CN110032967A - A method of trailing personnel are identified under the current scene of more people - Google Patents

A method of trailing personnel are identified under the current scene of more people Download PDF

Info

Publication number
CN110032967A
CN110032967A CN201910284717.6A CN201910284717A CN110032967A CN 110032967 A CN110032967 A CN 110032967A CN 201910284717 A CN201910284717 A CN 201910284717A CN 110032967 A CN110032967 A CN 110032967A
Authority
CN
China
Prior art keywords
personnel
video pictures
face
people
current scene
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
CN201910284717.6A
Other languages
Chinese (zh)
Inventor
高强
陈煦文
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.)
Shenzhen Wanrui Intelligent Technology Co Ltd
Original Assignee
Shenzhen Wanrui Intelligent 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 Shenzhen Wanrui Intelligent Technology Co Ltd filed Critical Shenzhen Wanrui Intelligent Technology Co Ltd
Priority to CN201910284717.6A priority Critical patent/CN110032967A/en
Publication of CN110032967A publication Critical patent/CN110032967A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/10Terrestrial scenes
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168Feature extraction; Face representation
    • G06V40/171Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
    • GPHYSICS
    • G07CHECKING-DEVICES
    • G07CTIME 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
    • G07C9/00Individual registration on entry or exit
    • G07C9/30Individual registration on entry or exit not involving the use of a pass
    • G07C9/32Individual registration on entry or exit not involving the use of a pass in combination with an identity check
    • G07C9/37Individual 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)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Collating Specific Patterns (AREA)
  • Alarm Systems (AREA)

Abstract

The invention discloses a kind of methods that trailing personnel are identified under the current scene of more people, comprising: carries out Face datection to the video pictures of shooting;Judge in video pictures with the presence or absence of face;If so, extracting the human face data in video pictures;Identification is carried out to the personnel in video pictures according to human face data;Identity information after identification is pushed into display screen;Judge whether the personnel in video pictures have right of access;If it is not, then display screen according to the location of the personnel in video pictures carries out corresponding prompt and guidance to it.The present invention is by carrying out Face datection to the personnel in video pictures, the trailing personnel that not right of access can be effectively prevented enter current gate mouth, and for the mode of this long-range identification face, so that not needing to slow down or stand firm when current in current gate mouth, and then quick passage may be implemented, flexibly and effectively big flow entrance can be managed.

Description

A method of trailing personnel are identified under the current scene of more people
Technical field
The present invention relates to recognition of face, more specifically a kind of side that trailing personnel are identified under the current scene of more people Method.
Background technique
The logic that is commonly designed of the current security system of personnel is: current door default is closed, and ordinary person is impassable.When having After the people of right of access is authenticated by modes such as recognition of face, two dimensional code, IC card, current door is let pass.
But such operation is in the presence of the security risk that can not identify " trailing " behavior: after i.e. someone passes through authentication, without logical The people of row permission can trail the people by gate inhibition, system trailing personnel can not timely be identified, be prompted, being guided or Warning.
Summary of the invention
It is identified under the current scene of more people it is an object of the invention to overcome the deficiencies of the prior art and provide one kind and trails people The method of member.
To achieve the above object, the invention adopts the following technical scheme: people is trailed in a kind of identification under the current scene of more people The method of member, which comprises
Face datection is carried out to the video pictures of shooting;
Judge in video pictures with the presence or absence of face;
If so, extracting the human face data in video pictures;
Identification is carried out to the personnel in video pictures according to human face data;
Identity information after identification is pushed into display screen;
Judge whether the personnel in video pictures have right of access;
If it is not, then display screen according to the location of the personnel in video pictures carries out corresponding prompt and guidance to it.
Its further technical solution are as follows: whether there is face step in the judgement video pictures, specifically include following Step:
Video pictures are filtered;
Judge whether to obtain face feature point from filtering, wherein face feature point include face contour, eyebrow, nose, Eyes and lip;
If so, obtaining the position of face feature point;
The position of face feature point and average characteristics face are compared;
Judge whether comparing result meets threshold requirement;
If so, can determine that is a face.
Its further technical solution are as follows: the human face data step extracted in video pictures specifically includes following step It is rapid:
Cut all people's face region picture in video pictures;
Extract face recognition features' point in human face region picture;
Characteristic value calculating is carried out to face recognition features' point.
Its further technical solution are as follows: described that identification step is carried out to the personnel in video pictures according to human face data Suddenly, specifically includes the following steps:
Access white list face information;
Characteristic value and white list face information are compared;
Judge whether the personnel in video pictures are personnel in white list;
If so, transferring the identity information that the personnel in video pictures store in white list, and in marking video picture Personnel be white list personnel;
If it is not, then intercepting the image of counterpart personnel in video pictures as identity information, and the people in marking video picture Member is non-white list personnel.
Its further technical solution are as follows: whether the personnel judged in video pictures have right of access step, tool Body the following steps are included:
Judge whether it is white list personnel;
If so, issuing right of access voucher;
If it is not, then judging whether the personnel in video pictures are disadvantaged group personnel, wherein disadvantaged group personnel include old People, child, pregnant woman or disabled person;
If so, notifying current gate mouth administrative staff.
Its further technical solution are as follows: the display screen carries out it according to the location of the personnel in video pictures Corresponding prompt and directing step, specifically includes the following steps:
It obtains according to the location of personnel in video pictures information;
Judge whether the personnel in video pictures enter first area;
If so, display screen plays leading question, the personnel in video pictures is guided to register or leave;
If it is not, then judging whether the personnel in video pictures enter second area;
If so, display screen carries out voice warning, while warning message is pushed to Security Personnel.
Its further technical solution are as follows: the first area is warning zone, and the second area is expulsion region;It is described The distance between region and current gate mouth is expelled to be less than the distance between the warning zone and current gate mouth.
Compared with the prior art, the invention has the advantages that: one kind provided by the invention identifies under the current scene of more people The method of trailing personnel can be effectively prevented no right of access by carrying out Face datection to the personnel in video pictures Trailing personnel enter current gate mouth, and for the mode of this long-range identification face, so that not needing to subtract when current Speed is stood firm in current gate mouth, and then quick passage may be implemented, can flexibly and effectively to big flow entrance into Row management.In addition, entrance can be reduced to the people of Security Personnel by identification, guidance, alarm to no right of access personnel Force request, to reduce costs.
The above description is only an overview of the technical scheme of the present invention, can in order to better understand technical measure It is implemented in accordance with the contents of the specification, and in order to make above and other objects of the present invention, feature and advantage brighter Show understandable, special below to lift preferred embodiment, detailed description are as follows.
Detailed description of the invention
Fig. 1 is a kind of flow chart for the method specific embodiment that trailing personnel are identified under the current scene of more people of the present invention One;
Fig. 2 is a kind of flow chart for the method specific embodiment that trailing personnel are identified under the current scene of more people of the present invention Two;
Fig. 3 is a kind of flow chart for the method specific embodiment that trailing personnel are identified under the current scene of more people of the present invention Three;
Fig. 4 is a kind of flow chart for the method specific embodiment that trailing personnel are identified under the current scene of more people of the present invention Four;
Fig. 5 is a kind of flow chart for the method specific embodiment that trailing personnel are identified under the current scene of more people of the present invention Five;
Fig. 6 is a kind of flow chart for the method specific embodiment that trailing personnel are identified under the current scene of more people of the present invention Six.
Specific embodiment
In order to more fully understand technology contents of the invention, combined with specific embodiments below to technical solution of the present invention into One step introduction and explanation, but not limited to this.
It should be appreciated that herein, relational terms such as first and second and the like are used merely to an entity/behaviour Work/object is distinguished with another entity/operation/object, without necessarily requiring or implying these entity/operation/objects Between there are any actual relationship or orders.
It is also understood that the terms "include", "comprise" or any other variant thereof is intended to cover non-exclusive inclusion, So that the process, method, article or the system that include a series of elements not only include those elements, but also including not having The other element being expressly recited, or further include for this process, method, article or the intrinsic element of system.Do not having In the case where having more limitations, the element that is limited by sentence "including a ...", it is not excluded that include the element process, There is also other identical elements in method, article or system.
As shown in figures 1 to 6, the present invention provides a kind of method that trailing personnel are identified under the current scene of more people, this method Include:
S10, Face datection is carried out to the video pictures of shooting;
S20, judge in video pictures with the presence or absence of face, if so, S30, human face data in video pictures is then extracted, if It is no, then return step S10;
S40, identification is carried out to the personnel in video pictures according to human face data;
S50, the identity information after identification is pushed into display screen;
S60, judge whether the personnel in video pictures have right of access;If it is not, S70, then display screen is drawn according to video The location of personnel in face carry out corresponding prompt and guidance to it, if so, S80, then allowing to pass through.
Specifically, in step S10, picture that video pictures are shot from camera.
Further, step S20 specifically includes the following steps:
S201, video pictures are filtered;
S202, judge whether to obtain face feature point from filtering, wherein face feature point include face contour, eyebrow, Nose, eyes and lip, if so, S203, the position of face feature point is then obtained, if it is not, then return step S201;
S204, the position of face feature point and average characteristics face are compared;
S205, judge whether comparing result meets threshold requirement, if so, S2051, then can determine that it is a face, if it is not, S2052, a face is not constituted.
Specifically, threshold value represents the goodness of fit of face feature point Yu average characteristics face in step S205, threshold value can basis Corresponding comparison rule is set.
Further, step S30 specifically includes the following steps:
S301, all people's face region picture in video pictures is cut;
Face recognition features' point in S302, extraction human face region picture;
S303, characteristic value calculating is carried out to face recognition features' point.
Specifically, needing to require to cut to each face when there is multiple faces in video pictures.
Further, step S40 specifically includes the following steps:
S401, access white list face information;
S402, characteristic value and white list face information are compared;
S403, judge whether personnel in video pictures are personnel in white list, if so, S4031, then transferring video picture The identity information that personnel in face store in white list, and the personnel in marking video picture are white list personnel, if it is not, S4032, the image of counterpart personnel in video pictures is then intercepted as identity information, and the personnel in marking video picture are non-white List personnel.
Further, step S60 specifically includes the following steps:
S601, judge whether it is white list personnel;If so, S6012, issue right of access voucher, if it is not, S6011, then Judge whether the personnel in video pictures are disadvantaged group personnel, wherein disadvantaged group personnel include old man, child, pregnant woman or Disabled person;
If so, S60111, current gate mouth administrative staff are then notified, if it is not, then portion issues right of access voucher to S60112.
Further, step S70 specifically includes the following steps:
S701, it obtains according to the location of personnel in video pictures information;
S702, judge whether the personnel in video pictures enter first area, if so, S704, then display screen play guidance Language guides the personnel in video pictures to register or leave, if it is not, S703, then judging whether is personnel in video pictures Into second area;
If so, S705, then display screen carry out voice warning, while warning message is pushed to Security Personnel, if it is not, then returning Step S701.
Specifically, first area is warning zone, second area is expulsion region;It expels between region and current gate mouth Distance be less than the distance between warning zone and current gate mouth.
It is above-mentioned that technology contents of the invention are only further illustrated with embodiment, in order to which reader is easier to understand, but not It represents embodiments of the present invention and is only limitted to this, any technology done according to the present invention extends or recreation, by of the invention Protection.Protection scope of the present invention is subject to claims.

Claims (7)

1. a kind of method for identifying trailing personnel under the current scene of more people, which is characterized in that the described method includes:
Face datection is carried out to the video pictures of shooting;
Judge in video pictures with the presence or absence of face;
If so, extracting the human face data in video pictures;
Identification is carried out to the personnel in video pictures according to human face data;
Identity information after identification is pushed into display screen;
Judge whether the personnel in video pictures have right of access;
If it is not, then display screen according to the location of the personnel in video pictures carries out corresponding prompt and guidance to it.
2. a kind of method for identifying trailing personnel under the current scene of more people according to claim 1, which is characterized in that institute It whether there is face step in the judgement video pictures stated, specifically includes the following steps:
Video pictures are filtered;
Judge whether to obtain face feature point from filtering, wherein face feature point includes face contour, eyebrow, nose, eyes And lip;
If so, obtaining the position of face feature point;
The position of face feature point and average characteristics face are compared;
Judge whether comparing result meets threshold requirement;
If so, can determine that is a face.
3. a kind of method for identifying trailing personnel under the current scene of more people according to claim 1, which is characterized in that institute That states extracts the human face data step in video pictures, specifically includes the following steps:
Cut all people's face region picture in video pictures;
Extract face recognition features' point in human face region picture;
Characteristic value calculating is carried out to face recognition features' point.
4. a kind of method for identifying trailing personnel under the current scene of more people according to claim 3, which is characterized in that institute That states carries out identification step to the personnel in video pictures according to human face data, specifically includes the following steps:
Access white list face information;
Characteristic value and white list face information are compared;
Judge whether the personnel in video pictures are personnel in white list;
If so, transferring the identity information that the personnel in video pictures store in white list, and the people in marking video picture Member is white list personnel;
If it is not, then intercepting the image of counterpart personnel in video pictures as identity information, and the personnel in marking video picture are Non- white list personnel.
5. a kind of method for identifying trailing personnel under the current scene of more people according to claim 4, which is characterized in that institute Whether the personnel judged in video pictures stated have right of access step, specifically includes the following steps:
Judge whether it is white list personnel;
If so, issuing right of access voucher;
If it is not, then judge whether the personnel in video pictures are disadvantaged group personnel, wherein disadvantaged group personnel include old man, it is small Child, pregnant woman or disabled person;
If so, notifying current gate mouth administrative staff.
6. a kind of method for identifying trailing personnel under the current scene of more people according to claim 1, which is characterized in that institute The display screen stated carries out corresponding prompt and directing step to it according to the location of the personnel in video pictures, specifically includes Following steps:
It obtains according to the location of personnel in video pictures information;
Judge whether the personnel in video pictures enter first area;
If so, display screen plays leading question, the personnel in video pictures is guided to register or leave;
If it is not, then judging whether the personnel in video pictures enter second area;
If so, display screen carries out voice warning, while warning message is pushed to Security Personnel.
7. a kind of method for identifying trailing personnel under the current scene of more people according to claim 6, which is characterized in that institute Stating first area is warning zone, and the second area is expulsion region;Between the expulsion region and current gate mouth away from From less than the distance between the warning zone and current gate mouth.
CN201910284717.6A 2019-04-10 2019-04-10 A method of trailing personnel are identified under the current scene of more people Pending CN110032967A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910284717.6A CN110032967A (en) 2019-04-10 2019-04-10 A method of trailing personnel are identified under the current scene of more people

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910284717.6A CN110032967A (en) 2019-04-10 2019-04-10 A method of trailing personnel are identified under the current scene of more people

Publications (1)

Publication Number Publication Date
CN110032967A true CN110032967A (en) 2019-07-19

Family

ID=67237900

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910284717.6A Pending CN110032967A (en) 2019-04-10 2019-04-10 A method of trailing personnel are identified under the current scene of more people

Country Status (1)

Country Link
CN (1) CN110032967A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110738769A (en) * 2019-09-19 2020-01-31 日立楼宇技术(广州)有限公司 forbidden user identification method, device, system and computer equipment
CN111223216A (en) * 2020-01-13 2020-06-02 郑州纷呈科技有限公司 Non-contact access control card swiping method
CN114038098A (en) * 2021-11-04 2022-02-11 厦门熵基科技有限公司 Trailing detection method, device, equipment and readable storage medium
CN114093058A (en) * 2021-10-25 2022-02-25 深圳市椰壳信息科技有限公司 Smart door lock-based home equipment linkage control method and device and smart door lock
CN114613056A (en) * 2022-03-17 2022-06-10 深圳创维-Rgb电子有限公司 Gate control method, device, equipment and computer readable storage medium

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105957286A (en) * 2015-12-18 2016-09-21 许昌学院 Intelligent community safety method
CN106033539A (en) * 2015-03-20 2016-10-19 上海宝信软件股份有限公司 Meeting guiding method and system based on video face recognition
CN106156688A (en) * 2015-03-10 2016-11-23 上海骏聿数码科技有限公司 A kind of dynamic human face recognition methods and system
CN106408832A (en) * 2016-08-29 2017-02-15 重庆交通大学 Interference-free visitor monitoring method and interference-free visitor monitoring system
CN206259149U (en) * 2016-11-14 2017-06-16 扬州大学 A kind of scenic spot location aware bears guider with people
CN108052919A (en) * 2017-12-26 2018-05-18 北斗七星(重庆)物联网技术有限公司 A kind of safety-protection system and method based on recognition of face
CN108961495A (en) * 2018-06-25 2018-12-07 北京蜂盒科技有限公司 A kind of data-updating method and device based on recognition of face
CN109145734A (en) * 2018-07-17 2019-01-04 深圳市巨龙创视科技有限公司 Algorithm is captured in IPC Intelligent human-face identification based on 4K platform
CN109493555A (en) * 2018-12-05 2019-03-19 郑州升达经贸管理学院 A kind of campus dormitory building safety defense monitoring system based on intelligent monitoring technology

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106156688A (en) * 2015-03-10 2016-11-23 上海骏聿数码科技有限公司 A kind of dynamic human face recognition methods and system
CN106033539A (en) * 2015-03-20 2016-10-19 上海宝信软件股份有限公司 Meeting guiding method and system based on video face recognition
CN105957286A (en) * 2015-12-18 2016-09-21 许昌学院 Intelligent community safety method
CN106408832A (en) * 2016-08-29 2017-02-15 重庆交通大学 Interference-free visitor monitoring method and interference-free visitor monitoring system
CN206259149U (en) * 2016-11-14 2017-06-16 扬州大学 A kind of scenic spot location aware bears guider with people
CN108052919A (en) * 2017-12-26 2018-05-18 北斗七星(重庆)物联网技术有限公司 A kind of safety-protection system and method based on recognition of face
CN108961495A (en) * 2018-06-25 2018-12-07 北京蜂盒科技有限公司 A kind of data-updating method and device based on recognition of face
CN109145734A (en) * 2018-07-17 2019-01-04 深圳市巨龙创视科技有限公司 Algorithm is captured in IPC Intelligent human-face identification based on 4K platform
CN109493555A (en) * 2018-12-05 2019-03-19 郑州升达经贸管理学院 A kind of campus dormitory building safety defense monitoring system based on intelligent monitoring technology

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110738769A (en) * 2019-09-19 2020-01-31 日立楼宇技术(广州)有限公司 forbidden user identification method, device, system and computer equipment
CN111223216A (en) * 2020-01-13 2020-06-02 郑州纷呈科技有限公司 Non-contact access control card swiping method
CN114093058A (en) * 2021-10-25 2022-02-25 深圳市椰壳信息科技有限公司 Smart door lock-based home equipment linkage control method and device and smart door lock
CN114038098A (en) * 2021-11-04 2022-02-11 厦门熵基科技有限公司 Trailing detection method, device, equipment and readable storage medium
CN114038098B (en) * 2021-11-04 2024-02-06 厦门熵基科技有限公司 Trailing detection method, trailing detection device, trailing detection equipment and readable storage medium
CN114613056A (en) * 2022-03-17 2022-06-10 深圳创维-Rgb电子有限公司 Gate control method, device, equipment and computer readable storage medium
CN114613056B (en) * 2022-03-17 2024-03-12 深圳创维-Rgb电子有限公司 Gate control method, device, equipment and computer readable storage medium

Similar Documents

Publication Publication Date Title
CN110032967A (en) A method of trailing personnel are identified under the current scene of more people
CN107480658B (en) Face recognition device and method based on multi-angle video
CN109376639B (en) Accompanying personnel early warning system and method based on portrait recognition
CN108053615B (en) Method for detecting fatigue driving state of driver based on micro-expression
CN101587485B (en) Face information automatic login method based on face recognition technology
US8340366B2 (en) Face recognition system
CN103714631B (en) ATM cash dispenser intelligent monitor system based on recognition of face
CN106997629A (en) Access control method, apparatus and system
CN109359625A (en) The method and system of customer identification is judged based on head and shoulder detection and face recognition technology
CN104992148A (en) ATM terminal human face key points partially shielding detection method based on random forest
CN105868689A (en) Cascaded convolutional neural network based human face occlusion detection method
CN105825176A (en) Identification method based on multi-mode non-contact identity characteristics
CN109286788A (en) A kind of safety defense monitoring system based on cloud computing
CN112434578A (en) Mask wearing normative detection method and device, computer equipment and storage medium
CN103839049A (en) Double-person interactive behavior recognizing and active role determining method
CN111797677A (en) Face recognition living body detection method based on face iris recognition and thermal imaging technology
WO2022121498A1 (en) Identity recognition method, model training method, apparatuses, and device and storage medium
KR101515214B1 (en) Identification method using face recognition and entrance control system and method thereof using the identification method
CN110211251A (en) A kind of face identification method, device, storage medium and recognition of face terminal
CN111599044A (en) Access control safety management system based on multi-mode biological feature recognition
CN107516076A (en) Portrait identification method and device
CN103208144A (en) Dormitory-management system based on face recognition
JP5877678B2 (en) Face authentication database management method, face authentication database management apparatus, and face authentication database management program
CN107025435A (en) A kind of face recognition processing method and system
KR20020032048A (en) Face cognition the preservation a means

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20190719

RJ01 Rejection of invention patent application after publication