CN111666780A - Intelligent door control security method based on emotion recognition technology - Google Patents

Intelligent door control security method based on emotion recognition technology Download PDF

Info

Publication number
CN111666780A
CN111666780A CN201910163283.4A CN201910163283A CN111666780A CN 111666780 A CN111666780 A CN 111666780A CN 201910163283 A CN201910163283 A CN 201910163283A CN 111666780 A CN111666780 A CN 111666780A
Authority
CN
China
Prior art keywords
emotion
module
intelligent
state
visitor
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
CN201910163283.4A
Other languages
Chinese (zh)
Inventor
王春雷
尉迟学彪
毛鹏轩
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.)
Beijing Rostec Technology Co ltd
Original Assignee
Beijing Rostec 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 Beijing Rostec Technology Co ltd filed Critical Beijing Rostec Technology Co ltd
Priority to CN201910163283.4A priority Critical patent/CN111666780A/en
Publication of CN111666780A publication Critical patent/CN111666780A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • 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
    • G06V40/174Facial expression recognition
    • G06V40/176Dynamic expression
    • 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
    • G06V40/172Classification, e.g. identification
    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B25/00Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems
    • G08B25/01Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium
    • G08B25/08Alarm systems in which the location of the alarm condition is signalled to a central station, e.g. fire or police telegraphic systems characterised by the transmission medium using communication transmission lines

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Emergency Management (AREA)
  • Alarm Systems (AREA)

Abstract

The invention discloses an intelligent gate control security method based on an emotion recognition technology, which can realize active discovery and early warning of potential suspicious visitors and human-computer interaction and emotion interaction between home intelligent equipment and a main person through intelligent detection and analysis of the emotion state of a user. The video data stream receiving module receives external video data; the face recognition comparison module is used for judging whether the user is a family member or an external visitor; the emotion state evaluation module is used for realizing recognition and evaluation of the emotion states of the family members; the emotion intelligent interaction module is used for realizing linkage control and man-machine interaction on the household intelligent equipment; the abnormal emotion detection module is used for detecting whether an external visitor has abnormal emotion; the suspicious visitor alarm module is used for realizing alarm pushing of visitors with abnormal emotions; the emotional state database is used for storing and accessing emotional state data; and the emotion data analysis module is used for realizing summary statistical analysis on emotion state data of family members and external visitors.

Description

Intelligent door control security method based on emotion recognition technology
Technical Field
The invention relates to the technical field of gating security, in particular to an intelligent gating security method based on an emotion recognition technology.
Background
With the continuous promotion of the trend of artificial intelligence, the intelligent home industry develops rapidly, and the intellectualization is the inevitable development trend of future homes. The door lock is the first line of defense of family safety, therefore realize "intelligent gate security protection" is the prerequisite of realizing intelligent family. At present, every big tradition firm and emerging internet enterprise have a lot of force intelligent gate security protection market, and intelligent gate security protection market is the explosive growth situation.
At present, advanced technologies such as fingerprint identification, iris identification, face identification and the like are introduced into various manufacturers to improve the technical content and the core competitiveness of the home intelligent gating security product. The intelligent door control security system with the built-in face recognition technology can recognize the face of a user in real time through the electronic peep hole and compare the face with the known face, and therefore the door opening verification process is finally achieved. Because the technology belongs to a non-contact identity recognition technology and does not need to be in contact with recognition equipment, the acceptance degree of a user on the technology is improved, and in addition, the face recognition speed is high, the precision is high, so the technology is popular in the aspects of safety and operability, and becomes one of the identity recognition technologies commonly adopted by intelligent gate control security.
However, the current intelligent gating security based on the face recognition technology also has certain limitations. Generally speaking, the intelligent gate control security only identifies the user according to the facial image data of the user collected by the electronic peep hole, so as to determine whether the user is a master or a visitor, but the intelligent gate control security does not have the real-time identification and analysis capability on the emotional state of the user. In real-world scenarios, the emotional state is a very valuable reference, whether to the host or the visitor. For example, if the real-time recognition and analysis of the emotional state of the user can be further realized, the method can help to realize the active discovery and early warning of potential suspicious visitors, and meanwhile, the better man-machine interaction and emotional interaction between the host and various home intelligent devices can be realized based on the emotional state of the host.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides an intelligent gating security method based on an emotion recognition technology. Compared with the existing intelligent door control security technology, the intelligent door control security method provided by the invention can realize real-time perception, identification and analysis of the emotion state of the user, thereby realizing active discovery and early warning of potential suspicious visitors, and realizing better man-machine interaction and emotion interaction between the owner and various household intelligent devices based on the emotion state of the owner.
The invention provides an intelligent gating security method based on emotion recognition technology, and a basic functional flow of the intelligent gating security method is shown in an attached figure 1. Wherein:
the video data stream receiving module is used for receiving video data collected by the electronic cat eye and the monitoring camera;
the face recognition comparison module is responsible for judging whether the identity of the user is a family member or an external visitor;
the emotion state evaluation module is responsible for recognizing and evaluating the emotion states of the family members;
the emotion intelligent interaction module is responsible for switching the corresponding working states of the family intelligent equipment according to the emotion state evaluation result of the family member;
the abnormal emotion detection module is used for detecting whether an external visitor has abnormal emotion including anger and attack tendency;
the suspicious visitor alarm module is responsible for pushing alarm information of an external visitor with abnormal emotion;
the emotional state database module is used for storing and taking emotional state data of family members and external visitors;
and the emotion data analysis module is responsible for realizing summary statistics and analysis of emotion state data of family members and external visitors.
Compared with the prior art, the invention has the beneficial effects that: the invention provides an intelligent gate control security method based on emotion recognition technology, which can not only recognize the identity of a visitor (a family member/an external visitor), but also sense, recognize and analyze the emotion states of the family member and the external visitor in real time, thereby realizing the active discovery and early warning of potential suspicious visitors, realizing the objective evaluation of the emotion states of the family member, and realizing better man-machine interaction and emotion interaction between family members and various family intelligent devices based on the emotion states of the family members.
Drawings
Fig. 1 is a flow chart showing the detailed function of the method.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
In the invention, the video data stream receiving module is responsible for receiving video data collected by video collecting equipment such as an electronic cat eye, a monitoring camera and the like and pushing the data to the face recognition comparison module.
The face recognition comparison module is responsible for judging the identity of the user, namely judging whether the user is a family member or an external visitor; the module is constructed based on faceNet, and uses MySQL database to access the image data information related to the human face; and if the judgment result is that the family is the family, triggering an emotion state evaluation module, otherwise triggering an abnormal emotion detection module.
The emotion state evaluation module is responsible for recognizing and evaluating the emotion states of the family members; the identification process is comprehensively judged based on two modes of facial expression identification and physiological vibration analysis of a person, and the final result of the evaluation process is divided into 3 states of positive, negative and neutral.
The emotion intelligent interaction module is responsible for realizing linkage control and man-machine interaction on the family intelligent equipment according to the emotion state evaluation result of the family member (automatically switching the working state of indoor related intelligent equipment according to different emotion states of the family member); the linkage process of the module and each intelligent device is based on two network connection modes of WiFi and ZigBee.
The abnormal emotion detection module is used for detecting whether an external visitor has abnormal emotion including anger and attack tendency; the detection process is comprehensively judged based on two modes of facial expression recognition and physiological vibration analysis of a person; if the result of the determination is yes, the suspicious visitor alarm module is triggered.
The physiological vibration analysis in the emotion state evaluation module and the abnormal emotion detection module is to carry out quantitative calculation on the amplitude and the frequency of micro vibration of facial muscles of a person so as to obtain an emotion state value of the person; wherein the amplitude is represented by the formula
Figure BDA0001985416490000041
Determining, wherein x and y represent coordinate values of the point in the image, n represents the total frame number of the image, Vx,y,iRepresenting the displacement amplitude of the point in the ith frame; the frequency is represented by
Figure BDA0001985416490000042
Is determined in whichiRepresenting the difference between different frames at the ith point of the image.
The suspicious visitor alarm module is responsible for pushing external visitor alarm information with abnormal emotion to a preset intelligent terminal so as to remind a host that the external visitor has abnormal emotion; the alarm information specifically comprises time, place, visitor image, stay duration, stay times and the like.
The emotional state database module realizes the summary storage of the result data generated by the emotional state evaluation module and the abnormal emotion detection module by using a MySQL database.
The emotion data analysis module is responsible for realizing statistical analysis of emotion state summarized data of family members and external visitors, wherein the emotion state summarized data comprises the occurrence times, duration and the like of different emotion states; on one hand, the emotion change situation of the family members in a specific time period is analyzed and evaluated so as to better realize emotional intelligent interaction; on the other hand, potentially suspicious persons who are often outside the door can also be identified, and the owner can be reminded to take further precautions.

Claims (9)

1. An intelligent gating security method based on emotion recognition technology is characterized in that: the intelligent detection and analysis of the emotion state of the user can be used for realizing active discovery and early warning of potential suspicious visitors and realizing more humanized man-machine interaction and emotion interaction between the household intelligent equipment and a host, and the intelligent detection and emotion detection system specifically comprises eight functional modules, namely video data stream receiving, face recognition comparison, emotion state assessment, emotion intelligent interaction, abnormal emotion detection, suspicious visitor alarming, an emotion state database and emotion data analysis.
2. The method of claim 1, wherein: the face recognition comparison module is used for judging whether the identity of the user is a family member or an external visitor; the module is constructed based on faceNet and uses MySQL database to access the image data information related to the human face.
3. The method of claim 1, wherein: the emotion state evaluation module is used for realizing recognition and evaluation of the emotion states of the family members; the identification process is comprehensively judged based on two modes of facial expression identification and physiological vibration analysis of a person, and the final result of the evaluation process is divided into a positive state, a negative state and a neutral state.
4. The method of claim 1, wherein: the emotion intelligent interaction module is used for switching the corresponding working state of the family intelligent equipment according to the emotion state evaluation result of the family member; the module and each intelligent device are linked based on two network connection modes of WiFi and ZigBee.
5. The method of claim 1, wherein: the abnormal emotion detection module is used for detecting whether an external visitor has abnormal emotion including anger and attack tendency; the detection process is comprehensively judged based on two modes of facial expression recognition and physiological vibration analysis of the human.
6. The method of claim 1, wherein: the suspicious visitor alarm module is used for pushing alarm information of an external visitor with abnormal emotion; the alarm information specifically comprises time, place, visitor image, stay duration and stay times.
7. The method of claim 1, wherein: the emotion state database module is used for accessing the emotion state evaluation result data of the family member in the claim 3 and the suspicious visitor alarm information data in the claim 6; the database used by this module is also MySQL.
8. The method of claim 1, wherein: the emotion data analysis module is used for realizing summary statistics and analysis of emotion state data of family members and external visitors; wherein the statistical information comprises the frequency and duration of the occurrence of different emotional states.
9. The method according to claims 3 and 5, characterized in that: the physiological vibration analysis refers to a process of quantitatively calculating the amplitude and the frequency of the micro vibration of the facial muscles of the person so as to obtain the emotional state value of the person; wherein the amplitude is represented by the formula
Figure FDA0001985416480000021
Calculated, wherein x and y represent coordinate values of the point in the image, n represents the total frame number of the image, Vx,y,iRepresenting the displacement amplitude of the point in the ith frame; the frequency is represented by
Figure FDA0001985416480000022
Is calculated to giveiRepresenting the difference between different frames at the ith point of the image.
CN201910163283.4A 2019-03-05 2019-03-05 Intelligent door control security method based on emotion recognition technology Pending CN111666780A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910163283.4A CN111666780A (en) 2019-03-05 2019-03-05 Intelligent door control security method based on emotion recognition technology

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910163283.4A CN111666780A (en) 2019-03-05 2019-03-05 Intelligent door control security method based on emotion recognition technology

Publications (1)

Publication Number Publication Date
CN111666780A true CN111666780A (en) 2020-09-15

Family

ID=72381517

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910163283.4A Pending CN111666780A (en) 2019-03-05 2019-03-05 Intelligent door control security method based on emotion recognition technology

Country Status (1)

Country Link
CN (1) CN111666780A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113409507A (en) * 2021-06-15 2021-09-17 深圳市纽贝尔电子有限公司 Control method based on face recognition
WO2022257044A1 (en) * 2021-06-09 2022-12-15 京东方科技集团股份有限公司 Interaction method, interaction system, and electronic device

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022257044A1 (en) * 2021-06-09 2022-12-15 京东方科技集团股份有限公司 Interaction method, interaction system, and electronic device
CN113409507A (en) * 2021-06-15 2021-09-17 深圳市纽贝尔电子有限公司 Control method based on face recognition

Similar Documents

Publication Publication Date Title
CN103839373B (en) A kind of unexpected abnormality event Intelligent Recognition alarm device and warning system
US11217076B1 (en) Camera tampering detection based on audio and video
US10593174B1 (en) Automatic setup mode after disconnect from a network
US11647165B1 (en) Audio/video recording and communication doorbell devices including transistor assemblies, and associated systems and methods
CN202257856U (en) Driver fatigue-driving monitoring device
Lim et al. iSurveillance: Intelligent framework for multiple events detection in surveillance videos
CN109376639B (en) Accompanying personnel early warning system and method based on portrait recognition
CN105427421A (en) Entrance guard control method based on face recognition
US11341825B1 (en) Implementing deterrent protocols in response to detected security events
CN202130312U (en) Driver fatigue driving monitoring device
CN109298785A (en) A kind of man-machine joint control system and method for monitoring device
CN110133610A (en) ULTRA-WIDEBAND RADAR action identification method based on time-varying distance-Doppler figure
CA2714603A1 (en) Video sensor and alarm system and method with object and event classification
CN105844128A (en) Method and device for identity identification
US10713928B1 (en) Arming security systems based on communications among a network of security systems
US11164435B1 (en) Audio/video recording and communication doorbell devices with supercapacitors
US12073698B1 (en) Security device with user-configurable motion detection settings
CN109191769A (en) A kind of smart home burglary-resisting system
US10733857B1 (en) Automatic alteration of the storage duration of a video
US10490033B1 (en) Customized notifications based on device characteristics
CN111666780A (en) Intelligent door control security method based on emotion recognition technology
Ray et al. An intelligent vision system for monitoring security and surveillance of ATM
US11163097B1 (en) Detection and correction of optical filter position in a camera device
US11032128B2 (en) Using a local hub device as a substitute for an unavailable backend device
CN109583396A (en) A kind of region prevention method, system and terminal based on CNN two stages human testing

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
WD01 Invention patent application deemed withdrawn after publication
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20200915