CN110532882A - Recognition of face safety alarm system and equipment based on embedded artificial intelligent chip - Google Patents

Recognition of face safety alarm system and equipment based on embedded artificial intelligent chip Download PDF

Info

Publication number
CN110532882A
CN110532882A CN201910692119.2A CN201910692119A CN110532882A CN 110532882 A CN110532882 A CN 110532882A CN 201910692119 A CN201910692119 A CN 201910692119A CN 110532882 A CN110532882 A CN 110532882A
Authority
CN
China
Prior art keywords
module
data
recognition
video
face
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
CN201910692119.2A
Other languages
Chinese (zh)
Inventor
熊杰
涂俊峰
马博
刘华祠
刘建
杜峰
马兰芳
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.)
Yangtze University
Original Assignee
Yangtze University
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 Yangtze University filed Critical Yangtze University
Priority to CN201910692119.2A priority Critical patent/CN110532882A/en
Publication of CN110532882A publication Critical patent/CN110532882A/en
Pending legal-status Critical Current

Links

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
    • G06V40/172Classification, e.g. identification

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Alarm Systems (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

The invention belongs to intelligent identification technology fields, disclose a kind of recognition of face safety alarm system and equipment based on embedded artificial intelligent chip, video data acquiring module is for acquiring video information;Data relay module is used to obtain the frame image in video information;Real-time detection module carries out live Face detection, identification for development board;Judgement is used for local development board with alarm module and obtains recognition result, and judges alert level, if alert level is excessively high, directly transmits warning message;Forwarding, storage of the data conversion storage module for data;Data acquisition module is sent to user mobile phone for video, so that user is obtained alarm result in time and handles.The present invention has the characteristics that directly to carry out real-time face identification, real time monitoring alarm, perpetuation of testimony and at low cost to the video of transmission, and user can be used directly cell phone application and play display real-time pictures.

Description

Recognition of face safety alarm system and equipment based on embedded artificial intelligent chip
Technical field
The invention belongs to intelligent identification technology field more particularly to a kind of face knowledges based on embedded artificial intelligent chip Other safety alarm system and equipment.
Background technique
Currently, the immediate prior art:
Security protection problem is always distinct issues in a life, and either all there is some by gate inhibition or monitor mode Indeterminable problem, such as: Realtime Alerts, evidence video save, machine initiative recognition etc..Under this current big environment, Either household safety-protection, shop security protection or company's security protection all be there is a problem that many, although visible security protection produces on the market Product emerge one after another, but monitor in real time alarm means be it is not satisfactory, what is had can only monitor, some need touch red line, Also some is to be gate inhibition, but these are all inflexible, is difficult to accomplish to prevent safely when tackling those experienced invaders Shield.
The prior art cannot and alarm and cannot will invade the long-acting preservation of evidence, and recognition of face process is not perfect, The product of nearly all energy recognition of face is all to send data to third-party server to identify, is not product itself identification, this Sample just produces some problems (such as delay, safety, loss of data);And partially intelligentized some product costs are generally higher.
In conclusion problem of the existing technology is:
(1) prior art does recognition of face mostly to rely on third-party server resource, this causes identification process to need By network channel, then delay length is certainly existed, the problems such as loss of data, real-time performance is not caught up with regard to some yet.
(2) prior art can not achieve intelligent extraction invasion evidence and save, and can only save monitor video collected, this It allows for being more troublesome when searching evidence.
(3) prior art is in the majority with entrance guard security system, and entrance guard security system can not ensure in region nobody completely.
(4) prior art cannot and alarm.
(5) the partially intelligentized product cost of the prior art is generally higher.
Solve the difficulty of above-mentioned technical problem:
Difficulty of the invention is how to replace the first extraction data progress server identification of legacy system mode then anti- It is fed to mobile terminal and obtains recognition result;The alarm decision grade how changed in tradition is single, and warning effect is undesirable etc..For It solves these problems and uses highly integrated artificial intelligence chip as identification hardware, while overcoming traditional alert mode Unification, Intelligent treatment on-site supervision areas case, live evidence save etc., and retain user under traditional mode and can look at any time See that the function of monitoring site situation, real-time performance are more much higher than traditional scheme.
Solve the meaning of above-mentioned technical problem:
It solves recognition of face and needs to rely on external server resource, shorten reaction process and the time of identification, and provide The functions such as real time intelligent control, evidence store, alarm issues, realize the real time monitoring video identification early warning security protection system of complete set System.
Summary of the invention
In view of the problems of the existing technology, the present invention provides a kind of, and the face based on embedded artificial intelligent chip is known Other safety alarm system and method.
The invention is realized in this way a kind of recognition of face safety alarm system based on embedded artificial intelligent chip, Specifically module includes:
Video data acquiring module, data relay module, real-time detection module, judgement and alarm module, data conversion storage mould Block, data acquisition module.
Video data acquiring module: for acquiring video information;Including video capture device and transmission connectivity port, by taking the photograph As head obtains video data and by connectivity port real-time Transmission to data relay module.
Data relay module: it for obtaining the frame image in video information, is then forwarded to processing unit;It is connect including data By temporary storage module and micro treatment module, micro process is carried out by obtaining the data that upper level is sent, obtains the frame in data information Image is sent in real time according to the frame number that detection identification module needs.
Real-time detection module: live Face detection, identification are carried out for development board;The frame image sended over is passed through JetsonNano development board carries out real-time Face detection, identification operation, obtains recognition result.
Judgement and alarm module: recognition result is obtained for local development board, and alert level is judged, if alarm Grade is excessively high, then directly transmits warning message;And recognition result is differentiated, obtain its corresponding alert level, grade compared with User terminal is sent to when low to be confirmed whether to need to alarm, when grade is highest if skip data conversion storage and data acquisition module is straight Receive and send warning message.
Data conversion storage module: forwarding, storage for data;Higher level's judgement and alarm mould are obtained by external network server module Block obtains correct judging result, and video data is stored in the transmission that server end is next step users' mobile end and does standard It is standby.
Data acquisition module: for sending the video to user mobile phone, user is made to obtain alarm result in time and locating Reason;Mainly in the mobile terminal of user, user checks the video data obtained from server end, carries out judging whether to need in time Carry out alert process.
Further, the real-time detection module judgement has stranger, then the data such as alert level is stored in development board and deposited It stores up in space.The development board memory space is only used for storage evidence video.
Further, the data conversion storage module, system is by video data transmission to outer net SRS service routine, alarming result It is sent to MQTT service routine, and video is stored in the memory space of the end PC.
Another object of the present invention is to provide the recognition of face peace based on embedded artificial intelligent chip described in a kind of carrying The recognition of face security alarm equipment of anti-alarm system.
In conclusion advantages of the present invention and good effect are as follows:
The present invention acquires real-time video using camera, and recognition of face part is added in real-time video, all the time Recognition of face is done, alarm form is taken directly to prompt the user with once detecting and having stranger in the monitoring area, can be solved Certainly the problem of security protection real-time, and the problem of also can solve the direct perpetuation of testimony when invader swarms into, full set work is handed over It is solved by computer.
Hardware resource using ARM intelligent integrated development board (Jetson Nano) as identification, can be directly to the view of transmission Frequency carries out real-time face identification, and no need to send data to identify to third-party server.
It is real that the present invention can accomplish that cell phone application broadcasting display can be used directly in real time monitoring alarm, evidence preservation and user When picture, and alarm system of the present invention is at low cost.
Detailed description of the invention
Fig. 1 is the recognition of face safety alarm system knot provided in an embodiment of the present invention based on embedded artificial intelligent chip Structure schematic diagram.
In figure: 1, video data acquiring module;2, data relay module;3, real-time detection module;4, judgement and alarm mould Block;5, data conversion storage module;6, data acquisition module.
Fig. 2 is the recognition of face safety alarm system work provided in an embodiment of the present invention based on embedded artificial intelligent chip Make schematic diagram.
Fig. 3 is the recognition of face safety alarm system provided in an embodiment of the present invention based on embedded artificial intelligent chip Workflow text block diagram.
Fig. 4 is the recognition of face safety alarm system provided in an embodiment of the present invention based on embedded artificial intelligent chip The data flow diagram of image information.
Fig. 5 is provided in an embodiment of the present invention by warning message upload server schematic diagram.
Fig. 6, which is video data transmission provided in an embodiment of the present invention, separately deposits flow chart to distal end.
Fig. 7 is recognition of face False Rate figure provided in an embodiment of the present invention.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to embodiments, to the present invention It is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not used to Limit the present invention.
The prior art cannot and alarm.The partially intelligentized product cost of the prior art is generally higher.
In view of the problems of the existing technology, the present invention provides a kind of, and the face based on embedded artificial intelligent chip is known Other safety alarm system and equipment, are with reference to the accompanying drawing explained in detail the present invention.
Hardware device system used by the embodiment of the present invention is based on NVIDIA company in newest in 2019 conference of GTC The Jetson Nano development board of publication, small-sized but powerful CUDA-X AI, which is calculated as running modern AI workflow, to be provided The calculated performance of 472 kilomegabits.There is energy conservation again, power consumption is down to 5 watts.Jetson Nano development board includes one piece of 4 core A57CPU, 128 core Maxwell framework GPU and 4G memories.It is at least one times more powerful than traditional raspberry pie development board performance, more suitable The hardware for closing the embodiment of the present invention just needs.
And in model selection, it is more heavily weighted toward lightweight and Performance optimization, it is deep using the open source for having obtained MIT License Degree study human face recognition model MobileFaceNet the advantage is that required amount of ram very little when model operates normally, but model Discrimination is higher than 99.47% again, and the embodiment of the present invention carries out applicability optimization and improvement on the basis of its script model, increases The grade judgement of user terminal face database being autonomously generated after system and model identification.
Warning message transmitting terminal, the embodiment of the present invention increase transfer transition end external network server, send for development board Identification information reception and user terminal information push, be connected with the users' mobile end APP of autonomous Design, push to APP Interface plays evidence video in real time, and provides the convenient method of Rapid Alarm.
As shown in Fig. 1 to 2, the recognition of face security protection report provided in an embodiment of the present invention based on embedded artificial intelligent chip Alert system includes:
Video data acquiring module 1, data relay module 2, real-time detection module 3, judgement and alarm module 4, data turn Storing module 5, data acquisition module 6.
Video data acquiring module 1, for acquiring video information.
Then data relay module 2 is forwarded for obtaining the frame image in video information to processing unit.
Real-time detection module 3 carries out live Face detection, identification for development board.
Judgement and alarm module 4 obtain recognition result for local development board, and judge alert level, if alert It reports grade excessively high, then directly transmits warning message.
Data conversion storage module 5, forwarding, storage for data.
Data acquisition module 6, for sending the video to user mobile phone, user can be handled in time after obtaining alarm result.
In embodiments of the present invention, video data acquiring module 1: including video capture device and transmitting connectivity port, by Camera obtains video data and by connectivity port real-time Transmission to data relay module.
Data relay module 2: receiving temporary storage module and micro treatment module including data, the number sent by obtaining upper level According to micro process is carried out, the frame image in data information is obtained, is sent in real time according to the frame number that detection identification module needs.
Real-time detection module 3: the frame image sended over is subjected to real-time face by Jetson Nano development board and is determined Position, identification operation, obtain recognition result.
Judgement and alarm module 4: local development board obtains recognition result, and judges alert level, if alarm etc. Grade is excessively high, then directly transmits warning message;Recognition result is differentiated, its corresponding alert level is obtained, when grade is lower User terminal is sent to be confirmed whether to need to alarm, when grade is highest if skip data conversion storage and data acquisition module and directly send out Send warning message.
Data conversion storage module 5: higher level's judgement is obtained by external network server module and obtains correctly judging to tie with alarm module Fruit, and video data is stored in the transmission that server end is next step users' mobile end and is prepared.
Data acquisition module 6: mainly in the mobile terminal of user, user checks the video data obtained from server end, It carries out judging whether to need to carry out alert process in time.
In embodiments of the present invention, in real-time detection module 3, if system judgement has stranger, by alert level etc. Data are stored in development board memory space.Development board memory space is only used for storage evidence video.
In embodiments of the present invention, in data conversion storage module 5, video data transmission to outer net SRS is serviced journey by system Sequence, alarming result is sent to MQTT service routine, and video is stored in the memory space of the end PC.
Recognition of face safety alarm system provided in an embodiment of the present invention based on embedded artificial intelligent chip, application In, video data acquiring module 1 is acquired video information;In data relay module 2, the frame figure in video information is obtained Then picture is forwarded to processing unit;In real-time detection module 3 after development board is positioned, identified to live face, judgement with Alarm module 4 obtains development board recognition result, and judges alert level, if alert level is excessively high, directly Send warning message;Then through data conversion storage module 5 by video data transmission to outer net SRS service routine, alarming result is sent To MQTT service routine;Finally be sent to user mobile phone via 6 video of data acquisition module, user obtain alarm as a result, can and When handle.
Below with reference to operation logic, the invention will be further described.
A kind of recognition of face safety alarm system fortune based on embedded artificial intelligent chip provided in an embodiment of the present invention Row principle includes: video acquisition;Face detection, recognition of face;Alert level judgement, evidence storage, warning message upload service Device;Video data transmission is separately deposited to distal end, video uploads external network server;User terminal video information is shown, warning message obtains.
In embodiments of the present invention, video acquisition includes:
Camera data is obtained using the library language call opencv python, video information is directly read into memory, then Etc. to be identified and transmission.
In embodiments of the present invention, Face detection, recognition of face include:
Face detection: Face detection is realized using deep learning model M TCNN, the extraction of human face data is completed, is used for down One step recognition of face;
Recognition of face: it realizes that face vector extracts using deep learning model M obileFaceNet, obtains face characteristic value Vector, calculates its face vector Euclidean distance size imported with initialization, and whether setting threshold decision Euclidean distance belongs to Threshold interval then can determine whether that face whether there is in the face vector library imported to reversely judge whether comprising stranger.
In embodiments of the present invention, alert level judgement, evidence storage, warning message upload server include:
Alert level judgement, evidence storage: be classified alarm according to recognition result, can be divided into three grades: level-one is alert Report: monitoring area is containing only stranger;Second-level alarm: monitoring area stranger and the people recognized exist simultaneously;Three-level alarm: prison Control region nobody or only exist the people recognized.
If it is determined that being primary alarm, then trigger data unloading module, by the face feature of invader and action situation video As evidence Locale Holding on machine (JetsonNano development board).
Warning message upload server: as shown in fig. 6, sending the alert level determined in 0,1,2 form MQTT server, server are only responsible for these data of transfer, and not responsible alarm makes a decision, and judgement transfers to cell phone application program to judge. In view of network transmission is there may be offline condition, the mode that short message PUSH message can be added in alarm module realizes that secondary alarm pushes away It send.
In embodiments of the present invention, video data transmission is separately deposited to distal end, video uploads external network server and includes:
Video data transmission is separately deposited to distal end: as shown in fig. 7, using the ICP/IP protocol of internet, being built with remote host Vertical connection sends data, and video information is storable in be established on the computer that socket is connect with it, this computer is usually Another computer being set as in local area network can be used outer net computer as storage resource if any indult.
Video uploads external network server: after another computer under local area network gets data, while saving, By the server (srs, Red5 etc.) of video frame transmission to RTMP agreement, user hand generator terminal can use APP to server at this time It pulls video information and receives the method that the information that MQTT server transport comes is alarmed as prompt in real time.
In embodiments of the present invention, user terminal video information is shown, warning message acquisition includes:
User terminal mobile phone APP can show real time monitoring picture by the way of pulling RTMP video flowing, while by MQTT Even if message obtain and can reach real time alarm function.It can alarm to ensure network connection failure also while also increase short message report Alert notice.
The present invention is further explained below with reference to the term that the present invention uses.
In embodiments of the present invention, the library opencv: an image processing module of computer open source, for obtaining camera Data.ICP/IP protocol: network communication protocol, internet communication architecture.MobileFaceNet: a kind of deep learning Intelligent recognition model, can be used for the functions such as machine recognition image, and essence is exactly that the matrix of image slices vegetarian refreshments calculates.MTCNN: wide A general model for deep learning Face detection, function are exactly to realize face location alignment in image, search etc..Depth Study: feature extraction is done to input data using compuman's artificial neural networks, to reach the ability that machine learns similar to human brain.
In embodiments of the present invention, JetsonNano development board: in April, 2019 has height up to what company released by tall and handsome Integrated embedded (ARM) development board that can support deep learning.Matrix convolution operation: artificial neural network in computer deep learning The bottom calculation of network, is present in CNN neural network.
In embodiments of the present invention, human face recognition model: the black box calculated for recognition of face, the model is practical to be exactly One group of extremely complex mathematical formulae, only he is from computer learning, after image is calculated by the mathematical formulae Another group of data are just obtained, this group of data can serve as the foundation of classification.RTMP agreement: Real Time Messaging Protocol (real-time messages transport protocol), can be with real-time transmission of video by a kind of streaming media transmission protocol of Flash Adoub Frame, but need intermediate server as terminal.Third party instruction under ffmpeg:Linux operating system, is capable of handling The data of the image information of some complexity.MQTT agreement: Message Queuing Telemetry Transport (message team Column telemetering transport protocol) by a kind of agreement of the IBM instant messaging released, it is transmitted for message, relies on intermediate server transfer Transmit message.
You is given to the present invention combined with specific embodiments below not describe.
Embodiment
In embodiments of the present invention, Fig. 3 is the face provided in an embodiment of the present invention based on embedded artificial intelligent chip Identify the workflow text block diagram of safety alarm system.Fig. 4 is provided in an embodiment of the present invention based on embedded artificial intelligence The data flow diagram of the image information of the recognition of face safety alarm system of chip.Fig. 5 is provided in an embodiment of the present invention by alarm Information upload server schematic diagram.Fig. 6, which is video data transmission provided in an embodiment of the present invention, separately deposits flow chart to distal end.
Five groups of the face recognition accuracy rate that the following are embedded intelligent chips in living based on true monitor video Test result, the data comprising 1,000 frames or so in each group, each group is all to first pass through machine recognition to be sentenced by manual identified again The disconnected result obtained.In following table, it (is only to occur in experiment that first row represents anyone label that will appear in life herein People, using initials as label);Secondary series indicates whether intelligent chip can identify this person (understanding this person);Third column Really to occur the number of the people in this Framed Data;4th column indicate the actually detected number for coming out the people of recognizer, the Five are classified as the recognition accuracy of corresponding label.Because in every Framed Data centainly whether there is or not face occur frame, no face Frame may include multiple faces in one frame data, but " the actual number that can not be embodied herein, but one is arranged with e tag representation Amount " add up it can be concluded that summation be greater than totalframes as a result, and can illustrate to have partial data frame to include multiple faces.
The identification accuracy that can illustrate scheme in these data, may be very high for the recognition accuracy of certain people, The others's discrimination is also possible to relatively low, but when frequency of occurrence is larger, available biggish identification is quasi- Really.Special circumstances explanation: since the m label people in five groups of experiments is that band cap occurs, since cap may block face's letter Breath, so relatively low compared with being compared with other tag recognition rates.
Meanwhile the false judgment in five groups of experiments embodies in table six, judge situation by accident: A → B is indicated label A It has judged by accident into label B;Frame number: for false judgment number;Mistake totalframes: for the totalframes to malfunction in this experiment;False Rate: To there is the probability of false judgment in this experiment.In contrast ratio is lower for its total erroneous judgement frame number, as a result more considerable;Such as It is total ratio of error figure shown in Fig. 7.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention Made any modifications, equivalent replacements, and improvements etc., should all be included in the protection scope of the present invention within mind and principle.

Claims (10)

1. a kind of recognition of face safety alarm system based on embedded artificial intelligent chip, which is characterized in that described based on embedding The recognition of face safety alarm system for entering formula artificial intelligence chip includes:
Video data acquiring module, for acquiring video information;
Then data relay module is forwarded for obtaining the frame image in video information to processing unit;
Real-time detection module carries out live Face detection, identification for development board;
Judgement and alarm module obtain recognition result for local development board, and judge alert level, if alert level It is excessively high, then directly transmit warning message;
Data conversion storage module, forwarding, storage for data;
Data acquisition module, for sending the video to user mobile phone, user obtains alarm as a result, processing in time.
2. the recognition of face safety alarm system as described in claim 1 based on embedded artificial intelligent chip, feature exist In video data acquiring module includes video capture device and transmission connectivity port, is obtained video data by camera and is passed through Connectivity port real-time Transmission is to data relay module.
3. the recognition of face safety alarm system as described in claim 1 based on embedded artificial intelligent chip, feature exist In data relay module includes that data receive temporary storage module and micro treatment module, is carried out by obtaining the data that upper level is sent Micro process obtains the frame image in data information, is sent in real time according to the frame number that detection identification module needs.
4. the recognition of face safety alarm system as described in claim 1 based on embedded artificial intelligent chip, feature exist In the frame image sended over is carried out real-time Face detection, identification by Jetson Nano development board by real-time detection module Operation obtains recognition result.
5. the recognition of face safety alarm system as described in claim 1 based on embedded artificial intelligent chip, feature exist In the real-time detection module is also used to judge there is stranger, then the data such as alert level is stored in development board memory space It is interior.
6. the recognition of face safety alarm system as described in claim 1 based on embedded artificial intelligent chip, feature exist In judgement is also used to local development board with alarm module and obtains recognition result, and judges alert level, if alert level It is excessively high, then directly transmit warning message;Recognition result is differentiated, its corresponding alert level is obtained, is sent out when grade is lower Send to user terminal and be confirmed whether to need to alarm, when grade is highest if skip data conversion storage and data acquisition module directly transmits Warning message.
7. the recognition of face safety alarm system as described in claim 1 based on embedded artificial intelligent chip, feature exist In data conversion storage module obtains higher level's judgement by external network server module and obtains correct judging result with alarm module, and will Video data is stored in the transmission that server end is next step users' mobile end and prepares.
8. the recognition of face safety alarm system as described in claim 1 based on embedded artificial intelligent chip, feature exist In data conversion storage module is also used to video data transmission to outer net SRS service routine, and alarming result is sent to MQTT service journey Sequence, and video is stored in the memory space of the end PC.
9. the recognition of face safety alarm system as described in claim 1 based on embedded artificial intelligent chip, feature exist In data acquisition module is mounted on the mobile terminal of user, and user checks the video data obtained from server end, sentenced in time It is disconnected whether to need to carry out alert process.
10. a kind of people for carrying the recognition of face safety alarm system based on embedded artificial intelligent chip described in claim 1 Face identifies security alarm equipment.
CN201910692119.2A 2019-07-30 2019-07-30 Recognition of face safety alarm system and equipment based on embedded artificial intelligent chip Pending CN110532882A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910692119.2A CN110532882A (en) 2019-07-30 2019-07-30 Recognition of face safety alarm system and equipment based on embedded artificial intelligent chip

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910692119.2A CN110532882A (en) 2019-07-30 2019-07-30 Recognition of face safety alarm system and equipment based on embedded artificial intelligent chip

Publications (1)

Publication Number Publication Date
CN110532882A true CN110532882A (en) 2019-12-03

Family

ID=68660752

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910692119.2A Pending CN110532882A (en) 2019-07-30 2019-07-30 Recognition of face safety alarm system and equipment based on embedded artificial intelligent chip

Country Status (1)

Country Link
CN (1) CN110532882A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111243143A (en) * 2020-03-25 2020-06-05 广东汇泰龙科技股份有限公司 Method and system for identifying and warning strangers outside door
CN112634560A (en) * 2020-12-13 2021-04-09 复旦大学 Intelligent anti-theft system based on microwave radar
CN112653874A (en) * 2020-12-01 2021-04-13 杭州勋誉科技有限公司 Storage device and intelligent video monitoring system
CN114550435A (en) * 2022-01-26 2022-05-27 高新兴科技集团股份有限公司 Early warning information display method, terminal and system
CN114745229A (en) * 2022-02-15 2022-07-12 成都臻识科技发展有限公司 Embedded AI video gateway and implementation method thereof

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103268680A (en) * 2013-05-29 2013-08-28 北京航空航天大学 Intelligent monitoring and anti-theft system for family
CN106297128A (en) * 2016-10-20 2017-01-04 中南民族大学 A kind of Smart Home burglary-resisting system
CN109309808A (en) * 2017-07-26 2019-02-05 梭维智能科技(深圳)有限公司 A kind of monitoring system and method based on recognition of face

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103268680A (en) * 2013-05-29 2013-08-28 北京航空航天大学 Intelligent monitoring and anti-theft system for family
CN106297128A (en) * 2016-10-20 2017-01-04 中南民族大学 A kind of Smart Home burglary-resisting system
CN109309808A (en) * 2017-07-26 2019-02-05 梭维智能科技(深圳)有限公司 A kind of monitoring system and method based on recognition of face

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
苗志程: "《移动终端中主动预警系统的设计与实现》", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111243143A (en) * 2020-03-25 2020-06-05 广东汇泰龙科技股份有限公司 Method and system for identifying and warning strangers outside door
CN111243143B (en) * 2020-03-25 2022-06-21 广东汇泰龙科技股份有限公司 Method and system for identifying and warning strangers outside door
CN112653874A (en) * 2020-12-01 2021-04-13 杭州勋誉科技有限公司 Storage device and intelligent video monitoring system
CN112634560A (en) * 2020-12-13 2021-04-09 复旦大学 Intelligent anti-theft system based on microwave radar
CN114550435A (en) * 2022-01-26 2022-05-27 高新兴科技集团股份有限公司 Early warning information display method, terminal and system
CN114745229A (en) * 2022-02-15 2022-07-12 成都臻识科技发展有限公司 Embedded AI video gateway and implementation method thereof
CN114745229B (en) * 2022-02-15 2024-04-12 成都臻识科技发展有限公司 Embedded AI video gateway and implementation method thereof

Similar Documents

Publication Publication Date Title
CN110532882A (en) Recognition of face safety alarm system and equipment based on embedded artificial intelligent chip
CN110532881A (en) A kind of recognition of face security alarm method based on embedded artificial intelligent chip
CN105100724B (en) A kind of smart home telesecurity monitoring method of view-based access control model analysis
CN108839036A (en) Home intelligent health supervision robot
CN103268680A (en) Intelligent monitoring and anti-theft system for family
CN109359712A (en) Electric operating information dynamic collection monitoring device and its application method
CN116563797B (en) Monitoring management system for intelligent campus
CN209543514U (en) Monitoring and alarm system based on recognition of face
CN107633645A (en) A kind of cell intelligent safety and defence system
CN206863783U (en) Bayonet socket managing and control system
CN109544870A (en) Alarm decision method and intelligent monitor system for intelligent monitor system
CN109019213A (en) A kind of personal safety early warning elevator implementation method and its system
CN107705425A (en) A kind of automatic vending machine warning system of anti-violence damage and technology unlocking
CN202856897U (en) Intelligent video monitoring system based on face recognition
CN112257527A (en) Mobile phone detection method based on multi-target fusion and space-time video sequence
CN115620471A (en) Image identification security system based on big data screening
CN107506727A (en) A kind of intelligent video supervisory systems based on Internet of Things
CN115205581A (en) Fishing detection method, fishing detection device and computer readable storage medium
CN110246292A (en) Domestic video monitoring method, apparatus and storage medium
CN111507294B (en) Classroom security early warning system and method based on three-dimensional face reconstruction and intelligent recognition
CN104463114A (en) Method for catching images and quickly recognizing targets and embedded device
CN209373685U (en) A kind of non-formula entrance guard device based on recognition of face
CN209044724U (en) A kind of gate inhibition's net connection safety management system
CN207352688U (en) A kind of Household access control system based on things-internet gateway
CN115083132B (en) Research and judgment method for reducing false alarm rate of fire alarm

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