CN113449567A - Face temperature detection method and device, electronic equipment and storage medium - Google Patents
Face temperature detection method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113449567A CN113449567A CN202010229946.0A CN202010229946A CN113449567A CN 113449567 A CN113449567 A CN 113449567A CN 202010229946 A CN202010229946 A CN 202010229946A CN 113449567 A CN113449567 A CN 113449567A
- Authority
- CN
- China
- Prior art keywords
- face
- sample set
- trained
- detection model
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 204
- 238000012549 training Methods 0.000 claims abstract description 94
- 238000000034 method Methods 0.000 claims abstract description 50
- 238000000605 extraction Methods 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 9
- 230000036760 body temperature Effects 0.000 abstract description 16
- 206010005908 Body temperature conditions Diseases 0.000 abstract description 4
- 238000012360 testing method Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 10
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000009529 body temperature measurement Methods 0.000 description 3
- 238000001931 thermography Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000005484 gravity Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000013138 pruning Methods 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012634 optical imaging Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/0022—Radiation pyrometry, e.g. infrared or optical thermometry for sensing the radiation of moving bodies
- G01J5/0025—Living bodies
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G01J2005/0077—Imaging
Abstract
The invention provides a face temperature detection method, a face temperature detection device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring a face image to be recognized, wherein the face image to be recognized comprises a face infrared heat map; inputting the face image to be recognized into a pre-trained face temperature detection model for recognition to obtain face identity information and face temperature information corresponding to the face image to be recognized; the pre-trained face temperature detection model is obtained by training a pre-trained face detection model according to a face sample set, wherein the face sample set comprises face infrared thermal image samples. Therefore, the identity recognition and body temperature test of the target personnel can be directly completed by collecting the face infrared heat map in the face image of the target personnel, and the body temperature condition of the target personnel can be monitored and managed conveniently. And then reduced the human cost and improved temperature detection work efficiency.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a face temperature detection method and device, electronic equipment and a storage medium.
Background
At present, when the body temperature of corresponding target personnel needs to be monitored and managed, when the body temperature of the target personnel needs to be measured in scenes such as hospitals, communities, schools and the like, intelligent identification of the body temperature cannot be achieved, and only relevant workers can be dispatched to measure the temperature of each target personnel and inquire and register relevant identity information.
Disclosure of Invention
The embodiment of the invention provides a face temperature detection method, which can finish identity recognition and body temperature detection of target personnel by using an infrared chart and can improve the working efficiency.
In a first aspect, an embodiment of the present invention provides a face temperature detection method, including the following steps:
acquiring a face image to be recognized, wherein the face image to be recognized comprises a face infrared heat map;
inputting the face image to be recognized into a pre-trained face temperature detection model for recognition to obtain face identity information and face temperature information corresponding to the face image to be recognized;
the pre-trained face temperature detection model is obtained by training a pre-trained face detection model according to a face sample set, wherein the face sample set comprises face infrared thermal image samples.
Optionally, the face sample set further includes a first face RGB image sample, and the training method of the pre-trained face temperature detection model includes:
acquiring the face sample set;
acquiring a pre-trained face detection model;
inputting the face sample set into a pre-trained face detection model to train the pre-trained face detection model, and reducing the input weight of the first face RGB image sample in the training process, so that the pre-trained face detection model learns the prediction of face temperature information according to the face infrared heat image sample to obtain the pre-trained face temperature detection model.
Optionally, the inputting the face sample set into a pre-trained face detection model to train the pre-trained face detection model, and reducing the input weight of the first face RGB image sample in the training process includes:
carrying out branch reduction processing on the pre-trained face detection model so as to enable the pre-trained face detection model to adapt to single-channel input of the face infrared thermograph sample;
and inputting the face sample set into the pre-trained face detection model after the branch subtraction for training, and reducing the input weight of the first face RGB image sample to zero in the training process.
Optionally, the acquiring the face sample set includes:
acquiring a first face RGB image sample set, wherein the first face RGB image sample set comprises a first face identity label;
acquiring a face infrared heat map sample set, wherein the face infrared heat map sample comprises a face temperature label;
and forming the face sample set according to the first face RGB image sample set and the face infrared heat image sample set.
Optionally, the acquiring the first face RGB pattern book set includes:
acquiring a plurality of first face RGB images;
inputting the plurality of first face RGB images into a face RGB primary feature extraction model to extract primary features of the face RGB images so as to obtain a plurality of first face RGB image primary features;
and obtaining the first face RGB map sample set based on the plurality of first face RGB map primary features.
Optionally, the acquiring a face infrared heat map sample set includes:
acquiring a plurality of face infrared heat maps;
inputting the plurality of face infrared heat maps into a face infrared heat map primary feature extraction model to extract face infrared heat map primary features so as to obtain a plurality of face infrared heat map primary features;
and obtaining the face infrared heat image sample set based on the primary features of the face infrared heat images.
Optionally, the obtaining of the pre-trained face detection model includes:
acquiring a second face RGB image sample set, wherein the second face RGB image sample set comprises a second face identity label;
and inputting the second face RGB pattern sample set into a pre-training model for training, so that the pre-training model learns the prediction of face identity information according to the second face RGB pattern sample set to obtain the pre-trained face detection model.
In a second aspect, an embodiment of the present invention further provides a face temperature detection apparatus, where the apparatus includes:
the system comprises an acquisition module, a recognition module and a processing module, wherein the acquisition module is used for acquiring a face image to be recognized, and the face image to be recognized comprises a face infrared heat map;
the recognition module is used for inputting the face image to be recognized into a pre-trained face temperature detection model for recognition to obtain face identity information and face temperature information corresponding to the face image to be recognized;
the pre-trained face temperature detection model is obtained by training a pre-trained face detection model according to a face sample set, wherein the face sample set comprises face infrared thermal image samples.
In a third aspect, an embodiment of the present invention provides an electronic device, including: the human face temperature detection method comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the computer program to realize the steps in the human face temperature detection method provided by the embodiment of the invention.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements the steps in the face temperature detection method provided in the embodiment of the present invention.
In the embodiment of the invention, a face image to be recognized is acquired, wherein the face image to be recognized comprises a face infrared heat map; inputting the face image to be recognized into a pre-trained face temperature detection model for recognition to obtain face identity information and face temperature information corresponding to the face image to be recognized; the pre-trained face temperature detection model is obtained by training a pre-trained face detection model according to a face sample set, wherein the face sample set comprises face infrared thermal image samples. Therefore, the identity recognition and body temperature test of the target personnel can be directly completed by collecting the face infrared heat map in the face image of the target personnel, and the body temperature condition of the target personnel can be monitored and managed conveniently. And then solve among the prior art, can not accomplish the intelligent recognition of body temperature, can only dispatch relevant staff and carry out the temperature measurement and inquire identity information and register for every target person, and the human cost that leads to is high, the problem that temperature detection work efficiency is low. And then reduced the human cost and improved temperature detection work efficiency.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art 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 of a face temperature detection method according to an embodiment of the present invention;
FIG. 2 is a flowchart of a training method of a face temperature detection model according to an embodiment of the present invention;
FIG. 3 is a flow chart of a method provided in step 201 of the embodiment of FIG. 2;
FIG. 4 is a flow chart of one method provided in step 202 of the embodiment of FIG. 2;
FIG. 5 is a flow chart of a method provided in step 203 of the embodiment of FIG. 2;
FIG. 6 is a schematic diagram of an infrared thermographic model inspection provided by an embodiment of the present invention;
fig. 7 is a schematic structural diagram of a face temperature detection apparatus according to an embodiment of the present invention;
FIG. 8 is a schematic diagram of another structure provided by the training module according to the embodiment of the present invention;
FIG. 9 is a schematic diagram of a structure provided by the training submodule in the embodiment of FIG. 8;
FIG. 10 is a schematic diagram of a structure provided by the first obtaining submodule in the embodiment of FIG. 8;
FIG. 11 is a schematic diagram of a structure provided by the second obtaining submodule in the embodiment of FIG. 8;
fig. 12 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, fig. 1 is a flowchart of a face temperature detection method according to an embodiment of the present invention, as shown in fig. 1, including the following steps:
The face image to be recognized is a face image of a target person to be recognized in an application scene. The application scenario may be a certain hospital, a certain cell, a certain campus, a certain unit, or the like, or other application scenarios requiring the body temperature of the target person to be detected. More specifically, the system may be used in an entrance guard system of a hospital, a community, a campus, an entrance or exit of a unit, etc. In this embodiment, an access control system of an entrance of an application scene in which body temperature needs to be detected is mainly taken as an example for description. The face image to be recognized may be a face image of a target person entering or exiting a cell, a campus, an entrance or an exit of a unit. The face image to be recognized comprises a face infrared heat image, and the face infrared heat image can be called an infrared heat image. The target person may be one or more. The number of the face images to be recognized can be one or more, and when the number of the target persons is multiple, the number of the corresponding face images to be recognized is multiple. The corresponding human face infrared heat maps are also multiple.
The human face infrared heat map can be acquired by an infrared heat map imaging device. The human face infrared thermography imaging device can be an infrared thermography and the like. The human face infrared thermal image can be acquired by aligning an infrared thermal imager at an entrance or an exit of a unit in a district, a campus or a hospital to the human face of a target person, and is used for detecting the human face temperature of the target person and further detecting the body temperature of the target person. The infrared thermal imager can also be called as a thermal infrared imager, and the thermal infrared imager receives an infrared radiation energy distribution pattern of a detected object by using an infrared detector and an optical imaging objective lens and reflects the infrared radiation energy distribution pattern onto a photosensitive element of the infrared detector so as to obtain an infrared thermal image, wherein the thermal image corresponds to a thermal distribution field on the surface of an object.
The face image to be recognized may further include a face R (red) G (green) B (blue) image, which is used to recognize face identity information of the target person. The face RGB image may be a still image or a dynamic video image frame of a face of a target person acquired by a face image acquisition device (a camera or the like) deployed at a cell portal, a campus portal, or a unit portal. Of course, the camera may be a face camera, a portrait camera, or a common RGB image camera.
It should be understood that the thermal infrared imager and the face camera are arranged on the same horizontal line, for example, on the same horizontal line, on the left, on the right, and on the same horizontal line, on the lower, on the right, on the same horizontal line. Therefore, the human faces of the target people aligned by the infrared thermal imaging camera and the human face angles of the target people corresponding to the human face camera can be basically consistent. And further ensuring that the target person aligned by the infrared thermal imager and the target person aligned by the face camera are the same person.
Specifically, when a target person needs to enter and exit the entrance guard, the target person is aligned through the infrared thermal imager, the human face infrared thermal image corresponding to the target person is collected, and then the human face image to be recognized of the target person is obtained. Certainly, the target person can be aligned through the face camera, the RGB images of the target person are collected, and then the face image to be recognized is formed with the face infrared thermal image.
The pre-trained face temperature detection model is obtained by training a pre-trained face detection model according to a face sample set, wherein the face sample set comprises face infrared heat image samples.
The pre-trained face temperature detection model is used for detecting the face temperature of the target person, and then the body temperature of the target person is detected. The face temperature detection model can be a face temperature detection neural network, a face temperature detection convolutional network and the like.
The face identity information is face identity information of a target person corresponding to the face image to be recognized. The face identity information can be information including name, face image, certificate number, contact information, family address, work unit, physical condition and the like. The face identity information may be stored in an identity database. The identity database may be a database provided by an authoritative institution or organization for storing the face identity information of the target person. The identity database may store face identity information for a plurality of persons.
The face temperature information may be face temperature information of a target person corresponding to the face image to be recognized, and the corresponding face temperature information may be body temperature information of the target person corresponding to the face image to be recognized. The face temperature information may include the temperature, the time for measuring the temperature, etc., for example, the temperature detected by person a at 12 o' clock is 36.1C.
The face sample set is a face sample set composed of face samples used for training a pre-trained face detection model. The face sample set may include a face infrared heat map sample and may also include a first face RGB map sample. The face sample set may be stored in a local preset face sample set database, or stored in an external memory, such as a usb disk. Therefore, when the face sample set is used, the face sample set can be directly called from a local preset face sample set database or from an external memory. The face sample sets in the remote face sample set database may also be invoked remotely via a network link. The face sample set includes a plurality of face samples, and specifically, may include a plurality of face infrared heat map samples of persons, and may further include a plurality of first face RGB map samples of persons. Of course, the first face RGB image sample here is a face RGB image sample used for being used as an input of a pre-trained face detection model together with the face infrared heat image sample to train the pre-trained face detection model to obtain the face temperature detection model. Certainly, the pre-trained face temperature detection model can be obtained by training the pre-trained face detection model only by taking the face infrared thermal image as the input of the pre-trained face detection model without taking the first face RGB pattern as the input of the pre-trained face detection model. It should be noted that the pre-trained face detection model may be a pre-trained face detection neural network or a convolutional network.
Specifically, after the face image to be recognized is acquired, the acquired face image to be recognized can be used as input data of a pre-trained face temperature detection model, and the face identity information of the target person corresponding to the face image to be recognized is recognized and the face temperature information of the target person corresponding to the face image to be recognized is detected through the pre-trained face temperature detection model. More specifically, the human face infrared chart is used as input data of a pre-trained human face temperature detection model, then the human face infrared chart is subjected to human face detection through the pre-trained human face temperature detection model, and corresponding human face temperature is given. Thus, when a target person goes in and out of an entrance of a cell, a campus, a unit and the like, the face identity information of the target person and the body temperature corresponding to the target person can be identified. Certainly, when the face image to be recognized includes images of a plurality of persons, the images of the plurality of persons are input into a pre-trained face temperature detection model for face detection and corresponding temperatures are given, so that a plurality of groups of face identity information and face temperature information corresponding to the plurality of persons can be obtained.
In an embodiment of the present invention, the identified face identity information and face temperature information may be analyzed, and when a target person with abnormal face temperature is detected, an alarm may be issued. Therefore, the system can remind the workers of the relevant working units to take corresponding management measures and carry out special monitoring management on the abnormal temperature workers.
In the embodiment of the invention, the human face image to be recognized is acquired and comprises a human face infrared heat map; inputting the face image to be recognized into a pre-trained face temperature detection model for recognition to obtain face identity information and face temperature information corresponding to the face image to be recognized; the pre-trained face temperature detection model is obtained by training a pre-trained face detection model according to a face sample set, wherein the face sample set comprises face infrared thermal image samples. Therefore, the identity recognition and body temperature test of the target personnel can be directly completed by collecting the face infrared heat map in the face image of the target personnel, and the body temperature condition of the target personnel can be monitored and managed conveniently. And then solve among the prior art, can not accomplish the intelligent recognition of body temperature, can only dispatch relevant staff and carry out the temperature measurement and inquire identity information and register for every target person, and the human cost that leads to is high, the problem that temperature detection work efficiency is low. And then reduced the human cost and improved temperature detection work efficiency.
Referring to fig. 2, fig. 2 is a flowchart of a training method of a face temperature detection model according to an embodiment of the present invention, where the training method of the face temperature detection model includes the steps of:
Specifically, referring to fig. 3, fig. 3 is a flowchart of a method provided in step 201 in the embodiment of fig. 2, where step 201 includes:
and 301, acquiring a first face RGB image sample set.
The first face RGB map sample set may include a plurality of first face RGB map samples, and each first face RGB map sample includes a first face identity tag. The first face identity tag may be a tag used to represent face identity information of a target person corresponding to the first face RGB pattern. The first face identity label can be a name, a certificate number, a face feature and the like. The first face RGB image sample set may be stored in a preset face RGB pattern database, or may be acquired in real time by a corresponding face RGB image acquisition device. The first face RGB map all correspondingly contains a unique first face identity tag.
Specifically, a plurality of first face RGB maps are acquired. And inputting the plurality of first face RGB images into a face RGB primary feature extraction model to extract primary features of the face RGB images so as to obtain a plurality of primary features of the first face RGB images. And obtaining a first face RGB map sample set based on the primary features of the plurality of first face RGB maps.
More specifically, first face RGB maps corresponding to a plurality of target persons may be obtained, and the primary features of the first face RGB maps of each first face RGB map may be extracted through a face RGB primary feature extraction model, stored, and formed into a first face RGB map sample set based on the primary features of the first face RGB maps corresponding to the plurality of target persons. Therefore, when model training is carried out, the primary features of the first face RGB image can be directly used for training, the whole first face RGB image input model does not need to be trained, and the input data volume of the first face RGB image can be reduced. Therefore, the primary feature extraction model of the face RGB image can improve the dependence of the model on the face RGB image.
The face infrared heat map sample set may include a plurality of face infrared heat map samples, and each face infrared heat map sample includes a face temperature tag. The face temperature label may be a label used for representing face temperature information of a target person corresponding to the face infrared thermal image. The face temperature label may be a degree of temperature. The face infrared heat map sample set can be stored in a preset face infrared heat map sample database or acquired in real time through face infrared heat map acquisition equipment.
Specifically, a plurality of face infrared heat maps are acquired. And inputting the plurality of face infrared heat maps into a face infrared heat map primary feature extraction model to extract primary features of the face infrared heat maps so as to obtain a plurality of face infrared heat map primary features. And obtaining a face infrared heat image sample set based on the primary features of the face infrared heat images.
More specifically, a face infrared heat map sample set can be formed by acquiring face infrared heat maps corresponding to a plurality of target people, extracting and storing a face infrared heat map primary feature of each face infrared heat map through a face infrared heat map primary feature extraction model, and forming the face infrared heat map sample set based on the face infrared heat map primary features corresponding to the plurality of target people. Therefore, when model training is carried out, the primary features of the face infrared chart can be directly used for training, the whole face infrared chart is not required to be input into a model for training, and the input data volume of the face infrared chart can be reduced. The human face infrared heat image primary feature extraction model can improve the dependence of the model on the human face infrared heat image. And primary feature dimensions of the first face RGB image and the face infrared heat image can be ensured to be consistent.
And 303, forming a face sample set according to the first face RGB image sample set and the face infrared heat image sample set.
Specifically, after a first face RGB image sample set and a face infrared heat image sample set are acquired respectively, the two sample sets jointly form a face sample set.
The human face infrared heat map has certain similarity with the human face RGB map in characteristic representation, such as contour and the like.
Specifically, referring to fig. 4, fig. 4 is a flowchart of a method provided in step 202 in the embodiment of fig. 2, where step 202 includes:
And step 402, inputting the second face RGB pattern sample set into a pre-training model for training, so that the pre-training model learns the prediction of the face identity information according to the second face RGB pattern sample set to obtain a pre-trained face detection model.
The second face RGB map sample set may include a plurality of second face RGB map samples, and each second face RGB map sample includes a second face identity tag. The second face identity tag may be a tag used to represent face identity information of a target person corresponding to the second face RGB pattern. The second face identity label can be a name, a certificate number, face features and the like. The second face RGB image sample set may be stored in a preset face RGB pattern database, or may be acquired in real time by a corresponding face RGB image acquisition device. The second face RGB image is one-to-one correspondence including a unique second face identity tag.
The second face RGB map sample set may be the same as or different from the first face RGB map sample set. The second face RGB pattern book set may also include face RGB samples of a plurality of people.
The pre-training model may be a preset model that has not been trained. The pre-trained model may be a pre-trained neural network or a convolutional network. The pre-trained model is not able to recognize or detect any information when the pre-trained model has not been trained. The convolution kernel of the pre-trained model may be a convolution kernel set to 3 x 3.
Specifically, after the second face RGB image sample set is obtained, the face recognition training is performed by inputting the second face RGB image sample set into the pre-training model, so that the pre-training model can learn the prediction of the face identity information according to the second face RGB image sample set, and thus the pre-training model is trained as the face detection model.
It should be understood that when the second face RGB image sample set is different from the first face RGB image sample set, it means that the pre-trained face detection model is only obtained by training the second face RGB pattern sample set.
When the second face RGB image sample set is the same as the first face RGB image sample set, it can also be described that the pre-trained face detection model is obtained by training the first face RGB pattern sample set.
Wherein, the input weight of the first face RGB image sample is a ratio of the first face RGB image sample in the face sample set, and may be represented as a first face RGB pattern sample number/a face sample lump sample number, when the face sample set only includes the first face RGB pattern sample and the human infrared heatmap sample, the input weight of the first face RGB image sample may be represented as a first face RGB pattern sample number/(face infrared heatmap sample number + first face RGB pattern sample number), for example, when there is a face sample set, the face sample set has 100 face samples, wherein there are 40 first face RGB pattern samples and 60 human infrared heatmap samples, then 100 face samples in the face sample set are trained as a pre-trained face detection model, at this time, the input weight of the first face RGB image sample is 40/100, the input weight of the first face RGB is also 2/5. The input weight may also be represented by a weight coefficient.
The above-mentioned reducing the input weight of the first face RGB image sample in the training process may be that, when a face sample set is input into a face detection model trained in advance for training, that is, in the iteration process, the specific gravity of the first face RGB image sample in the face sample set is continuously reduced by using a preset reduction value as a reduction unit.
Specifically, referring to fig. 5, fig. 5 is a flowchart of a method provided in step 203 of the embodiment of fig. 2, where step 203 includes:
For example, the pre-trained face detection model includes a convolution kernel of 3 × 3, and the convolution kernel of 3 × 3 is reduced in dimension to become a convolution network of 3 × 1.
Specifically, the first face RGB image in the first face RGB image sample is three channels, which are an R channel, a G channel, and a B channel. For this purpose, the pre-trained face detection model may be a convolution kernel of 3 × 3, and each layer of convolution kernel is convolved with the R channel, the G channel, and the B channel, respectively. And the infrared heat map is a single channel, so in order to better retain the parameters of the pre-trained model and reduce the size of the model, the pre-trained face detection model is subjected to a pruning (dimension reduction) process, and 2/3 is deleted to share a smaller channel so as to adapt to the single-channel face infrared heat map, for example, a 3 × 3 convolution kernel is reduced in dimension and then changed into a 3 × 1 convolution kernel so as to adapt to the single channel of the convolution face infrared heat map. In the branch reduction process, the gradient size corresponding to each convolution kernel is counted according to back propagation, and then the convolution kernel with the smaller gradient 2/3 is deleted. Because infrared heatmaps provide less information than RGB maps and the model size becomes correspondingly smaller.
Specifically, after the pre-trained face detection model is subjected to the branch subtraction processing, the pre-trained face detection model is trained, and the input weight of the first face RGB image sample is reduced. And (4) until the input weight of the first face RGB image sample is reduced to zero, and further obtaining a face temperature detection model.
The above-mentioned reducing the input weight of the first face RGB image sample to zero in the training process may be that, when the first face sample set is input into a pre-trained face detection model for training, that is, the specific gravity of the first face RGB image sample in the face sample set is continuously reduced by using a preset reduction value as a reduction unit in an iteration process until the input weight of the first face RGB image sample is reduced to zero, so that only an infrared chart exists in the face sample set, and after the pre-trained face detection model is converted into a face temperature detection model, the face identity information and face temperature information corresponding to the infrared chart of the face can be identified through the face temperature detection model. Specifically, a preset reduction value is preset, the input weight of the first face RGB image sample is reduced by using the preset reduction value as a unit until the input weight of the first face RGB image sample is reduced to zero, and thus the training of the face temperature detection model can be finished.
Illustratively, the preset reduction value is set to 1/10, the input weight of the first face RGB pattern and the face infrared chart sample when being input into the pre-trained face detection model for training is 1/2, the input weight of the face infrared chart at this time is also 1/2, and the pre-trained face detection model outputs corresponding face identity information and face temperature information at this time. When the first face RGB pattern and the face infrared heat image sample are input into a pre-trained face detection model for training for the second time, the input weight of the first face RGB pattern sample is reduced to 4/10 on the basis of the first input weight by taking a preset reduction value of 1/10 as a unit, the input weight of the face infrared heat image is also 6/10, and the pre-trained face detection model outputs corresponding face identity information and face temperature information.
And when the first face RGB pattern and the face infrared heat image sample are input into a pre-trained face detection model for training, reducing the input weight of the first face RGB pattern sample to 3/10 on the basis of the second input weight by taking a preset reduction value of 1/10 as a unit, wherein the input weight of the face infrared heat image is also 7/10, and the pre-trained face detection model outputs corresponding face identity information and face temperature information.
After N times of training (N is an integer larger than 3), the input weight of the first face RGB pattern and the face infrared chart sample at the last time are input into a pre-trained face detection model for identification and detection is 0, at the moment, the input weight of the face infrared chart sample in the face sample set is changed into 1, namely, the face samples in the face sample set are all face infrared charts, and the first face RGB sample does not exist in the face sample set. Under the condition that the first face RGB image sample does not exist in the face sample set, the pre-trained face detection model can also identify face identity information and face temperature information corresponding to the corresponding face infrared chart through the face infrared chart sample. When the input weight of the first face RGB image sample is reduced to zero, the pre-trained face detection model is trained as a face temperature detection model, and the face temperature detection model can recognize face identity information and face temperature information corresponding to the face infrared chart only through the face infrared chart sample.
It should be noted that the smaller the preset reduction value is, the slower the input weight of the first face RGB image sample is reduced, the more training times of the pre-trained face detection model will be, the more accurately the parameters of the pre-trained face detection model can be adjusted to the model size, and the better face temperature detection model can be obtained.
Referring to fig. 6, fig. 6 is a schematic diagram of an infrared thermograph model detection provided in an embodiment of the present invention, and a specific engineering process is to initially train a pre-trained face detection model using a common RGB image and an infrared thermograph as input, and provide identity information and temperature information corresponding to each face. The weight of the RGB image is gradually reduced in the training process, the weight of the RGB input is reduced to 0 after the training is finished, and the functions of identity recognition and temperature detection of target personnel can be finished only by the infrared chart.
In order to improve the performance of the network, the RGB image and the infrared heat map are not simply superposed, primary features of the two images are extracted by respectively designing two small convolutional network modules, and the primary feature extraction module can improve the dependence of the network on the RGB image and ensure the feature dimensions of the two images to be consistent. In the training process, the contribution of the RGB image to the network is controlled by adjusting the weight coefficient, and the training weight coefficient is reduced to 0.
In an embodiment of the present invention, when the first face RGB image sample set is different from the second face RGB image sample set, the pre-training model is trained through the second face RGB image sample set to obtain the face detection model, so that the face detection model can recognize corresponding face identity information based on the second face RGB image. And then, the first face RGB image sample set and the face infrared chart are jointly used as the input of a pre-trained face detection model to perform face recognition and temperature detection training on the pre-trained face detection model, and then the pre-trained face detection model is trained into a face temperature detection model. The input weight of the first face RGB image sample is continuously reduced in the training process of the face temperature detection model, corresponding face identity information and face temperature information are given, and then the face temperature detection model can identify the corresponding face identity information and face temperature information only according to the face infrared heat map. The detection capability of the face temperature detection model is improved.
In another embodiment of the present invention, when the first face RGB image sample set is the same as the second face RGB image sample set, the pre-training model is trained through the first face RGB image sample set to obtain a face detection model, and then the pre-training face detection model is subjected to face recognition and temperature detection training by using the first face RGB image sample set and the face infrared chart as the input of the pre-training face detection model, so that the pre-training face detection model is trained as a face temperature detection model. The input weight of the first face RGB image sample is continuously reduced in the training process of the face temperature detection model, corresponding face identity information and face temperature information are given, and then the face temperature detection model can identify the corresponding face identity information and face temperature information only according to the face infrared heat map. The detection capability of the face temperature detection model is improved.
In the embodiment of the invention, the face sample set is used for training the pre-trained face detection model in advance so that the pre-trained face detection model learns the identity information of the recognized face and the temperature information of the detected face according to the face sample set, and thus, the face temperature detection model can be directly used for carrying out identity recognition and temperature detection on the face image to be recognized through the face infrared chart. The body temperature condition of the management target personnel is convenient to monitor. And then solve among the prior art, can not accomplish the intelligent recognition of body temperature, can only dispatch relevant staff and carry out the temperature measurement and inquire identity information and register for every target person, and the human cost that leads to is high, the problem that temperature detection work efficiency is low. And then reduced the human cost and improved temperature detection work efficiency.
Referring to fig. 7, fig. 7 is a schematic structural diagram of a face temperature detection apparatus according to an embodiment of the present invention, and as shown in fig. 7, the face temperature detection apparatus 600 includes:
the acquisition module 601 is configured to acquire a face image to be recognized, where the face image to be recognized includes a face infrared thermal image;
the recognition module 602 is configured to input a face image to be recognized into a pre-trained face temperature detection model for recognition, so as to obtain face identity information and face temperature information corresponding to the face image to be recognized;
the pre-trained face temperature detection model is obtained by training a pre-trained face detection model according to a face sample set, wherein the face sample set comprises face infrared heat image samples.
Optionally, as shown in fig. 8, the face sample set further includes a first face RGB image sample, and the training module 603 includes:
a first obtaining sub-module 6031, configured to obtain a face sample set;
a second obtaining submodule 6032, configured to obtain a pre-trained face detection model;
the training sub-module 6033 is configured to input the face sample set into a pre-trained face detection model to train the pre-trained face detection model, and reduce the input weight of the first face RGB image sample in the training process, so that the pre-trained face detection model learns prediction of face temperature information according to the face infrared chart sample to obtain the pre-trained face temperature detection model.
Optionally, as shown in fig. 9, the training submodule 6033 includes:
a branch-reducing processing unit 60331, configured to perform branch-reducing processing on the pre-trained face detection model, so that the pre-trained face detection model adapts to single-channel input of a face infrared thermograph sample;
the first training unit 60332 is configured to input the face sample set to the pre-trained face detection model after the branch subtraction for training, and reduce the input weight of the first face RGB image sample to zero in the training process.
Optionally, as shown in fig. 10, the first obtaining sub-module 6031 includes:
a first obtaining unit 60311, configured to obtain a first face RGB image sample set, where the first face RGB image sample set includes a first face identity label;
a second obtaining unit 60312, configured to obtain a face infrared thermal image sample set, where the face infrared thermal image sample includes a face temperature tag;
a forming unit 60313 for forming a face sample set from the first face RGB image sample set and the face infrared heat map sample set.
Optionally, the first obtaining unit includes:
the first acquisition subunit is used for acquiring a plurality of first face RGB images;
the first extraction subunit is used for inputting the plurality of first face RGB images into a face RGB primary feature extraction model to carry out face RGB image primary feature extraction so as to obtain a plurality of first face RGB image primary features;
the first forming subunit is used for forming a first face RGB image sample set based on the primary features of the plurality of first face RGB images.
Optionally, the second obtaining unit includes:
the second acquisition subunit is used for acquiring a plurality of face infrared heat maps;
the second extraction subunit is used for inputting the plurality of face infrared heat maps into a face infrared heat map primary feature extraction model to extract the face infrared heat map primary features so as to obtain a plurality of face infrared heat map primary features;
the second forming subunit forms a face infrared heat map sample set based on the plurality of face infrared heat map primary features.
Optionally, as shown in fig. 11, the second obtaining sub-module 6032 includes:
a third obtaining unit 60321, configured to obtain a second face RGB image sample set, where the second face RGB image sample set includes a second face identity tag;
the second training unit 60322 is configured to input the second face RGB pattern sample set into the pre-training model for training, so that the pre-training model learns the prediction of the face identity information according to the second face RGB pattern sample set to obtain a pre-trained face detection model.
It should be noted that the face temperature detection apparatus 600 provided in the embodiment of the present invention may be applied to a mobile phone, a monitor, a computer, a server, and other devices that need to perform face temperature detection.
The face temperature detection device 600 provided by the embodiment of the invention can realize each process realized by the face temperature detection method in the method embodiment, and can achieve the same beneficial effects. To avoid repetition, further description is omitted here.
Referring to fig. 12, fig. 12 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, as shown in fig. 12, including: a memory 702, a processor 701, and a computer program stored on the memory 702 and executable on the processor 701, wherein:
the processor 701 is configured to call the computer program stored in the memory 702, and perform the following steps:
acquiring a face image to be recognized, wherein the face image to be recognized comprises a face infrared heat map;
inputting a face image to be recognized into a face temperature detection model trained in advance for recognition, and obtaining face identity information and face temperature information corresponding to the face image to be recognized;
the pre-trained face temperature detection model is obtained by training a pre-trained face detection model according to a face sample set, wherein the face sample set comprises face infrared heat image samples.
Optionally, the face sample set further includes a first face RGB image sample, and the training method of the pre-trained face temperature detection model executed by the processor 701 includes:
acquiring a face sample set;
acquiring a pre-trained face detection model;
inputting the face sample set into a pre-trained face detection model to train the pre-trained face detection model, and reducing the input weight of the first face RGB image sample in the training process, so that the pre-trained face detection model learns the prediction of face temperature information according to the face infrared chart sample to obtain the pre-trained face temperature detection model.
Optionally, the inputting, by the processor 701, the face sample set into the pre-trained face detection model to train the pre-trained face detection model, and reducing the input weight of the first face RGB image sample in the training process includes:
carrying out branch reduction processing on a pre-trained face detection model so as to enable the pre-trained face detection model to adapt to single-channel input of a face infrared thermograph sample;
and inputting the face sample set into a pre-trained face detection model after the branch subtraction for training, and reducing the input weight of the first face RGB image sample to zero in the training process.
Optionally, the obtaining of the face sample set by the processor 701 includes:
acquiring a first face RGB image sample set, wherein the first face RGB image sample set comprises a first face identity label;
acquiring a face infrared heat map sample set, wherein the face infrared heat map sample comprises a face temperature label;
and forming a face sample set according to the first face RGB image sample set and the face infrared heat image sample set.
Optionally, the acquiring of the first face RGB pattern book set by the processor 701 includes:
acquiring a plurality of first face RGB images;
inputting the plurality of first face RGB images into a face RGB primary feature extraction model to extract primary features of the face RGB images so as to obtain a plurality of first face RGB image primary features;
and obtaining a first face RGB map sample set based on the primary features of the plurality of first face RGB maps.
Optionally, the acquiring of the face infrared heat map sample set by the processor 701 includes:
acquiring a plurality of face infrared heat maps;
inputting the plurality of face infrared heat maps into a face infrared heat map primary feature extraction model to extract primary features of the face infrared heat maps so as to obtain a plurality of primary features of the face infrared heat maps;
and obtaining a face infrared heat image sample set based on the primary features of the face infrared heat images.
Optionally, the obtaining of the pre-trained face detection model performed by the processor 701 includes:
acquiring a second face RGB image sample set, wherein the second face RGB image sample set comprises a second face identity label;
and inputting the second face RGB pattern sample set into a pre-training model for training, so that the pre-training model learns the prediction of the face identity information according to the second face RGB pattern sample set to obtain a pre-trained face detection model.
The electronic device 700 may be a device that can be applied to a mobile phone, a monitor, a computer, a server, and the like that require face temperature detection.
The electronic device 700 provided by the embodiment of the present invention can implement each process implemented by the face temperature detection method in the above method embodiments, and can achieve the same beneficial effects, and for avoiding repetition, the details are not repeated here.
The embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements each process of the face temperature detection method provided in the embodiment of the present invention, and can achieve the same technical effect, and in order to avoid repetition, the computer program is not described herein again.
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 a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above disclosure is only for the purpose of illustrating the preferred embodiments of the present invention, and it is therefore to be understood that the invention is not limited by the scope of the appended claims.
Claims (10)
1. A face temperature detection method is characterized by comprising the following steps:
acquiring a face image to be recognized, wherein the face image to be recognized comprises a face infrared heat map;
inputting the face image to be recognized into a pre-trained face temperature detection model for recognition to obtain face identity information and face temperature information corresponding to the face image to be recognized;
the pre-trained face temperature detection model is obtained by training a pre-trained face detection model according to a face sample set, wherein the face sample set comprises face infrared thermal image samples.
2. The method as claimed in claim 1, wherein the face sample set further includes a first face RGB image sample, and the training method of the pre-trained face temperature detection model includes:
acquiring the face sample set;
acquiring a pre-trained face detection model;
inputting the face sample set into a pre-trained face detection model to train the pre-trained face detection model, and reducing the input weight of the first face RGB image sample in the training process, so that the pre-trained face detection model learns the prediction of face temperature information according to the face infrared heat image sample to obtain the pre-trained face temperature detection model.
3. The method of claim 2, wherein said inputting the set of face samples into a pre-trained face detection model to train the pre-trained face detection model and reduce input weights of the first face RGB map samples during training comprises:
carrying out branch reduction processing on the pre-trained face detection model so as to enable the pre-trained face detection model to adapt to single-channel input of the face infrared thermograph sample;
and inputting the face sample set into the pre-trained face detection model after the branch subtraction for training, and reducing the input weight of the first face RGB image sample to zero in the training process.
4. The method of claim 2, wherein said obtaining the face sample set comprises:
acquiring a first face RGB image sample set, wherein the first face RGB image sample set comprises a first face identity label;
acquiring a face infrared heat map sample set, wherein the face infrared heat map sample comprises a face temperature label;
and forming the face sample set according to the first face RGB image sample set and the face infrared heat image sample set.
5. The method of claim 4, wherein said obtaining a first set of face RGB patterns comprises:
acquiring a plurality of first face RGB images;
inputting the plurality of first face RGB images into a face RGB primary feature extraction model to extract primary features of the face RGB images so as to obtain a plurality of first face RGB image primary features;
and obtaining the first face RGB map sample set based on the plurality of first face RGB map primary features.
6. The method of claim 4, wherein said obtaining a sample set of infrared heat maps of human faces comprises:
acquiring a plurality of face infrared heat maps;
inputting the plurality of face infrared heat maps into a face infrared heat map primary feature extraction model to extract face infrared heat map primary features so as to obtain a plurality of face infrared heat map primary features;
and obtaining the face infrared heat image sample set based on the primary features of the face infrared heat images.
7. The method of claim 2, wherein the obtaining a pre-trained face detection model comprises:
acquiring a second face RGB image sample set, wherein the second face RGB image sample set comprises a second face identity label;
and inputting the second face RGB pattern sample set into a pre-training model for training, so that the pre-training model learns the prediction of face identity information according to the second face RGB pattern sample set to obtain the pre-trained face detection model.
8. A face temperature detection apparatus, the apparatus comprising:
the system comprises an acquisition module, a recognition module and a processing module, wherein the acquisition module is used for acquiring a face image to be recognized, and the face image to be recognized comprises a face infrared heat map;
the recognition module is used for inputting the face image to be recognized into a pre-trained face temperature detection model for recognition to obtain face identity information and face temperature information corresponding to the face image to be recognized;
the pre-trained face temperature detection model is obtained by training a pre-trained face detection model according to a face sample set, wherein the face sample set comprises face infrared thermal image samples.
9. An electronic device, comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps in the face temperature detection method according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method for detecting a face temperature according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010229946.0A CN113449567B (en) | 2020-03-27 | 2020-03-27 | Face temperature detection method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010229946.0A CN113449567B (en) | 2020-03-27 | 2020-03-27 | Face temperature detection method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113449567A true CN113449567A (en) | 2021-09-28 |
| CN113449567B CN113449567B (en) | 2024-04-02 |
Family
ID=77807718
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010229946.0A Active CN113449567B (en) | 2020-03-27 | 2020-03-27 | Face temperature detection method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113449567B (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012235415A (en) * | 2011-05-09 | 2012-11-29 | Nec Software Kyushu Ltd | Image processing system, febrile person identifying method, image processing apparatus, and control method and program thereof |
| JP2012254222A (en) * | 2011-06-09 | 2012-12-27 | Teikyo Heisei Univ | Device for human dynamic face temperature change measurement by thermography and measuring method, and calibrator used for the same |
| CN103493112A (en) * | 2011-02-22 | 2014-01-01 | 菲力尔系统公司 | Infrared sensor systems and methods |
| CN106599797A (en) * | 2016-11-24 | 2017-04-26 | 北京航空航天大学 | Infrared face identification method based on local parallel nerve network |
| CN106845450A (en) * | 2017-02-22 | 2017-06-13 | 武汉科技大学 | Dark surrounds face identification method based near infrared imaging Yu deep learning |
| KR101754152B1 (en) * | 2016-01-25 | 2017-07-19 | 주식회사 에스원 | Thermal Patient Monitering System by Using Multiple Band Camera and Method thereof |
| CN108875752A (en) * | 2018-03-21 | 2018-11-23 | 北京迈格威科技有限公司 | Image processing method and device, computer readable storage medium |
| CN109308436A (en) * | 2017-07-28 | 2019-02-05 | 西南科技大学 | A kind of living body faces recognition methods based on active infrared video |
| CN109614910A (en) * | 2018-12-04 | 2019-04-12 | 青岛小鸟看看科技有限公司 | A kind of face identification method and device |
| CN109846463A (en) * | 2019-03-04 | 2019-06-07 | 武汉迅检科技有限公司 | Infrared face temp measuring method, system, equipment and storage medium |
| CN110032915A (en) * | 2018-01-12 | 2019-07-19 | 杭州海康威视数字技术股份有限公司 | A kind of human face in-vivo detection method, device and electronic equipment |
| CN110276248A (en) * | 2019-05-10 | 2019-09-24 | 杭州电子科技大学 | A kind of facial expression recognizing method based on sample weights distribution and deep learning |
| CN110543645A (en) * | 2019-09-04 | 2019-12-06 | 网易有道信息技术（北京）有限公司 | Machine learning model training method, medium, device and computing equipment |
| CN110797125A (en) * | 2018-08-01 | 2020-02-14 | 深圳云天励飞技术有限公司 | Human health detection system |
-
2020
- 2020-03-27 CN CN202010229946.0A patent/CN113449567B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103493112A (en) * | 2011-02-22 | 2014-01-01 | 菲力尔系统公司 | Infrared sensor systems and methods |
| JP2012235415A (en) * | 2011-05-09 | 2012-11-29 | Nec Software Kyushu Ltd | Image processing system, febrile person identifying method, image processing apparatus, and control method and program thereof |
| JP2012254222A (en) * | 2011-06-09 | 2012-12-27 | Teikyo Heisei Univ | Device for human dynamic face temperature change measurement by thermography and measuring method, and calibrator used for the same |
| KR101754152B1 (en) * | 2016-01-25 | 2017-07-19 | 주식회사 에스원 | Thermal Patient Monitering System by Using Multiple Band Camera and Method thereof |
| CN106599797A (en) * | 2016-11-24 | 2017-04-26 | 北京航空航天大学 | Infrared face identification method based on local parallel nerve network |
| CN106845450A (en) * | 2017-02-22 | 2017-06-13 | 武汉科技大学 | Dark surrounds face identification method based near infrared imaging Yu deep learning |
| CN109308436A (en) * | 2017-07-28 | 2019-02-05 | 西南科技大学 | A kind of living body faces recognition methods based on active infrared video |
| CN110032915A (en) * | 2018-01-12 | 2019-07-19 | 杭州海康威视数字技术股份有限公司 | A kind of human face in-vivo detection method, device and electronic equipment |
| CN108875752A (en) * | 2018-03-21 | 2018-11-23 | 北京迈格威科技有限公司 | Image processing method and device, computer readable storage medium |
| CN110797125A (en) * | 2018-08-01 | 2020-02-14 | 深圳云天励飞技术有限公司 | Human health detection system |
| CN109614910A (en) * | 2018-12-04 | 2019-04-12 | 青岛小鸟看看科技有限公司 | A kind of face identification method and device |
| CN109846463A (en) * | 2019-03-04 | 2019-06-07 | 武汉迅检科技有限公司 | Infrared face temp measuring method, system, equipment and storage medium |
| CN110276248A (en) * | 2019-05-10 | 2019-09-24 | 杭州电子科技大学 | A kind of facial expression recognizing method based on sample weights distribution and deep learning |
| CN110543645A (en) * | 2019-09-04 | 2019-12-06 | 网易有道信息技术（北京）有限公司 | Machine learning model training method, medium, device and computing equipment |
Non-Patent Citations (2)
| Title |
|---|
| G. HERMOSILLA VIGNEAU等: "Thermal Face Recognition Under Temporal Variation Conditions", IEEE ACCESS, pages 9663 - 9672 * |
| 谢征宇等: "基于视频的轨道交通车站乘客口罩佩戴检测及测温技术", 中国铁路, vol. 2020, no. 03, pages 126 - 131 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113449567B (en) | 2024-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107229930B (en) | Intelligent identification method for numerical value of pointer instrument | |
| CN105930822A (en) | Human face snapshot method and system | |
| CN110443969A (en) | A kind of fire point detecting method, device, electronic equipment and storage medium | |
| CN111814661A (en) | Human behavior identification method based on residual error-recurrent neural network | |
| CN107977656A (en) | A kind of pedestrian recognition methods and system again | |
| CN108121961A (en) | Inspection Activity recognition method, apparatus, computer equipment and storage medium | |
| CN109635676A (en) | A method of positioning source of sound from video | |
| CN109410211A (en) | The dividing method and device of target object in a kind of image | |
| CN109508583A (en) | A kind of acquisition methods and device of distribution trend | |
| CN111595450A (en) | Method, apparatus, electronic device and computer-readable storage medium for measuring temperature | |
| WO2024051067A1 (en) | Infrared image processing method, apparatus, and device, and storage medium | |
| CN108090922A (en) | Intelligent Target pursuit path recording method | |
| CN111652314A (en) | Temperature detection method and device, computer equipment and storage medium | |
| CN116797977A (en) | Method and device for identifying dynamic target of inspection robot and measuring temperature and storage medium | |
| CN111444837A (en) | Temperature measurement method and temperature measurement system for improving face detection availability in extreme environment | |
| CN108154199B (en) | High-precision rapid single-class target detection method based on deep learning | |
| CN113947796A (en) | Human body temperature trend detection method and device based on identity recognition | |
| CN113449567B (en) | Face temperature detection method and device, electronic equipment and storage medium | |
| CN110619365B (en) | Method for detecting falling water | |
| CN112525355A (en) | Image processing method, device and equipment | |
| CN115937971B (en) | Method and device for identifying hand-lifting voting | |
| CN116311400A (en) | Palm print image processing method, electronic device and storage medium | |
| CN110021036A (en) | Infrared target detection method, apparatus, computer equipment and storage medium | |
| TWI777689B (en) | Method of object identification and temperature measurement | |
| CN112784703A (en) | Multispectral-based personnel action track determination method |
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 |