Movatterモバイル変換


[0]ホーム

URL:


CN114157837B - Security attendance linkage system based on video surveillance cloud platform - Google Patents

Security attendance linkage system based on video surveillance cloud platform
Download PDF

Info

Publication number
CN114157837B
CN114157837BCN202111437013.1ACN202111437013ACN114157837BCN 114157837 BCN114157837 BCN 114157837BCN 202111437013 ACN202111437013 ACN 202111437013ACN 114157837 BCN114157837 BCN 114157837B
Authority
CN
China
Prior art keywords
face
video
time
unit
real
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202111437013.1A
Other languages
Chinese (zh)
Other versions
CN114157837A (en
Inventor
陈帅斌
蒋泽飞
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.)
Hangzhou Denghong Technology Co ltd
Original Assignee
Hangzhou Denghong 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 Hangzhou Denghong Technology Co ltdfiledCriticalHangzhou Denghong Technology Co ltd
Priority to CN202111437013.1ApriorityCriticalpatent/CN114157837B/en
Publication of CN114157837ApublicationCriticalpatent/CN114157837A/en
Application grantedgrantedCritical
Publication of CN114157837BpublicationCriticalpatent/CN114157837B/en
Activelegal-statusCriticalCurrent
Anticipated expirationlegal-statusCritical

Links

Classifications

Landscapes

Abstract

Translated fromChinese

本发明公开了一种基于视频监控云平台的安全考勤联动系统,包括对外单元、视频解析单元、存储自决策单元、正向监控单元、核向监控单元、数据截取单元、初算单元和考勤单元;通过正向监控单元在用户打卡时自动获取打卡视频;之后利用核向监控单元获取到目标区域的实时视频,此处获取时核向监控单元保持安装地方隐秘,获取到核向视频;之后正向监控单元将打卡视频传输到视频解析单元,核向监控单元用于将核向视频传输到视频解析单元;视频解析单元用于对打卡视频和核向视频,进行初步截取统计,得到实出人脸组和假性人脸,自动得到欺瞒行为人员和未打卡人员;本申请简单有效,且易于实用。

The invention discloses a security attendance linkage system based on a video surveillance cloud platform, comprising an external unit, a video analysis unit, a storage self-decision unit, a forward monitoring unit, a check-in monitoring unit, a data interception unit, a preliminary calculation unit and an attendance unit; the forward monitoring unit automatically obtains a clock-in video when a user clocks in; then the check-in video is obtained by using the check-in monitoring unit, and the check-in monitoring unit keeps the installation place secret during the acquisition to obtain the check-in video; then the forward monitoring unit transmits the clock-in video to the video analysis unit, and the check-in monitoring unit is used to transmit the check-in video to the video analysis unit; the video analysis unit is used to perform preliminary interception and statistics on the clock-in video and the check-in video, obtain a real face group and a false face, and automatically obtain a person with deceptive behavior and a person who has not clocked in; the application is simple, effective, and easy to use.

Description

Safety attendance linkage system based on video monitoring cloud platform
Technical Field
The invention belongs to the field of linkage attendance monitoring, relates to a video monitoring technology, and in particular relates to a safety attendance linkage system based on a video monitoring cloud platform.
Background
The patent with the publication number of CN109284983A discloses a 2.4G remote video snapshot-based attendance reporting system, which comprises a communication service center, a base station, a video monitoring system, a 2.4G remote attendance terminal, a router, a WeChat enterprise number server, a mobile terminal mobile phone, a 2.4G card reader, video equipment and an electronic student card, wherein the 2.4G remote attendance terminal automatically senses and reads the electronic student card to generate a student attendance record, the student attendance record is uploaded to the communication service center, the communication service center analyzes and processes the attendance record and sends an instruction to the video monitoring system, video of 15 seconds before and after the student attendance time is extracted, and the student attendance record is pushed to parents of the student through the WeChat enterprise number. The school security management method can effectively improve school security management and promote campus informatization construction, can check videos of children entering and exiting a school in real time through a micro-signal enterprise signal on a mobile phone for parents to make the parents more safe, and can provide powerful basis for the school to work attendance records for the accurate responsibility accident handling of the school.
The patent with the publication number of CN205582024U also provides a student attendance machine for video monitoring, which comprises a real-time video acquisition module, a central processing unit, a card reader, a clock module, a display module and a communication module, wherein the output ends of the real-time video acquisition module and the card reader are connected with the central processing unit, the output end of the central processing unit is connected with the communication module, the communication module is connected with an external background server, and the central processing unit is also connected with the clock module and the display module respectively. The real-time video in front of the attendance machine is collected, and the communication module is arranged in the attendance machine and can communicate with an external background server in real time.
However, the two patents provide a video recognition card punching machine and the prior art of related video snapshot attendance, but the video recognition can be spoofed in a certain way and the actual video is not monitored in a linkage way for the two, so that under the condition of automatic recognition card punching, whether corresponding personnel have the condition that the attendance situation is inconsistent with the actual work record or not can be detected by self-help, statistics is carried out for the actual attendance of the personnel, and a solution is provided based on the situation.
Disclosure of Invention
The invention aims to provide a safety attendance linkage system based on a video monitoring cloud platform.
The aim of the invention can be achieved by the following technical scheme:
the safety attendance linkage system based on the video monitoring cloud platform comprises an external unit, a video analysis unit, a storage self-decision unit, a forward monitoring unit, a nuclear monitoring unit, a data interception unit, a primary calculation unit and an attendance unit;
The forward monitoring unit is video card punching equipment arranged at a designated position of the target area and used for automatically acquiring card punching video when a user punches cards, and the core direction monitoring unit is monitoring camera equipment arranged in the target area and used for acquiring real-time video of the target area and marking the real-time video as core direction video;
the forward monitoring unit is used for transmitting the card punching video to the video analysis unit, and the nuclear monitoring unit is used for transmitting the nuclear video to the video analysis unit;
The video analysis unit is used for carrying out preliminary interception statistics on the card punching video and the nuclear video to obtain a real face group and a fake face;
The video analysis unit is used for transmitting the false face and the real face group to the data interception unit, the data interception unit stores conventional working hours which refer to the actual working hours of the personnel in the target area, and the data interception unit receives the video analysis unit and transmits the video analysis unit to the real face group and carries out follow-up monitoring action on the video analysis unit, and the follow-up monitoring action is carried out once every day after the working hours, so that the vanishing time and vanishing times of all the real faces are obtained;
the data interception unit is used for transmitting the vanishing time and vanishing times of the false face and the real face to the preliminary calculation unit, and the preliminary calculation unit is used for carrying out preliminary calculation on the vanishing time and vanishing times of the real face to obtain the passive face, the conventional face and the regular face.
Further, the specific mode of preliminary interception statistics is as follows:
Step one, acquiring the number of real-time people in a card punching video and simultaneously acquiring the number of standard on-duty people;
step two, when the number of real-time people is consistent with the number of standard on duty people, no treatment is carried out;
step three, generating a fine verification signal, automatically acquiring all face information in the card punching video at the moment, matching the face information with standard face information, marking the non-existing standard face information as an absent face, and marking the non-existing face information in the standard face information as an excessive face;
Step four, after the working time starts for T1, T1 is preset time, all face information in the nuclear direction video is automatically acquired again, and the face information is marked as a nuclear direction face information group;
Step five, acquiring all face information in the card punching video, and marking the face information as a card punching face group; comparing the card-punching face group with the nuclear face information group, and marking the inconsistent card-punching face group as a false face;
Step six, marking the face with the same card-punching face group and nuclear face information as a real face group;
and step seven, obtaining a false face and a real face group.
Further, the following specific modes of monitoring behavior are:
s1, acquiring all real face groups;
s2, acquiring the vanishing time and vanishing times of all the real faces in the real face group, wherein the vanishing time refers to the time when the real faces are not detected, the vanishing times refers to the time when the single face vanishing time exceeds T1, and the mark that the real faces do not return to the target area is one time;
and S3, obtaining the vanishing time and vanishing times of all the real faces.
Further, the time T1 in step S2 is specifically a preset value for the manager.
Further, the specific value of the T1 time in step S2 defines the value range by:
s201, collecting office workers in all target areas;
s202, optionally selecting an office worker, and acquiring the time of not acquiring the real face every time in a day under the condition that the office worker does not ask for a business trip;
S203, when all the time marks are disappeared, all the disappeared time marks form a disappeared time group Pi, i=1.
S204, acquiring an average value of the vanishing time group, calculating absolute values of differences between all vanishing times and the average value, and summing all the absolute values to obtain a difference sum value;
s205, when the difference sum is larger than X1, automatically deleting the vanishing time, otherwise, not processing, and firstly removing the corresponding vanishing time with the largest absolute value according to the mode that the absolute value is from large to small;
S206, repeating the steps of S204-S206 again for the rest vanishing time until the difference sum value is less than or equal to X1, wherein X1 is a preset value;
S207, obtaining the mean value of the vanishing time after deletion at the moment, and marking the mean value as reasonable time;
S208, acquiring reasonable time of all office workers, calculating a mean value, acquiring a median between the maximum value of the reasonable time and the mean value, and marking the median with an upper limit;
The value of T1 satisfies the range from the target lower limit to the target upper limit.
Further, the preliminary calculation processing specifically comprises the following steps:
SS1, calculating the abrasion loss value according to a formula, wherein the specific calculation formula is as follows:
the extinction value = 0.41 x vanishing time +0.59 x vanishing times;
here, 0.41 and 0.59 are weights preset by the manager;
SS2, when the abrasion loss value is greater than X3, recognizing it as a negative face;
when the X2 is less than or equal to the extinction value and less than or equal to X3, the extinction value is considered as a conventional face;
The remaining marks are marked as regular faces.
Further, the primary calculation unit is used for transmitting the false face, the negative face, the conventional face and the regular face to the video analysis unit by means of the attendance unit, and the video analysis unit is used for transmitting the time stamps of the false face, the negative face, the conventional face and the regular face to the self-decision unit.
Further, the storage self-decision unit receives the passive face with the timestamp, the conventional face and the regular face transmitted by the video analysis unit, and performs self-statistical analysis, specifically:
redefining the person corresponding to the face marked as negative in more than 5 days in a single month as a person with a poor recommendation;
redefining a person marked as corresponding to the regular face on more than eighty-five percent of days in a single month as a referral person;
marking the person corresponding to the fake face as a non-trusted person;
The self-decision unit is used for transmitting the non-trusted personnel, the differential personnel and the excellent personnel to the external unit for real-time display.
The invention has the beneficial effects that:
The method comprises the steps of automatically acquiring a card punching video when a user punches a card by a forward monitoring unit, acquiring a real-time video of a target area by a nuclear monitoring unit, keeping a mounting place secret when acquiring the real-time video, and acquiring the nuclear video;
the video analysis unit is used for carrying out preliminary interception statistics on the card punching video and the nuclear video to obtain a real face group and a fake face, and automatically obtaining the cheating behavior personnel and the non-card punching personnel.
Drawings
The present invention is further described below with reference to the accompanying drawings for the convenience of understanding by those skilled in the art.
Fig. 1 is a system block diagram of the present invention.
Detailed Description
As shown in fig. 1, the security attendance linkage system based on the video monitoring cloud platform provided by the application comprises an external unit, a video analysis unit, a storage self-decision unit, a forward monitoring unit, a nuclear monitoring unit, a data interception unit, a preliminary calculation unit and an attendance unit;
The forward monitoring unit is a video card punching device arranged at a designated position of the target area and used for automatically acquiring a card punching video when a user punches a card;
the forward monitoring unit is used for transmitting the card punching video to the video analysis unit, and the nuclear monitoring unit is used for transmitting the nuclear video to the video analysis unit;
the video analysis unit is used for carrying out preliminary interception statistics on the card punching video and the nuclear video, and specifically comprises the following steps of:
Step one, acquiring the number of real-time people in a card punching video and simultaneously acquiring the number of standard on-duty people;
step two, when the number of real-time people is consistent with the number of standard on duty people, no treatment is carried out;
step three, generating a fine verification signal, automatically acquiring all face information in the card punching video at the moment, matching the face information with standard face information, marking the non-existing standard face information as an absent face, and marking the non-existing face information in the standard face information as an excessive face;
Step four, after the working time starts for T1, T1 is preset time, all face information in the nuclear direction video is automatically acquired again, and the face information is marked as a nuclear direction face information group;
Step five, acquiring all face information in the card punching video, and marking the face information as a card punching face group; comparing the card-punching face group with the nuclear face information group, and marking the inconsistent card-punching face group as a false face;
Step six, marking the face with the same card-punching face group and nuclear face information as a real face group;
Step seven, obtaining a false face and a real face group;
The video analysis unit is used for transmitting the false face and the real face group to the data interception unit, the data interception unit stores conventional working hours, the conventional working hours refer to the working hours of the actual working of the personnel in the target area, the data interception unit receives the video analysis unit and transmits the video analysis unit to the real face group, and carries out follow-up monitoring action on the real face group, and the follow-up monitoring action is carried out once every day after working, specifically comprises the following steps:
s1, acquiring all real face groups;
s2, acquiring the vanishing time and vanishing times of all the real faces in the real face group, wherein the vanishing time refers to the time when the real faces are not detected, the vanishing times refers to the time when the single face vanishing time exceeds T1, and the mark that the real faces do not return to the target area is one time;
The time T1 here is specifically a preset value by a manager, and the value range may be defined by the following manner:
s201, collecting office workers in all target areas;
s202, optionally selecting an office worker, and acquiring the time of not acquiring the real face every time in a day under the condition that the office worker does not ask for a business trip;
S203, when all the time marks are disappeared, all the disappeared time marks form a disappeared time group Pi, i=1.
S204, acquiring an average value of the vanishing time group, calculating absolute values of differences between all vanishing times and the average value, and summing all the absolute values to obtain a difference sum value;
s205, when the difference sum is larger than X1, automatically deleting the vanishing time, otherwise, not processing, and firstly removing the corresponding vanishing time with the largest absolute value according to the mode that the absolute value is from large to small;
S206, repeating the steps of S204-S206 again for the rest vanishing time until the difference sum value is less than or equal to X1, wherein X1 is a preset value;
S207, obtaining the mean value of the vanishing time after deletion at the moment, and marking the mean value as reasonable time;
S208, acquiring reasonable time of all office workers, calculating a mean value, acquiring a median between the maximum value of the reasonable time and the mean value, and marking the median with an upper limit;
s209, the value of T1 is satisfied within the range from the target lower limit to the target upper limit;
s3, obtaining the vanishing time and vanishing times of all the real faces;
the data interception unit is used for transmitting the vanishing time and vanishing times of the false face and the real face to the preliminary calculation unit, and the preliminary calculation unit is used for carrying out preliminary calculation processing on the vanishing time and vanishing times of the real face, and the preliminary calculation processing comprises the following specific steps:
SS1, calculating the abrasion loss value according to a formula, wherein the specific calculation formula is as follows:
the extinction value = 0.41 x vanishing time +0.59 x vanishing times;
here, 0.41 and 0.59 are weights preset by the manager;
SS2, when the abrasion loss value is greater than X3, recognizing it as a negative face;
when the X2 is less than or equal to the extinction value and less than or equal to X3, the extinction value is considered as a conventional face;
Marking the rest as regular faces;
The primary calculation unit is used for transmitting the false face, the negative face, the conventional face and the regular face to the video analysis unit by means of the attendance unit, and the video analysis unit is used for transmitting the time stamps of the false face, the negative face, the conventional face and the regular face to the storage decision unit;
The storage self-decision unit receives the passive face with the timestamp, the conventional face and the regular face transmitted by the video analysis unit, and performs self-statistical analysis, specifically:
redefining the person corresponding to the face marked as negative in more than 5 days in a single month as a person with a poor recommendation;
redefining a person marked as corresponding to the regular face on more than eighty-five percent of days in a single month as a referral person;
marking the person corresponding to the fake face as a non-trusted person;
The self-decision unit is used for transmitting the non-trusted personnel, the differential personnel and the excellent personnel to the external unit for real-time display.
The method comprises the steps of automatically acquiring a card punching video when a user punches a card by a forward monitoring unit, acquiring a real-time video of a target area by a nuclear monitoring unit, keeping a mounting place secret when acquiring the real-time video, and acquiring the nuclear video;
the video analysis unit is used for carrying out preliminary interception statistics on the card punching video and the nuclear video to obtain a real face group and a fake face, and automatically obtaining the cheating behavior personnel and the non-card punching personnel.
The foregoing is merely illustrative of the structures of this invention and various modifications, additions and substitutions for those skilled in the art can be made to the described embodiments without departing from the scope of the invention or from the scope of the invention as defined in the accompanying claims.

Claims (3)

CN202111437013.1A2021-11-292021-11-29 Security attendance linkage system based on video surveillance cloud platformActiveCN114157837B (en)

Priority Applications (1)

Application NumberPriority DateFiling DateTitle
CN202111437013.1ACN114157837B (en)2021-11-292021-11-29 Security attendance linkage system based on video surveillance cloud platform

Applications Claiming Priority (1)

Application NumberPriority DateFiling DateTitle
CN202111437013.1ACN114157837B (en)2021-11-292021-11-29 Security attendance linkage system based on video surveillance cloud platform

Publications (2)

Publication NumberPublication Date
CN114157837A CN114157837A (en)2022-03-08
CN114157837Btrue CN114157837B (en)2025-04-25

Family

ID=80784211

Family Applications (1)

Application NumberTitlePriority DateFiling Date
CN202111437013.1AActiveCN114157837B (en)2021-11-292021-11-29 Security attendance linkage system based on video surveillance cloud platform

Country Status (1)

CountryLink
CN (1)CN114157837B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN114898253B (en)*2022-04-262025-04-25杭州登虹科技有限公司 A surveillance video transmission system based on video content analysis
CN114866843B (en)*2022-05-062023-08-11杭州登虹科技有限公司Video data encryption system for network video monitoring
CN114629183B (en)*2022-05-172022-08-05时代云英(深圳)科技有限公司Little grid system of distributing type clean energy

Citations (2)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN107481343A (en)*2017-07-222017-12-15华中师范大学A kind of check class attendance based on face recognition technology is registered system and its method of work
CN108665231A (en)*2018-03-262018-10-16崔战宾Construction Visualized management system and method

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN104794607B (en)*2015-04-242018-03-09凯拔(中国)科技有限公司A kind of method of regular work attendance initial data and order of classes or grades at school data during work attendance calculates
CN107767477B (en)*2017-09-052021-05-28深圳市盛路物联通讯技术有限公司Information processing method and related equipment
CN112489235A (en)*2020-10-302021-03-12郑州富联智能工坊有限公司Attendance checking device and method thereof

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
CN107481343A (en)*2017-07-222017-12-15华中师范大学A kind of check class attendance based on face recognition technology is registered system and its method of work
CN108665231A (en)*2018-03-262018-10-16崔战宾Construction Visualized management system and method

Also Published As

Publication numberPublication date
CN114157837A (en)2022-03-08

Similar Documents

PublicationPublication DateTitle
CN114157837B (en) Security attendance linkage system based on video surveillance cloud platform
CN109255731A (en)A kind of architectural engineering labor service personnel management system and management method
CN107944838A (en)A kind of intelligent barrier gate Field Monitoring System and method
CN201508555U (en)Internet bar management system based on face recognition
CN106650855A (en)Fire-fighting equipment comprehensive management system
CN113792836B (en)Multi-level safety intelligent park control method and system
CN112233263A (en)Attendance management system based on face image recognition
CN107424252A (en)A kind of site staff's real-name management system and method
CN110738178A (en)Garden construction safety detection method and device, computer equipment and storage medium
CN206179048U (en)Personal identification device
CN112839200B (en)Power plant violation behavior identification method and system based on 5G technology and network server
CN111523432A (en) A smart construction site safety helmet detection system and method
CN107578160A (en)Construction personnel's real-name management method
CN113793441B (en)Campus visitor safety analysis system based on thing networking
CN108596503B (en)Abnormal working hour judgment method based on non-inductive card punching
CN113837030A (en)Intelligent personnel management and control method and system for epidemic situation prevention and control and computer equipment
CN111581417A (en)Identity recognition method, terminal, system and storage medium for power distribution room constructors
CN110991979A (en)Attendance management method, device and equipment for intelligent construction site and computer storage medium
CN106326835A (en)Human face data collection statistical system and method for gas station convenience store
CN112528952A (en)Working state intelligent recognition system for electric power business hall personnel
CN114550330A (en) Construction site management personnel supervision and management system
CN114420302A (en)Intelligent epidemic prevention control system for enterprises and public institutions
CN107610261B (en)System capable of managing entrance and exit of construction site
CN113326747A (en)Teaching worker face recognition attendance checking method and system
CN111045372A (en) An intelligent site management system

Legal Events

DateCodeTitleDescription
PB01Publication
PB01Publication
SE01Entry into force of request for substantive examination
SE01Entry into force of request for substantive examination
GR01Patent grant
GR01Patent grant

[8]ページ先頭

©2009-2025 Movatter.jp