CN115063852A - Method, device, storage medium and processor for determining staff attendance information - Google Patents

Method, device, storage medium and processor for determining staff attendance information Download PDF

Info

Publication number
CN115063852A
CN115063852A CN202210609519.4A CN202210609519A CN115063852A CN 115063852 A CN115063852 A CN 115063852A CN 202210609519 A CN202210609519 A CN 202210609519A CN 115063852 A CN115063852 A CN 115063852A
Authority
CN
China
Prior art keywords
pedestrian
image
information
attendance
determining
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
Application number
CN202210609519.4A
Other languages
Chinese (zh)
Inventor
黄跃峰
尹倩倩
肖英杰
周志忠
廖登
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhongke Yungu Technology Co Ltd
Original Assignee
Zhongke Yungu Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Zhongke Yungu Technology Co Ltd filed Critical Zhongke Yungu Technology Co Ltd
Priority to CN202210609519.4A priority Critical patent/CN115063852A/en
Publication of CN115063852A publication Critical patent/CN115063852A/en
Pending legal-status Critical Current

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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/51—Indexing; Data structures therefor; Storage structures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/5866—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/10—Office automation; Time management
    • G06Q10/105—Human resources
    • 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
    • G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/761—Proximity, similarity or dissimilarity 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
    • G06V40/20—Movements or behaviour, e.g. gesture recognition
    • 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
    • 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
    • G07C9/00—Individual registration on entry or exit
    • G07C9/30—Individual registration on entry or exit not involving the use of a pass
    • G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
    • G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Business, Economics & Management (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Human Computer Interaction (AREA)
  • Health & Medical Sciences (AREA)
  • Human Resources & Organizations (AREA)
  • General Health & Medical Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Software Systems (AREA)
  • Library & Information Science (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Medical Informatics (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • Artificial Intelligence (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Psychiatry (AREA)
  • Social Psychology (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The embodiment of the application provides a method, a device, a processor and a storage medium for determining staff attendance information. The method comprises the following steps: establishing a pedestrian image database; inputting the pedestrian image in the pedestrian image database into a pedestrian re-identification model; determining pedestrian track information of pedestrians under different image acquisition devices, which is contained in the pedestrian image, through a pedestrian re-identification model; judging whether the pedestrian corresponding to the pedestrian image is a target employee or not according to the image information of the pedestrian image and the information in the worker database; and under the condition that the pedestrian corresponding to the pedestrian image is the target employee, determining the attendance information of the target employee according to the pedestrian track information. Through above-mentioned technical scheme, need not staff's initiative cooperation attendance work, reduce the influence that external factor carries out normal attendance to the staff, further promote staff's attendance fairness, increase substantially staff's attendance rate of accuracy.

Description

Method, device, storage medium and processor for determining staff attendance information
Technical Field
The present application relates to the field of attendance management, and in particular, to a method, an apparatus, a storage medium, and a processor for determining employee attendance information.
Background
Common employee attendance methods include fingerprint attendance, magnetic card attendance, face recognition attendance, and the like. With the rapid development of artificial intelligence, the face recognition attendance method is more and more widely applied. Face recognition attendance relies heavily on the acquisition of faces by cameras. The face recognition attendance is realized by collecting the face of an employee through a camera at a specific position so as to complete attendance of the employee, and the condition that the employee forgets to punch a card to check the attendance and the attendance of the employee is abnormal can be caused. When the camera is used for recognizing the face, external environmental factors can influence the accuracy of face recognition, so that normal attendance of staff cannot be finished.
Disclosure of Invention
An object of the embodiments of the present application is to provide a method, an apparatus, a storage medium, and a processor for determining employee attendance information.
In order to achieve the above object, a first aspect of the present application provides a method for determining employee attendance information, including:
establishing a pedestrian image database;
inputting the pedestrian images in the pedestrian image database into a pedestrian re-identification model;
determining pedestrian track information of pedestrians under different image acquisition devices, which is contained in the pedestrian image, through a pedestrian re-identification model;
judging whether the pedestrian corresponding to the pedestrian image is a target employee or not according to the image information of the pedestrian image and the information in the worker database;
and under the condition that the pedestrian corresponding to the pedestrian image is the target employee, determining the attendance information of the target employee according to the pedestrian track information.
In an embodiment of the application, the step of determining the pedestrian trajectory information of the pedestrian under different image acquisition devices, which is included in the pedestrian image, through the pedestrian re-identification model comprises the following steps: comparing each pedestrian image with all pedestrian images in the pedestrian image database to determine the similarity between each pedestrian image and all pedestrian images; determining pedestrian images with the similarity larger than a preset threshold value in a pedestrian image database as candidate pedestrian images; determining pedestrian track information of pedestrians under different image acquisition devices contained in each pedestrian image according to image information carried by the candidate pedestrian images; wherein the image information includes time information and position information of the image pickup device corresponding to the image of the pedestrian candidate.
In the embodiment of the application, when a pedestrian corresponding to the pedestrian image is a target person, determining attendance information of the target person according to the pedestrian trajectory information includes: arranging time information of the pedestrian trajectory information included in the candidate pedestrian images according to a time sequence when a pedestrian corresponding to the pedestrian image is a target member; acquiring first time information and second time information of a pedestrian in a candidate pedestrian image; under the condition that the first time information and the second time information of the pedestrians in the candidate pedestrian image accord with a preset attendance checking rule, determining that the attendance checking information of the target staff is normal attendance checking; and under the condition that the first time information and/or the second time information of the pedestrian in the candidate pedestrian image do not accord with the preset attendance checking rule, obtaining attendance checking management data of the target employee, and determining the attendance checking information of the target employee according to the attendance checking management data.
In the embodiment of the application, when a pedestrian corresponding to the pedestrian image is a target person, determining attendance information of the target person according to the pedestrian trajectory information includes: arranging time information of the candidate pedestrian images included in the pedestrian trajectory information according to a time sequence when a pedestrian corresponding to the pedestrian image is a target member; acquiring first time information and second time information of a pedestrian in a candidate pedestrian image; under the condition that the time difference value between the first time information and the second time information of the pedestrians in the candidate pedestrian image accords with preset attendance checking duration, determining that the attendance checking information of the target employee is normal attendance; and under the condition that the time difference value between the first time information and the second time information of the pedestrian in the candidate pedestrian image does not accord with the preset attendance time length, acquiring attendance management data of the target employee, and determining the attendance information of the target employee according to the attendance management data.
In an embodiment of the application, determining the attendance information of the target employee according to the attendance management data includes: determining that the attendance information of the target employee is normal attendance under the condition that the attendance management data comprises leave-asking data or rest data; and under the condition that the attendance management data does not comprise leave data or rest data, determining that the attendance information of the target employee is abnormal attendance.
In an embodiment of the present application, establishing a pedestrian image database includes: acquiring a pedestrian image acquired by image acquisition equipment; inputting the pedestrian image into a target detection model so as to detect one or more pedestrians contained in the pedestrian image through the target detection model; acquiring the image position of each pedestrian in a pedestrian image output by a target detection model; extracting an image area where each pedestrian is located in each pedestrian image according to the image position where each pedestrian is located; and establishing a corresponding pedestrian image database according to the image area of each pedestrian.
In an embodiment of the present application, the pedestrian images in the pedestrian image database include image feature information, wherein the image feature information includes at least one of a pedestrian face, a pedestrian pose, a pedestrian dress, and a pedestrian hairstyle.
In an embodiment of the present application, acquiring an image of a pedestrian acquired by an image acquisition device includes: determining the installation position of the image acquisition equipment; identifying the pedestrian image according to the installation position to determine the position of the pedestrian in the pedestrian image; and acquiring the pedestrian image carrying the position information and the time information and acquired by the image acquisition equipment.
In the embodiment of the application, judging whether the pedestrian corresponding to the pedestrian image is the target employee according to the image information of the pedestrian image and the information in the worker database comprises: detecting a face contained in the image information of the pedestrian image to determine the frontal face image information of the pedestrian in the pedestrian image; and determining the pedestrian in the pedestrian image of the pedestrian image as the target employee according to the front face image information and the information in the worker database.
In an embodiment of the present application, determining a pedestrian in a pedestrian image of a pedestrian image as a target employee based on the front face image information and information in the worker database includes: comparing the front face image information with image information in a worker database; in the case where the front face image information coincides with the image information in the worker database, the pedestrian in the pedestrian image is determined as the target employee.
In an embodiment of the application, the method further comprises: and under the condition that the front face image information is inconsistent with the image information in the member worker database, storing the information of the pedestrian corresponding to the front face image information, wherein the information of the pedestrian corresponding to the front face image information comprises the front face image information of the pedestrian and the access information of the pedestrian.
A second aspect of the application provides a machine-readable storage medium having instructions stored thereon, which when executed by a processor, cause the processor to be configured to perform the above-described method for determining employee attendance information.
A third aspect of the present application provides a processor configured to perform the above-mentioned method for determining employee attendance information.
A fourth aspect of the present application provides an apparatus for determining employee attendance information, comprising: the image acquisition equipment is used for acquiring a pedestrian image; and the processor described above.
Through above-mentioned technical scheme, need not staff's initiative cooperation attendance work, reduce the influence of external factor to staff's attendance, further improve the fairness of staff's attendance, increase substantially the rate of accuracy of staff's attendance. Meanwhile, the pedestrian images in the pedestrian image database are traversed through the pedestrian re-recognition model, the action route of the pedestrian in the attendance area can be determined quickly and accurately, and a good reference basis is provided for determining staff attendance information.
Additional features and advantages of embodiments of the present application will be described in detail in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the embodiments of the disclosure, but are not intended to limit the embodiments of the disclosure. In the drawings:
fig. 1 schematically illustrates a flow diagram of a method for determining employee attendance information according to an embodiment of the present application;
fig. 2 schematically shows a block diagram of an apparatus for determining employee attendance information according to an embodiment of the present application;
fig. 3 schematically shows an internal structural diagram of a computer device according to an embodiment of the present application.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it should be understood that the specific embodiments described herein are only used for illustrating and explaining the embodiments of the present application and are not used for limiting the embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Fig. 1 schematically shows a flowchart of a method for determining employee attendance information according to an embodiment of the present application. As shown in fig. 1, in an embodiment of the present application, a method for determining attendance information of an employee is provided, which includes the following steps:
step 101, establishing a pedestrian image database.
And 102, inputting the pedestrian image in the pedestrian image database into a pedestrian re-identification model.
And 103, determining the pedestrian track information of the pedestrians under different image acquisition devices contained in the pedestrian image through the pedestrian re-identification model.
And 104, judging whether the pedestrian corresponding to the pedestrian image is the target employee or not according to the image information of the pedestrian image and the information in the worker database.
And 105, when the pedestrian corresponding to the pedestrian image is the target employee, determining attendance information of the target employee according to the pedestrian track information.
To determine attendance information for an employee, the processor may build a pedestrian image database. The pedestrian image database may include an image area where each pedestrian is located in the pedestrian image. The pedestrian image database may refer to a collection of images of each pedestrian within a day captured by the image capture device.
In one embodiment, establishing the pedestrian image database comprises: acquiring a pedestrian image acquired by image acquisition equipment; inputting the pedestrian image into a target detection model so as to detect one or more pedestrians contained in the pedestrian image through the target detection model; acquiring the image position of each pedestrian in a pedestrian image output by a target detection model; extracting an image area where each pedestrian is located in each pedestrian image according to the image position where each pedestrian is located; and establishing a corresponding pedestrian image database according to the image area of each pedestrian.
The processor may acquire an image of a pedestrian captured by the image capture device. The image capturing device may be a video camera, a still camera, a recorder, or other devices with image capturing functions. Before the pedestrian images are collected, the image collecting equipment can be deployed according to the position points of the staff possibly appearing in the attendance checking area. Wherein, the attendance area can be an industrial park. The location points can refer to places such as gates, canteens and office buildings in the attendance checking area where workers frequently go in and out. Thus, the image acquisition device can be installed at a plurality of position points in the attendance checking area, and the image acquisition device can comprise a plurality of position points. After the image capture device is deployed, images of pedestrians can be captured by the image capture device at multiple location points. The image of the pedestrian collected by each image collecting device can contain a plurality of pedestrians.
In order to acquire a large number of pedestrian images in real time, a smart camera may be used. The intelligent camera can acquire video data of pedestrians passing through the installation position point of the intelligent camera in one day. The video data may refer to each frame of the pedestrian image in the photographic video captured by the camera. After the images of the pedestrians are shot, the intelligent camera can transmit the collected images to the processor in time in a wireless transmission or wired transmission mode.
After acquiring the image of the pedestrian acquired by the image acquisition device, the processor may input the image of the pedestrian to the target detection model, and may then detect one or more pedestrians contained in the image of the pedestrian through the target detection model. The pedestrian image can carry position information and time information. The target detection model may include Fast R-CNN and SSD, among others. The processor may acquire an image position where each pedestrian is located included in the pedestrian image output by the target detection model. Then, the processor can extract an image area where each pedestrian is located in each pedestrian image according to the image position where each pedestrian is located. The processor can establish a corresponding pedestrian image database according to the image area where each pedestrian is located.
The image area where the pedestrian is located may include a certain pedestrian in the image of the pedestrian and the image background where the pedestrian is located. Specifically, in one embodiment, the pedestrian images in the pedestrian image database include image feature information, wherein the image feature information includes at least one of a pedestrian face, a pedestrian pose, a pedestrian fit, and a pedestrian hair style. That is, the image region where the pedestrian is located may further include image feature information of a certain pedestrian in the pedestrian image. Wherein the image feature information may include at least one of a pedestrian face, a pedestrian pose, a pedestrian dress, and a pedestrian hairstyle. The image characteristic information may also include the personal belongings of the pedestrian, etc.
For example, if one pedestrian image captured by the image capturing apparatus 1 is input to the target detection model and the pedestrian image includes A, B and C, the detection result may include an image area in which the pedestrian a is located, an image area in which the pedestrian B is located, and an image area in which the pedestrian C is located. For convenience of description, an image region in which the pedestrian a is located, an image region in which the pedestrian B is located, and an image region in which the pedestrian C is located may be respectively represented as a pedestrian image a, a pedestrian image B, and a pedestrian image C. That is, a single pedestrian image including a plurality of pedestrians is input to the target detection model, and a plurality of pedestrian images including a certain pedestrian can be detected. A corresponding pedestrian image database can be established through a plurality of pedestrian images containing a certain pedestrian.
In one embodiment, acquiring the image of the pedestrian acquired by the image acquisition device comprises: determining the installation position of the image acquisition equipment; identifying the pedestrian image according to the installation position to determine the position of the pedestrian in the pedestrian image; and acquiring the pedestrian image carrying the position information and the time information and acquired by the image acquisition equipment.
The processor may determine an installation location of the image capture device. The installation position of the image acquisition equipment can be set according to the position points of the staff possibly appearing in the attendance checking area. The processor may then identify the pedestrian image according to the installation location of the image capture device to determine the location of the pedestrian in the pedestrian image. The processor can acquire the pedestrian image carrying the position information and the time information and acquired by the image acquisition device. The image acquisition equipment can perform time identification on the acquired pedestrian image. For example, if the image capturing apparatus 1 whose installation position is M captures one pedestrian image in the morning N and includes A, B and C three pedestrians, the positions of the pedestrians A, B and C at the time of the morning N may be determined as M.
After the pedestrian image database is established, the processor may input the pedestrian images in the pedestrian image database to the pedestrian re-recognition model. In one embodiment, the step of determining the pedestrian track information of the pedestrians under different image acquisition devices contained in the pedestrian image through the pedestrian re-identification model comprises the following steps: comparing each pedestrian image with all the pedestrian images in the pedestrian image database to determine the similarity between each pedestrian image and all the pedestrian images; determining pedestrian images with the similarity larger than a preset threshold value in a pedestrian image database as candidate pedestrian images; determining pedestrian track information of pedestrians under different image acquisition devices contained in each pedestrian image according to image information carried by the candidate pedestrian images; wherein the image information includes time information and position information of the image capturing device corresponding to the image of the pedestrian candidate.
In the case of inputting the pedestrian images in the pedestrian image database to the pedestrian re-recognition model, the pedestrian re-recognition model may traverse all the pedestrian images in the pedestrian image database according to each pedestrian image. Further, the pedestrian re-recognition model may compare each pedestrian image with all pedestrian images in the pedestrian image database to determine a similarity between each pedestrian image and all pedestrian images. Then, the pedestrian re-recognition model may determine pedestrian images in the pedestrian image database, the similarity of which is greater than a preset threshold, as pedestrian candidate images. When the pedestrian re-identification model determines the candidate pedestrian image corresponding to the first pedestrian image and needs to continuously determine the candidate pedestrian image corresponding to the second pedestrian image, the pedestrian re-identification model may not traverse the first pedestrian image and the candidate pedestrian image corresponding thereto. For example, the pedestrian image database includes pedestrian images a1, a2, A3 of a pedestrian a, pedestrian images B1, B2 of a pedestrian B, and pedestrian images C1, C2, C3 of a pedestrian C. If the pedestrian re-recognition model has determined the pedestrian images a1, a2, A3 of the pedestrian a, then the pedestrian images B1, B2 and the pedestrian images C1, C2, C3 in the pedestrian image database may be traversed without traversing the pedestrian images a1, a2, A3 when determining the pedestrian trajectory information of the pedestrian B by the pedestrian re-recognition model.
The pedestrian re-recognition model may also de-duplicate pedestrian images in the pedestrian image database when determining a pedestrian candidate image corresponding to each pedestrian image. The pedestrian re-identification model may then traverse all pedestrian images in the pedestrian image database from each pedestrian image after de-duplication. That is, each of the de-duplicated pedestrian images may be compared with all of the pedestrian images in the pedestrian image database to determine the similarity between each of the pedestrian images and all of the pedestrian images. Then, pedestrian images having a similarity greater than a preset threshold in the pedestrian image database may be determined as candidate pedestrian images. That is, for each pedestrian image after the deduplication, there may be a pedestrian image, i.e., a candidate pedestrian image, in the pedestrian image database corresponding to the pedestrian image with a similarity greater than a preset threshold. The pedestrian included in each of the de-duplicated pedestrian images and the pedestrian included in the candidate pedestrian image may be the same person.
The pedestrian candidate image may refer to an image captured by the image capturing device when a pedestrian in the pedestrian candidate image passes through a different image capturing device. The pedestrian candidate image may carry image information. The image information may include time information and position information of the image pickup device corresponding to the pedestrian candidate image. Further, the time information may refer to a time when a pedestrian in the pedestrian candidate image is captured by the image capturing device while passing through a different image capturing device. Thus, after determining the candidate pedestrian images, the processor can determine pedestrian track information of pedestrians under different image acquisition devices contained in each pedestrian image according to the image information carried by the candidate pedestrian images.
The processor can determine pedestrian track information of pedestrians under different image acquisition devices contained in the pedestrian image through the pedestrian re-identification model. Further, the processor can judge whether the pedestrian corresponding to the pedestrian image is the target employee or not according to the image information of the pedestrian image and the information in the employee worker database.
In one embodiment, the step of judging whether the pedestrian corresponding to the pedestrian image is the target employee according to the image information of the pedestrian image and the information in the worker-worker database comprises the following steps: detecting a face contained in the image information of the pedestrian image to determine the frontal face image information of the pedestrian in the pedestrian image; and determining the pedestrian in the pedestrian image of the pedestrian image as the target employee according to the front face image information and the information in the worker database.
In order to further determine whether the pedestrian corresponding to the pedestrian image is the target employee, the processor may detect the face of the pedestrian included in the pedestrian image to determine the frontal face image information of the pedestrian in the pedestrian image. The processor may then determine a pedestrian in the pedestrian image as the target employee based on the front face image information and the image information in the person worker database.
In one embodiment, determining a pedestrian in a pedestrian image of a pedestrian image as a target employee based on the frontal image information and information in the member worker database comprises: comparing the front face image information with image information in a worker database; in the case where the front face image information coincides with the image information in the worker database, the pedestrian in the pedestrian image is determined as the target employee.
The processor may compare the front-face image information with the image information in the member-worker database to determine whether the front-face image information of the pedestrian in the candidate pedestrian image is consistent with the image information in the member-worker database. The frontal face image information may include feature information such as facial features and hair style of the pedestrian. In the case where it is determined that the front face image information coincides with the image information in the worker database, the processor may determine a pedestrian in the pedestrian image as the target worker.
In one embodiment, the method further comprises: and under the condition that the front face image information is inconsistent with the image information in the worker database, storing the information of the pedestrian corresponding to the front face image information, wherein the information of the pedestrian corresponding to the front face image information comprises the front face image information of the pedestrian and the access information of the pedestrian.
The processor may compare the front-face image information with the image information in the member-worker database to determine whether the front-face image information of the pedestrian in the candidate pedestrian image is consistent with the image information in the member-worker database. In the case where the front face image information is not consistent with the image information in the worker database, the processor may save information of the pedestrian corresponding to the front face image information. The information of the pedestrian corresponding to the front face image information includes front face image information of the pedestrian and access information of the pedestrian. Further, the frontal face image information may include feature information such as facial five sense organs and hair style of the pedestrian. The access information may include the access time and the access address of the pedestrian, and the like.
Under the condition that the pedestrian corresponding to the pedestrian image is determined to be the target employee, the processor can determine attendance information of the target employee according to the pedestrian track information. The attendance information can include normal attendance information and abnormal attendance information. When the target staff is in abnormal attendance, the corresponding attendance information is abnormal attendance information. When the target staff normally goes out, the corresponding attendance information is normal attendance information. The abnormal attendance information may include late arrival and/or early departure, etc.
In one embodiment, when the pedestrian corresponding to the pedestrian image is the target person, determining the attendance information of the target person according to the pedestrian trajectory information includes: arranging time information of the candidate pedestrian images included in the pedestrian trajectory information according to a time sequence when a pedestrian corresponding to the pedestrian image is a target member; acquiring first time information and second time information of a pedestrian in a candidate pedestrian image; under the condition that the first time information and the second time information of the pedestrians in the candidate pedestrian image accord with a preset attendance checking rule, determining that the attendance checking information of the target staff is normal attendance checking; and under the condition that the first time information and/or the second time information of the pedestrian in the candidate pedestrian image do not accord with the preset attendance checking rule, obtaining attendance checking management data of the target employee, and determining the attendance checking information of the target employee according to the attendance checking management data.
The processor may arrange time information of the pedestrian-candidate images included in the pedestrian trajectory information in chronological order when the pedestrian corresponding to the pedestrian image is the target person. Then, the processor may acquire the first time information and the second time information of the pedestrian in the pedestrian-candidate image. The first time information may refer to time information of a first image acquired by the image acquisition device when a pedestrian in the candidate pedestrian image appears in the attendance checking area. The second time information may refer to time information of a last image captured by the image capturing device before a pedestrian in the pedestrian candidate image leaves the attendance area.
The processor may determine whether the first time information and/or the second time information of the pedestrian in the candidate pedestrian image complies with a preset attendance check rule. The preset attendance rule may refer to preset attendance time. Under the condition that the first time information and the second time information of the pedestrians in the candidate pedestrian image accord with preset attendance checking rules, the processor can determine that the attendance checking information of the target staff is normal attendance. Under the condition that the first time information and/or the second time information of the pedestrians in the candidate pedestrian image do not meet the preset attendance checking rule, the processor can acquire attendance checking management data of the target staff and determine attendance checking information of the target staff according to the attendance checking management data. The attendance management data can comprise leave data or rest data of the target employee.
For example, if the preset attendance time may be 8 am to 5 pm, the first time information of the pedestrian in the candidate pedestrian image is 7 am, and the second time information is 6 pm. Then, the attendance of the target employee is the case of going off duty in the morning and evening, namely the first time information and/or the second time information of the pedestrian meet the preset attendance rules. At this time, the processor may determine that the attendance information of the target employee is a normal attendance.
For example, if the preset attendance checking time may be 8 am to 5 pm, the first time information of the pedestrian in the candidate pedestrian image is 9 am, and the second time information is 6 pm. Then, the attendance of the target employee is the late-to-late-off-duty condition, that is, the first time information of the pedestrian does not accord with the preset attendance rule. At this time, the processor may obtain attendance management data of the target employee, and determine attendance information of the target employee according to the attendance management data.
In one embodiment, when the pedestrian corresponding to the pedestrian image is the target person, determining the attendance information of the target person according to the pedestrian trajectory information includes: arranging time information of the candidate pedestrian images included in the pedestrian trajectory information according to a time sequence when a pedestrian corresponding to the pedestrian image is a target member; acquiring first time information and second time information of a pedestrian in a candidate pedestrian image; determining that the attendance information of the target employee is normal attendance when the time difference value between the first time information and the second time information of the pedestrian in the candidate pedestrian image is greater than or equal to the preset attendance duration; and under the condition that the time difference value between the first time information and the second time information of the pedestrian in the candidate pedestrian image is smaller than the preset attendance checking duration, obtaining attendance checking management data of the target employee, and determining the attendance checking information of the target employee according to the attendance checking management data.
The processor may arrange time information of the pedestrian-candidate images included in the pedestrian trajectory information in chronological order when the pedestrian corresponding to the pedestrian image is the target person. Then, the processor may acquire first time information and second time information of the pedestrian in the pedestrian candidate image. The first time information may refer to time information of a first image acquired by the image acquisition device when a pedestrian in the candidate pedestrian image appears in the attendance checking area. The second time information may refer to time information of a last image captured by the image-capturing device before a pedestrian in the pedestrian-candidate images leaves the attendance area.
The processor may determine a time difference value between the first time information and the second time information of the pedestrian in the pedestrian candidate image. Then, the processor can acquire the preset attendance checking duration and compare the time difference between the first time information and the second time information with the preset attendance checking duration. Under the condition that the time difference value between the first time information and the second time information is larger than or equal to the preset attendance checking duration, the processor can determine that the attendance checking information of the target staff is normally attendance. Under the condition that the time difference value between the first time information and the second time information is smaller than the preset attendance checking duration, the processor can acquire attendance checking management data of the target staff and determine attendance checking information of the target staff according to the attendance checking management data. The attendance management data can comprise leave data or rest data of the target employee. Through time difference between the first time information and the second time information of the target staff and preset attendance time length are compared, under the condition that the target staff can carry out elastic card punching, the accuracy of staff attendance management can be further improved.
For example, if the first time information of the pedestrian in the pedestrian candidate image is 9 am and the second time information is 6 pm, the time difference between the first time information and the second time information is 9 hours. At this time, if the preset attendance time is 8 hours, that is, the time difference is greater than the preset attendance time, the processor may determine that the attendance information of the target employee is normal attendance. If the preset attendance time is 9 hours, namely the time difference is equal to the preset attendance time, the processor can determine that the attendance information of the target staff is normal attendance. If the preset attendance time is 10 hours, namely the time difference is smaller than the preset attendance time, the processor can acquire the attendance management data of the target employee and determine the attendance information of the target employee according to the attendance management data.
In one embodiment, determining attendance information for the target employee based on the attendance management data comprises: determining that the attendance information of the target employee is normal attendance under the condition that the attendance management data comprises leave-asking data or rest data; and under the condition that the attendance management data does not comprise leave data or rest data, determining that the attendance information of the target employee is abnormal attendance.
The attendance management data can be leave data or rest data. The leave data may include leave category, leave time, leave number of days, leave reason, and the like. The leave category may include leave, sick and sick, and annual leave, etc. The rest data may include the time of the rest, the number of days of the rest, and the like. Unusual attendance may refer to late arrival or early departure, etc.
Under the condition of obtaining the attendance management data of the target employee, the processor can determine the attendance information of the target employee according to the attendance management data. Specifically, in the case that the attendance management data includes leave data or call data, the processor may determine that the attendance information of the target employee is normal attendance. The attendance management data can refer to leave-asking data or rest data of the current attendance day. Under the condition that the attendance management data does not comprise leave data or rest data, the processor can determine that the attendance information of the target employee is abnormal attendance.
For example, if it is required to determine attendance information of target employee a in 12 days in 4 months, and the processor may acquire that the leave-asking time in the leave-asking data of target employee a is 11 days in 4 months and the number of leave-asking days is 3 days, the processor may determine that the leave-asking data of target employee a is included in the attendance management data. At this time, the processor may determine that the attendance information of the target employee a is normal attendance. If the processor can acquire that the leave asking time in the leave asking data of the target employee A is 4 months and 11 days, and the leave asking days are 1 day, the processor can determine that the leave asking data of the target employee A is not contained in the attendance management data. At this time, the processor may determine that the attendance information of target employee a is an abnormal attendance.
Through above-mentioned technical scheme, need not staff's initiative cooperation attendance work, reduce the influence of external factor to staff's attendance, further improve the fairness of staff's attendance, increase substantially the rate of accuracy of staff's attendance. Meanwhile, all pedestrian images in the pedestrian image database are traversed through the pedestrian re-recognition model, the action route of the pedestrian in the attendance area can be determined quickly and accurately, and a good reference basis is provided for determining staff attendance information.
Fig. 1 is a schematic flow chart of a method for determining attendance information of an employee in one embodiment. It should be understood that, although the steps in the flowchart of fig. 1 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a portion of the steps in fig. 1 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
The embodiment of the application provides a processor, wherein the processor is used for running a program, and the method for determining staff attendance information is executed when the program runs.
In one embodiment, as shown in fig. 2, an apparatus for determining staff attendance information is provided, which includes an image capture device 201 and a processor 202, wherein the image capture device 201 is used for capturing images of pedestrians.
An embodiment of the present application provides a storage medium, on which a program is stored, and the program, when executed by a processor, implements the above method for determining employee attendance information.
In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 3. The computer device includes a processor a01, a network interface a02, a memory (not shown), and a database (not shown) connected by a system bus. Wherein processor a01 of the computer device is used to provide computing and control capabilities. The memory of the computer device comprises an internal memory a03 and a non-volatile storage medium a 04. The non-volatile storage medium a04 stores an operating system B01, a computer program B02, and a database (not shown in the figure). The internal memory a03 provides an environment for the operation of the operating system B01 and the computer program B02 in the nonvolatile storage medium a 04. The database of the computer device is used for storing data such as pedestrian images. The network interface a02 of the computer device is used for communication with an external terminal through a network connection. The computer program B02 is executed by the processor a01 to implement a method for determining employee attendance information.
It will be appreciated by those skilled in the art that the configuration shown in fig. 3 is a block diagram of only a portion of the configuration associated with the present application, and is not intended to limit the computing device to which the present application may be applied, and that a particular computing device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.
The embodiment of the application provides equipment, the equipment comprises a processor, a memory and a program which is stored on the memory and can run on the processor, and the following steps are realized when the processor executes the program: establishing a pedestrian image database; inputting the pedestrian images in the pedestrian image database into a pedestrian re-identification model; determining pedestrian track information of pedestrians under different image acquisition devices, which is contained in the pedestrian image, through a pedestrian re-identification model; judging whether the pedestrian corresponding to the pedestrian image is a target employee or not according to the image information of the pedestrian image and the information in the worker database; and under the condition that the pedestrian corresponding to the pedestrian image is the target employee, determining the attendance information of the target employee according to the pedestrian track information.
In one embodiment, the step of determining the pedestrian track information of the pedestrians under different image acquisition devices contained in the pedestrian image through the pedestrian re-identification model comprises the following steps: comparing each pedestrian image with all pedestrian images in the pedestrian image database to determine the similarity between each pedestrian image and all pedestrian images; determining pedestrian images with the similarity larger than a preset threshold value in a pedestrian image database as candidate pedestrian images; determining pedestrian track information of pedestrians under different image acquisition devices contained in each pedestrian image according to image information carried by the candidate pedestrian image; wherein the image information includes time information and position information of the image capturing device corresponding to the image of the pedestrian candidate.
In one embodiment, when the pedestrian corresponding to the pedestrian image is the target person, determining the attendance information of the target person according to the pedestrian trajectory information includes: arranging time information of the candidate pedestrian images included in the pedestrian trajectory information according to a time sequence when a pedestrian corresponding to the pedestrian image is a target member; acquiring first time information and second time information of a pedestrian in a candidate pedestrian image; under the condition that the first time information and the second time information of the pedestrians in the candidate pedestrian image accord with a preset attendance checking rule, determining that the attendance checking information of the target staff is normal attendance checking; and under the condition that the first time information and/or the second time information of the pedestrian in the candidate pedestrian image do not accord with the preset attendance checking rule, obtaining attendance checking management data of the target employee, and determining the attendance checking information of the target employee according to the attendance checking management data.
In one embodiment, when the pedestrian corresponding to the pedestrian image is the target employee, determining the attendance information of the target employee according to the pedestrian trajectory information comprises: arranging time information of the candidate pedestrian images included in the pedestrian trajectory information according to a time sequence when a pedestrian corresponding to the pedestrian image is a target member; acquiring first time information and second time information of a pedestrian in a candidate pedestrian image; determining that the attendance information of the target employee is normal attendance when the time difference value between the first time information and the second time information of the pedestrian in the candidate pedestrian image is greater than or equal to the preset attendance duration; and under the condition that the time difference value between the first time information and the second time information of the pedestrian in the candidate pedestrian image is smaller than the preset attendance checking duration, obtaining attendance checking management data of the target employee, and determining the attendance checking information of the target employee according to the attendance checking management data.
In one embodiment, determining attendance information for the target employee based on the attendance management data comprises: determining that the attendance information of the target employee is normal attendance under the condition that the attendance management data comprises leave-asking data or rest data; and under the condition that the attendance management data does not comprise leave data or rest data, determining that the attendance information of the target employee is abnormal attendance.
In one embodiment, establishing the pedestrian image database comprises: acquiring a pedestrian image acquired by image acquisition equipment; inputting the pedestrian image into a target detection model so as to detect one or more pedestrians contained in the pedestrian image through the target detection model; acquiring the image position of each pedestrian in a pedestrian image output by a target detection model; extracting an image area where each pedestrian is located in each pedestrian image according to the image position where each pedestrian is located; and establishing a corresponding pedestrian image database according to the image area of each pedestrian.
In one embodiment, the pedestrian images in the pedestrian image database include image feature information, wherein the image feature information includes at least one of a pedestrian face, a pedestrian pose, a pedestrian dress, and a pedestrian hairstyle.
In one embodiment, acquiring the image of the pedestrian acquired by the image acquisition device comprises: determining the installation position of the image acquisition equipment; identifying the pedestrian image according to the installation position to determine the position of the pedestrian in the pedestrian image; and acquiring the pedestrian image carrying the position information and the time information and acquired by the image acquisition equipment.
In one embodiment, the judging whether the pedestrian corresponding to the pedestrian image is the target employee according to the image information of the pedestrian image and the information in the worker database comprises: detecting a face contained in the image information of the pedestrian image to determine the frontal face image information of the pedestrian in the pedestrian image; and determining the pedestrian in the pedestrian image of the pedestrian image as the target employee according to the front face image information and the information in the worker database.
In one embodiment, determining a pedestrian in a pedestrian image of a pedestrian image as a target employee based on the front face image information and information in the member worker database comprises: comparing the front face image information with image information in a worker database; in the case where the front face image information coincides with the image information in the worker database, the pedestrian in the pedestrian image is determined as the target employee.
In one embodiment, the method further comprises: and under the condition that the front face image information is inconsistent with the image information in the worker database, storing the information of the pedestrian corresponding to the front face image information, wherein the information of the pedestrian corresponding to the front face image information comprises the front face image information of the pedestrian and the access information of the pedestrian.
The present application further provides a computer program product adapted to perform a program for initializing the following method steps when executed on a data processing device: establishing a pedestrian image database; inputting the pedestrian images in the pedestrian image database into a pedestrian re-identification model; determining pedestrian track information of pedestrians under different image acquisition devices, which is contained in the pedestrian image, through a pedestrian re-identification model; judging whether the pedestrian corresponding to the pedestrian image is a target employee or not according to the image information of the pedestrian image and the information in the worker database; and under the condition that the pedestrian corresponding to the pedestrian image is the target employee, determining the attendance information of the target employee according to the pedestrian track information.
In one embodiment, the step of determining the pedestrian track information of the pedestrians under different image acquisition devices contained in the pedestrian image through the pedestrian re-identification model comprises the following steps: comparing each pedestrian image with all pedestrian images in the pedestrian image database to determine the similarity between each pedestrian image and all pedestrian images; determining pedestrian images with the similarity larger than a preset threshold value in a pedestrian image database as candidate pedestrian images; determining pedestrian track information of pedestrians under different image acquisition devices contained in each pedestrian image according to image information carried by the candidate pedestrian image; wherein the image information includes time information and position information of the image capturing device corresponding to the image of the pedestrian candidate.
In one embodiment, when the pedestrian corresponding to the pedestrian image is the target employee, determining the attendance information of the target employee according to the pedestrian trajectory information comprises: arranging time information of the candidate pedestrian images included in the pedestrian trajectory information according to a time sequence when a pedestrian corresponding to the pedestrian image is a target member; acquiring first time information and second time information of a pedestrian in a candidate pedestrian image; under the condition that the first time information and the second time information of the pedestrians in the candidate pedestrian image accord with a preset attendance checking rule, determining that the attendance checking information of the target staff is normal attendance checking; and under the condition that the first time information and/or the second time information of the pedestrian in the candidate pedestrian image do not accord with the preset attendance checking rule, obtaining attendance checking management data of the target employee, and determining the attendance checking information of the target employee according to the attendance checking management data.
In one embodiment, when the pedestrian corresponding to the pedestrian image is the target person, determining the attendance information of the target person according to the pedestrian trajectory information includes: arranging time information of the candidate pedestrian images included in the pedestrian trajectory information according to a time sequence when a pedestrian corresponding to the pedestrian image is a target member; acquiring first time information and second time information of a pedestrian in a candidate pedestrian image; determining that the attendance information of the target employee is normal attendance when the time difference value between the first time information and the second time information of the pedestrian in the candidate pedestrian image is greater than or equal to the preset attendance duration; and under the condition that the time difference value between the first time information and the second time information of the pedestrian in the candidate pedestrian image is smaller than the preset attendance checking duration, obtaining attendance checking management data of the target employee, and determining the attendance checking information of the target employee according to the attendance checking management data.
In one embodiment, determining attendance information for the target employee based on the attendance management data comprises: determining that the attendance information of the target employee is normal attendance under the condition that the attendance management data comprises leave-asking data or rest data; and under the condition that the attendance management data does not comprise leave data or rest data, determining that the attendance information of the target employee is abnormal attendance.
In one embodiment, building a pedestrian image database comprises: acquiring a pedestrian image acquired by image acquisition equipment; inputting the pedestrian image into a target detection model to detect one or more pedestrians contained in the pedestrian image through the target detection model; acquiring the image position of each pedestrian in the pedestrian image output by the target detection model; extracting an image area where each pedestrian is located in each pedestrian image according to the image position where each pedestrian is located; and establishing a corresponding pedestrian image database according to the image area of each pedestrian.
In one embodiment, the pedestrian images in the pedestrian image database include image feature information, wherein the image feature information includes at least one of a pedestrian face, a pedestrian pose, a pedestrian dress, and a pedestrian hairstyle.
In one embodiment, acquiring the image of the pedestrian acquired by the image acquisition device comprises: determining the installation position of the image acquisition equipment; identifying the pedestrian image according to the installation position to determine the position of the pedestrian in the pedestrian image; and acquiring the pedestrian image carrying the position information and the time information and acquired by the image acquisition equipment.
In one embodiment, the judging whether the pedestrian corresponding to the pedestrian image is the target employee according to the image information of the pedestrian image and the information in the worker database comprises: detecting a face contained in the image information of the pedestrian image to determine the frontal face image information of the pedestrian in the pedestrian image; and determining the pedestrian in the pedestrian image of the pedestrian image as the target employee according to the front face image information and the information in the worker database.
In one embodiment, determining a pedestrian in a pedestrian image of a pedestrian image as a target employee based on the front face image information and information in the member worker database comprises: comparing the front face image information with image information in a worker database; in the case where the front face image information coincides with the image information in the worker database, the pedestrian in the pedestrian image is determined as the target employee.
In one embodiment, the method further comprises: and under the condition that the front face image information is inconsistent with the image information in the worker database, storing the information of the pedestrian corresponding to the front face image information, wherein the information of the pedestrian corresponding to the front face image information comprises the front face image information of the pedestrian and the access information of the pedestrian.
As will be appreciated by one skilled in the art, 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 embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams 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.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). The memory is an example of a computer-readable medium.
Computer-readable media, including both permanent and non-permanent, removable and non-removable media, may implement the information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in the process, method, article, or apparatus that comprises the element.
The above are merely examples of the present application and are not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims (14)

1. A method for determining employee attendance information, the method comprising:
establishing a pedestrian image database;
inputting the pedestrian images in the pedestrian image database into a pedestrian re-identification model;
determining pedestrian track information of pedestrians under different image acquisition devices, which is contained in the pedestrian image, through the pedestrian re-identification model;
judging whether the pedestrian corresponding to the pedestrian image is a target employee or not according to the image information of the pedestrian image and the information in the employee worker database;
and under the condition that the pedestrian corresponding to the pedestrian image is the target employee, determining the attendance information of the target employee according to the pedestrian track information.
2. The method for determining attendance information of an employee according to claim 1, wherein the determining, by the pedestrian re-identification model, pedestrian trajectory information of a pedestrian included in the pedestrian image under different image acquisition devices comprises:
comparing each pedestrian image with all pedestrian images in the pedestrian image database to determine the similarity between each pedestrian image and all pedestrian images;
determining pedestrian images with the similarity larger than a preset threshold value in the pedestrian image database as candidate pedestrian images;
determining pedestrian track information of pedestrians under different image acquisition devices contained in each pedestrian image according to the image information carried by the candidate pedestrian image;
wherein the image information includes time information and position information of an image capturing device corresponding to the pedestrian candidate image.
3. The method for determining attendance information of an employee according to claim 2, wherein when the pedestrian corresponding to the pedestrian image is a target employee, determining the attendance information of the target employee according to the pedestrian trajectory information includes:
arranging time information of candidate pedestrian images included in the pedestrian trajectory information according to a time sequence when a pedestrian corresponding to the pedestrian image is a target person;
acquiring first time information and second time information of a pedestrian in the candidate pedestrian image;
under the condition that the first time information and the second time information of the pedestrians in the candidate pedestrian image accord with a preset attendance checking rule, determining that the attendance checking information of the target employee is normal attendance;
and under the condition that the first time information and/or the second time information of the pedestrian in the candidate pedestrian image do not accord with a preset attendance checking rule, acquiring attendance checking management data of the target employee, and determining the attendance checking information of the target employee according to the attendance checking management data.
4. The method for determining attendance information of employees according to claim 2, wherein when the pedestrian corresponding to the pedestrian image is a target employee, determining the attendance information of the target employee according to the pedestrian trajectory information comprises:
arranging time information of candidate pedestrian images included in the pedestrian trajectory information according to a time sequence when a pedestrian corresponding to the pedestrian image is a target person;
acquiring first time information and second time information of a pedestrian in the candidate pedestrian image;
determining that the attendance information of the target employee is normal attendance when a time difference value between first time information and second time information of the pedestrian in the candidate pedestrian image is greater than or equal to a preset attendance duration;
and acquiring attendance management data of the target employee under the condition that the time difference value between the first time information and the second time information of the pedestrian in the candidate pedestrian image is smaller than a preset attendance duration, and determining the attendance information of the target employee according to the attendance management data.
5. The method for determining attendance information of an employee according to any one of claims 3 or 4, wherein the determining of the attendance information of the target employee from the attendance management data comprises:
determining that the attendance information of the target employee is normal attendance under the condition that the attendance management data comprises leave-asking data or rest data;
and under the condition that the attendance management data does not comprise leave data or rest data, determining that the attendance information of the target employee is abnormal attendance.
6. The method for determining employee attendance information according to claim 1, wherein the establishing a pedestrian image database comprises:
acquiring a pedestrian image acquired by image acquisition equipment;
inputting the pedestrian image into a target detection model to detect one or more pedestrians contained in the pedestrian image through the target detection model;
acquiring the image position of each pedestrian in the pedestrian image output by the target detection model;
extracting an image area where each pedestrian is located in each pedestrian image according to the image position where each pedestrian is located;
and establishing a corresponding pedestrian image database according to the image area of each pedestrian.
7. The method for determining employee attendance information as claimed in claim 6 wherein the pedestrian images in the pedestrian image database include image characteristic information, wherein the image characteristic information includes at least one of pedestrian face, pedestrian pose, pedestrian wear and pedestrian hairstyle.
8. The method for determining attendance information of an employee according to claim 6, wherein the acquiring of the image of the pedestrian acquired by the image acquisition device comprises:
determining the installation position of the image acquisition equipment;
identifying the pedestrian image according to the installation position to determine the position of the pedestrian in the pedestrian image;
and acquiring the pedestrian image carrying the position information and the time information and acquired by the image acquisition equipment.
9. The method for determining attendance information of an employee according to claim 1, wherein the determining whether the pedestrian corresponding to the pedestrian image is the target employee based on the image information of the pedestrian image and the information in the employee worker database comprises:
detecting a face contained in the image information of the pedestrian image to determine the frontal face image information of the pedestrian in the pedestrian image;
and determining the pedestrian in the pedestrian image of the pedestrian image as a target employee according to the information in the front face image information and the information in the worker database.
10. The method for determining attendance information for employees of claim 9, wherein the determining of a pedestrian in a pedestrian image of the pedestrian image as a target employee from information in the face image information and a personnel worker database comprises:
comparing the front face image information with image information in a worker database;
and under the condition that the front face image information is consistent with the image information in the worker database, determining the pedestrian in the pedestrian image as a target employee.
11. The method for determining employee attendance information of claim 10, the method further comprising:
and under the condition that the front face image information is inconsistent with the image information in the worker database, storing the information of the pedestrian corresponding to the front face image information, wherein the information of the pedestrian corresponding to the front face image information comprises the front face image information of the pedestrian and the access information of the pedestrian.
12. A machine-readable storage medium having instructions stored thereon, which when executed by a processor causes the processor to be configured to perform a method for determining employee attendance information in accordance with any one of claims 1 to 11.
13. A processor configured to perform the method for determining employee attendance information according to any one of claims 1 to 11.
14. An apparatus for determining employee attendance information, comprising:
the image acquisition equipment is used for acquiring a pedestrian image; and
the processor of claim 13.
CN202210609519.4A 2022-05-31 2022-05-31 Method, device, storage medium and processor for determining staff attendance information Pending CN115063852A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210609519.4A CN115063852A (en) 2022-05-31 2022-05-31 Method, device, storage medium and processor for determining staff attendance information

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210609519.4A CN115063852A (en) 2022-05-31 2022-05-31 Method, device, storage medium and processor for determining staff attendance information

Publications (1)

Publication Number Publication Date
CN115063852A true CN115063852A (en) 2022-09-16

Family

ID=83198641

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210609519.4A Pending CN115063852A (en) 2022-05-31 2022-05-31 Method, device, storage medium and processor for determining staff attendance information

Country Status (1)

Country Link
CN (1) CN115063852A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117910997A (en) * 2024-03-19 2024-04-19 北京卓越未来国际医药科技发展有限公司 Working hour statistical method, device, equipment and medium based on clinical test project

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117910997A (en) * 2024-03-19 2024-04-19 北京卓越未来国际医药科技发展有限公司 Working hour statistical method, device, equipment and medium based on clinical test project

Similar Documents

Publication Publication Date Title
US20220092881A1 (en) Method and apparatus for behavior analysis, electronic apparatus, storage medium, and computer program
EP3855343A1 (en) Customer visit analysis method and apparatus, and storage medium
CN108446681B (en) Pedestrian analysis method, device, terminal and storage medium
CN109858354B (en) Face identity library, track table establishment method and face track query method and system
CN102945366A (en) Method and device for face recognition
CN112906483B (en) Target re-identification method, device and computer readable storage medium
CN108197544B (en) Face analysis method, face filtering method, face analysis device, face filtering device, embedded equipment, medium and integrated circuit
CN110705476A (en) Data analysis method and device, electronic equipment and computer storage medium
CN111724496A (en) Attendance checking method, attendance checking device and computer readable storage medium
CN111476685B (en) Behavior analysis method, device and equipment
CN115063852A (en) Method, device, storage medium and processor for determining staff attendance information
CN111163073A (en) Flow data processing method and device
CN114140663A (en) Multi-scale attention and learning network-based pest identification method and system
CN112687044A (en) Method, system, medium, and apparatus for managing staying person
CN111985438A (en) Static face processing method, device and equipment
CN115129916A (en) Method, device, storage medium and processor for determining staff attendance information
CN113343004B (en) Object identification method and device, storage medium and electronic device
CN114092809A (en) Object identification method and device and electronic equipment
CN116597501A (en) Video analysis algorithm and edge device
CN115346143A (en) Behavior detection method, electronic device, and computer-readable medium
CN113468948A (en) View data based security and protection control method, module, equipment and storage medium
CN111177465A (en) Method and device for determining category
CN113095110B (en) Method, device, medium and electronic equipment for dynamically warehousing face data
CN112241683B (en) Method and system for identifying and judging fellow persons
CN111709369A (en) Personnel identification method, device, equipment and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination