CN110379108A - A kind of method and its system of unmanned shop anti-thefting monitoring - Google Patents

A kind of method and its system of unmanned shop anti-thefting monitoring Download PDF

Info

Publication number
CN110379108A
CN110379108A CN201910764535.9A CN201910764535A CN110379108A CN 110379108 A CN110379108 A CN 110379108A CN 201910764535 A CN201910764535 A CN 201910764535A CN 110379108 A CN110379108 A CN 110379108A
Authority
CN
China
Prior art keywords
unmanned shop
monitoring
variation characteristic
action
monitoring point
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.)
Granted
Application number
CN201910764535.9A
Other languages
Chinese (zh)
Other versions
CN110379108B (en
Inventor
李应聪
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.)
Zhenyou Dongguan Electronic Technology Co ltd
Original Assignee
Pnas (dongguan) High Tech Investment 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 Pnas (dongguan) High Tech Investment Co Ltd filed Critical Pnas (dongguan) High Tech Investment Co Ltd
Priority to CN201910764535.9A priority Critical patent/CN110379108B/en
Publication of CN110379108A publication Critical patent/CN110379108A/en
Application granted granted Critical
Publication of CN110379108B publication Critical patent/CN110379108B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G08SIGNALLING
    • G08BSIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B13/00Burglar, theft or intruder alarms
    • G08B13/18Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
    • G08B13/189Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
    • G08B13/194Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
    • G08B13/196Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
    • G08B13/19602Image analysis to detect motion of the intruder, e.g. by frame subtraction
    • G08B13/19613Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Alarm Systems (AREA)
  • Burglar Alarm Systems (AREA)

Abstract

The present invention relates to anti-thefting monitoring technical fields, the method and its system of a kind of unmanned shop anti-thefting monitoring are specifically disclosed, including carrying out preset processing and being interconnected with unmanned shop management system, the information resources of monitoring point static state are obtained, compare adjacent information resources twice to judge whether to change;If changing, video is submitted to extract variation characteristic, and analyze and determine to variation characteristic;If belonging to irregular change, then behavior object is locked and starts anti-theft early-warning processing, can accurately identify whether situation changes in unmanned shop by image static analysis with this, the video of the period is submitted if changing and carries out dynamic analysis, without analyzing whole video, it and is that dynamic discriminance analysis targetedly is carried out to the changed period, improve recognition efficiency, and the object of action of irregular change is locked, facilitate background monitoring, anti-theft early-warning processing can be carried out, is prevented trouble before it happens.

Description

A kind of method and its system of unmanned shop anti-thefting monitoring
Technical field
The present invention relates to anti-thefting monitoring technical field, specifically discloses a kind of method of unmanned shop anti-thefting monitoring and its be System.
Background technique
With the development of science and technology, the shopping way of people becomes more and more diversified, has gradually appeared nothing on the market The shop of people's management.The appearance in unmanned shop has brought convenience, and storekeeper may not need concrete management, and then for shopper It can be done shopping, and can independently paid with entering unmanned shop in 24 hours one day at any time, without being lined up.
Currently, common unmanned shop anti-theft monitoring system is usually to install camera in unmanned shop, then manually rear Platform in unmanned shop to being monitored, when discovery someone steals commodity alarm.However, current unmanned shop anti-theft monitoring system is simultaneously It is not perfect, it is highly dependent on the artificial monitoring in backstage, cannot not only prejudge out suspicion behavior, but also is easy to happen discovery and steals Surreptitiously behavior not in time the case where, to bring loss to unmanned shop storekeeper.
Therefore, it is necessary to a kind of schemes that can solve the above problem.
Summary of the invention
In order to overcome shortcoming and defect existing in the prior art, a purpose of the present invention is that it is anti-to provide a kind of unmanned shop Steal the method and its system of monitoring.
To achieve the above object, the present invention uses following scheme.
A kind of method of unmanned shop anti-thefting monitoring, comprising:
Preset processing a little is monitored to space in unmanned shop, and is interconnected with unmanned shop management system;
Moment obtains the information resources of monitoring point static state, compares the adjacent information resources that obtain twice to judge the corresponding nothing in monitoring point Whether situation changes in people shop;
If changing, the video of monitoring point is submitted to extract variation characteristic, and carry out to the variation characteristic extracted It analyzes and determines;
If belonging to irregular change, behavior object is locked, and starts anti-theft early-warning processing.
Further, described that preset processing a little is monitored to space in unmanned shop and mutual with unmanned shop management system Connection, comprising:
Space in unmanned shop is divided into several regions, and several monitoring points are set in each region;
Each region is numbered, the monitoring point list in each numbering area is established, monitoring point list and monitoring point are provided Source is interrelated;
Each monitoring point is accessed in unmanned shop management system by related protocol.
Further, moment obtains the information resources of monitoring point static state, compare adjacent acquisition information resources twice with Judge whether situation changes in the corresponding unmanned shop in monitoring point, comprising:
Moment obtains the still image of monitoring point, identifies with CNN convolutional neural networks to still image;
Judge whether the still image of adjacent two frame changes;
If changing, the related video for intercepting the monitoring point is made to submit and be prepared;If there is no variations, to the prison Image, video of the control point within the period there is no variation carry out discard processing.
It is further, described that still image is identified with CNN convolutional neural networks, comprising:
The convolution kernel being adapted with still image is determined by the way that different convolution kernels is constantly arranged, using at the beginning of the convolution kernel of adaptation Step extracts the feature of image, and determines image in the output valve of convolutional layer;
The output valve of convolutional layer is sent to Chi Huacengzuochiization and is acted on, to remove picture noise, retains the main feature of image;
The feature of image parts is summarized by the effect of full articulamentum, generates classifier, carries out Forecasting recognition.
Further, it includes facial structure variation characteristic, limb that the video for submitting monitoring point, which extracts variation characteristic, Body language change feature and action trail variation characteristic.
Further, the variation characteristic extracted is analyzed and determined, comprising:
Face characteristic in face's variation characteristic and face database is subjected to big data analysis, is judged whether and stealing people Form it is similar, wherein at least include eye position, corners of the mouth curvature and eyebrow camber;
Limbs speech variation characteristic in limbs speech variation characteristic and body language database is subjected to big data analysis, judgement It is whether similar with the variation of the limbs speech of stealing people, wherein at least including involved party head whether look about, limbs Whether roll up;
Judge whether action trail is similar with the variation of the action trail of stealing people, whether wherein at least includes involved party one Whether determine to hover, stop in commodity in range is more than the scheduled time;
If structure change feature, body language variation characteristic and action trail variation characteristic are consistent with stealing, mark For irregular change.
Further, described that behavior object is locked, and start anti-theft early-warning processing, comprising:
To the object of action setting locking frame of irregular change in video, and make to lock the shifting of frame following behavior object It is dynamic;
It is broadcasted by voice system into unmanned shop and reminds voice;
Watchful information is sent to object of action mobile terminal.
Further, after starting anti-theft early-warning processing, antitheft tracing and monitoring is carried out to the object of action of irregular change, Specifically:
Identify whether object of action is Chong Die with commodity region in video, and judges that object of action leaves quotient behind commodity region Whether product region changes;
If commodity region changes, the mobile terminal of object of action and the connection of unmanned shop door are disconnected, until recognizing row It is just accessed again after completing payment for object.
The present invention also provides a kind of systems of unmanned shop anti-thefting monitoring, including server;
Server includes processor and storage equipment;
Processor is adapted for carrying out program instruction;
Equipment is stored, storage program instruction is suitable for, described program instruction is suitable for being loaded by processor and being executed above-mentioned to realize Unmanned shop anti-thefting monitoring method.
The present invention also provides a kind of mobile terminals, comprising:
Processor is adapted for carrying out program instruction;
Equipment is stored, storage program instruction is suitable for, described program instruction is suitable for being loaded by processor and being executed above-mentioned to realize Unmanned shop anti-thefting monitoring method.
Beneficial effects of the present invention: the method and its system of a kind of unmanned shop anti-thefting monitoring are provided, by unmanned shop Space is monitored preset processing a little and interconnects with unmanned shop management system, and it is quiet can to obtain constantly monitoring point when being monitored The information resources of state compare the adjacent information resources that obtain twice to judge whether situation becomes in the corresponding unmanned shop in monitoring point Change;If changing, the video of monitoring point is submitted to extract variation characteristic, and divide the variation characteristic extracted Analysis judgement;If belonging to irregular change, anti-theft early-warning processing is locked and started to behavior object, image is passed through with this Static analysis can accurately identify whether situation changes in unmanned shop, will corresponding period if changing Video, which is submitted, carries out dynamic analysis, without can not only economize on resources to whole video analysis, Er Qieshi Dynamic discriminance analysis targetedly is carried out to the changed period, recognition efficiency can be greatly improved, and to non- The object of action of normal variation is locked, and background monitoring is facilitated, and can also carry out anti-theft early-warning processing to object of action, can be with It prevents trouble before it happens.
Detailed description of the invention
Fig. 1 is the flow diagram of anti-thefting monitoring of embodiment of the present invention method.
Specific embodiment
For the ease of the understanding of those skilled in the art, the present invention is made further below with reference to examples and drawings Bright, the content that embodiment refers to not is limitation of the invention.
A kind of method of unmanned shop anti-thefting monitoring is analyzed by static image analysis and dynamic video to reduce dynamic The process of analysis allows to targetedly be analyzed, and improves the efficiency of analysis identification, to reach better antitheft prison The effect of control, detailed process are as shown in Figure 1, comprising:
In order to can comprehensively monitor to the space carried out in unmanned shop, need to be monitored space in unmanned shop a little preset It handles and is interconnected with unmanned shop management system.Preferably, the space in unmanned shop is divided if preset processing includes at least Dry region, and several monitoring points are set in each region, each monitoring point can be directed at the different positions of the area planar It sets, each monitoring point can also be directed to the different height of same position, thus realize the monitoring of horizontal space and longitudinal space, It realizes to comprehensively being monitored in unmanned shop.Then each region is numbered, establishes the monitoring point range in each numbering area Table, monitoring point list and monitoring point resource is interrelated, it can be convenient with this and each monitoring point be managed, be also convenient for people Work inquires the resource information of some monitoring point.After the setting for completing monitoring point, by related protocol by each monitoring point It accesses in unmanned shop management system, realizes the functions such as live preview, playing back videos, speech talkback.
When being monitored to unmanned shop, discriminance analysis all is carried out to video if it is whole, larger workload can account for There is the resource of analysis, then probably analysis monitoring point does not change during this period of time, the waste of resource is caused, and Inefficiency.Therefore, the present invention is in such a way that static analysis and dynamic analysis combine.Specifically, the moment obtains monitoring point Static information resources, the static information resource carry out still image based on still image, with CNN convolutional neural networks Identification, image recognition compare adjacent obtain twice information resources (namely still image of adjacent two frame) to judge to monitor after coming out Whether situation changes in the corresponding unmanned shop of point, and the image identified through CNN convolutional neural networks can quickly judge Whether change.Illustrate that the corresponding unmanned shop region in the monitoring point is walked about if changing, therefore can be by the time The video of section submits analysis to obtain variation characteristic, and the related video for needing to intercept the monitoring point before submission mentions It hands over and prepares, for example format conversion, marked zone number, monitoring point list etc., in order to subsequent extraction signature analysis.If There is no variation, then illustrate this monitoring point during this period of time without the stream of people, since there is no variations, without being divided Analysis, therefore image of the monitoring point within the period there is no variation, video can be lost without reservation Abandoning processing is conducive to store more changed videos to discharge the storage space of system.
More specifically, it includes different by being constantly arranged for carrying out identification to still image with CNN convolutional neural networks Convolution kernel determines the convolution kernel being adapted with still image, tentatively extracts the feature of image using the convolution kernel of adaptation, and true Image is determined in the output valve of convolutional layer;The output valve of convolutional layer is sent to Chi Huacengzuochiization and is acted on, to remove picture noise, is protected Stay the main feature of image;The feature of image parts is summarized by the effect of full articulamentum, generates classifier, into Row Forecasting recognition.
The variation characteristic extracted need to then be analyzed and determined.The video of monitoring point is submitted to extract variation special Sign includes but is not limited to facial structure variation characteristic, body language variation characteristic and action trail variation characteristic.It not passes herein The features such as the face for identifying object of action of system judge whether recidivist determines suspect for it, but variation characteristic is passed through Big data analysis judges whether it is similar with the form of stealing people, so as to preferably carry out control to object of action.
Specifically, the face characteristic in face's variation characteristic and face database is subjected to big data analysis, judged whether It is similar with the form of stealing people, it wherein at least include eye position, corners of the mouth curvature and eyebrow camber;Limbs speech is changed Limbs speech variation characteristic in feature and body language database carries out big data analysis, judges whether with stealing people's The variation of limbs speech is similar, and wherein at least whether the head including involved party looks about, whether limbs roll up;Judgement behavior rail Whether mark is similar with the variation of the action trail of stealing people, wherein at least whether hover in a certain range including involved party, Whether stop in commodity is more than the scheduled time;If structure change feature, body language variation characteristic and action trail variation are special Sign is consistent with stealing, then is labeled as irregular change.
Certainly, even if object of action meets the form of stealing, it can be used as and pay close attention to object, but object of action is simultaneously Unexecuted stealing, in order to prevent trouble before it happens, to the object of action setting locking frame of irregular change in video, and And make to lock the movement of frame following behavior object, so that backstage personnel conveniently be allowed to know that behavior object is abnormal condition, it is convenient for Backstage personnel are reminded to pay close attention to.Start anti-theft early-warning processing simultaneously, for example prompting is broadcasted into unmanned shop by voice system Voice can remind the other staff in unmanned shop to pay attention to the property of keeping oneself.Further, since unmanned shop is to use to be scanned into The mode of door, unmanned shop management system is connected to the mobile terminal of object of action when entering, and can be moved to object of action Dynamic terminal sends watchful information, can under the premise of not causing that personnel are alarmed in other shops watchful object of action, can give way Stealing is actively abandoned for object.
Object of action still carries out theft after watchful in order to prevent, therefore after starting anti-theft early-warning processing, to improper The object of action of variation carries out antitheft tracing and monitoring.Specifically, identify whether object of action is heavy with commodity region in video It is folded, and judge whether commodity region changes after object of action leaves commodity region;If commodity region changes, break Unmanned shop can not be opened by scanning by opening the mobile terminal of object of action and the connection of unmanned shop door namely behavior object , it is just accessed again until recognizing after object of action completes payment, the openable unmanned shop of object of action ability after accessing again Door leaves.It can ensure the commercial articles safety in unmanned shop to avoid allowing behavior object to flee from unmanned shop after stealing with this, avoid The loss of storekeeper.It can also at will be inputted after avoiding object of action from stealing plus the type and its corresponding price of identification commodity The door that one price can open unmanned shop is fled from.
A kind of method of unmanned shop anti-thefting monitoring provided by the invention, can accurately be identified by the static analysis of image Whether situation changes in unmanned shop out, submits the video of corresponding period if changing and carries out dynamic point Analysis can not only economize on resources, but also be targetedly to changed without analyzing whole video Period carries out dynamic discriminance analysis, can greatly improve recognition efficiency, and carry out to the object of action of irregular change Locking, facilitates background monitoring, can also carry out anti-theft early-warning processing to object of action, can prevent trouble before it happens.
The present invention provides also a kind of system of unmanned shop anti-thefting monitoring, including server;
Server includes processor and storage equipment;
Processor is adapted for carrying out program instruction;
Equipment is stored, storage program instruction is suitable for, described program instruction is suitable for being loaded by processor and being executed to realize above-mentioned state Unmanned shop anti-thefting monitoring method.
The present invention provides a kind of mobile terminal, comprising:
Processor is adapted for carrying out program instruction;
Equipment is stored, storage program instruction is suitable for, described program instruction is suitable for being loaded by processor and being executed above-mentioned to realize Unmanned shop anti-thefting monitoring method.
The above is only present pre-ferred embodiments, is not intended to limit the present invention in any form, although The present invention is disclosed as above with preferred embodiment, and however, it is not intended to limit the invention, any person skilled in the art, It does not depart within the scope of technical solution of the present invention, when the technology contents using the disclosure above make a little change or are modified to equivalent change The equivalent embodiment of change, but without departing from the technical solutions of the present invention, technology refers to above embodiments according to the present invention Made any simple modification, equivalent change and modification, belong in the range of technical solution of the present invention.

Claims (10)

1. a kind of method of unmanned shop anti-thefting monitoring characterized by comprising
Preset processing a little is monitored to space in unmanned shop, and is interconnected with unmanned shop management system;
Moment obtains the information resources of monitoring point static state, compares the adjacent information resources that obtain twice to judge the corresponding nothing in monitoring point Whether situation changes in people shop;
If changing, the video of monitoring point is submitted to extract variation characteristic, and carry out to the variation characteristic extracted It analyzes and determines;
If belonging to irregular change, behavior object is locked, and starts anti-theft early-warning processing.
2. a kind of method of unmanned shop anti-thefting monitoring according to claim 1, which is characterized in that described to empty in unmanned shop Between be monitored preset processing a little, and interconnected with unmanned shop management system, comprising:
Space in unmanned shop is divided into several regions, and several monitoring points are set in each region;
Each region is numbered, the monitoring point list in each numbering area is established, monitoring point list and monitoring point are provided Source is interrelated;
Each monitoring point is accessed in unmanned shop management system by related protocol.
3. a kind of method of unmanned shop anti-thefting monitoring according to claim 1, which is characterized in that the moment obtains monitoring The static information resources of point compare the adjacent information resources that obtain twice to judge whether situation is sent out in the corresponding unmanned shop in monitoring point Changing, comprising:
Moment obtains the still image of monitoring point, identifies with CNN convolutional neural networks to still image;
Judge whether the still image of adjacent two frame changes;
If changing, the related video for intercepting the monitoring point is made to submit and be prepared;If there is no variations, to the prison Image, video of the control point within the period there is no variation carry out discard processing.
4. a kind of method of unmanned shop anti-thefting monitoring according to claim 3, which is characterized in that described to use CNN convolution Neural network identifies still image, comprising:
The convolution kernel being adapted with still image is determined by the way that different convolution kernels is constantly arranged, using at the beginning of the convolution kernel of adaptation Step extracts the feature of image, and determines image in the output valve of convolutional layer;
The output valve of convolutional layer is sent to Chi Huacengzuochiization and is acted on, to remove picture noise, retains the main feature of image;
The feature of image parts is summarized by the effect of full articulamentum, generates classifier, carries out Forecasting recognition.
5. a kind of method of unmanned shop anti-thefting monitoring according to claim 1, which is characterized in that the submission monitoring point It includes facial structure variation characteristic, body language variation characteristic and action trail variation characteristic that video, which extracts variation characteristic,.
6. a kind of method of unmanned shop anti-thefting monitoring according to claim 5, which is characterized in that the change extracted Change feature to be analyzed and determined, comprising:
Face characteristic in face's variation characteristic and face database is subjected to big data analysis, is judged whether and stealing people Form it is similar, wherein at least include eye position, corners of the mouth curvature and eyebrow camber;
Limbs speech variation characteristic in limbs speech variation characteristic and body language database is subjected to big data analysis, judgement It is whether similar with the variation of the limbs speech of stealing people, wherein at least including involved party head whether look about, limbs Whether roll up;
Judge whether action trail is similar with the variation of the action trail of stealing people, whether wherein at least includes involved party one Whether determine to hover, stop in commodity in range is more than the scheduled time;
If structure change feature, body language variation characteristic and action trail variation characteristic are consistent with stealing, mark For irregular change.
7. a kind of method of unmanned shop anti-thefting monitoring according to claim 1, which is characterized in that described to behavior object It is locked, and starts anti-theft early-warning processing, comprising:
To the object of action setting locking frame of irregular change in video, and make to lock the shifting of frame following behavior object It is dynamic;
It is broadcasted by voice system into unmanned shop and reminds voice;
Watchful information is sent to object of action mobile terminal.
8. a kind of method of unmanned shop anti-thefting monitoring according to claim 1, which is characterized in that at starting anti-theft early-warning After reason, antitheft tracing and monitoring is carried out to the object of action of irregular change, specifically:
Identify whether object of action is Chong Die with commodity region in video, and judges that object of action leaves quotient behind commodity region Whether product region changes;
If commodity region changes, the mobile terminal of object of action and the connection of unmanned shop door are disconnected, until recognizing row It is just accessed again after completing payment for object.
9. a kind of system of unmanned shop anti-thefting monitoring, which is characterized in that including server;
Server includes processor and storage equipment;
Processor is adapted for carrying out program instruction;
Equipment is stored, storage program instruction is suitable for, described program instruction is suitable for being loaded by processor and being executed to realize that right is wanted Seek unmanned shop anti-thefting monitoring method described in 1 to 8 any one.
10. a kind of mobile terminal characterized by comprising
Processor is adapted for carrying out program instruction;
Equipment is stored, storage program instruction is suitable for, described program instruction is suitable for being loaded by processor and being executed to realize that right is wanted Seek unmanned shop anti-thefting monitoring method described in 1 to 8 any one.
CN201910764535.9A 2019-08-19 2019-08-19 Method and system for monitoring theft prevention of unmanned store Active CN110379108B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910764535.9A CN110379108B (en) 2019-08-19 2019-08-19 Method and system for monitoring theft prevention of unmanned store

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910764535.9A CN110379108B (en) 2019-08-19 2019-08-19 Method and system for monitoring theft prevention of unmanned store

Publications (2)

Publication Number Publication Date
CN110379108A true CN110379108A (en) 2019-10-25
CN110379108B CN110379108B (en) 2021-09-24

Family

ID=68259800

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910764535.9A Active CN110379108B (en) 2019-08-19 2019-08-19 Method and system for monitoring theft prevention of unmanned store

Country Status (1)

Country Link
CN (1) CN110379108B (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110992617A (en) * 2019-12-12 2020-04-10 徐州科睿安防科技有限公司 Double-end single-shot type anti-damage security monitoring equipment
CN111223260A (en) * 2020-01-19 2020-06-02 上海智勘科技有限公司 Method and system for intelligently monitoring goods theft prevention in warehousing management
CN111311630A (en) * 2020-01-19 2020-06-19 上海智勘科技有限公司 Method and system for intelligently counting quantity of goods through videos in warehousing management
CN112598745A (en) * 2020-12-14 2021-04-02 北京爱笔科技有限公司 Method and device for determining person-goods associated events
CN113393625A (en) * 2021-05-08 2021-09-14 中电海康集团有限公司 Anti-theft alarm evidence obtaining method and system for intelligent lamp pole
CN114359836A (en) * 2022-01-10 2022-04-15 长春师范大学 Automatic-identification monitoring system and monitoring method based on computer

Citations (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106603999A (en) * 2017-02-17 2017-04-26 上海创米科技有限公司 Video monitoring alarming method and system
CN107067621A (en) * 2017-04-21 2017-08-18 湖南孚利购科技有限公司 A kind of theft preventing method and system
RU173468U1 (en) * 2017-03-27 2017-08-29 Акционерное общество "ЭЛВИС-НеоТек" DEVICE FOR CASCADE PROCESSING OF THE IMAGE FLOW USING SURFACE NEURAL NETWORKS
CN107123006A (en) * 2017-07-12 2017-09-01 杨智勇 A kind of smart shopper system
CN107330684A (en) * 2017-07-06 2017-11-07 广州联业商用机器人科技股份有限公司 A kind of intelligent unmanned shop of management and control in high in the clouds and its automatic settlement method
CN107392734A (en) * 2017-08-04 2017-11-24 湖州靖源信息技术有限公司 A kind of unmanned convenience store and application method
CN206833628U (en) * 2017-06-07 2018-01-02 厦门尊科电子有限公司 A kind of unmanned cash register self-service device of convenience store
CN206907130U (en) * 2017-06-08 2018-01-19 上海芯店网络科技有限公司 A kind of Intelligent unattended vending system
CN207337465U (en) * 2017-07-06 2018-05-08 广州联业商用机器人科技股份有限公司 A kind of unmanned shop of high in the clouds intelligence management and control
US20180268618A1 (en) * 2017-03-17 2018-09-20 Toshiba Tec Kabushiki Kaisha Facility gate control system and method
US10140820B1 (en) * 2015-07-25 2018-11-27 Gary M. Zalewski Devices for tracking retail interactions with goods and association to user accounts for cashier-less transactions
CN109003360A (en) * 2018-06-27 2018-12-14 深圳市赛亿科技开发有限公司 A kind of management method and system of unmanned supermarket
CN109002772A (en) * 2018-06-27 2018-12-14 深圳市赛亿科技开发有限公司 A kind of measure of supervision and system of unmanned supermarket's customer behavior
CN109285246A (en) * 2018-08-03 2019-01-29 深圳神目信息技术有限公司 The management-control method and managing and control system of unattended supermarket
CN109345360A (en) * 2018-11-23 2019-02-15 青岛海信智能商用***股份有限公司 Unmanned shop theft preventing method and device
CN109389793A (en) * 2018-10-16 2019-02-26 深圳众宝城贸易有限公司 A kind of super anti-theft monitoring system of quotient
CN109558785A (en) * 2017-09-25 2019-04-02 北京缤歌网络科技有限公司 Safety defense monitoring system and the unmanned convenience store for applying it
CN109671214A (en) * 2018-09-12 2019-04-23 盈奇科技(深圳)有限公司 A kind of unmanned supermarket of gravity sensing
CN109741135A (en) * 2018-12-28 2019-05-10 北京每日优鲜电子商务有限公司 Control method, control system and the Intelligent portable shop in Intelligent portable shop
CN109920180A (en) * 2019-01-23 2019-06-21 北京小牛智能科技有限公司 Antitheft system for supermarket, supermarket self-checkout method and client
CN109977896A (en) * 2019-04-03 2019-07-05 上海海事大学 A kind of supermarket's intelligence vending system

Patent Citations (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10140820B1 (en) * 2015-07-25 2018-11-27 Gary M. Zalewski Devices for tracking retail interactions with goods and association to user accounts for cashier-less transactions
CN106603999A (en) * 2017-02-17 2017-04-26 上海创米科技有限公司 Video monitoring alarming method and system
US20180268618A1 (en) * 2017-03-17 2018-09-20 Toshiba Tec Kabushiki Kaisha Facility gate control system and method
RU173468U1 (en) * 2017-03-27 2017-08-29 Акционерное общество "ЭЛВИС-НеоТек" DEVICE FOR CASCADE PROCESSING OF THE IMAGE FLOW USING SURFACE NEURAL NETWORKS
CN107067621A (en) * 2017-04-21 2017-08-18 湖南孚利购科技有限公司 A kind of theft preventing method and system
CN206833628U (en) * 2017-06-07 2018-01-02 厦门尊科电子有限公司 A kind of unmanned cash register self-service device of convenience store
CN206907130U (en) * 2017-06-08 2018-01-19 上海芯店网络科技有限公司 A kind of Intelligent unattended vending system
CN107330684A (en) * 2017-07-06 2017-11-07 广州联业商用机器人科技股份有限公司 A kind of intelligent unmanned shop of management and control in high in the clouds and its automatic settlement method
CN207337465U (en) * 2017-07-06 2018-05-08 广州联业商用机器人科技股份有限公司 A kind of unmanned shop of high in the clouds intelligence management and control
CN107123006A (en) * 2017-07-12 2017-09-01 杨智勇 A kind of smart shopper system
CN107392734A (en) * 2017-08-04 2017-11-24 湖州靖源信息技术有限公司 A kind of unmanned convenience store and application method
CN109558785A (en) * 2017-09-25 2019-04-02 北京缤歌网络科技有限公司 Safety defense monitoring system and the unmanned convenience store for applying it
CN109003360A (en) * 2018-06-27 2018-12-14 深圳市赛亿科技开发有限公司 A kind of management method and system of unmanned supermarket
CN109002772A (en) * 2018-06-27 2018-12-14 深圳市赛亿科技开发有限公司 A kind of measure of supervision and system of unmanned supermarket's customer behavior
CN109285246A (en) * 2018-08-03 2019-01-29 深圳神目信息技术有限公司 The management-control method and managing and control system of unattended supermarket
CN109671214A (en) * 2018-09-12 2019-04-23 盈奇科技(深圳)有限公司 A kind of unmanned supermarket of gravity sensing
CN109389793A (en) * 2018-10-16 2019-02-26 深圳众宝城贸易有限公司 A kind of super anti-theft monitoring system of quotient
CN109345360A (en) * 2018-11-23 2019-02-15 青岛海信智能商用***股份有限公司 Unmanned shop theft preventing method and device
CN109741135A (en) * 2018-12-28 2019-05-10 北京每日优鲜电子商务有限公司 Control method, control system and the Intelligent portable shop in Intelligent portable shop
CN109920180A (en) * 2019-01-23 2019-06-21 北京小牛智能科技有限公司 Antitheft system for supermarket, supermarket self-checkout method and client
CN109977896A (en) * 2019-04-03 2019-07-05 上海海事大学 A kind of supermarket's intelligence vending system

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
付维娜 于萍: "《拓扑同构与视频目标跟踪》", 31 May 2018, 电子科技大学出版社 *
沈雁,王环,戴瑜兴: "基于改进深度孪生网络的分类器及其应用", 《计算机工程与应用》 *

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110992617A (en) * 2019-12-12 2020-04-10 徐州科睿安防科技有限公司 Double-end single-shot type anti-damage security monitoring equipment
CN111223260A (en) * 2020-01-19 2020-06-02 上海智勘科技有限公司 Method and system for intelligently monitoring goods theft prevention in warehousing management
CN111311630A (en) * 2020-01-19 2020-06-19 上海智勘科技有限公司 Method and system for intelligently counting quantity of goods through videos in warehousing management
CN111311630B (en) * 2020-01-19 2023-05-23 上海智勘科技有限公司 Method and system for intelligently counting cargo quantity through video in warehouse management
CN112598745A (en) * 2020-12-14 2021-04-02 北京爱笔科技有限公司 Method and device for determining person-goods associated events
CN112598745B (en) * 2020-12-14 2024-05-28 北京爱笔科技有限公司 Method and device for determining person-goods association event
CN113393625A (en) * 2021-05-08 2021-09-14 中电海康集团有限公司 Anti-theft alarm evidence obtaining method and system for intelligent lamp pole
CN114359836A (en) * 2022-01-10 2022-04-15 长春师范大学 Automatic-identification monitoring system and monitoring method based on computer
CN114359836B (en) * 2022-01-10 2022-09-13 长春师范大学 Automatic-identification monitoring system and monitoring method based on computer

Also Published As

Publication number Publication date
CN110379108B (en) 2021-09-24

Similar Documents

Publication Publication Date Title
CN110379108A (en) A kind of method and its system of unmanned shop anti-thefting monitoring
US11776308B2 (en) Frictionless access control system embodying satellite cameras for facial recognition
CN205788358U (en) Work attendance gate control system
CN108875341A (en) A kind of face unlocking method, device, system and computer storage medium
CN106204948A (en) Locker management method and locker managing device
US20210201610A1 (en) Methods and System for Distributed Cameras and Demographics Analysis
CN108932776A (en) A kind of two dimensional code access control system and operation method based on face characteristic value
CN105427421A (en) Entrance guard control method based on face recognition
KR102012672B1 (en) Anti-crime system and method using face recognition based people feature recognition
US20230368559A1 (en) Information processing apparatus, information processing method, and non-transitory computer-readable storage medium
CN110276320A (en) Guard method, device, equipment and storage medium based on recognition of face
CN206162736U (en) Access control system based on face recognition
CN107369263A (en) A kind of recognition of face locker system based on cloud computing platform
CN109243030A (en) A kind of control method and system of night contactless access control system
JP2019096179A (en) Behavior monitoring system
NZ581770A (en) Facility access integrated with other security systems
CN112002094A (en) Cell personnel management method based on triangular positioning
US20210390287A1 (en) Unsupervised enrollment for anti-theft facial recognition system
CN102289908A (en) Image analysis-based independent association real-time anti-theft system
CN108681720A (en) A kind of testimony of a witness veritification management system and method
CN209312110U (en) A kind of intelligent door lock system based on technology of Internet of things
CN110246292A (en) Domestic video monitoring method, apparatus and storage medium
CN109712289A (en) A kind of garden security information processing method and processing device based on intelligent management platform
JP2017054361A (en) Monitoring system and passage management system
CN208752683U (en) A kind of ticket-checking system based on big data and recognition of face

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
GR01 Patent grant
GR01 Patent grant
CP01 Change in the name or title of a patent holder

Address after: 523000 room 1107, No. 2, Hongfu East Road, Dongcheng Street, Dongguan City, Guangdong Province

Patentee after: Zhenyou (Dongguan) Electronic Technology Co.,Ltd.

Address before: 523000 room 1107, No. 2, Hongfu East Road, Dongcheng Street, Dongguan City, Guangdong Province

Patentee before: PNAs (Dongguan) high tech Investment Co.,Ltd.

CP01 Change in the name or title of a patent holder