CN106981150A - A kind of supermarket's intelligent anti-theft system and method - Google Patents
A kind of supermarket's intelligent anti-theft system and method Download PDFInfo
- Publication number
- CN106981150A CN106981150A CN201710258328.7A CN201710258328A CN106981150A CN 106981150 A CN106981150 A CN 106981150A CN 201710258328 A CN201710258328 A CN 201710258328A CN 106981150 A CN106981150 A CN 106981150A
- Authority
- CN
- China
- Prior art keywords
- user
- weight
- supermarket
- weight data
- identity code
- 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
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Social Psychology (AREA)
- Psychiatry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Burglar Alarm Systems (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a kind of supermarket's intelligent anti-theft system and method, wherein system includes camera unit, weight sensor platform, server platform, alarm unit, camera unit, the video image for gathering in/out user, server platform is sent to by video image；Weight sensor platform, for gathering the weight data of in/out user and being uploaded to server platform；Server platform, is compared with weight threshold for user in video image to be marked, and by the difference of weight data twice of the user of mark, is not processed if weight data difference is not more than weight threshold, otherwise send alarm command to alarm unit；Alarm unit, for receiving and performing alarm command.Recognition of face and movement locus of the present invention by the user to in/out supermarket judge and front and rear weight twice judges, realizes the purpose for preventing that supermarket's commodity from losing, improves antitheft efficiency, reduce supermarket anti-theft cost.
Description
Technical field
The present invention relates to burglary-resisting installation technical field, and in particular to a kind of supermarket's intelligent anti-theft system and method.
Background technology
It is well known that forefront of the supermarket as retail business, its type of merchandize is complete, mode is chosen arbitrarily, greatly side
Our life.Simultaneously, superelevation flow of the people, and commodity freely choose placement, to pilferage behavior create compared with into
Ripe condition, and this case is more universal and serious in recent years, in international industry statistic, large-scale sales field has about 4/1000ths
Lose goods rate, actual conditions, far above this ratio, according to statistics, domestic supermarket is general because stealing brought average loss rate
In 1%-2%, annual because the loss that stealing is caused is up to several hundred billion yuan, supermarket is being stopped loss on antitheft, and input is required for every year
Great people's force-summing device, but effect is not reaching to expection.
The content of the invention
The purpose of the present invention is to realize to enter in/out supermarket user using face recognition technology and movement locus algorithm
Line flag, while according to the stolen risk of the body weight of in/out supermarket user difference reduction supermarket commodity.
To achieve these goals, it is a primary object of the present invention to provide a kind of supermarket's intelligent anti-theft system, it is intended to change
Rate is stopped loss in terms of the stealing of kind supermarket.
To achieve these goals, the invention provides a kind of supermarket's intelligent anti-theft system, including camera unit, weight
Sensor platform, server platform, alarm unit, wherein,
Camera unit, the video image for gathering in/out user, server platform is sent to by video image；
Weight sensor platform, for gathering the weight data of in/out user and being uploaded to server platform；
Server platform, for user in video image to be marked, the weight of the user marked twice before and after calculating
Data difference, and weight DBMS difference is compared with weight threshold, do not do and locate if weight data difference is not more than weight threshold
Reason, otherwise sends alarm command to alarm unit；
Alarm unit, for receiving and performing alarm command.
Further, server platform includes
Identity recognizing unit, user to be detected is marked for receiving video image, and according to face recognition technology,
Obtain the Identity Code of user to be detected, inquire about default antitheft database, judge whether to store in antitheft database and need
The Identity Code of user is detected, is not process, otherwise stores to antitheft database；
Weight acquiring unit, the weight data for detecting Identity Code correspondence user；
Processing unit, the direction of motion for judging Identity Code correspondence user using movement locus algorithm, if motion
Direction is into then storing Identity Code and its corresponding weight data to antitheft database；The direction of motion is, and obtains body
The weight data of part identification code correspondence user and the weight data progress mathematic interpolation by it and in antitheft database, judge difference
Whether it is more than weight threshold, is then to send alarm command to alarm unit, does not otherwise process.
Further, alarm unit is indicator lamp, alarm bell, display screen or buzzer.
Further, camera unit goes out and/or porch installed in supermarket.
Further, weight sensor stage+module is going out and/or porch.
Present invention also offers a kind of supermarket's intelligent antitheft method, comprise the following steps：
Gather the video image of in/out user；
The video image of in/out user is handled using face recognition technology, user to be detected is marked, obtained
To the Identity Code of user to be detected；
After the direction of motion that the corresponding user of Identity Code is judged according to movement locus algorithm, the Identity Code is obtained
The weight data of correspondence user, Identity Code and its corresponding weight data are stored to default antitheft database, calculated
The difference of the weight data twice of Identity Code correspondence user, judges whether difference is more than weight threshold, is then to alarm unit
Alarm command is sent, is not otherwise processed.
In the above-mentioned technical solutions, recognition of face and movement locus of the present invention by the user to in/out supermarket is sentenced
Disconnected and front and rear weight twice judges, realizes the purpose for preventing that supermarket's commodity from losing, improves antitheft efficiency, reduces supermarket and prevents
Steal cost.
Brief description of the drawings
, below will be to institute in embodiment in order to illustrate more clearly of the embodiment of the present application or technical scheme of the prior art
The accompanying drawing needed to use is briefly described, it should be apparent that, drawings in the following description are only one described in the present invention
A little embodiments, for those of ordinary skill in the art, can also obtain other accompanying drawings according to these accompanying drawings.
Fig. 1 is the structure of block diagram schematic diagram of supermarket's intelligent anti-theft system one embodiment of the present invention；
Fig. 2 is the schematic flow sheet of supermarket's intelligent antitheft method one embodiment of the present invention.
Embodiment
In order that those skilled in the art more fully understands technical scheme, below in conjunction with accompanying drawing to this hair
It is bright to be further detailed.
The present invention provides a kind of supermarket's intelligent anti-theft system.
Reference picture 1, Fig. 1 is the system framework schematic diagram of intelligent anti-theft system embodiment of the present invention.What the present embodiment was provided
Intelligent anti-theft system includes camera unit 01, weight sensor platform 02, server platform 03, alarm unit 04.
Wherein,
Camera unit 01, the video image for gathering in/out user, server platform is sent to by video image；
Weight sensor platform 02, for gathering the weight data of in/out user and being uploaded to server platform；
Server platform 03, for user in video image to be marked, the weight of the user marked twice before and after calculating
Data difference is measured, and weight DBMS difference is compared with weight threshold, is not done if weight data difference is not more than weight threshold
Processing, otherwise sends alarm command to alarm unit；
Alarm unit 04, for receiving and performing alarm command.
Operation principle：Camera unit 01 carries out video acquisition, and video image is sent into server platform 03；Weight is passed
Sensor platform 02 carries out the weight information collection of subject, upload the data to server platform 03；Server platform 03
According to the video image and weight data information of upload, face recognition technology, movement locus tracing algorithm, antitheft algorithm computing are carried out
And alarm signal is sent to alarm unit 04, by face recognition technology, unique identity code is carried out to subject and is recorded,
And the corresponding weight information data of unique identity code are extracted, this group of data are i.e. as under unique identity code
The fundamental analysis data of antitheft algorithm, by movement locus tracing algorithm, judgement personnel enter or walked out, antitheft algorithm root
According to the entrance under unique identity code information, walk out when weight sampled value compare, the result of analysis is provided, while will accordingly believe
Breath issues alarm unit 04；The judgement signal that alarm unit 04 is sent according to server platform 03, makes corresponding warning response,
Complete antitheft arrangement process.
In the present embodiment, camera unit uses camera module, and being connected to server by the mode such as netting twine or USB line puts down
Platform carries out data transmission.Weight sensor platform is connected to server platform entirely through methods such as RS232 serial ports and carries out data
Transmission.Server platform, as general-purpose computer server, it is main to complete related algorithm work.Alarm unit, by indicator lamp or
Buzzer or other modes composition, comprising its control board, are connected by RS232 mouthfuls or other communication modes with server platform
Connect.In the present embodiment, alarm unit is indicator lamp, alarm bell, display screen or buzzer.Camera unit installed in supermarket go out and/
Or porch.Weight sensor stage+module is going out and/or porch.
Further, server platform includes
Identity recognizing unit, user to be detected is marked for receiving video image, and according to face recognition technology,
Obtain the Identity Code of user to be detected, inquire about default antitheft database, judge whether to store in antitheft database and need
The Identity Code of user is detected, is not process, otherwise stores to antitheft database；
Specifically, development environment of the face recognition technology based on opencv face recognition technologies used in the present invention, leads to
The eigenface analysis method of current maturation is crossed, the first preliminary personnel to passing in and out supermarket carry out the sampling of face sample, then carry out
The pretreatment action of image, pretreatment is specifically included：Image light compensation, GTG adjustment, Gaussian smoothing, adjustment picture contrast
And the processing such as binaryzation, then face is detected, by determining these independences of the face such as eye iris, the wing of nose, corners of the mouth profile
The extraction of characteristic point, is trained using these characteristics and sets up detection model grader and mark personnel's independent numbering information,
It is used as initial database resource.In concrete application, the facial image of turnover supermarket personnel (personnel i.e. to be identified) is obtained first,
Carried out after being pre-processed to the facial image after characteristic point data extraction, by the screening of graders at different levels, and and database resource
Model is compared, finally according to Nearest neighbor rule locating personnel's information, for the new personal information not having in database, carries out
The supplement of database and the study again of grader, constantly improve is circulated with this, is finally reached preferable actual recognition capability.
Weight acquiring unit, the weight data for detecting Identity Code correspondence user；
Processing unit, the direction of motion for judging Identity Code correspondence user using movement locus algorithm, if motion
Direction is into then storing Identity Code and its corresponding weight data to antitheft database；If the direction of motion is, obtain
It is simultaneously carried out mathematic interpolation by the weight data of Identity Code correspondence user with the weight data in antitheft database, and it is poor to judge
Whether value is more than weight threshold, is then to send alarm command to alarm unit, does not otherwise process.
Movement locus algorithm uses prior art in the present invention, to tracked personnel targets, carries out characteristic information
Modeling (data that the modeling of recognition of face is directly used during concrete application), by the positioning of characteristic information in sequence of frames of video,
By Meansh i ft track algorithms, and according to Kalman filter as target state estimator method, track following is completed, is provided
Vector value is run in track, provides direction, the position isovector information of tracked moving target.Specific determination, which enters, still walks out
During the judgement of supermarket, the position coordinates system at supermarket gateway is initially set up, coordinate position on the basis of entrance, outlet is secondly defined
Reference point (actual conditions have the unification of two reference points or individually separate two kinds of situations), when movement locus video algorithm trace into by
After testing staff is with respect to the coordinate position change of gateway datum mark, respective motion vectors value is obtained according to this result of variations, come
Judgement is to enter (direction vector is away from gateway coordinate reference points), still walks out (direction vector is close to coordinate reference points),
Judged with the course bearing of this determination personnel.
In the present embodiment, when have personnel by when, the video image of collection is sent to server and put down by camera unit 01
Platform 03, server platform 03 is distinguished personnel by face recognition algorithms, and records unique identity code, is such as had only
One Identity Code then directly invokes the coding, enters or walks while distinguishing subject by movement locus algorithm
Go out.When subject is by weight sensor platform 02, weight sensor platform 02 sends the corresponding weight information of acquisition
To server platform 03, server platform 03 is contrasted according to this weight information with the information record under the unique encodings before,
If subject is judged as entering, only record preserves this sampling gravimetric value, if subject is judged as walking out, and at this
Gravimetric value when walking out is more than entered fashionable gravimetric value adjacent to last time, then the personnel have the suspicious of pilferage, sent warning indicators letter
Number, if the gravimetric value when this is walked out is equal to or less than neighbouring last time and enters fashionable gravimetric value, then it represents that do not steal behavior,
Send normal signal or do not process, the different information that alarm unit 04 is provided according to server platform 03 make corresponding sound
Should, give Supermarket management personnel and accordingly point out, the prompting can be indicator lamp, alarm or other, so as to complete whole equipment
Antitheft flow.
In the present embodiment, by the respective independent discrepancy weight information comparison value of subject, detection knot is easily provided
Really, meanwhile, can more accurately be analyzed, those personnel have frequent pilferage according to the historical data cumulative statistics of each personnel
Behavior, provides accurate information to Supermarket management personnel, facilitates related management, the pilferage for improving supermarket stops loss rate.
As shown in Fig. 2 present invention also offers a kind of supermarket's intelligent antitheft method, comprising the following steps：
S101, the video image for gathering in/out user；
When it is implemented, video image acquisition is carried out to the user of all in/out supermarkets using camera, to utilize people
Face identification technology carries out identity marks to user in video image, the difference to user is realized, so as to for each discrepancy supermarket
User is detected.Realized when it is implemented, camera can install multiple cameras at supermarket's in/out mouth to in/out supermarket
All angles carry out 360 ° of IMAQs without dead angle.
S102, using face recognition technology the video image of in/out user is handled, rower is entered to user to be detected
Note, obtains the Identity Code of user to be detected；
S103, judged according to movement locus algorithm after the direction of motion of the corresponding user of Identity Code, obtain the identity
The weight data of identification code correspondence user, Identity Code and its corresponding weight data are stored to default antitheft data
Storehouse, calculates the difference of the weight data twice of Identity Code correspondence user, judges whether difference is more than weight threshold, be then to police
Show that unit sends alarm command, otherwise do not process.
When it is implemented, the weight data of the Identity Code correspondence user obtained optionally utilizes in/out supermarket position
Locate ground erection weight sensor, to realize the purpose of detection user's weight.
Some one exemplary embodiments of the present invention are only described by way of explanation above, undoubtedly, for ability
The those of ordinary skill in domain, without departing from the spirit and scope of the present invention, can be with a variety of modes to institute
The embodiment of description is modified.Therefore, above-mentioned accompanying drawing and description are inherently illustrative, should not be construed as to the present invention
The limitation of claims.
Claims (6)
1. a kind of supermarket's intelligent anti-theft system, it is characterised in that put down including camera unit, weight sensor platform, server
Platform, alarm unit, wherein,
Camera unit, the video image for gathering in/out user, server platform is sent to by video image；
Weight sensor platform, for gathering the weight data of in/out user and being uploaded to server platform；
Server platform, for user in video image to be marked, the weight data of the user marked twice before and after calculating
Difference, and weight DBMS difference is compared with weight threshold, do not processed if weight data difference is not more than weight threshold, it is no
Then alarm command is sent to alarm unit；
Alarm unit, for receiving and performing alarm command.
2. supermarket's intelligent anti-theft system according to claim 1, it is characterised in that server platform includes
Identity recognizing unit, is marked to user to be detected for receiving video image, and according to face recognition technology, obtains
Whether the Identity Code of user to be detected, inquires about default antitheft database, judge to be stored with antitheft database to be detected
The Identity Code of user, is not process, and is otherwise stored to antitheft database；
Weight acquiring unit, the weight data for detecting Identity Code correspondence user；
Processing unit, the direction of motion for judging Identity Code correspondence user using movement locus algorithm, if the direction of motion
To enter, then Identity Code and its corresponding weight data are stored to antitheft database；If the direction of motion is, identity is obtained
It is simultaneously carried out mathematic interpolation by the weight data of identification code correspondence user with the weight data in antitheft database, judges that difference is
It is no to be more than weight threshold, it is then to send alarm command to alarm unit, does not otherwise process.
3. supermarket's intelligent anti-theft system according to claim 1, it is characterised in that alarm unit is indicator lamp, alarm bell, shown
Display screen or buzzer.
4. supermarket's intelligent anti-theft system according to claim 1, it is characterised in that camera unit goes out installed in supermarket
And/or porch.
5. supermarket's intelligent anti-theft system according to claim 1, it is characterised in that weight sensor stage+module is going out
And/or porch.
6. a kind of supermarket's intelligent antitheft method, it is characterised in that comprise the following steps：
Gather the video image of in/out user；
The video image of in/out user is handled using face recognition technology, user to be detected is marked, treated
Detect the Identity Code of user；
After the direction of motion that the corresponding user of Identity Code is judged according to movement locus algorithm, Identity Code correspondence is obtained
The weight data of user, Identity Code and its corresponding weight data are stored to default antitheft database, identity is calculated
The difference of the weight data twice of identification code correspondence user, judges whether difference is more than weight threshold, is sent to alarm unit
Alarm command, is not otherwise processed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710258328.7A CN106981150A (en) | 2017-04-19 | 2017-04-19 | A kind of supermarket's intelligent anti-theft system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710258328.7A CN106981150A (en) | 2017-04-19 | 2017-04-19 | A kind of supermarket's intelligent anti-theft system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106981150A true CN106981150A (en) | 2017-07-25 |
Family
ID=59343901
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710258328.7A Pending CN106981150A (en) | 2017-04-19 | 2017-04-19 | A kind of supermarket's intelligent anti-theft system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106981150A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107403527A (en) * | 2017-08-24 | 2017-11-28 | 葛代荣 | Gate system of weighing for unmanned supermarket |
| CN107918990A (en) * | 2017-11-29 | 2018-04-17 | 西安超嗨网络科技有限公司 | A kind of antitheft system for supermarket and method |
| CN108021865A (en) * | 2017-11-03 | 2018-05-11 | 阿里巴巴集团控股有限公司 | The recognition methods of illegal act and device in unattended scene |
| CN108682109A (en) * | 2018-06-18 | 2018-10-19 | 陈彤云 | A kind of detecting system based on bus |
| CN108896151A (en) * | 2018-06-18 | 2018-11-27 | 陈彤云 | A kind of detection system based on inspection station |
| CN109326097A (en) * | 2018-10-12 | 2019-02-12 | 盈奇科技（深圳）有限公司 | A kind of anti-lost system of public transport based on gravity sensing |
| CN109377733A (en) * | 2018-10-12 | 2019-02-22 | 盈奇科技（深圳）有限公司 | A kind of public transport alarm system based on gravity sensing |
| CN110162232A (en) * | 2018-02-11 | 2019-08-23 | 中国移动通信集团终端有限公司 | Screen display method, device, equipment and storage medium with display screen |
| TWI715244B (en) * | 2019-10-14 | 2021-01-01 | 新煒科技有限公司 | Article anti-theft method, device, computer device and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1632919A2 (en) * | 2004-09-02 | 2006-03-08 | N.V. Nederlandsche Apparatenfabriek NEDAP | Electronic article surveilance system and method |
| US20140180757A1 (en) * | 2012-12-20 | 2014-06-26 | Wal-Mart Stores, Inc. | Techniques For Recording A Consumer Shelf Experience |
| CN104392370A (en) * | 2014-11-06 | 2015-03-04 | 上海斐讯数据通信技术有限公司 | Electronic commerce system and method for automatically acquiring customer information |
| CN106251543A (en) * | 2016-08-17 | 2016-12-21 | 孙留红 | A kind of antitheft system for supermarket and method |
| CN205983603U (en) * | 2016-06-30 | 2017-02-22 | 杭州腾森信息科技有限公司 | Supermarket goods ends damage system |
-
2017
- 2017-04-19 CN CN201710258328.7A patent/CN106981150A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1632919A2 (en) * | 2004-09-02 | 2006-03-08 | N.V. Nederlandsche Apparatenfabriek NEDAP | Electronic article surveilance system and method |
| US20140180757A1 (en) * | 2012-12-20 | 2014-06-26 | Wal-Mart Stores, Inc. | Techniques For Recording A Consumer Shelf Experience |
| CN104392370A (en) * | 2014-11-06 | 2015-03-04 | 上海斐讯数据通信技术有限公司 | Electronic commerce system and method for automatically acquiring customer information |
| CN205983603U (en) * | 2016-06-30 | 2017-02-22 | 杭州腾森信息科技有限公司 | Supermarket goods ends damage system |
| CN106251543A (en) * | 2016-08-17 | 2016-12-21 | 孙留红 | A kind of antitheft system for supermarket and method |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107403527A (en) * | 2017-08-24 | 2017-11-28 | 葛代荣 | Gate system of weighing for unmanned supermarket |
| US10783362B2 (en) | 2017-11-03 | 2020-09-22 | Alibaba Group Holding Limited | Method and apparatus for recognizing illegal behavior in unattended scenario |
| CN108021865A (en) * | 2017-11-03 | 2018-05-11 | 阿里巴巴集团控股有限公司 | The recognition methods of illegal act and device in unattended scene |
| KR102429739B1 (en) | 2017-11-03 | 2022-08-04 | 어드밴스드 뉴 테크놀로지스 씨오., 엘티디. | Method and apparatus for recognizing illegal behavior in unattended scenario |
| KR102256895B1 (en) | 2017-11-03 | 2021-05-31 | 어드밴스드 뉴 테크놀로지스 씨오., 엘티디. | Method and apparatus for recognizing illegal activities in unattended scenarios |
| KR20210057838A (en) * | 2017-11-03 | 2021-05-21 | 어드밴스드 뉴 테크놀로지스 씨오., 엘티디. | Method and apparatus for recognizing illegal behavior in unattended scenario |
| WO2019085589A1 (en) * | 2017-11-03 | 2019-05-09 | 阿里巴巴集团控股有限公司 | Method and apparatus for recognizing illegal behavior in unattended scenario |
| CN108021865B (en) * | 2017-11-03 | 2020-02-21 | 阿里巴巴集团控股有限公司 | Method and device for identifying illegal behaviors in unattended scene |
| KR20200054277A (en) * | 2017-11-03 | 2020-05-19 | 알리바바 그룹 홀딩 리미티드 | Method and apparatus for recognizing illegal behavior in unmanned scenarios |
| US10990813B2 (en) | 2017-11-03 | 2021-04-27 | Advanced New Technologies Co., Ltd. | Method and apparatus for recognizing illegal behavior in unattended scenario |
| CN107918990A (en) * | 2017-11-29 | 2018-04-17 | 西安超嗨网络科技有限公司 | A kind of antitheft system for supermarket and method |
| CN110162232A (en) * | 2018-02-11 | 2019-08-23 | 中国移动通信集团终端有限公司 | Screen display method, device, equipment and storage medium with display screen |
| CN108896151A (en) * | 2018-06-18 | 2018-11-27 | 陈彤云 | A kind of detection system based on inspection station |
| CN108682109A (en) * | 2018-06-18 | 2018-10-19 | 陈彤云 | A kind of detecting system based on bus |
| CN109377733B (en) * | 2018-10-12 | 2020-09-01 | 盈奇科技（深圳）有限公司 | Bus alarm system based on gravity sensing |
| CN109326097B (en) * | 2018-10-12 | 2020-09-01 | 盈奇科技（深圳）有限公司 | Bus anti-loss system based on gravity sensing |
| CN109377733A (en) * | 2018-10-12 | 2019-02-22 | 盈奇科技（深圳）有限公司 | A kind of public transport alarm system based on gravity sensing |
| CN109326097A (en) * | 2018-10-12 | 2019-02-12 | 盈奇科技（深圳）有限公司 | A kind of anti-lost system of public transport based on gravity sensing |
| TWI715244B (en) * | 2019-10-14 | 2021-01-01 | 新煒科技有限公司 | Article anti-theft method, device, computer device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106981150A (en) | A kind of supermarket's intelligent anti-theft system and method | |
| CN109657575B (en) | Intelligent video tracking algorithm for outdoor constructors | |
| CN105405154B (en) | Target object tracking based on color-structure feature | |
| CN101739686B (en) | Moving object tracking method and system thereof | |
| CN107679471B (en) | Indoor personnel air post detection method based on video monitoring platform | |
| CN110751022A (en) | Urban pet activity track monitoring method based on image recognition and related equipment | |
| CN103310444B (en) | A kind of method of the monitoring people counting based on overhead camera head | |
| CN109670441A (en) | A kind of realization safety cap wearing knows method for distinguishing, system, terminal and computer readable storage medium | |
| CN103942850A (en) | Medical staff on-duty monitoring method based on video analysis and RFID (radio frequency identification) technology | |
| CN101325690A (en) | Method and system for detecting human flow analysis and crowd accumulation process of monitoring video flow | |
| CN104933710A (en) | Intelligent analysis method of store people stream track on the basis of surveillance video | |
| CN101739551A (en) | Method and system for identifying moving objects | |
| CN103679212A (en) | Method for detecting and counting personnel based on video image | |
| CN104318578A (en) | Video image analyzing method and system | |
| CN111126153B (en) | Safety monitoring method, system, server and storage medium based on deep learning | |
| CN103237197B (en) | For the method for the self adaptation multiple features fusion of robust tracking | |
| CN111325048B (en) | Personnel gathering detection method and device | |
| CN103854292A (en) | Method and device for calculating number of people and population motion direction | |
| CN104616006A (en) | Surveillance video oriented bearded face detection method | |
| CN111681382A (en) | Method for detecting temporary fence crossing in construction site based on visual analysis | |
| CN107038415A (en) | A kind of anomaly detection method based on artificial intelligence video, system and device | |
| CN106558061A (en) | A kind of cash register loss prevention method and system based on cloud computing | |
| CN109684986A (en) | A kind of vehicle analysis method and system based on automobile detecting following | |
| CN109583339A (en) | A kind of ATM video brainpower watch and control method based on image procossing | |
| CN115861940A (en) | Working scene behavior evaluation method and system based on human body tracking and recognition technology |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170725 |