermal imaging temperature at the corresponding coordinate position, that is, the forehead temperature of the user, that is, the human body temperature detected by the user, can be directly obtained. In the embodiment, the coordinates of the forehead of the user in the visible light image are converted and calculated to obtain the coordinates of the forehead of the user in the thermal imaging image, and then temperature measurement is performed, so that the temperature measurement result is more accurate; simultaneously, this application is to carrying out the temperature measurement to the forehead position, also can promote the degree of accuracy of temperature measurement.
In an embodiment, before the step S2 of detecting the coordinates of the forehead of the user in the visible light image, the method further includes:
step S101, detecting a face frame of a user in the visible light image;
step S102, detecting the coordinates of the upper left corner and the upper right corner of the face frame, and acquiring the width of the visible light image;
step S103, acquiring a first margin between the upper left corner of the face frame and the leftmost side of the visible light image according to the upper left corner coordinate of the face frame;
step S104, calculating a second margin between the upper right corner of the face frame and the rightmost side of the visible light image according to the width of the visible light image and the upper right corner coordinate of the face frame;
step S105, calculating a margin difference value of the first margin and the second margin, and performing filtering processing on the margin difference value based on a filter to obtain a filtering margin difference value;
step S106, judging whether the filtering margin difference value is within a first preset range, and judging whether a vertical coordinate in an upper left corner coordinate or an upper right corner coordinate of the face frame is within a second preset range;
step S107, if the filtering margin difference value is within a first preset range and the ordinate is within a second preset range, determining that the face of the user is centered; and if the filtering edge distance difference value is not in a first preset range and/or the ordinate is not in a second preset range, judging that the face of the user is not centered, and sending out prompt information for prompting the user to be centered.
In this embodiment, when the face of the user is not centered, inaccurate temperature measurement is easily caused, and therefore, before temperature measurement, it is necessary to detect whether the face is centered. In this embodiment, a face frame of a user in a visible light image is identified based on a face identification algorithm, and based on the face frame, coordinates of four corners of the face frame in the visible light image can be acquired. In this embodiment, whether the face is centered is determined, and only the face needs to be applied to the upper left-corner coordinate and the upper right-corner coordinate, and meanwhile, the width of the visible light image needs to be acquired.
Specifically, the coordinates of the upper left corner of the face frame are (X0, Y0), the coordinates of the upper right corner of the face frame are (X1, Y0), and according to the abscissa X0 of the coordinates of the upper left corner of the face frame, the first distance W1 from the upper left corner of the face frame to the leftmost side of the visible light image can be obtained and is X0. According to the width W 'of the visible light image and the abscissa X1 of the coordinate of the upper right corner of the face frame, the second margin W2 from the upper right corner of the face frame to the rightmost side of the visible light image can be calculated as W' -X1.
Further, an absolute value W3= | W1-W2 |, which is a difference between the first edge and the second edge, is calculated, and since the face recognition algorithm is continuously processing image data, the absolute value W3 is continuously calculated, and an IIR Filter is used to perform filtering processing in order to remove noise and to smooth an absolute value output, so that the filtered edge difference is obtained. And then, determining that the filtering edge distance difference is within a first preset range (e.g. 150 pixels), and determining whether the ordinate in the top left-hand coordinate or the top right-hand coordinate of the face frame is within a second preset range, i.e. determining whether Y0 is within a second preset range (e.g. 250 pixels and 550 pixels), if the above conditions are met, determining that the current face is centered, and executing the next action.
In an embodiment, the step S4 of obtaining the coordinates of the forehead of the user in the thermal imaging image based on the coordinates of the forehead of the user in the visible light image and the distance of the user from the visible light camera includes:
acquiring the size of a thermal imaging pixel and the size of a visible light pixel;
acquiring a thermal imaging focal length and a visible light focal length;
calculating an geometric scaling factor based on the thermal imaging focal length, the visible light focal length, the thermal imaging pixel size and the visible light pixel size;
acquiring a coordinate of a central area in a display picture of the temperature measuring equipment;
acquiring the horizontal distance between the visible light camera and the thermal imaging camera;
detecting a horizontal rotation angle, a pitch angle and an inclination angle of the face of the user in the visible light image;
calculating the offset of the visible light image relative to the thermal imaging image based on the horizontal rotation angle, the pitch angle and the tilt angle of the user face, the geometric scaling factor, the centered area coordinate, the horizontal distance, the thermal imaging pixel size, the thermal imaging focal length, the coordinate of the user forehead in the visible light image and the distance from the user to the visible light camera;
calculating the coordinates of the user's forehead in the thermal imaging image based on the offset and the coordinates of the user's forehead in the visible light image.
In this embodiment, since the thermal imaging pixel size and the visible light pixel size are different, and the thermal imaging focal length and the visible light focal length are also different, the proportions of the thermal imaging image and the visible light image in the same user are also different, and therefore, the geometric scaling factor can be calculated based on the thermal imaging focal length, the visible light focal length, the thermal imaging pixel size and the visible light pixel size. Further, the offset of the visible light image relative to the thermal imaging image is calculated, so that the coordinates of the forehead of the user in the thermal imaging image can be calculated according to the offset. For example, the offset is δ, and the forehead of the user has coordinates in the visible light imageThe forehead of the user has coordinates in the thermal imaging image。
In this embodiment, the above formula for calculating the scaling factor is:
wherein k is an equal scaling coefficient,in order to achieve the thermal imaging focal length,the focal length of the visible light is set,for the size of the thermal imaging pixel,is the visible pixel size.
In an embodiment, the calculation formula for calculating the offset of the visible light image relative to the thermal imaging image is as follows:
where δ is the offset and the centered area coordinate is,Is the thermal imaging focal length, D is the horizontal distance, k is the geometric scaling factor, D is the distance of the user from the visible camera,for the size of the thermal imaging pixel, α, θ and Ω are the horizontal rotation angle, the pitch angle and the tilt angle of the user face, respectively, and γ and A, B, C are estimation coefficients, respectively.
In this embodiment, the parameters γ and A, B, C are estimation coefficients calculated by a local scatter smoothing estimation algorithm according to the face size and samples at different distances in advance.
In another embodiment, the step of detecting the coordinates of the forehead of the user in the visible-light image comprises:
inputting the visible light image into a preset forehead detection network model, and detecting to obtain the coordinates of the forehead of the user in the visible light image;
specifically, the training step of the preset forehead detection network model includes:
acquiring a face frame in a training sample;
taking the upper left corner and the upper right corner of the face frame in the training sample as reference points, and acquiring an image of a preset area above the face frame as a forehead key point feature image;
inputting the forehead key point feature image into a convolutional neural network for regression operation, correcting deviation by adopting least square regression, and training on the basis of a gradient descent algorithm and a back propagation algorithm to obtain a global minimum value or a local minimum value of a loss function so as to train to obtain the forehead detection network model; wherein the loss function of the convolutional neural network is a cross entropy loss function.
In another embodiment, the step of detecting the distance from the user to the visible light camera based on the visible light image comprises:
detecting the width of the face of the user in the visible light image;
detecting a horizontal corner of a user face in the visible light image;
calculating the distance between the user and the visible light camera based on the width of the user face in the visible light image and the horizontal rotation angle of the user face in the visible light image;
wherein the calculation formula for calculating the distance from the user to the visible light camera is as follows:
D=λ*(1-βCosα)* W;
d is the distance between the user and the visible light camera, W is the width of the user face in the visible light image, alpha is the horizontal rotation angle of the user face in the visible light image, and beta and lambda are distance conversion coefficients.
In this embodiment, since the face does not necessarily completely face the camera, the face may have a deflection angle (including the above horizontal rotation angle) in the image, and the size of the face deflection angle and the face frame may affect the distance calculation between the face and the visible light camera, the above estimation formula is proposed in this embodiment to calculate the distance from the user to the visible light camera.
In this embodiment, before the step of calculating the distance from the user to the visible light camera based on the width of the user's face in the visible light image and the horizontal rotation angle of the user's face in the visible light image, the method includes:
acquiring a plurality of first sample data; each piece of first sample data comprises a sample distance from a sample face to a visible light camera, a horizontal rotation angle of the sample face in a corresponding visible light image, and a width of the sample face in the corresponding visible light image;
and inputting each first sample data into a preset depth network model for iterative training to obtain the distance conversion coefficient.
In another embodiment, after the step of obtaining the thermal imaging temperature of the coordinate position of the forehead in the thermal imaging image, the method further includes:
detecting whether the user is centered;
if not, acquiring a centering offset value of the user and a centering position;
inputting the centering deviation value into a preset temperature compensation model, and calculating to obtain a temperature compensation value;
and calculating to obtain a final temperature according to the temperature compensation value and the thermal imaging temperature of the coordinate position of the forehead of the user in the thermal imaging image, wherein the final temperature is used as a temperature detection result of the user.
In this embodiment, if the face of the user is not centered in the visible light image, the accuracy of temperature detection may be affected; in order to reduce the temperature detection error, a temperature compensation model is preset in this embodiment, and is used to calculate a corresponding temperature compensation value for the user and the centered position under different centered offset values, and finally the final temperature may be calculated according to the sum of the temperature compensation value and the thermal imaging temperature of the coordinate position where the forehead is located in the thermal imaging image.
In this embodiment, the temperature compensation model is trained based on a convolutional neural network, and the training data includes different centering offset values of the user and the centering position, and corresponding temperature compensation values. In other embodiments, the convolutional neural network can be comprehensively trained by combining the face deflection angle of the user, the centering offset value of the face and the corresponding temperature compensation value, so that a temperature compensation model with better judgment capability can be obtained.
Referring to fig. 2, an embodiment of the present application further provides a temperature detection device based on a visible light image and a thermal imaging image, which is applied to a temperature measurement device, where the temperature measurement device includes a visible light camera and a thermal imaging camera, and the temperature detection device based on the visible light image and the thermal imaging image includes:
the acquisition unit 10 is used for acquiring a visible light image of a user based on the visible light camera and acquiring a thermal imaging image of the user based on the thermal imaging camera;
a first coordinate detecting unit 20, configured to detect a coordinate of the forehead of the user in the visible light image;
a distance detection unit 30 configured to detect a distance from the user to the visible-light camera based on the visible-light image;
a second coordinate detecting unit 40, configured to calculate coordinates of the forehead of the user in the thermal imaging image based on the coordinates of the forehead of the user in the visible light image and a distance from the user to the visible light camera;
and the temperature detection unit 50 is configured to obtain a thermal imaging temperature of a coordinate position where the forehead of the user is located in the thermal imaging image, as a temperature detection result for the user.
In this embodiment, please refer to the above embodiments of the temperature detection method for the specific implementation of each unit in the temperature detection apparatus, which is not described herein again.
Referring to fig. 3, a computer device, which may be a server and whose internal structure may be as shown in fig. 3, is also provided in the embodiment of the present application. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the computer designed processor is used to provide computational and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing temperature detection data and the like. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a temperature detection method.
Those skilled in the art will appreciate that the architecture shown in fig. 3 is only a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects may be applied.
An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements a temperature detection method. It is to be understood that the computer-readable storage medium in the present embodiment may be a volatile-readable storage medium or a non-volatile-readable storage medium.
In summary, the method and the device for detecting temperature based on visible light images and thermal imaging images provided in the embodiments of the present application include acquiring visible light images of a user based on the visible light camera, and acquiring thermal imaging images of the user based on the thermal imaging camera; detecting the coordinates of the forehead of the user in the visible light image; detecting the distance from the user to the visible light camera based on the visible light image; calculating the coordinates of the forehead of the user in the thermal imaging image based on the coordinates of the forehead of the user in the visible light image and the distance of the user from the visible light camera; and acquiring the thermal imaging temperature of the coordinate position of the forehead of the user in the thermal imaging image as a temperature detection result of the user. According to the method and the device, the coordinate of the forehead of the user in the visible light image is converted and calculated to obtain the coordinate of the forehead of the user in the thermal imaging image, and then temperature measurement is carried out, so that the temperature measurement result is more accurate; simultaneously, this application is to carrying out the temperature measurement to the forehead position, also can promote the degree of accuracy of temperature measurement.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium provided herein and used in the examples may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), double-rate SDRAM (SSRSDRAM), Enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, apparatus, article, or method that includes the element.
The above description is only for the preferred embodiment of the present application and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings of the present application, or which are directly or indirectly applied to other related technical fields, are intended to be included within the scope of the present application.
Claims (10)
1. A temperature detection method based on a visible light image and a thermal imaging image is applied to temperature measurement equipment, wherein the temperature measurement equipment comprises a visible light camera and a thermal imaging camera, and the temperature detection method is characterized by comprising the following steps:
collecting a visible light image of a user based on the visible light camera and collecting a thermal imaging image of the user based on the thermal imaging camera;
detecting the coordinates of the forehead of the user in the visible light image;
detecting the distance from the user to the visible light camera based on the visible light image;
calculating the coordinates of the forehead of the user in the thermal imaging image based on the coordinates of the forehead of the user in the visible light image and the distance of the user from the visible light camera;
and acquiring the thermal imaging temperature of the coordinate position of the forehead of the user in the thermal imaging image as a temperature detection result of the user.
2. The method according to claim 1, wherein the step of detecting the coordinates of the forehead of the user in the visible light image further comprises:
detecting a face frame of a user in the visible light image;
detecting the coordinates of the upper left corner and the upper right corner of the face frame, and acquiring the width of the visible light image;
acquiring a first margin between the upper left corner of the face frame and the leftmost side of the visible light image according to the upper left corner coordinate of the face frame;
calculating a second edge distance from the upper right corner of the face frame to the rightmost side of the visible light image according to the width of the visible light image and the upper right corner coordinate of the face frame;
calculating a margin difference value of the first margin and the second margin, and filtering the margin difference value based on a filter to obtain a filtering margin difference value;
judging whether the filtering edge distance difference value is within a first preset range or not, and judging whether a vertical coordinate in an upper left corner coordinate or an upper right corner coordinate of the face frame is within a second preset range or not;
if the filtering edge distance difference value is within a first preset range and the ordinate is within a second preset range, judging that the face of the user is centered;
and if the filtering edge distance difference value is not in a first preset range and/or the ordinate is not in a second preset range, judging that the face of the user is not centered, and sending out prompt information for prompting the user to be centered.
3. The method according to claim 1, wherein the step of obtaining the coordinates of the forehead of the user in the thermal image based on the coordinates of the forehead of the user in the visible light image and the distance from the user to the visible light camera comprises:
acquiring the size of a thermal imaging pixel and the size of a visible light pixel;
acquiring a thermal imaging focal length and a visible light focal length;
calculating an geometric scaling factor based on the thermal imaging focal length, the visible light focal length, the thermal imaging pixel size and the visible light pixel size;
acquiring a coordinate of a central area in a display picture of the temperature measuring equipment;
acquiring the horizontal distance between the visible light camera and the thermal imaging camera;
detecting a horizontal rotation angle, a pitch angle and an inclination angle of the face of the user in the visible light image;
calculating the offset of the visible light image relative to the thermal imaging image based on the horizontal rotation angle, the pitch angle and the tilt angle of the user face, the geometric scaling factor, the centered area coordinate, the horizontal distance, the thermal imaging pixel size, the thermal imaging focal length, the coordinate of the user forehead in the visible light image and the distance from the user to the visible light camera;
calculating the coordinates of the user's forehead in the thermal imaging image based on the offset and the coordinates of the user's forehead in the visible light image.
4. The method according to claim 3, wherein the formula for calculating the scaling coefficient is:
5. The method according to claim 3, wherein the calculation formula for calculating the shift amount of the visible light image relative to the thermal imaging image is:
where δ is the offset and the centered area coordinate is,Is the thermal imaging focal length, D is the horizontal distance, k is the geometric scaling factor, D is the distance of the user from the visible camera,for the size of the thermal imaging pixel, α, θ and Ω are the horizontal rotation angle, the pitch angle and the tilt angle of the user face, respectively, and γ and A, B, C are estimation coefficients, respectively.
6. The method according to claim 1, wherein the step of detecting the coordinates of the forehead of the user in the visible light image comprises:
inputting the visible light image into a preset forehead detection network model, and detecting to obtain the coordinates of the forehead of the user in the visible light image;
wherein the training step of the preset forehead detection network model comprises the following steps:
acquiring a face frame in a training sample;
taking the upper left corner and the upper right corner of the face frame in the training sample as reference points, and acquiring an image of a preset area above the face frame as a forehead key point feature image;
inputting the forehead key point feature image into a convolutional neural network for regression operation, correcting deviation by adopting least square regression, and training on the basis of a gradient descent algorithm and a back propagation algorithm to obtain a global minimum value or a local minimum value of a loss function so as to train to obtain the forehead detection network model; wherein the loss function of the convolutional neural network is a cross entropy loss function.
7. The method according to claim 1, wherein the step of detecting the distance from the user to the visible-light camera based on the visible-light image comprises:
detecting the width of the face of the user in the visible light image;
detecting a horizontal corner of a user face in the visible light image;
calculating the distance between the user and the visible light camera based on the width of the user face in the visible light image and the horizontal rotation angle of the user face in the visible light image;
wherein the calculation formula for calculating the distance from the user to the visible light camera is as follows:
D=λ*(1-βCosα)* W;
d is the distance between the user and the visible light camera, W is the width of the user face in the visible light image, alpha is the horizontal rotation angle of the user face in the visible light image, and beta and lambda are distance conversion coefficients.
8. The method according to claim 7, wherein the step of calculating the distance from the user to the visible light camera based on the width of the user's face in the visible light image and the horizontal rotation angle of the user's face in the visible light image is preceded by the step of:
acquiring a plurality of first sample data; each piece of first sample data comprises a sample distance from a sample face to a visible light camera, a horizontal rotation angle of the sample face in a corresponding visible light image, and a width of the sample face in the corresponding visible light image;
and inputting each first sample data into a preset depth network model for iterative training to obtain the distance conversion coefficient.
9. The utility model provides a temperature-detecting device based on visible light image and thermal imaging image, is applied to temperature measurement equipment on, temperature measurement equipment includes visible light camera and thermal imaging camera, its characterized in that, temperature-detecting device based on visible light image and thermal imaging image includes:
the acquisition unit is used for acquiring a visible light image of a user based on the visible light camera and acquiring a thermal imaging image of the user based on the thermal imaging camera;
a first coordinate detection unit, configured to detect a coordinate of the forehead of the user in the visible light image;
a distance detection unit for detecting a distance from the user to the visible light camera based on the visible light image;
a second coordinate detection unit, configured to calculate coordinates of the forehead of the user in the thermal imaging image based on the coordinates of the forehead of the user in the visible light image and a distance from the user to the visible light camera;
and the temperature detection unit is used for acquiring the thermal imaging temperature of the coordinate position of the forehead of the user in the thermal imaging image as the temperature detection result of the user.
10. A computer device comprising a memory and a processor, the memory having stored therein a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method according to any of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110093688.2A CN112414558B (en) | 2021-01-25 | 2021-01-25 | Temperature detection method and device based on visible light image and thermal imaging image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110093688.2A CN112414558B (en) | 2021-01-25 | 2021-01-25 | Temperature detection method and device based on visible light image and thermal imaging image |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112414558A true CN112414558A (en) | 2021-02-26 |
CN112414558B CN112414558B (en) | 2021-04-23 |
Family
ID=74783215
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110093688.2A Active CN112414558B (en) | 2021-01-25 | 2021-01-25 | Temperature detection method and device based on visible light image and thermal imaging image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112414558B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113008380A (en) * | 2021-03-10 | 2021-06-22 | 五邑大学 | Intelligent AI body temperature early warning method, system and storage medium |
CN113095190A (en) * | 2021-04-01 | 2021-07-09 | 武汉理工大学 | Non-contact temperature measurement and identity recognition system |
CN113269036A (en) * | 2021-04-13 | 2021-08-17 | 杭州魔点科技有限公司 | Method, system, device and storage medium for determining face coordinates on thermal imaging |
CN113297941A (en) * | 2021-05-18 | 2021-08-24 | 宁波书写芯忆科技有限公司 | Remote AI intelligent temperature measurement face recognition system |
CN113701894A (en) * | 2021-08-30 | 2021-11-26 | 深圳科卫机器人科技有限公司 | Face temperature measurement method and device, computer equipment and storage medium |
CN114152349A (en) * | 2021-11-30 | 2022-03-08 | 深圳Tcl新技术有限公司 | Temperature measuring method, temperature measuring device, storage medium and electronic equipment |
CN114960854A (en) * | 2022-08-01 | 2022-08-30 | 深圳市海清视讯科技有限公司 | Hand washing guiding method, device and system based on thermal imaging |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105701827A (en) * | 2016-01-15 | 2016-06-22 | 中林信达(北京)科技信息有限责任公司 | Method and device for jointly calibrating parameters of visible light camera and infrared camera |
CN107976257A (en) * | 2016-10-21 | 2018-05-01 | 杭州海康威视数字技术股份有限公司 | A kind of method for displaying image of infrared thermography, device and infrared thermography |
CN109670422A (en) * | 2018-12-05 | 2019-04-23 | 北京旷视科技有限公司 | Face datection information display method, device, equipment and storage medium |
CN110738142A (en) * | 2019-09-26 | 2020-01-31 | 广州广电卓识智能科技有限公司 | method, system and storage medium for self-adaptively improving face image acquisition |
CN111083381A (en) * | 2019-12-31 | 2020-04-28 | 深圳市道通智能航空技术有限公司 | Image fusion method and device, double-optical camera and unmanned aerial vehicle |
CN111579077A (en) * | 2020-04-08 | 2020-08-25 | 北京遥感设备研究所 | Dual-band image position calibration and information interaction display system and method |
CN112033545A (en) * | 2020-08-17 | 2020-12-04 | 深圳市视美泰技术股份有限公司 | Human body temperature infrared measurement method and device and computer equipment |
CN112241700A (en) * | 2020-10-15 | 2021-01-19 | 希望银蕨智能科技有限公司 | Multi-target forehead temperature measurement method for forehead accurate positioning |
-
2021
- 2021-01-25 CN CN202110093688.2A patent/CN112414558B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105701827A (en) * | 2016-01-15 | 2016-06-22 | 中林信达(北京)科技信息有限责任公司 | Method and device for jointly calibrating parameters of visible light camera and infrared camera |
CN107976257A (en) * | 2016-10-21 | 2018-05-01 | 杭州海康威视数字技术股份有限公司 | A kind of method for displaying image of infrared thermography, device and infrared thermography |
CN109670422A (en) * | 2018-12-05 | 2019-04-23 | 北京旷视科技有限公司 | Face datection information display method, device, equipment and storage medium |
CN110738142A (en) * | 2019-09-26 | 2020-01-31 | 广州广电卓识智能科技有限公司 | method, system and storage medium for self-adaptively improving face image acquisition |
CN111083381A (en) * | 2019-12-31 | 2020-04-28 | 深圳市道通智能航空技术有限公司 | Image fusion method and device, double-optical camera and unmanned aerial vehicle |
CN111579077A (en) * | 2020-04-08 | 2020-08-25 | 北京遥感设备研究所 | Dual-band image position calibration and information interaction display system and method |
CN112033545A (en) * | 2020-08-17 | 2020-12-04 | 深圳市视美泰技术股份有限公司 | Human body temperature infrared measurement method and device and computer equipment |
CN112241700A (en) * | 2020-10-15 | 2021-01-19 | 希望银蕨智能科技有限公司 | Multi-target forehead temperature measurement method for forehead accurate positioning |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113008380A (en) * | 2021-03-10 | 2021-06-22 | 五邑大学 | Intelligent AI body temperature early warning method, system and storage medium |
CN113095190A (en) * | 2021-04-01 | 2021-07-09 | 武汉理工大学 | Non-contact temperature measurement and identity recognition system |
CN113269036A (en) * | 2021-04-13 | 2021-08-17 | 杭州魔点科技有限公司 | Method, system, device and storage medium for determining face coordinates on thermal imaging |
CN113297941A (en) * | 2021-05-18 | 2021-08-24 | 宁波书写芯忆科技有限公司 | Remote AI intelligent temperature measurement face recognition system |
CN113701894A (en) * | 2021-08-30 | 2021-11-26 | 深圳科卫机器人科技有限公司 | Face temperature measurement method and device, computer equipment and storage medium |
CN114152349A (en) * | 2021-11-30 | 2022-03-08 | 深圳Tcl新技术有限公司 | Temperature measuring method, temperature measuring device, storage medium and electronic equipment |
CN114152349B (en) * | 2021-11-30 | 2023-11-14 | 深圳Tcl新技术有限公司 | Temperature measurement method and device, storage medium and electronic equipment |
CN114960854A (en) * | 2022-08-01 | 2022-08-30 | 深圳市海清视讯科技有限公司 | Hand washing guiding method, device and system based on thermal imaging |
CN114960854B (en) * | 2022-08-01 | 2023-01-06 | 深圳市海清视讯科技有限公司 | Hand washing guiding method, device and system based on thermal imaging |
Also Published As
Publication number | Publication date |
---|---|
CN112414558B (en) | 2021-04-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112414558B (en) | Temperature detection method and device based on visible light image and thermal imaging image | |
CN111964789B (en) | Temperature measuring method, temperature measuring device, computer equipment and storage medium | |
WO2019184885A1 (en) | Method, apparatus and electronic device for calibrating extrinsic parameters of camera | |
CN110211185B (en) | Method for identifying characteristic points of calibration pattern in group of candidate points | |
WO2022121189A1 (en) | Method and apparatus for measuring temperature, and computer device | |
CN103180690B (en) | Pattern assay method, pattern determinator and utilize its program | |
JP6444283B2 (en) | Posture determination device | |
CN116433737A (en) | Method and device for registering laser radar point cloud and image and intelligent terminal | |
CN111144398A (en) | Target detection method, target detection device, computer equipment and storage medium | |
US20220015644A1 (en) | Fever Detector by Distant Multipixel Thermal Imaging | |
CN110542482B (en) | Blind pixel detection method and device and electronic equipment | |
CN113749646A (en) | Monocular vision-based human body height measuring method and device and electronic equipment | |
CN105551042A (en) | Determination method and apparatus for mark point positions of scanning bed | |
CN112215878B (en) | X-ray image registration method based on SURF feature points | |
JP2008116206A (en) | Apparatus, method, and program for pattern size measurement | |
CN111160442B (en) | Image classification method, computer device, and storage medium | |
CN109902695B (en) | Line feature correction and purification method for image pair linear feature matching | |
CN116797648A (en) | Width measuring method, device, equipment, system and medium for material deformation process | |
CN108416811B (en) | Camera self-calibration method and device | |
CN113808108A (en) | Visual inspection method and system for defects of printed film | |
JP2004220371A (en) | Image processing method, image processor, image processing program, and recording medium recorded with image processing program | |
CN113269036A (en) | Method, system, device and storage medium for determining face coordinates on thermal imaging | |
CN112770041A (en) | Image processing method for switching multiple zoom lenses and camera | |
CN112798812B (en) | Target speed measuring method based on monocular vision | |
CN110658618A (en) | Method and device for fitting and focusing sample image, computer equipment and storage medium |
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 |