CN111353367A - Face attendance checking method, device, equipment and storage medium based on thermal imaging - Google Patents
Face attendance checking method, device, equipment and storage medium based on thermal imaging Download PDFInfo
- Publication number
- CN111353367A CN111353367A CN201910765972.2A CN201910765972A CN111353367A CN 111353367 A CN111353367 A CN 111353367A CN 201910765972 A CN201910765972 A CN 201910765972A CN 111353367 A CN111353367 A CN 111353367A
- Authority
- CN
- China
- Prior art keywords
- face
- attendance
- thermal imaging
- personnel
- frame picture
- 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.)
- Pending
Links
Images
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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- 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
- 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
- G06V40/40—Spoof detection, e.g. liveness detection
- G06V40/45—Detection of the body part being alive
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
- G07C1/10—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people together with the recording, indicating or registering of other data, e.g. of signs of identity
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a face attendance checking method, device, equipment and storage medium based on thermal imaging, and belongs to the technical field of image processing. The method comprises the following steps: acquiring a common camera image video and a thermal imaging camera image video in the same area at the same time; acquiring a living object set according to the common camera image video and the thermal imaging camera image video; comparing each face characteristic value in the living body object set with a face characteristic value in a personnel information table which is input in advance to obtain an attendance personnel set; acquiring personnel information of attendance personnel in the attendance personnel set according to the attendance personnel set and the personnel information table; and respectively drawing the personnel information of the attendance personnel on corresponding head portraits in the common camera image video. The user can obtain all the lists of people who actually arrive and are living bodies in a short time; the detection error caused by the reasons such as figure pictures, figure statues and the like can be effectively prevented.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a human face attendance checking method, a human face attendance checking device, human face attendance checking equipment and a human face attendance checking storage medium based on thermal imaging.
Background
In life, teaching and enterprises, the condition of roll attendance in a specific place is often met. The common camera is used for photographing and detecting the face to obtain the real person list, the required environment requirement is higher, if the wall or the person clothes are provided with head portrait patterns, the common camera cannot distinguish whether the face is the living face, and therefore the detection result is in error, and the attendance data fails.
Disclosure of Invention
In view of the above, the present invention is directed to a method, an apparatus, a device and a storage medium for checking attendance on human face based on thermal imaging, wherein a user can obtain a list of all persons who actually arrive and are real living bodies in a very short time; the occurrence of detection errors caused by the figure pictures, figure statues and other reasons can be effectively prevented.
Based on the above purpose, the invention provides a face attendance method based on thermal imaging, which comprises the following steps:
acquiring a common camera image video and a thermal imaging camera image video in the same area at the same time;
acquiring a living object set according to the common camera image video and the thermal imaging camera image video;
comparing each face characteristic value in the living body object set with a face characteristic value in a personnel information table which is input in advance to obtain an attendance personnel set;
acquiring personnel information of attendance personnel in the attendance personnel set according to the attendance personnel set and the personnel information table;
and respectively drawing the personnel information of the attendance personnel on corresponding head portraits in the common camera image video.
Preferably, the obtaining a living object set according to the common camera image video and the thermal imaging camera image video includes:
extracting a first video frame picture from the common camera image video;
extracting a second video frame picture corresponding to the first video frame picture from the thermal imaging camera image video;
obtaining coordinate positions, width heights and characteristic values of all human faces in the first video frame picture according to the first video frame picture;
acquiring a face thermal imaging picture corresponding to the face in the second video frame picture according to the coordinate position and the width height of each face;
and judging whether the face corresponding to each face thermal imaging picture is a living body object face to obtain the living body object set.
More preferably, the extracting the first video frame picture from the common camera image video includes:
determining the extraction time period of the common camera image video;
and extracting the last frame picture in the extraction time period as the first video frame picture.
More preferably, the extracting, by the thermal imaging camera image video, a second video frame picture corresponding to the first video frame picture includes:
recording a first time for acquiring the first video frame picture;
and extracting a second video frame picture corresponding to the first time from the thermal imaging camera image video.
More preferably, the obtaining of the coordinate positions, the width heights, and the feature values of all the faces in the first video frame picture according to the first video frame picture includes:
converting the first video frame picture into a gray-scale image, and performing gray-scale image histogram equalization operation on the gray-scale image;
and scanning the gray level image subjected to the gray level image histogram equalization operation to obtain the coordinate positions, the width heights and the characteristic values of all the human faces in the first video frame image.
Preferably, the comparing the face characteristic value in the living body object set with a face characteristic value in a pre-entered staff information table to obtain an attendance staff set includes:
calculating each face characteristic value in the living body object set and the face characteristic value in the pre-recorded personnel information table to obtain a floating point numerical value;
and comparing the floating point numerical value with a threshold value to obtain the attendance checking personnel set.
Preferably, the method further comprises entering a personnel information table in advance, wherein the personnel information table entry comprises:
inputting the faces of all the personnel to be checked;
extracting the face characteristic values of all the personnel to be checked;
and storing the personnel information and the face characteristic value of all the personnel to be checked to obtain the personnel information table.
Based on the same inventive concept, the invention also provides a human face attendance device based on thermal imaging, which comprises:
the image video acquisition module is used for acquiring a common camera image video and a thermal imaging camera image video in the same region at the same time;
the living body object set obtaining module is used for obtaining a living body object set according to the common camera image video and the thermal imaging camera image video;
the attendance checking personnel set obtaining module is used for comparing the face characteristic value in the living body object set with a face characteristic value in a personnel information table which is input in advance to obtain an attendance checking personnel set;
the attendance staff information obtaining module is used for obtaining the staff information of the attendance staff in the attendance staff set according to the attendance staff set and the staff information table;
and the information drawing module is used for respectively drawing the personnel information of the attendance personnel on corresponding head portraits in the common camera image video.
Preferably, the living object set obtaining module includes:
the first video frame picture acquisition unit is used for extracting a first video frame picture from the common camera image video;
the second video frame picture acquisition unit is used for extracting a second video frame picture corresponding to the first video frame picture from the thermal imaging camera image video;
the face information obtaining unit is used for obtaining the coordinate positions, the width heights and the characteristic values of all faces in the first video frame picture according to the first video frame picture;
the face thermal imaging picture acquisition unit is used for acquiring a face thermal imaging picture corresponding to the face in the second video frame picture according to the coordinate position and the width height of each face;
and the living body object set obtaining unit is used for judging whether the face corresponding to each face thermal imaging picture is a living body object face to obtain the living body object set.
More preferably, the first video frame picture acquiring unit is configured to:
determining the extraction time period of the common camera image video;
and extracting the last frame picture in the extraction time period as the first video frame picture.
More preferably, the second video frame picture acquiring unit is configured to:
recording a first time for acquiring the first video frame picture;
and extracting a second video frame picture corresponding to the first time from the thermal imaging camera image video.
More preferably, the face information obtaining unit is configured to:
converting the first video frame picture into a gray-scale image, and performing gray-scale image histogram equalization operation on the gray-scale image;
and scanning the gray level image subjected to the gray level image histogram equalization operation to obtain the coordinate positions, the width heights and the characteristic values of all the human faces in the first video frame image.
Preferably, the attendance checking staff set obtaining module includes:
a floating point numerical value obtaining unit, configured to calculate each face characteristic value in the living object set and a face characteristic value in the pre-entered person information table to obtain a floating point numerical value;
and the attendance personnel set obtaining unit is used for comparing the floating point numerical value with a threshold value to obtain the attendance personnel set.
Preferably, the device further comprises a personnel information table entry module for entering a personnel information table in advance; the personnel information table entry module comprises:
the face input unit is used for inputting the faces of all the persons to be checked;
the human face characteristic value extraction unit is used for extracting human face characteristic values of all the persons to be checked;
and the personnel information table obtaining unit is used for storing the personnel information and the face characteristic value of all the personnel to be checked and obtaining the personnel information table.
Based on the same inventive concept, the present invention also provides an electronic device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements any one of the methods described above when executing the program.
Based on the same inventive concept, the present invention also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform any of the methods described above.
From the above, according to the human face attendance checking method, device, equipment and storage medium based on thermal imaging provided by the invention, the thermal imaging camera receives infrared rays emitted by an object, converts the temperature into a colored real-time video image to be displayed, and judges whether a detection target is a living body according to the heat distribution in the real-time video image; the living body detection can be simultaneously carried out for multiple people, the data source is guaranteed to be real, errors of detection data caused by face pictures or statues can be effectively prevented, and the data result is guaranteed to be real and effective.
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 schematic flow chart of a method of an embodiment of the present invention;
FIG. 2 is an explanation of step S20 in FIG. 1;
fig. 3 is an explanation of step S201 in fig. 2;
FIG. 4 is an explanation of step S202 in FIG. 2;
FIG. 5 is an explanatory view of step S203 in FIG. 2;
FIG. 6 is an explanatory view of step S30 in FIG. 1;
FIG. 7 is a schematic view of a personnel information form entry flow diagram;
fig. 8 is a schematic structural diagram of an apparatus according to an embodiment of the present invention.
Detailed Description
In order that the objects, aspects and advantages of the present invention will become more apparent, the present invention will be further described in detail with reference to the following detailed description of preferred embodiments thereof, which is illustrated in the accompanying drawings.
It should be noted that all expressions using "first" and "second" in the embodiments of the present invention are used for distinguishing two entities with the same name but different names or different parameters, and it should be noted that "first" and "second" are merely for convenience of description and should not be construed as limitations of the embodiments of the present invention, and they are not described in any more detail in the following embodiments.
The embodiment of the invention provides a face attendance method based on thermal imaging, which comprises the following steps:
acquiring a common camera image video and a thermal imaging camera image video in the same area at the same time;
acquiring a living object set according to the common camera image video and the thermal imaging camera image video;
comparing each face characteristic value in the living body object set with a face characteristic value in a personnel information table which is input in advance to obtain an attendance personnel set;
acquiring personnel information of attendance personnel in the attendance personnel set according to the attendance personnel set and the personnel information table;
and respectively drawing the personnel information of the attendance personnel on corresponding head portraits in the common camera image video.
Fig. 1 is a schematic flow chart of a method according to an embodiment of the present invention, and as shown in fig. 1, in an embodiment of a face attendance method based on thermal imaging provided by the present invention, the method includes:
s10, acquiring a common camera image video and a thermal imaging camera image video in the same area at the same time;
the common camera and the thermal imaging camera simultaneously acquire images of the same area, and respectively acquire the image video of the common camera and the image video of the thermal imaging camera in the same area at the same time.
S20, acquiring a living object set according to the common camera image video and the thermal imaging camera image video;
the thermal imaging camera can receive infrared rays emitted by an object, converts the temperature into a colored real-time video image to be displayed, and judges whether a detection target is a living body according to heat distribution in the real-time video image.
A face set can be obtained according to the ordinary camera image video obtained in the step S10, and whether the face in the face set is a living object face can be judged through the thermal imaging camera image video; and if the human face in the human face set is judged to be the living body object human face, the detected living body object human face forms the living body object set. And if the human face in the human face set is judged to be a non-living object human face, the human face is error data, and the detected non-living object human face forms a non-living object set.
S30, comparing each face characteristic value in the living body object set with a face characteristic value in a pre-recorded personnel information table to obtain an attendance personnel set;
before face attendance, all the staff to be checked need to be subjected to information statistics in advance to obtain a staff information table. The personnel information table comprises the human face images, the human face characteristic values, the names, the sexes, the ages and other personnel information of all the personnel to be examined. And comparing each face characteristic value in the living body object set obtained in the step S20 with a face characteristic value in the personnel information table which is recorded in advance to obtain an attendance personnel set. It should be noted that the living object set also includes non-attendance persons other than all the persons to be checked, and the detected non-attendance persons are stored in the non-attendance person set. The face feature value refers to data such as shapes and sizes of parts such as eyes, nose, mouth, and chin of the face.
S40, obtaining staff information of the attendance staff in the attendance staff set according to the attendance staff set and the staff information table;
the staff information table contains the face images, the face characteristic values, the names, the sexes, the ages and other staff information of all the staff to be checked, the attendance staff set obtained in the step S30 and the staff information table are subjected to combined query, and the staff information of the attendance staff in the attendance staff set can be obtained. It should be noted that, when the attendance personnel set obtained in step S30 and the personnel information table are jointly queried, each face feature value in the attendance personnel set obtained in step S30 and a face feature value in the personnel information table are compared one by one to obtain a similarity percentage, and when the similarity percentage is greater than a threshold, the matching is successful, and the threshold is 80%.
S50, drawing the staff information of the attendance staff on corresponding head portraits in the common camera image video respectively;
when the image video is edited, the image video is firstly decomposed into a plurality of frames of pictures, then the pictures are edited, and the edited pictures are edited into the image video, so that the image video editing is completed.
And respectively drawing all the faces in the attendance personnel set on a common camera video frame picture extracted from the common camera video through the recorded face coordinate position and the face width height, and respectively drawing the personnel information of the attendance personnel in the attendance personnel set on a head portrait corresponding to the common camera video frame picture, so that all the faces in the attendance personnel set are respectively drawn on the common camera video, and the personnel information of the attendance personnel is respectively drawn on a corresponding head portrait in the common camera video.
And respectively drawing all the faces in the non-attendance personnel set on a common camera video frame picture extracted from the common camera image video through the recorded face coordinate position and the face width height, so that all the faces in the non-attendance personnel set are respectively drawn on the common camera image video.
The steps S10 to S50 may be repeated several times until the attendance is completed. In the embodiment of the present invention, preferably, the steps S10 to S50 are cycled for 6 times, and the attendance is complete.
Fig. 2 is an explanation of step S20 in fig. 1, and in particular, the step S20 of obtaining a living object set from the normal camera image video and the thermal imaging camera image video includes:
s201, extracting a first video frame picture from the common camera image video;
the image video is composed of countless frames of pictures, and one frame is extracted from the common camera image video to be used as a first video frame picture.
S202, extracting a second video frame picture corresponding to the first video frame picture from the thermal imaging camera image video;
because the common camera and the thermal imaging camera simultaneously acquire images in the same area, the image video of the common camera and the image video of the thermal imaging camera are synchronous, and after the first video frame picture is extracted from the image video of the common camera, the second video frame picture corresponding to the first video frame picture can be extracted from the image video of the thermal imaging camera.
S203, obtaining coordinate positions, width heights and characteristic values of all human faces in the first video frame picture according to the first video frame picture;
and detecting the first video frame picture by using an Intel vision library OpenCV to obtain all faces in the first video frame picture and coordinate positions, width heights and widths of all the faces, wherein all the faces in the detected first video frame picture form a face set.
And according to the first video frame picture, calculating a character string value describing the face mark point, namely a face characteristic value, through an FR SDK provided by Intel, and calculating each face in the face set to obtain a corresponding characteristic value.
S204, obtaining a face thermal imaging picture corresponding to the face in the second video frame picture according to the coordinate position and the width height of each face;
because the common camera image video and the thermal imaging camera image video are synchronous, the same face coordinate position and the same width height in the common camera image video and the thermal imaging camera image video correspond to the same face at the same time; and in the face set obtained from the first video frame picture, according to the coordinate position and the width height of each face, a corresponding face thermal imaging picture can be obtained from the second video frame picture.
S205, judging whether the face corresponding to each face thermal imaging picture is a living body object face, and obtaining the living body object set.
Judging all the face thermal imaging pictures obtained from the second video frame picture, if the face corresponding to a certain face thermal imaging picture is detected to be a non-living object face, the face corresponding to the face thermal imaging picture is a pattern on a wall or clothes, storing the face corresponding to the face thermal imaging picture into a non-living object set, and continuing to judge other face thermal imaging pictures without operating the face subsequently. It should be noted that, when all the face thermal imaging pictures obtained from the second video frame picture are judged, possible human body ROI regions Rt and Rm are respectively compared through thermal imaging threshold analysis and motion analysis, then a mixed ROI region Rf is obtained through ROI fusion, then the height and width of the human body region are respectively adjusted, and finally the final Pedestrian ROI is determined through the width/height ratio and area judgment.
And if the face corresponding to a certain face thermal imaging picture is detected to be the face of the living body object, storing the face corresponding to the face thermal imaging picture into a living body object set to obtain the living body object set.
Fig. 3 is an explanation of step S201, specifically, the step S201 extracts a first video frame picture from the normal camera image video, and includes:
s2011, determining an extraction time period of the image video of the common camera;
the image video is composed of countless frames of pictures, and when one frame is extracted from the ordinary camera image video as a first video frame picture, an extraction period of the ordinary camera image video is determined first. In the embodiment of the present invention, preferably, the extraction period is determined to be 1 second.
S2012, extracting the last frame picture in the extraction time period as the first video frame picture;
and after the extraction time period is determined, extracting the last frame picture of the common camera image video in the extraction time period as the first video frame picture. In the embodiment of the present invention, preferably, the extraction period is determined to be 1 second, the ordinary camera image video generates 15 to 30 frames of pictures per second, and the last frame of picture is extracted as the first video frame picture.
Fig. 4 is an explanation of step S202, specifically, the step S202 extracts, from the thermal imaging camera image video, a second video frame picture corresponding to the first video frame picture, and includes:
s2021, recording the first time for acquiring the first video frame picture;
in an embodiment of the present invention, preferably, the first time is accurate to milliseconds.
S2022, extracting a second video frame picture corresponding to the first time from the thermal imaging camera image video;
the common camera image video and the thermal imaging camera image video are synchronous, so that after the first video frame picture is obtained by the common camera image video, the first time for extracting the first video frame picture is recorded, and then the second video frame picture is extracted from the thermal imaging camera image video according to the first time, wherein the second video frame picture corresponds to the first video frame picture.
Fig. 5 is an explanation of step S203, specifically, the step S203 obtains the coordinate positions, width heights, and feature values of all faces in the first video frame picture according to the first video frame picture, and includes:
s2031, converting the first video frame picture into a gray-scale image, and performing gray-scale image histogram equalization operation on the gray-scale image;
s2032, scanning the gray level image subjected to gray level image histogram equalization operation to obtain coordinate positions, width heights and characteristic values of all human faces in the first video frame image;
when scanning the gray scale image subjected to gray scale image histogram equalization operation, taking the gray scale image boundary as an example, the image in the computer is a matrix formed by numbers, the computer program firstly calculates the gray scale value X in the whole window, then calculates the black gray scale value Y in the rectangular frame, then calculates (X-2Y) to obtain a difference value, calculates the ratio of the difference value to the X, if the ratio is within the threshold range, the gray scale image boundary accords with the boundary characteristics, continues to scan other areas of the gray scale image to obtain the coordinate positions and the width heights of all the human faces in the first video frame image, and the detected all the human faces in the first video frame image form a human face set.
According to the first video frame picture, character string values (characteristic values) describing face mark points are obtained through FR SDK calculation provided by Intel, and each face in the face set is respectively calculated to obtain corresponding characteristic values
Fig. 6 is an explanation of step S30, specifically, step S30 is implemented by comparing each face feature value in the living object set with a face feature value in a pre-entered staff information table to obtain an attendance staff set, and includes:
s301, calculating each face characteristic value in the living body object set and the face characteristic value in the pre-recorded personnel information table to obtain a floating point numerical value;
and calculating each face characteristic value in the living body object set and the face characteristic value in the pre-recorded personnel information table through an FR SDK provided by Intel to obtain a floating point numerical value corresponding to each face characteristic value, wherein the floating point numerical value is between 0 and 1.
S302, comparing the floating point numerical value with a threshold value to obtain the attendance checking personnel set;
comparing each floating point numerical value obtained in the step S301 with a threshold, if the floating point numerical value is greater than the threshold, it indicates that the face feature value corresponding to the floating point numerical value is included in the staff information table, and the face corresponding to the face feature value is from the staff to be checked in the staff information table and is stored in the attendance staff set. If the floating point numerical value is smaller than the threshold value, the fact that the face characteristic value corresponding to the floating point numerical value is not included in the staff information table is indicated, and the face corresponding to the face characteristic value does not belong to staff to be checked in the staff information table and is a non-attendance staff and is stored in a non-attendance staff set. Preferably, in the embodiment of the present invention, the threshold is 0.55, and the attendance success rate is the highest.
Fig. 7 is a schematic view of a staff information table entry flow, specifically, in an embodiment of the present invention, the method for checking attendance on a human face based on thermal imaging further includes entering a staff information table in advance, where the staff information table entry includes:
s001, inputting the faces of all the staff to be checked;
s002, extracting the face characteristic values of all the staff to be checked;
and S003, storing the personnel information and the face characteristic values of all the personnel to be checked to obtain the personnel information table.
Note that the person information includes information such as name, sex, age, and the like.
Fig. 8 is a schematic structural diagram of an apparatus according to an embodiment of the present invention, and as shown in fig. 8, the apparatus for checking attendance on a human face based on thermal imaging disclosed in the embodiment of the present invention includes:
an image video acquiring module 801, configured to acquire a common camera image video and a thermal imaging camera image video in the same area at the same time;
a living object set obtaining module 802, configured to obtain a living object set according to the common camera image video and the thermal imaging camera image video;
an attendance personnel set obtaining module 803, configured to compare the face feature value in the living object set with a face feature value in a personnel information table entered in advance, to obtain an attendance personnel set;
an attendance staff information obtaining module 804, configured to obtain staff information of attendance staff in the attendance staff set according to the attendance staff set and the staff information table;
and the information drawing module 805 is configured to respectively draw the staff information of the attendance staff on corresponding head portraits in the ordinary camera image video.
In this embodiment of the present invention, the living object set obtaining module 802 includes:
the first video frame picture acquisition unit is used for extracting a first video frame picture from the common camera image video;
the second video frame picture acquisition unit is used for extracting a second video frame picture corresponding to the first video frame picture from the thermal imaging camera image video;
the face information obtaining unit is used for obtaining the coordinate positions, the width heights and the characteristic values of all faces in the first video frame picture according to the first video frame picture;
the face thermal imaging picture acquisition unit is used for acquiring a face thermal imaging picture corresponding to the face in the second video frame picture according to the coordinate position and the width height of each face;
and the living body object set obtaining unit is used for judging whether the face corresponding to each face thermal imaging picture is a living body object face to obtain the living body object set.
Specifically, the first video frame picture acquiring unit is configured to:
determining the extraction time period of the common camera image video;
and extracting the last frame picture in the extraction time period as the first video frame picture.
Specifically, the second video frame picture acquiring unit is configured to:
recording a first time for acquiring the first video frame picture;
and extracting a second video frame picture corresponding to the first time from the thermal imaging camera image video.
Specifically, the face information obtaining unit is configured to:
converting the first video frame picture into a gray-scale image, and performing gray-scale image histogram equalization operation on the gray-scale image;
and scanning the gray level image subjected to the gray level image histogram equalization operation to obtain the coordinate positions, the width heights and the characteristic values of all the human faces in the first video frame image.
In this embodiment of the present invention, the attendance personnel set obtaining module 803 includes:
a floating point numerical value obtaining unit, configured to calculate each face characteristic value in the living object set and a face characteristic value in the pre-entered person information table to obtain a floating point numerical value;
and the attendance personnel set obtaining unit is used for comparing the floating point numerical value with a threshold value to obtain the attendance personnel set.
In the embodiment of the present invention, the apparatus further includes a personnel information table entry module (not shown in the figure) for entering a personnel information table in advance; the personnel information table entry module comprises:
the face input unit is used for inputting the faces of all the persons to be checked;
the human face characteristic value extraction unit is used for extracting human face characteristic values of all the persons to be checked;
and the personnel information table obtaining unit is used for storing the personnel information and the face characteristic value of all the personnel to be checked and obtaining the personnel information table.
The apparatus of the foregoing embodiment is used to implement the corresponding method in the foregoing embodiment, and has the beneficial effects of the corresponding method embodiment, which are not described herein again.
The embodiment of the invention also provides a face attendance device based on thermal imaging, the device comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, and the processor realizes any one of the above methods based on the thermal imaging when executing the program.
Embodiments of the present invention also provide a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the method for checking attendance on a human face based on thermal imaging.
Those of ordinary skill in the art will understand that: the discussion of any embodiment above is meant to be exemplary only, and is not intended to intimate that the scope of the disclosure, including the claims, is limited to these examples; within the idea of the invention, also features in the above embodiments or in different embodiments may be combined, steps may be implemented in any order, and there are many other variations of the different aspects of the invention as described above, which are not provided in detail for the sake of brevity.
In addition, well known power/ground connections to Integrated Circuit (IC) chips and other components may or may not be shown within the provided figures for simplicity of illustration and discussion, and so as not to obscure the invention. Furthermore, devices may be shown in block diagram form in order to avoid obscuring the invention, and also in view of the fact that specifics with respect to implementation of such block diagram devices are highly dependent upon the platform within which the present invention is to be implemented (i.e., specifics should be well within purview of one skilled in the art). Where specific details (e.g., circuits) are set forth in order to describe example embodiments of the invention, it should be apparent to one skilled in the art that the invention can be practiced without, or with variation of, these specific details. Accordingly, the description is to be regarded as illustrative instead of restrictive.
While the present invention has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic ram (dram)) may use the discussed embodiments.
The embodiments of the invention are intended to embrace all such alternatives, modifications and variances that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, substitutions, improvements and the like that may be made without departing from the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (16)
1. A face attendance method based on thermal imaging is characterized by comprising the following steps:
acquiring a common camera image video and a thermal imaging camera image video in the same area at the same time;
acquiring a living object set according to the common camera image video and the thermal imaging camera image video;
comparing each face characteristic value in the living body object set with a face characteristic value in a personnel information table which is input in advance to obtain an attendance personnel set;
acquiring personnel information of attendance personnel in the attendance personnel set according to the attendance personnel set and the personnel information table;
and respectively drawing the personnel information of the attendance personnel on corresponding head portraits in the common camera image video.
2. The thermal imaging-based human face attendance method of claim 1, wherein the obtaining of the set of living objects from the normal camera image video and the thermal imaging camera image video comprises:
extracting a first video frame picture from the common camera image video;
extracting a second video frame picture corresponding to the first video frame picture from the thermal imaging camera image video;
obtaining coordinate positions, width heights and characteristic values of all human faces in the first video frame picture according to the first video frame picture;
acquiring a face thermal imaging picture corresponding to the face in the second video frame picture according to the coordinate position and the width height of each face;
and judging whether the face corresponding to each face thermal imaging picture is a living body object face to obtain the living body object set.
3. The thermal imaging-based face attendance method of claim 2, wherein the extracting of the first video frame picture from the common camera image video comprises:
determining the extraction time period of the common camera image video;
and extracting the last frame picture in the extraction time period as the first video frame picture.
4. The thermal imaging-based face attendance method of claim 2, wherein the video extraction by the thermal imaging camera image of the second video frame picture corresponding to the first video frame picture comprises:
recording a first time for acquiring the first video frame picture;
and extracting a second video frame picture corresponding to the first time from the thermal imaging camera image video.
5. The thermal imaging-based face attendance method of claim 2, wherein the obtaining of the coordinate positions, the width heights and the feature values of all the faces in the first video frame picture from the first video frame picture comprises:
converting the first video frame picture into a gray-scale image, and performing gray-scale image histogram equalization operation on the gray-scale image;
and scanning the gray level image subjected to the gray level image histogram equalization operation to obtain the coordinate positions, the width heights and the characteristic values of all the human faces in the first video frame image.
6. The thermal imaging-based human face attendance method of claim 1, wherein the comparing of the human face characteristic values in the living object set with human face characteristic values in a pre-entered personnel information table to obtain an attendance personnel set comprises:
calculating each face characteristic value in the living body object set and the face characteristic value in the pre-recorded personnel information table to obtain a floating point numerical value;
and comparing the floating point numerical value with a threshold value to obtain the attendance checking personnel set.
7. The thermal imaging-based face attendance method of claim 1, further comprising pre-entering a staff information table, the staff information table entry comprising:
inputting the faces of all the personnel to be checked;
extracting the face characteristic values of all the personnel to be checked;
and storing the personnel information and the face characteristic value of all the personnel to be checked to obtain the personnel information table.
8. A human face attendance device based on thermal imaging, the device comprising:
the image video acquisition module is used for acquiring a common camera image video and a thermal imaging camera image video in the same region at the same time;
the living body object set obtaining module is used for obtaining a living body object set according to the common camera image video and the thermal imaging camera image video;
the attendance checking personnel set obtaining module is used for comparing the face characteristic value in the living body object set with a face characteristic value in a personnel information table which is input in advance to obtain an attendance checking personnel set;
the attendance staff information obtaining module is used for obtaining the staff information of the attendance staff in the attendance staff set according to the attendance staff set and the staff information table;
and the information drawing module is used for respectively drawing the personnel information of the attendance personnel on corresponding head portraits in the common camera image video.
9. The thermal imaging-based face attendance device of claim 8, wherein the live object set obtaining module comprises:
the first video frame picture acquisition unit is used for extracting a first video frame picture from the common camera image video;
the second video frame picture acquisition unit is used for extracting a second video frame picture corresponding to the first video frame picture from the thermal imaging camera image video;
the face information obtaining unit is used for obtaining the coordinate positions, the width heights and the characteristic values of all faces in the first video frame picture according to the first video frame picture;
the face thermal imaging picture acquisition unit is used for acquiring a face thermal imaging picture corresponding to the face in the second video frame picture according to the coordinate position and the width height of each face;
and the living body object set obtaining unit is used for judging whether the face corresponding to each face thermal imaging picture is a living body object face to obtain the living body object set.
10. The thermal imaging-based face attendance device of claim 9, wherein the first video frame picture acquisition unit is configured to:
determining the extraction time period of the common camera image video;
and extracting the last frame picture in the extraction time period as the first video frame picture.
11. The thermal imaging-based face attendance device of claim 9, wherein the second video frame picture acquisition unit is configured to:
recording a first time for acquiring the first video frame picture;
and extracting a second video frame picture corresponding to the first time from the thermal imaging camera image video.
12. The thermal imaging-based face attendance device of claim 9, wherein the face information obtaining unit is configured to:
converting the first video frame picture into a gray-scale image, and performing gray-scale image histogram equalization operation on the gray-scale image;
and scanning the gray level image subjected to the gray level image histogram equalization operation to obtain the coordinate positions, the width heights and the characteristic values of all the human faces in the first video frame image.
13. The thermal imaging-based human face attendance device of claim 8, wherein the attendance personnel set obtaining module comprises:
a floating point numerical value obtaining unit, configured to calculate each face characteristic value in the living object set and a face characteristic value in the pre-entered person information table to obtain a floating point numerical value;
and the attendance personnel set obtaining unit is used for comparing the floating point numerical value with a threshold value to obtain the attendance personnel set.
14. The thermal imaging-based human face attendance device of claim 8, wherein the device further comprises a personnel information table entry module for entering a personnel information table in advance; the personnel information table entry module comprises:
the face input unit is used for inputting the faces of all the persons to be checked;
the human face characteristic value extraction unit is used for extracting human face characteristic values of all the persons to be checked;
and the personnel information table obtaining unit is used for storing the personnel information and the face characteristic value of all the personnel to be checked and obtaining the personnel information table.
15. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1 to 7 when executing the program.
16. A non-transitory computer readable storage medium storing computer instructions for causing a computer to perform the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910765972.2A CN111353367A (en) | 2019-08-19 | 2019-08-19 | Face attendance checking method, device, equipment and storage medium based on thermal imaging |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910765972.2A CN111353367A (en) | 2019-08-19 | 2019-08-19 | Face attendance checking method, device, equipment and storage medium based on thermal imaging |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111353367A true CN111353367A (en) | 2020-06-30 |
Family
ID=71193908
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910765972.2A Pending CN111353367A (en) | 2019-08-19 | 2019-08-19 | Face attendance checking method, device, equipment and storage medium based on thermal imaging |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111353367A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115273401A (en) * | 2022-08-03 | 2022-11-01 | 浙江慧享信息科技有限公司 | Method and system for automatically sensing falling of person |
-
2019
- 2019-08-19 CN CN201910765972.2A patent/CN111353367A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115273401A (en) * | 2022-08-03 | 2022-11-01 | 浙江慧享信息科技有限公司 | Method and system for automatically sensing falling of person |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102596897B1 (en) | Method of motion vector and feature vector based fake face detection and apparatus for the same | |
| CN105335722B (en) | Detection system and method based on depth image information | |
| US11074436B1 (en) | Method and apparatus for face recognition | |
| CN108229509B (en) | Method and device for identifying object class and electronic equipment | |
| CN105740775B (en) | Three-dimensional face living body identification method and device | |
| CN109858375B (en) | Living body face detection method, terminal and computer readable storage medium | |
| CN108549852B (en) | Specific scene downlink person detector automatic learning method based on deep network enhancement | |
| JP2017033469A (en) | Image identification method, image identification device and program | |
| Datcu et al. | Noncontact automatic heart rate analysis in visible spectrum by specific face regions | |
| CN110287862B (en) | Anti-candid detection method based on deep learning | |
| US20150036893A1 (en) | Authentication device and method | |
| CN107944395B (en) | Method and system for verifying and authenticating integration based on neural network | |
| US10395090B2 (en) | Symbol detection for desired image reconstruction | |
| CN106203428A (en) | The image significance detection method merged based on blur estimation | |
| CN111353367A (en) | Face attendance checking method, device, equipment and storage medium based on thermal imaging | |
| CN109697421A (en) | Evaluation method, device, computer equipment and storage medium based on micro- expression | |
| CN113436735A (en) | Body weight index prediction method, device and storage medium based on face structure measurement | |
| CN110826495A (en) | Body left and right limb consistency tracking and distinguishing method and system based on face orientation | |
| US20220207261A1 (en) | Method and apparatus for detecting associated objects | |
| CN110991307B (en) | Face recognition method, device, equipment and storage medium | |
| US20220398866A1 (en) | Method and device of registering face based on video data, and electronic whiteboard | |
| CN110096959B (en) | People flow calculation method, device and computer storage medium | |
| CN113343948A (en) | Satisfaction degree analysis method and system and computer storage medium thereof | |
| CN113657187A (en) | Face recognition method, face recognition equipment and computer-readable storage medium | |
| JP5688514B2 (en) | Gaze measurement system, method and program |
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 |