CN112380938B - Face recognition and temperature measurement method, device, equipment and medium - Google Patents
Face recognition and temperature measurement method, device, equipment and medium Download PDFInfo
- Publication number
- CN112380938B CN112380938B CN202011219015.9A CN202011219015A CN112380938B CN 112380938 B CN112380938 B CN 112380938B CN 202011219015 A CN202011219015 A CN 202011219015A CN 112380938 B CN112380938 B CN 112380938B
- Authority
- CN
- China
- Prior art keywords
- feature vector
- face
- image
- similarity
- temperature measurement
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000009529 body temperature measurement Methods 0.000 title claims abstract description 86
- 238000000034 method Methods 0.000 title claims abstract description 57
- 239000013598 vector Substances 0.000 claims abstract description 319
- 238000004590 computer program Methods 0.000 claims description 14
- 238000004861 thermometry Methods 0.000 claims description 7
- 210000001503 joint Anatomy 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 15
- 238000012545 processing Methods 0.000 description 15
- 238000004891 communication Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
Classifications
-
- 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
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/0022—Radiation pyrometry, e.g. infrared or optical thermometry for sensing the radiation of moving bodies
- G01J5/0025—Living bodies
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/48—Thermography; Techniques using wholly visual means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G06V40/172—Classification, e.g. identification
-
- 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 discloses a face recognition and temperature measurement method, a device, equipment and a medium, which are used for solving the problem of low recognition accuracy when the face recognition and temperature measurement are carried out by the existing butt joint temperature measurement camera. According to the method, electronic equipment acquires a target face image based on a tracked face in a video stream sent by a temperature measurement camera to obtain a first feature vector, and then the first feature vector is respectively matched with each second feature vector in a face feature library and a third feature vector of each face image acquired by the temperature measurement camera in a current cache to determine and output a first target image and temperature information corresponding to the third feature vector meeting a similarity requirement. Because the electronic equipment obtains the target face image and the similarity of the third feature vector of each face image in the cache based on the video stream to determine the temperature information, even if the quality of the visible light face image collected by the temperature measuring camera is low, the face recognition and the temperature measurement can be accurately completed by combining the video stream sent by the temperature measuring camera.
Description
Technical Field
The present invention relates to the field of image processing technologies, and in particular, to a face recognition and temperature measurement method, apparatus, device, and medium.
Background
With the development of image processing technology, face recognition technology is widely applied to various fields of society. The face recognition electronic equipment is based on the feature vector stored in the face feature library, matches the feature vector of the image to be recognized, and takes the face image corresponding to the successfully matched feature vector as the recognized target image.
In addition, because of some special reasons, the demand of carrying out temperature measurement to the face is also higher and higher, and when electronic equipment docks temperature measurement camera and carries out face identification and temperature measurement, prior art scheme is: after the electronic equipment receives an image to be recognized containing a human face and an infrared image containing the human face sent by the temperature measuring camera, extracting a feature vector of the image to be recognized, determining a target image corresponding to a human face library based on the feature vector, and finally displaying temperature information corresponding to the target image and the infrared image to finish face recognition and temperature measurement.
In the prior art, when face recognition and temperature measurement are carried out, an image to be recognized sent by a temperature measurement camera is adopted, and if the image quality of the image to be recognized is low, the recognition accuracy is directly affected.
Disclosure of Invention
In view of the above, the invention provides a face recognition and temperature measurement method, device, equipment and medium, which are used for solving the problem of low recognition accuracy when the existing butt joint temperature measurement camera is used for face recognition and temperature measurement.
In a first aspect, the present invention provides a face recognition and temperature measurement method, the method comprising:
acquiring a target face image containing a face based on the tracked face in a video stream acquired by a received temperature measurement camera, and acquiring a first feature vector corresponding to the face in the target face image;
matching the first feature vector with each second feature vector stored in a face feature library, and determining a first target image corresponding to the successfully matched second feature vector;
Determining the similarity between the first feature vector and a third feature vector of each face image acquired by a temperature measurement camera stored in a current cache;
And outputting the temperature information corresponding to the third feature vector which is stored in the first target image and the current cache and meets the similarity requirement as the temperature information corresponding to the first target image.
Further, the determining, as the temperature value corresponding to the target image, the temperature value corresponding to the third feature vector satisfying the similarity requirement includes:
judging whether a third feature vector with the similarity larger than a set threshold value with the first feature vector exists or not;
if so, the third feature vector corresponding to the maximum similarity is used as the third feature vector meeting the similarity requirement.
Further, if there is no third feature vector having a similarity with the first feature vector greater than a set threshold, the method further includes:
and outputting prompt information that the temperature information is not acquired.
Further, the method further comprises:
and deleting the third feature vector meeting the similarity requirement and the corresponding temperature information in the current cache.
Further, the obtaining, based on the tracked face, the target face image including the face in the received video stream acquired by the thermometry camera includes:
carrying out face tracking in a video stream acquired by a received temperature measurement camera, acquiring an image containing the tracked face, and acquiring a face image containing the face;
and taking the face image with the image quality meeting the requirement as a target face image.
Further, the method further comprises:
Aiming at a third feature vector of each currently cached face image, if the cached time length of the third feature vector reaches a set time length threshold value, matching the third feature vector with each second feature vector stored in a face feature library, and determining a second target image corresponding to the successfully matched second feature vector; and outputting the temperature information corresponding to the second target image and the third feature vector.
In a second aspect, the present invention further provides a face recognition and temperature measurement device, where the device includes:
The acquisition module is used for acquiring a target face image containing the face based on the tracked face in a video stream acquired by the received temperature measurement camera and acquiring a first feature vector corresponding to the target face image;
The first determining module is used for matching the first feature vector with each second feature vector stored in the face feature library and determining a first target image corresponding to the successfully matched second feature vector;
the second determining module is used for determining the similarity between the first feature vector and a third feature vector of each face image acquired by the temperature measuring camera stored in the current cache;
And the output module is used for outputting the first target image and the temperature information corresponding to the third feature vector meeting the similarity requirement, which is stored in the current cache.
Further, the output module is specifically configured to determine whether a third feature vector with similarity to the first feature vector being greater than a set threshold exists; if so, the third feature vector corresponding to the maximum similarity is used as the third feature vector meeting the similarity requirement.
Further, the output module is further configured to output a prompt message that no temperature information is acquired if it is determined that there is no third feature vector with a similarity with the first feature vector being greater than a set threshold.
Further, the device further comprises:
And the deleting module is used for deleting the third feature vector meeting the similarity requirement and the corresponding temperature information in the current cache.
Further, the acquiring module is specifically configured to perform face tracking in a video stream acquired by the received temperature measurement camera, acquire an image including the tracked face, and acquire a face image including the face; and taking the face image with the image quality meeting the requirement as a target face image.
Further, the output module is further configured to match, for a third feature vector of each currently cached face image, the third feature vector with each second feature vector stored in the face feature library if the cached duration of the third feature vector reaches a set duration threshold, and determine a second target image corresponding to a second feature vector that is successfully matched; and outputting the temperature information corresponding to the second target image and the third feature vector.
In a third aspect, the present invention also provides an electronic device comprising a processor for implementing the steps of any one of the face recognition and temperature measurement methods described above when executing a computer program stored in a memory.
In a fourth aspect, the present invention also provides a computer readable storage medium storing a computer program which when executed by a processor implements the steps of the face recognition and temperature measurement method as described in any one of the above.
Because the third feature vector and the temperature information of each face image acquired by the temperature measurement camera are stored in the cache of the electronic equipment, when the electronic equipment acquires the target face image containing the face based on the tracked face in the received video stream acquired by the temperature measurement camera, a first feature vector is acquired, the first target image and the temperature information are determined based on the first feature vector, and the first target image and the corresponding temperature information are output. Therefore, the electronic equipment acquires the target face image based on the video stream acquired by the temperature measuring camera and determines the temperature information with the similarity of the third feature vector of each face image acquired by the temperature measuring camera stored in the cache, and even if the quality of the visible light face image acquired by the temperature measuring camera is low, the video stream transmitted by the temperature measuring camera is combined, so that face recognition and temperature measurement can be more accurately finished.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:
Fig. 1 is a schematic diagram of a face recognition and temperature measurement process according to an embodiment of the present invention;
fig. 2 is a schematic diagram of a video stream face recognition and temperature measurement process according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of another implementation process of face recognition and temperature measurement according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a face recognition and temperature measurement device according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which are derived by a person skilled in the art based on the embodiments of the invention, fall within the scope of protection of the invention.
In order to improve the recognition accuracy, the embodiment of the invention provides a face recognition and temperature measurement method, a device, equipment and a medium.
Example 1:
Fig. 1 is a schematic diagram of a face recognition and temperature measurement process according to an embodiment of the present invention, where the process includes the following steps:
S101: and acquiring a target face image containing the face based on the tracked face in the video stream acquired by the received temperature measurement camera, and acquiring a first feature vector corresponding to the target face image.
The face recognition and temperature measurement method provided by the embodiment of the invention is applied to electronic equipment, and the electronic equipment can be equipment such as a PC (personal computer), a server and the like which can perform image processing.
The electronic equipment pulls the video stream from the butt-joint temperature measuring camera, performs face tracking in the video stream, acquires face images containing the face according to the tracked face, and the number of the acquired face images can be 1 or a plurality of face images. After the electronic equipment acquires the face image, the face image is scratched to obtain a target face image, and a corresponding first feature vector is obtained based on the target face image.
The process of acquiring the first feature vector based on the image is the prior art, and is not described herein.
S102: and matching the first feature vector with each second feature vector stored in the face feature library, and determining a first target image corresponding to the successfully matched second feature vector.
The face feature library stores face images of users in the white list and feature vectors corresponding to the face images, the feature vectors contained in the face feature library are called second feature vectors for distinguishing the face images from the first feature vectors, and the process of acquiring the second feature vectors based on the images is the same as the process of acquiring the first feature vectors.
After the electronic equipment acquires the first feature vector of the target face image, the first feature vector is matched with each second feature vector stored in the face feature library, so that whether the second feature vector successfully matched with the first feature vector exists or not is determined.
When the first feature vector and the second feature vector are matched, since the dimensions of the first feature vector and the second feature vector are the same, the euclidean distance between the first feature vector and the second feature vector may be calculated, and the euclidean distance may be used as the similarity between the first feature vector and the second feature vector, or the cosine value of the first feature vector and the second feature vector may be calculated, and the similarity may be determined according to the cosine value.
In order to determine whether the first feature vector and the second feature vector are successfully matched, a similarity threshold is preset, and when the similarity is larger than the similarity threshold, the first feature vector and the second feature vector are determined to be matched, namely the second feature vector is the second feature vector successfully matched with the first feature vector.
After the second feature vector successfully matched is determined, the face image corresponding to the second feature vector successfully matched is determined according to the corresponding relation between the second feature vector and the face image stored in the face feature library, and the face image is used as a first target image.
S103: and determining the similarity between the first feature vector and a third feature vector of each face image acquired by a temperature measuring camera stored in the current cache, and outputting temperature information corresponding to the first target image and the third feature vector meeting the similarity requirement stored in the current cache.
When the electronic equipment is in butt joint with the temperature measuring camera, the temperature measuring camera can also track the human face, the temperature measuring camera adopts a human face snapshot function after tracking the human face, the infrared image and the visible light image containing the human face can be acquired, and the temperature measuring camera can directly send the snapped infrared image and visible light image containing the human face to the electronic equipment. The electronic equipment performs matting processing on the visible light image containing the human face sent by the temperature measurement camera, obtains the human face image in the visible light image, and performs feature extraction based on the human face image to obtain a third feature vector. In addition, the electronic equipment further processes based on the infrared image containing the face sent by the temperature measuring camera, acquires temperature information of the tracked face, and correspondingly stores the temperature information and the third feature vector into a cache.
If the buffer space is large enough, the face image corresponding to each third feature vector can be stored in the buffer for each third feature vector.
In order to reduce the pressure of the electronic device, the third feature vector and the temperature information stored in the cache of the electronic device may be acquired and sent by the temperature measurement camera, after the temperature measurement camera acquires the infrared image and the visible light image containing the face, the visible light image is subjected to image matting processing to acquire the face image therein, feature extraction is performed based on the face image to acquire the third feature vector, and the temperature measurement camera may also process the acquired infrared image to acquire the temperature information of the face area in the infrared image. After the temperature measuring camera acquires the third feature vector and the temperature information, the corresponding relation between the third feature vector and the temperature information is sent to the electronic equipment, and the electronic equipment stores the corresponding relation between the third feature vector and the temperature information in a local cache.
The temperature measuring camera not only can send the third feature vector and the corresponding temperature information to the electronic equipment, or contains the visible light image and the infrared image of the face, but also can send the image stream to the electronic equipment, and the electronic equipment can respectively receive the image stream and the video stream sent by the temperature measuring camera through two channels.
After the electronic device obtains the first feature vector, the similarity between the first feature vector and the third feature vector of each face image acquired by the temperature measurement camera stored in the current cache is determined, and the similarity calculation process is the same as the above process and is not repeated here.
And obtaining temperature information corresponding to a third feature vector meeting the similarity requirement, determining the temperature information as temperature information corresponding to the first target image, and outputting the first target image and the temperature information. The obtaining of the third feature vector satisfying the similarity requirement may be obtaining a third feature vector corresponding to the maximum value of the similarity.
Because the third feature vector and the temperature information of each face image acquired by the temperature measurement camera are stored in the cache of the electronic equipment, when the electronic equipment acquires the target face image containing the face based on the tracked face in the received video stream acquired by the temperature measurement camera, a first feature vector is acquired, the first target image and the temperature information are determined based on the first feature vector, and the first target image and the corresponding temperature information are output. Therefore, the electronic equipment acquires the target face image based on the video stream acquired by the temperature measuring camera and determines the temperature information with the similarity of the third feature vector of each face image acquired by the temperature measuring camera stored in the cache, and even if the quality of the visible light face image acquired by the temperature measuring camera is low, the video stream transmitted by the temperature measuring camera is combined, and the more accurate electronic equipment can finish face recognition and temperature measurement and improve the recognition accuracy.
Example 2:
in order to further improve the recognition accuracy, in the embodiment of the present invention, determining a third feature vector that meets a similarity requirement includes:
Judging whether a third feature vector with the similarity with the first feature vector being larger than a set threshold value exists or not;
if so, the third feature vector corresponding to the maximum similarity is used as the third feature vector meeting the similarity requirement.
In the embodiment of the invention, the electronic equipment is connected with the temperature measuring camera, the temperature measuring camera has an infrared scanning function, after the infrared scanning function is started, the temperature measuring camera can identify whether pedestrians exist in a scanning range, if so, the temperature measuring camera starts an image acquisition function to acquire an infrared image and a visible light image containing a human face, after the visible light image is acquired, the temperature measuring camera can perform image matting processing on the visible light image to acquire the human face image, the temperature measuring camera can also directly send the human face image to the electronic equipment, and the electronic equipment acquires a third feature vector of the human face image; the temperature measurement camera can also process the face image by itself to obtain a third feature vector of the face image.
In addition, the temperature measurement camera can process the infrared image to acquire temperature information of a face area, and send the temperature information to the electronic equipment, or the temperature measurement camera performs image matting processing on the infrared image to acquire an infrared face image, and sends the infrared face image to the electronic equipment, so that the electronic equipment acquires the temperature information of the face according to the infrared face image.
That is, the thermometry camera can perform face tracking, so as to acquire an infrared image and a visible light image of each pedestrian, which contain a face, and enable the electronic device to acquire a third feature vector and temperature information of each face image based on the method. After the electronic equipment acquires the third feature vector and the temperature information of each face image, the third feature vector and the temperature information are correspondingly stored.
After the electronic device obtains the first feature vector based on the video stream collected by the temperature measurement camera, in order to obtain the temperature information of the face corresponding to the first feature vector, the electronic device determines the similarity between the first feature vector and the third feature vector of each face image collected by the temperature measurement camera and contained in the current cache, so as to determine the third feature vector with the similarity meeting the requirement.
In order to further improve the recognition accuracy, the third feature vector satisfying the similarity requirement may be any one of the third feature vectors having a similarity with the first feature vector larger than the set threshold, but in order to further improve the recognition accuracy, when there is a third feature vector having a similarity larger than the set threshold, the third feature vector corresponding to the maximum value of the similarity may be used as the third feature vector satisfying the similarity requirement.
The set threshold can be flexibly set according to the needs, if the recognition accuracy is required to be further improved, the threshold can be set to be larger, and if the third feature vector meeting the similarity requirement can be determined each time, the threshold can be set to be smaller.
Example 3:
in order to further improve the recognition accuracy, in the embodiments of the present invention based on the above embodiments, if there is no third feature vector having a similarity with the first feature vector greater than a set threshold, the method further includes:
and outputting prompt information that the temperature information is not acquired.
In the embodiment of the invention, after the electronic device acquires the first feature vector based on the video stream acquired by the temperature measurement camera, in order to acquire the temperature information of the face corresponding to the first feature vector, the electronic device determines the similarity between the first feature vector and the third feature vector of each face image acquired by the temperature measurement camera and contained in the current cache, so as to determine the third feature vector with the similarity meeting the requirement.
And judging whether the similarity meets the requirement, presetting a threshold value, comparing the similarity with the set threshold value, and if a third feature vector meeting the similarity requirement does not exist, namely, a third feature vector with the similarity larger than the set threshold value does not exist, indicating that the face image similar to the face image corresponding to the first feature vector is not stored in the current cache, wherein the temperature information corresponding to the first feature vector cannot be obtained. In order to ensure that the temperature information of the face of the user corresponding to the first feature vector can be acquired, the electronic equipment outputs prompt information that the temperature information is not acquired at the moment so as to prompt the user to reenter the acquisition area, thereby facilitating the acquisition of the image and the video stream by the temperature measuring camera and ensuring that the temperature information of the face of the user is acquired.
Example 4:
in order to further improve the recognition accuracy, based on the above embodiments, in the embodiment of the present invention, the method further includes:
and deleting the third feature vector meeting the similarity requirement and the corresponding temperature information in the current cache.
After a third feature vector meeting the similarity requirement is determined according to the similarity between the first feature vector and the third feature vector stored in the current cache, the corresponding user identification and temperature measurement are determined after the first target image determined based on the first feature vector and the temperature information corresponding to the third feature vector meeting the similarity requirement are output. The limited cache space can continuously keep the feature vector and the temperature information of the user, which can affect the identification and the temperature measurement of the subsequent user, so that in order to ensure the identification and the temperature measurement of the subsequent user, in the embodiment of the invention, after outputting the temperature information corresponding to the first target image determined based on the first feature vector and the third feature vector meeting the similarity requirement, the third feature vector meeting the similarity requirement and the corresponding temperature information thereof are deleted in the current cache. The released buffer space can be used for storing the feature vectors and temperature information of other users.
After the electronic equipment acquires the first feature vector based on the video stream acquired by the temperature measurement camera, the first feature vector is matched with each second feature vector stored in the face feature library, and after the second feature vector successfully matched is determined, a first target image corresponding to the determined second feature vector can be obtained from the face library.
And then, determining the similarity between the first feature vector and the third feature vector stored in the current cache, and taking the temperature information corresponding to the third feature vector meeting the similarity requirement as the temperature information corresponding to the first target image.
After determining and acquiring the temperature information corresponding to the third feature vector meeting the similarity requirement, deleting the third feature vector meeting the similarity requirement and the temperature information corresponding to the third feature vector from the current cache, and releasing the cache space.
Fig. 2 is a schematic diagram of a face recognition and temperature measurement process according to an embodiment of the present invention, where the process includes:
s201: the electronic device performs face tracking based on the video stream acquired by the temperature measurement camera.
The electronic equipment pulls the video stream from the abutted temperature measuring camera, and performs face tracking based on the video stream to obtain a face image of the tracked face.
S202: and acquiring a target face image of the face according to the tracked face, and acquiring a first feature vector based on the target face image.
S203: and determining the similarity between the first feature vector and a third feature vector of each face image stored in the current cache.
S204: and judging whether a third feature vector with the similarity meeting the requirement of the similarity exists in the cache, if so, executing S205, and if not, executing S206.
S205: and taking the temperature information corresponding to the third feature vector meeting the similarity requirement as the temperature information of the acquired face, deleting the third feature vector meeting the similarity requirement and the temperature information corresponding to the third feature vector from the current cache, and then executing S207.
S206: the electronic equipment outputs prompt information of not collecting temperature information so as to prompt a user to reenter the collecting area.
S207: and matching the first feature vector with each second feature vector stored in the face feature library, determining a first target image corresponding to the successfully matched second feature vector, and outputting the first target image and the temperature information.
Example 5:
In order to further improve the recognition accuracy, in the embodiments of the present invention, the acquiring, based on the tracked face, the target face image including the face in the video stream acquired by the received thermometry camera includes:
carrying out face tracking in a video stream acquired by a received temperature measurement camera, acquiring an image containing the tracked face, and acquiring a face image containing the face;
And aiming at the image containing the same face, taking the face image with the image quality meeting the requirement as a target face image.
In the embodiment of the invention, the electronic equipment pulls the video stream from the abutted temperature measuring camera, performs face tracking in the video stream, acquires the image containing the face from the video stream aiming at the tracked face, and can acquire 1 or more images containing the face from the video stream, and after acquiring the images, performs image matting on the images to acquire the face image containing the tracked face in the video stream.
In the method, in order to further improve the recognition accuracy, in the embodiment of the invention, in the acquired face images containing the tracked face, the face image with the image quality meeting the requirement is selected, wherein the face image with the image quality meeting the requirement comprises the face image with the highest image quality, and the face image with the image quality meeting the requirement is taken as a target face image, so that the first feature vector of the target face image is acquired.
Because the face image with the highest image quality is taken as the target face image, the face contained in the target face image is closest to the face collected by the temperature measuring camera, the first feature vector extracted by the target face image is matched with each second feature vector in the face feature library, and the matched first target image can be found out from the face library more accurately when the first target image is acquired, so that the face recognition accuracy is further improved. In addition, when the similarity is calculated between the first feature vector extracted based on the target face image and the third feature vector stored in the cache, the matched third feature vector in the cache can be more accurately determined, so that corresponding temperature information is obtained, and the accuracy of temperature measurement is further ensured.
The images containing the tracked human faces, which are acquired from the video stream, can be multiple, the image quality of each image is basically the same as the quality of the human face image containing the human faces, the judgment of the image quality can be carried out based on the multiple images, in order to further improve the accuracy, the image matting processing can be carried out on each image, the corresponding human face image is acquired, and the image quality comparison is carried out based on the human face images. Whether the image quality meets the requirement or not can be judged according to the definition of the image, the inclination angle of the human face and the like. For example, a face image with the highest definition may be used as the target face image, or a face image with the smallest inclination angle of the face in the face image may be used as the target face image.
Example 6:
in order to further improve the recognition accuracy, based on the above embodiments, in the embodiment of the present invention, the method further includes:
Aiming at a third feature vector of each currently cached face image, if the cached time length of the third feature vector reaches a set time length threshold value, matching the third feature vector with each second feature vector stored in a face feature library, and determining a second target image corresponding to the successfully matched second feature vector; and outputting the second target image and taking the temperature information corresponding to the third feature vector as the temperature information of the second target image.
After determining a third feature vector meeting the similarity requirement according to the similarity between the first feature vector and the third feature vector stored in the current cache, outputting a first target image determined based on the first feature vector and temperature information corresponding to the third feature vector meeting the similarity requirement, determining that corresponding user identification and temperature measurement are finished, and deleting the third feature vector meeting the similarity requirement and the corresponding temperature information in the current cache. And the third feature vector and the corresponding temperature information which do not meet the similarity requirement in the cache space are continuously reserved, and the third feature vector and the temperature information which are continuously reserved in the cache are not processed for a long time, so that the cache space is occupied all the time, and the identification and temperature measurement of the subsequent users can be influenced.
Therefore, in order to ensure that the subsequent user can be identified and measured, in the embodiment of the invention, aiming at the third feature vector of each face image cached currently, if the cached time length of the third feature vector reaches a set time length threshold, matching the third feature vector with each second feature vector stored in a face feature library, and determining a second target image corresponding to the successfully matched second feature vector; and taking the temperature information corresponding to the third feature vector as the temperature information of the second target image, and outputting the temperature information corresponding to the second target image and the third feature vector.
The information reserved for a long time in the buffer space is processed in time, the accuracy of face recognition can be improved, meanwhile, the picture stream sent by the temperature measuring camera is prevented from being lost, and the released buffer space can be used for storing the characteristic vectors and the temperature information of other users.
Fig. 3 is a schematic diagram of another implementation process of face recognition and temperature measurement according to an embodiment of the present invention, where the process includes:
s301: the electronic equipment receives the image and temperature information acquired by the temperature measuring camera.
The electronic equipment is connected with the temperature measuring camera in a butt joint mode, an infrared image and a visible light image, which are acquired by the temperature measuring camera and contain areas where pedestrians are located, are acquired, then the visible light image is subjected to image matting processing to acquire a face image, and the infrared image is processed to acquire temperature information of the face area.
S302: and the electronic equipment performs feature extraction on the visible light image containing the human face acquired by the temperature measuring camera to extract a third feature vector.
S303: after the third feature vector and the temperature information of each face are obtained, the third feature vector and the temperature information are correspondingly stored.
And S304, checking the third feature vector in the cache and the cache duration of the corresponding temperature information at regular time.
S305, judging whether the time length of the third feature vector in the cache and the corresponding temperature information in the cache reaches a set time length threshold value, if so, executing S306, and if not, returning to S304.
S306, matching a third feature vector with the cache time reaching a set time threshold with each second feature vector stored in the face feature library, and determining a second target image corresponding to the successfully matched second feature vector; and taking the temperature information corresponding to the third feature vector as the temperature information of the second target image, and outputting the temperature information corresponding to the second target image and the third feature vector.
Example 7:
fig. 4 is a schematic structural diagram of a face recognition and temperature measurement device according to an embodiment of the present invention, where the device includes:
Acquisition module 401: the method comprises the steps of obtaining a target face image containing a face based on the tracked face in a video stream acquired by a received temperature measurement camera, and obtaining a first feature vector corresponding to the target face image;
the first determination module 402: the method comprises the steps of matching the first feature vector with each second feature vector stored in a face feature library, and determining a first target image corresponding to the successfully matched second feature vector;
The second determination module 403: the similarity of the first feature vector and a third feature vector of each face image acquired by a temperature measurement camera stored in the current cache is determined;
an output module 404: and the temperature information corresponding to the third feature vector meeting the similarity requirement and stored in the first target image and the current cache is output.
In a possible implementation manner, the output module 404 is specifically configured to determine whether a third feature vector having a similarity with the first feature vector is greater than a set threshold value; if so, the third feature vector corresponding to the maximum similarity is used as the third feature vector meeting the similarity requirement.
In a possible implementation manner, the output module 404 is specifically configured to determine whether a third feature vector having a similarity with the first feature vector is greater than a set threshold value; if so, the third feature vector corresponding to the maximum similarity is used as the third feature vector meeting the similarity requirement. In a possible implementation manner, the output module 404 is further configured to output a prompt message that no temperature information is collected if it is determined that there is no third feature vector with a similarity with the first feature vector greater than a set threshold.
In one possible embodiment, the apparatus further comprises:
And the deleting module is used for deleting the third feature vector meeting the similarity requirement and the corresponding temperature information in the current cache.
In a possible implementation manner, the obtaining module 401 is specifically configured to perform face tracking in a video stream collected by a received thermometry camera, obtain an image containing the tracked face, and obtain a face image containing the face; and taking the face image with the image quality meeting the requirement as a target face image.
In a possible manner, the output module 404 is further configured to match, for a third feature vector of each currently cached face image, the third feature vector with each second feature vector stored in the face feature library if the cached duration of the third feature vector reaches a set duration threshold, and determine a second target image corresponding to the second feature vector that is successfully matched; and outputting the temperature information corresponding to the second target image and the third feature vector.
Because the electronic equipment acquires the target face image based on the video stream acquired by the temperature measurement camera and determines the temperature information with the similarity of the third feature vector of each face image acquired by the temperature measurement camera stored in the cache, even if the quality of the visible light face image acquired by the temperature measurement camera is low, the video stream transmitted by the temperature measurement camera is combined, and the more accurate electronic equipment can finish face recognition and temperature measurement and improve the recognition accuracy.
Example 8:
On the basis of the above embodiments, the embodiment of the present invention further provides an electronic device, as shown in fig. 5, including: the device comprises a processor 501, a communication interface 502, a memory 503 and a communication bus, wherein the processor 501, the communication interface 502 and the memory 503 are in communication with each other through the communication bus 504.
The memory 503 has stored therein a computer program which, when executed by the processor 501, causes the processor 501 to perform the steps of:
acquiring a target face image containing a face based on the tracked face in a video stream acquired by a received temperature measurement camera, and acquiring a first feature vector corresponding to the face in the target face image;
matching the first feature vector with each second feature vector stored in a face feature library, and determining a first target image corresponding to the successfully matched second feature vector;
Determining the similarity between the first feature vector and a third feature vector of each face image acquired by a temperature measurement camera stored in a current cache;
And outputting the temperature information corresponding to the third feature vector which is stored in the first target image and the current cache and meets the similarity requirement as the temperature information corresponding to the first target image.
Further, the processor 501 is further configured to determine whether a third feature vector with greater similarity than the first feature vector is greater than a set threshold; if so, the third feature vector corresponding to the maximum similarity is used as the third feature vector meeting the similarity requirement.
Further, the processor 501 is further configured to output a prompt message that no temperature information is collected.
Further, the processor 501 is further configured to delete the third feature vector meeting the similarity requirement and the corresponding temperature information thereof in the current cache.
Further, the processor 501 is further configured to perform face tracking in a video stream acquired by the received thermometry camera, obtain an image including the tracked face, and obtain a face image including the face; and taking the face image with the image quality meeting the requirement as a target face image.
Further, the processor 501 is further configured to match, for a third feature vector of each currently cached face image, the third feature vector with each second feature vector stored in the face feature library if the cached duration of the third feature vector reaches a set duration threshold, and determine a second target image corresponding to a second feature vector that is successfully matched; and outputting the temperature information corresponding to the second target image and the third feature vector.
The communication bus mentioned by the server may be a peripheral component interconnect standard (PERIPHERAL COMPONENT INTERCONNECT, PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, etc. The communication bus may be classified as an address bus, a data bus, a control bus, or the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus.
The communication interface 502 is used for communication between the electronic device and other devices described above.
The Memory may include random access Memory (Random Access Memory, RAM) or may include Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the aforementioned processor.
The processor may be a general-purpose processor, including a central processing unit, a network processor (Network Processor, NP), etc.; but also digital instruction processors (DIGITAL SIGNAL Processing units, DSPs), application specific integrated circuits, field programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
Example 9:
On the basis of the above embodiments, the embodiments of the present invention further provide a computer readable storage medium having stored therein a computer program executable by an electronic device, which when run on the electronic device, causes the electronic device to perform the steps of:
The memory has stored therein a computer program which, when executed by the processor, causes the processor to perform the steps of:
acquiring a target face image containing a face based on the tracked face in a video stream acquired by a received temperature measurement camera, and acquiring a first feature vector corresponding to the face in the target face image;
matching the first feature vector with each second feature vector stored in a face feature library, and determining a first target image corresponding to the successfully matched second feature vector;
Determining the similarity between the first feature vector and a third feature vector of each face image acquired by a temperature measurement camera stored in a current cache;
And outputting the temperature information corresponding to the third feature vector which is stored in the first target image and the current cache and meets the similarity requirement as the temperature information corresponding to the first target image.
Further, the determining, as the temperature value corresponding to the target image, the temperature value corresponding to the third feature vector satisfying the similarity requirement includes:
judging whether a third feature vector with the similarity larger than a set threshold value with the first feature vector exists or not; if so, the third feature vector corresponding to the maximum similarity is used as the third feature vector meeting the similarity requirement.
Further, if there is no third feature vector having a similarity with the first feature vector greater than a set threshold, the method further includes:
and outputting prompt information that the temperature information is not acquired.
Further, the method further comprises:
and deleting the third feature vector meeting the similarity requirement and the corresponding temperature information in the current cache.
Further, the obtaining, based on the tracked face, the target face image including the face in the received video stream acquired by the thermometry camera includes:
carrying out face tracking in a video stream acquired by a received temperature measurement camera, acquiring an image containing the tracked face, and acquiring a face image containing the face;
and taking the face image with the image quality meeting the requirement as a target face image.
Further, the method further comprises:
Aiming at a third feature vector of each currently cached face image, if the cached time length of the third feature vector reaches a set time length threshold value, matching the third feature vector with each second feature vector stored in a face feature library, and determining a second target image corresponding to the successfully matched second feature vector; and outputting the temperature information corresponding to the second target image and the third feature vector.
Because the electronic equipment of the embodiment of the invention acquires the target face image based on the video stream acquired by the temperature measuring camera and determines the temperature information with the similarity of the third feature vector of each face image acquired by the temperature measuring camera stored in the cache, even if the quality of the visible light face image acquired by the temperature measuring camera is low, the face recognition and the temperature measurement can be more accurately finished by combining the video stream transmitted by the temperature measuring camera.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, it is intended that the present application also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. The face recognition and temperature measurement method is characterized by comprising the following steps:
acquiring a target face image containing a face based on the tracked face in a video stream acquired by a received temperature measurement camera, and acquiring a first feature vector corresponding to the target face image;
matching the first feature vector with each second feature vector stored in a face feature library, and determining a first target image corresponding to the successfully matched second feature vector;
Determining the similarity between the first feature vector and a third feature vector of each face image acquired by a temperature measurement camera stored in a current cache;
and outputting the temperature information corresponding to the first target image and the third feature vector meeting the similarity requirement stored in the current cache.
2. The method of claim 1, wherein determining a third feature vector that meets a similarity requirement comprises:
Judging whether a third feature vector with the similarity with the first feature vector being larger than a set threshold value exists or not;
if so, the third feature vector corresponding to the maximum similarity is used as the third feature vector meeting the similarity requirement.
3. The method of claim 2, wherein if there is no third feature vector having a similarity to the first feature vector greater than a set threshold, the method further comprises:
and outputting prompt information that the temperature information is not acquired.
4. The method according to claim 1 or 2, characterized in that the method further comprises:
and deleting the third feature vector meeting the similarity requirement and the corresponding temperature information in the current cache.
5. The method of claim 1, wherein the acquiring a target face image containing the face based on the tracked face in the received video stream acquired by the thermometry camera comprises:
carrying out face tracking in a video stream acquired by a received temperature measurement camera, acquiring an image containing the tracked face, and acquiring a face image containing the face;
and taking the face image with the image quality meeting the requirement as a target face image.
6. The method according to claim 1, wherein the method further comprises:
Aiming at a third feature vector of each currently cached face image, if the cached time length of the third feature vector reaches a set time length threshold value, matching the third feature vector with each second feature vector stored in a face feature library, and determining a second target image corresponding to the successfully matched second feature vector; and outputting the temperature information corresponding to the second target image and the third feature vector.
7. A face recognition and temperature measurement device, the device comprising:
The acquisition module is used for acquiring a target face image containing the face based on the tracked face in a video stream acquired by the received temperature measurement camera and acquiring a first feature vector corresponding to the target face image;
The first determining module is used for matching the first feature vector with each second feature vector stored in the face feature library and determining a first target image corresponding to the successfully matched second feature vector;
the second determining module is used for determining the similarity between the first feature vector and a third feature vector of each face image acquired by the temperature measuring camera stored in the current cache;
And the output module is used for outputting the first target image and the temperature information corresponding to the third feature vector meeting the similarity requirement, which is stored in the current cache.
8. The apparatus of claim 7, wherein the output module is further configured to, for a third feature vector of each currently cached face image, match the third feature vector with each second feature vector stored in the face feature library if a time length for which the third feature vector is cached reaches a set time length threshold, and determine a second target image corresponding to a second feature vector that is successfully matched; and outputting the temperature information corresponding to the second target image and the third feature vector.
9. An electronic device comprising at least a processor and a memory, the processor being adapted to implement the steps of the face recognition and temperature measurement method according to any one of claims 1-6 when executing a computer program stored in the memory.
10. A computer readable storage medium, characterized in that it stores a computer program which, when executed by a processor, implements the steps of the face recognition and temperature measurement method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011219015.9A CN112380938B (en) | 2020-11-04 | 2020-11-04 | Face recognition and temperature measurement method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011219015.9A CN112380938B (en) | 2020-11-04 | 2020-11-04 | Face recognition and temperature measurement method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112380938A CN112380938A (en) | 2021-02-19 |
| CN112380938B true CN112380938B (en) | 2024-05-03 |
Family
ID=74578795
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011219015.9A Active CN112380938B (en) | 2020-11-04 | 2020-11-04 | Face recognition and temperature measurement method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112380938B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113420629B (en) * | 2021-06-17 | 2023-04-28 | 浙江大华技术股份有限公司 | Image processing method, device, equipment and medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101793562A (en) * | 2010-01-29 | 2010-08-04 | 中山大学 | Face detection and tracking algorithm of infrared thermal image sequence |
| CN106250877A (en) * | 2016-08-19 | 2016-12-21 | 深圳市赛为智能股份有限公司 | Near-infrared face identification method and device |
| KR101754154B1 (en) * | 2016-01-25 | 2017-07-05 | 주식회사 에스원 | Fever Patient Monitering Syatem at Public Place by Using Multiple Band Camera and Statistical Sampling and Method thereof |
| 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 |
| CN110044486A (en) * | 2019-03-11 | 2019-07-23 | 武汉高德智感科技有限公司 | Method, apparatus, the equipment of repetition of alarms are avoided for human body inspection and quarantine system |
| CN110751015A (en) * | 2019-09-02 | 2020-02-04 | 合肥工业大学 | Perfusion optimization and artificial intelligence emotion monitoring method for facial infrared heat map |
| WO2020073505A1 (en) * | 2018-10-11 | 2020-04-16 | 平安科技（深圳）有限公司 | Image processing method, apparatus and device based on image recognition, and storage medium |
| CN111426388A (en) * | 2020-03-31 | 2020-07-17 | 高新兴科技集团股份有限公司 | Personnel body temperature measuring method, system, computer storage medium and electronic equipment |
| CN111507200A (en) * | 2020-03-26 | 2020-08-07 | 北京迈格威科技有限公司 | Body temperature detection method, body temperature detection device and dual-optical camera |
| CN111583593A (en) * | 2020-05-06 | 2020-08-25 | 长春市长光芯忆科技有限公司 | Dual-band self-adaptive intelligent temperature measurement face recognition method |
| CN111626125A (en) * | 2020-04-26 | 2020-09-04 | 浙江大华技术股份有限公司 | Face temperature detection method, system and device and computer equipment |
-
2020
- 2020-11-04 CN CN202011219015.9A patent/CN112380938B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101793562A (en) * | 2010-01-29 | 2010-08-04 | 中山大学 | Face detection and tracking algorithm of infrared thermal image sequence |
| KR101754154B1 (en) * | 2016-01-25 | 2017-07-05 | 주식회사 에스원 | Fever Patient Monitering Syatem at Public Place by Using Multiple Band Camera and Statistical Sampling and Method thereof |
| CN106250877A (en) * | 2016-08-19 | 2016-12-21 | 深圳市赛为智能股份有限公司 | Near-infrared face identification method and device |
| WO2020073505A1 (en) * | 2018-10-11 | 2020-04-16 | 平安科技（深圳）有限公司 | Image processing method, apparatus and device based on image recognition, and storage medium |
| 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 |
| CN110044486A (en) * | 2019-03-11 | 2019-07-23 | 武汉高德智感科技有限公司 | Method, apparatus, the equipment of repetition of alarms are avoided for human body inspection and quarantine system |
| CN110751015A (en) * | 2019-09-02 | 2020-02-04 | 合肥工业大学 | Perfusion optimization and artificial intelligence emotion monitoring method for facial infrared heat map |
| CN111507200A (en) * | 2020-03-26 | 2020-08-07 | 北京迈格威科技有限公司 | Body temperature detection method, body temperature detection device and dual-optical camera |
| CN111426388A (en) * | 2020-03-31 | 2020-07-17 | 高新兴科技集团股份有限公司 | Personnel body temperature measuring method, system, computer storage medium and electronic equipment |
| CN111626125A (en) * | 2020-04-26 | 2020-09-04 | 浙江大华技术股份有限公司 | Face temperature detection method, system and device and computer equipment |
| CN111583593A (en) * | 2020-05-06 | 2020-08-25 | 长春市长光芯忆科技有限公司 | Dual-band self-adaptive intelligent temperature measurement face recognition method |
Non-Patent Citations (1)
| Title |
|---|
| 双光谱智能体温检测与健康大数据管理系统;张洁茹等;北京航空航天大学学报;第46卷(第9期);第1739-1746页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112380938A (en) | 2021-02-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10657388B2 (en) | Robust simultaneous localization and mapping via removal of dynamic traffic participants | |
| CN110705405B (en) | Target labeling method and device | |
| CN109426785B (en) | Human body target identity recognition method and device | |
| CN109727275B (en) | Object detection method, device, system and computer readable storage medium | |
| CN111553234B (en) | Pedestrian tracking method and device integrating facial features and Re-ID feature ordering | |
| CN111127508B (en) | Target tracking method and device based on video | |
| CN111259868B (en) | Reverse vehicle detection method, system and medium based on convolutional neural network | |
| CN111639653B (en) | False detection image determining method, device, equipment and medium | |
| CN110660102B (en) | Speaker recognition method, device and system based on artificial intelligence | |
| EP3236366B1 (en) | Information processing apparatus, information processing method, and storage medium | |
| CN109447022B (en) | Lens type identification method and device | |
| CN113240880A (en) | Fire detection method and device, electronic equipment and storage medium | |
| CN110647818A (en) | Identification method and device for shielding target object | |
| CN113869137A (en) | Event detection method and device, terminal equipment and storage medium | |
| CN112380938B (en) | Face recognition and temperature measurement method, device, equipment and medium | |
| CN110298302B (en) | Human body target detection method and related equipment | |
| CN110472499B (en) | Pedestrian re-identification method and device | |
| CN111881740A (en) | Face recognition method, face recognition device, electronic equipment and medium | |
| CN113256683B (en) | Target tracking method and related equipment | |
| CN113158773B (en) | Training method and training device for living body detection model | |
| CN110610178A (en) | Image recognition method, device, terminal and computer readable storage medium | |
| CN114267076B (en) | Image identification method, device, equipment and storage medium | |
| CN110782439B (en) | Method and device for auxiliary detection of image annotation quality | |
| CN113205079A (en) | Face detection method and device, electronic equipment and storage medium | |
| CN109949335B (en) | Image processing method and device |
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 |