CN106558061A - A kind of cash register loss prevention method and system based on cloud computing - Google Patents
A kind of cash register loss prevention method and system based on cloud computing Download PDFInfo
- Publication number
- CN106558061A CN106558061A CN201510627838.8A CN201510627838A CN106558061A CN 106558061 A CN106558061 A CN 106558061A CN 201510627838 A CN201510627838 A CN 201510627838A CN 106558061 A CN106558061 A CN 106558061A
- Authority
- CN
- China
- Prior art keywords
- analysis
- cash register
- algorithm
- client
- setting
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of cash register loss prevention method and system based on cloud computing, for commercial video monitoring field, described method includes：Obtain the video flowing of collected by camera under shops's scene, setting POSE cashier's machine money caskets region, it is utilized respectively edge detection algorithm, color histogram analysis algorithm and extracts provincial characteristicss, by front and back's frame aspect ratio to analysis and region prospect symmetrical analysis, judges whether cash register money casket is opened；Setting customer payment analyzed area, is utilized respectively background modeling algorithm, target tracking algorism analysis client and stretches out one's hand action；Analysis result is opened with reference to money casket and client stretches out one's hand payment analysis result, combined and judge whether abnormal cash register.The embodiment of the present invention sets up the cash register loss prevention Video Analysis Technology on cloud computing conceptual view Information base, compared with the existing technology, can quickly and efficiently identify cash register Deviant Behavior, can more meet busincess intelligence demand.
Description
Technical field
The present invention relates to technical field of video monitoring, more particularly to a kind of cash register loss prevention method and system based on cloud computing.
Background technology
In the commercial field that intensified competition, profit become thin, take precautions against employee's theft and be increasingly taken seriously.According to incompletely statistics, the whole world is every year because of up to 1.78 hundred million dollars of direct economic loss caused by employee's theft.For many retail business companies, the partial loss direct relation company of gets a profit or loses.Therefore, increasing retailing enterprise takes up its loss prevention work.
At present business is out of the line the main two aspects method of industry loss prevention：One is configuration loss prevention assistant director, is taken precautions against by the way of direct surveillance；Two is to carry out video monitoring using photographic head, and direct surveillance or inquiry video record perform an analysis judgement.But both approaches have very big dependency to people, it is not preferably to select in the epoch of magnanimity information.
The content of the invention
The purpose of the present invention is there is a problem of that too relying on artificial screening obtains early warning information for the anti-damage method of traditional cashier's machine, propose a kind of cash register loss prevention method and system based on cloud computing, allow the program based on the Internet directly using Video Analysis Technology come the stolen event of automatic early-warning, loss prevention demand is provided for the super chain shops of business.
In order to reach foregoing invention purpose, the anti-damage method of a kind of cash register based on cloud computing that the embodiment of the present invention is proposed is achieved through the following technical solutions：
A kind of anti-damage method of the cash register based on cloud computing, methods described include：
Obtain the video flowing of collected by camera under shops's scene, setting POSE cashier's machine money caskets region, it is utilized respectively edge detection algorithm, color histogram analysis algorithm and extracts provincial characteristicss, by front and back's frame aspect ratio to analysis and region prospect symmetrical analysis, judges whether cash register money casket is opened；
Setting customer payment analyzed area, is utilized respectively background modeling algorithm, target tracking algorism analysis client and stretches out one's hand action；
Analysis result is opened with reference to money casket and client stretches out one's hand payment analysis result, combined and judge whether abnormal cash register.
In order to realize aforementioned invention purpose, the invention allows for a kind of cash register loss prevention system based on cloud computing, the system is achieved through the following technical solutions：
A kind of cash register loss prevention system based on cloud computing, the system include：
A set of cloud computing system, calculates for algorithm and result is transmitted；
One or more video acquisition units, obtain video flowing for gathering under shops's cash register scene；
Money casket open detection module, for obtaining the video flowing of collected by camera under shops's scene, setting detection zone, it is utilized respectively edge detection algorithm, color histogram analysis algorithm and extracts provincial characteristicss, by in front and back's frame aspect ratio to analysis and region prospect symmetrical analysis, judge whether cash register money casket is opened；
Customer payment behavior judge module, for setting customer payment analyzed area, is utilized respectively background modeling algorithm, target tracking algorism analysis client and stretches out one's hand action；
Cash register exception judge module, for stretching out one's hand payment analysis result with reference to money casket opening analysis result and client, combines and judges whether abnormal cash register.
A kind of cash register loss prevention method and system based on cloud computing proposed by the present invention, the generation of cash register Deviant Behavior can be detected using image sequence characteristic directly, taking full advantage of cloud computing technology carries out Shang Chao shops cash register supervision on a large scale, has broken away from the limitation of direct surveillance's inquiry.Therefore, the embodiment of the present invention sets up the cash register loss prevention Video Analysis Technology on cloud computing concept polyphaser Information base, compared with the existing technology, can quickly and efficiently identify cash register Deviant Behavior, can more meet the loss prevention demand of the super chain shops of business on a large scale.
Description of the drawings
Flow charts of the Fig. 1 for a kind of 1 image feature comparison method of the embodiment of the present invention.
Fig. 2 is a kind of 2 image feature comparison device composition schematic diagram of the embodiment of the present invention.
Specific embodiment
Below in conjunction with the accompanying drawings the present invention is described in further detail.
As shown in figure 1, for the flow chart of a kind of 1 image feature comparison method of the embodiment of the present invention, methods described includes：
S101. obtain the video flowing of collected by camera under shops's scene, setting POSE cashier's machine money caskets region, it is utilized respectively edge detection algorithm, color histogram analysis algorithm and extracts provincial characteristicss, by front and back's frame aspect ratio to analysis and region prospect symmetrical analysis, judges whether cash register money casket is opened；
S102. customer payment analyzed area is set, background modeling algorithm, target tracking algorism analysis client is utilized respectively and is stretched out one's hand action；
S103. analysis result is opened with reference to money casket and client stretches out one's hand payment analysis result, combine and judge whether abnormal cash register.
Using edge detection algorithm, such as canny, sobel, laplas etc., obtain horizontal edge or vertical edge, in statistics money casket detection zone, whether white pixel point sum and uniformity etc. meet given threshold, judge whether the distribution of white pixel point is in certain symmetrical, color histogram feature in eligible zoning again with regard to detection zone center.
Frame histogram feature contrast in front and back meets given threshold condition, it is believed that money casket occurs and opens event.
Using background modeling algorithm, such as GMM, codebook, vibe etc., carry out region foreground extraction, the strong Corner Feature of foreground extraction of area coinciding given threshold and histogram feature, the frame prospect in front and back for meeting setpoint distance threshold value carries out characteristic matching, meet matching condition is same target, sets up movement locus, stretches out one's hand the generation of payment event according to the walking direction client of setting.
If money casket opens event occurring, customer payment behavior occurs, then judge that cash register is normal；If money casket opens event occurring, and customer payment behavior not occurring, then early warning cash register exception；If money casket opens event not occurring, customer payment behavior occurs, then judge whether POSE machines background data base has fetched data, if there is conclusion of the business event, judges that cash register is normal, otherwise it is assumed that being abnormal cash register.
As shown in Fig. 2 in order to realize aforementioned invention purpose, being that the embodiment of the present invention 2 also proposed a kind of cash register loss prevention system based on cloud computing, the system is achieved through the following technical solutions：
A kind of cash register loss prevention system based on cloud computing, the system include：
A set of cloud computing system, calculates for algorithm and result is transmitted；
One or more video acquisition units, obtain video flowing for gathering under shops's cash register scene；
Money casket open detection module, for obtaining the video flowing of collected by camera under shops's scene, setting detection zone, it is utilized respectively edge detection algorithm, color histogram analysis algorithm and extracts provincial characteristicss, by in front and back's frame aspect ratio to analysis and region prospect symmetrical analysis, judge whether cash register money casket is opened；
Customer payment behavior judge module, for setting customer payment analyzed area, is utilized respectively background modeling algorithm, target tracking algorism analysis client and stretches out one's hand action；
Cash register exception judge module, for stretching out one's hand payment analysis result with reference to money casket opening analysis result and client, combines and judges whether abnormal cash register.
A kind of cash register loss prevention method and system based on cloud computing that the embodiment of the present invention is proposed, the generation of cash register Deviant Behavior can be detected using image sequence characteristic directly, taking full advantage of cloud computing technology carries out Shang Chao shops cash register supervision on a large scale, has broken away from the limitation of direct surveillance's inquiry.Therefore, the embodiment of the present invention sets up the cash register loss prevention Video Analysis Technology on cloud computing concept polyphaser Information base, compared with the existing technology, can quickly and efficiently identify cash register Deviant Behavior, can more meet the loss prevention demand of the super chain shops of business on a large scale.
Those skilled in the art of the art are appreciated that; above example of the present invention is only one of the preferred embodiments of the present invention; limit for length; here all embodiments can not be enumerated one by one; any enforcement that can embody the claims in the present invention technical scheme, all within the scope of the present invention.
It should be noted that; above content is with reference to specific embodiment further description made for the present invention; it cannot be assumed that the specific embodiment of the present invention is only limitted to this; under the above-mentioned guidance of the present invention; those skilled in the art can carry out various improvement and deformation on the basis of above-described embodiment, and these improve or deformation is within the scope of the present invention.
Claims (2)
1. the anti-damage method of a kind of cash register based on cloud computing, it is characterised in that methods described includes：
Obtain the video flowing of collected by camera under shops's scene, setting POSE cashier's machine money caskets region, it is utilized respectively edge detection algorithm, color histogram analysis algorithm and extracts provincial characteristicss, by front and back's frame aspect ratio to analysis and region prospect symmetrical analysis, judges whether cash register money casket is opened；
Setting customer payment analyzed area, is utilized respectively background modeling algorithm, target tracking algorism analysis client and stretches out one's hand action；
Analysis result is opened with reference to money casket and client stretches out one's hand payment analysis result, combined and judge whether abnormal cash register；
The utilization edge detection algorithm, color histogram analysis algorithm extract provincial characteristicss and specifically include：
Setting edge detection operator, extracts region vertical edge, vertical edge pixel point sum in statistical regions；Area image makees color space conversion, with reference to colourity, saturation and monochrome information, statistical regions color histogram；
The utilization background modeling algorithm, target tracking algorism analysis client stretch out one's hand action, specifically include：
Setting main flow background modeling algorithm carries out region foreground extraction, and the foreground target to meeting area threshold condition makees feature extraction, and movement locus are set up in the matching of frame target characteristic in front and back for meeting distance threshold, and it is that client stretches out one's hand payment behavior to judge that course bearing is analysed whether.
2. a kind of cash register loss prevention system based on cloud computing, the system include：
A set of cloud computing system, calculates for algorithm and result is transmitted；
One or more video acquisition units, obtain video flowing for gathering under shops's cash register scene；
Money casket open detection module, for obtaining the video flowing of collected by camera under shops's scene, setting detection zone, it is utilized respectively edge detection algorithm, color histogram analysis algorithm and extracts provincial characteristicss, by in front and back's frame aspect ratio to analysis and region prospect symmetrical analysis, judge whether cash register money casket is opened；
Customer payment behavior judge module, for setting customer payment analyzed area, is utilized respectively background modeling algorithm, target tracking algorism analysis client and stretches out one's hand action；
Cash register exception judge module, for stretching out one's hand payment analysis result with reference to money casket opening analysis result and client, combines and judges whether abnormal cash register；
The utilization edge detection algorithm, color histogram analysis algorithm extract provincial characteristicss and specifically include：
Setting edge detection operator, extracts region vertical edge, vertical edge pixel point sum in statistical regions；Area image makees color space conversion, with reference to colourity, saturation and monochrome information, statistical regions color histogram；
The utilization background modeling algorithm, target tracking algorism analysis client stretch out one's hand action, specifically include：
Setting main flow background modeling algorithm carries out region foreground extraction, and the foreground target to meeting area threshold condition makees feature extraction, and movement locus are set up in the matching of frame target characteristic in front and back for meeting distance threshold, and it is that client stretches out one's hand payment behavior to judge that course bearing is analysed whether.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510627838.8A CN106558061A (en) | 2015-09-29 | 2015-09-29 | A kind of cash register loss prevention method and system based on cloud computing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510627838.8A CN106558061A (en) | 2015-09-29 | 2015-09-29 | A kind of cash register loss prevention method and system based on cloud computing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106558061A true CN106558061A (en) | 2017-04-05 |
Family
ID=58415762
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510627838.8A Pending CN106558061A (en) | 2015-09-29 | 2015-09-29 | A kind of cash register loss prevention method and system based on cloud computing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106558061A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108334615A (en) * | 2018-02-07 | 2018-07-27 | 湖北统讯智能科技有限公司 | A kind of method of cash register loss prevention management system and its video frequency searching |
| CN109961457A (en) * | 2017-12-25 | 2019-07-02 | 北京顺智信科技有限公司 | A kind of cash register loss prevention method and system |
| CN110688965A (en) * | 2019-09-30 | 2020-01-14 | 北京航空航天大学青岛研究院 | IPT (inductive power transfer) simulation training gesture recognition method based on binocular vision |
| CN112749647A (en) * | 2020-12-30 | 2021-05-04 | 成都云盯科技有限公司 | Intelligent cash-receiving inspection method and system based on monitoring video |
| CN112818799A (en) * | 2021-01-26 | 2021-05-18 | 四川天翼网络服务有限公司 | Bank counter seal management method and system |
| CN113537034A (en) * | 2021-07-12 | 2021-10-22 | 上海商米科技集团股份有限公司 | Cash receiving loss prevention method and system |
| CN114463015A (en) * | 2022-04-11 | 2022-05-10 | 合肥的卢深视科技有限公司 | Payment supervision system, method, electronic device and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2529325Y (en) * | 2002-02-11 | 2003-01-01 | 黄光明 | Intelligent cash register monitoring apparatus |
| CN2643414Y (en) * | 2002-10-30 | 2004-09-22 | 深圳普诺玛商业安全设备有限公司 | Business spot monitor with alarm triggering and digital video recording |
| CN101268478A (en) * | 2005-03-29 | 2008-09-17 | 斯达普力特有限公司 | Method and apparatus for detecting suspicious activity using video analysis |
| CN102881100A (en) * | 2012-08-24 | 2013-01-16 | 济南纳维信息技术有限公司 | Video-analysis-based antitheft monitoring method for physical store |
| CN104299224A (en) * | 2014-08-21 | 2015-01-21 | 华南理工大学 | Method for property protection based on video image background matching |
-
2015
- 2015-09-29 CN CN201510627838.8A patent/CN106558061A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2529325Y (en) * | 2002-02-11 | 2003-01-01 | 黄光明 | Intelligent cash register monitoring apparatus |
| CN2643414Y (en) * | 2002-10-30 | 2004-09-22 | 深圳普诺玛商业安全设备有限公司 | Business spot monitor with alarm triggering and digital video recording |
| CN101268478A (en) * | 2005-03-29 | 2008-09-17 | 斯达普力特有限公司 | Method and apparatus for detecting suspicious activity using video analysis |
| CN102881100A (en) * | 2012-08-24 | 2013-01-16 | 济南纳维信息技术有限公司 | Video-analysis-based antitheft monitoring method for physical store |
| CN104299224A (en) * | 2014-08-21 | 2015-01-21 | 华南理工大学 | Method for property protection based on video image background matching |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109961457A (en) * | 2017-12-25 | 2019-07-02 | 北京顺智信科技有限公司 | A kind of cash register loss prevention method and system |
| CN109961457B (en) * | 2017-12-25 | 2023-06-23 | 百融至信(北京)科技有限公司 | Cashing loss prevention method and system |
| CN108334615A (en) * | 2018-02-07 | 2018-07-27 | 湖北统讯智能科技有限公司 | A kind of method of cash register loss prevention management system and its video frequency searching |
| CN110688965A (en) * | 2019-09-30 | 2020-01-14 | 北京航空航天大学青岛研究院 | IPT (inductive power transfer) simulation training gesture recognition method based on binocular vision |
| CN110688965B (en) * | 2019-09-30 | 2023-07-21 | 北京航空航天大学青岛研究院 | IPT simulation training gesture recognition method based on binocular vision |
| CN112749647A (en) * | 2020-12-30 | 2021-05-04 | 成都云盯科技有限公司 | Intelligent cash-receiving inspection method and system based on monitoring video |
| CN112749647B (en) * | 2020-12-30 | 2023-07-25 | 成都云盯科技有限公司 | Intelligent cashing inspection method and system based on monitoring video |
| CN112818799A (en) * | 2021-01-26 | 2021-05-18 | 四川天翼网络服务有限公司 | Bank counter seal management method and system |
| CN112818799B (en) * | 2021-01-26 | 2022-07-05 | 四川天翼网络服务有限公司 | Bank counter seal management method and system |
| CN113537034A (en) * | 2021-07-12 | 2021-10-22 | 上海商米科技集团股份有限公司 | Cash receiving loss prevention method and system |
| CN114463015A (en) * | 2022-04-11 | 2022-05-10 | 合肥的卢深视科技有限公司 | Payment supervision system, method, electronic device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106558061A (en) | A kind of cash register loss prevention method and system based on cloud computing | |
| CN104361327B (en) | A kind of pedestrian detection method and system | |
| Tian et al. | Robust and efficient foreground analysis for real-time video surveillance | |
| Stalder et al. | Cascaded confidence filtering for improved tracking-by-detection | |
| US9639747B2 (en) | Online learning method for people detection and counting for retail stores | |
| Saravanakumar et al. | Multiple human object tracking using background subtraction and shadow removal techniques | |
| KR100695155B1 (en) | Apparatus and method for detecting occluded face and apparatus and method for discriminating illicit transactor employing the same | |
| CN102982313B (en) | The method of Smoke Detection | |
| Hsu et al. | Passenger flow counting in buses based on deep learning using surveillance video | |
| JP5726596B2 (en) | Image monitoring device | |
| CN111209818A (en) | Video individual identification method, system, equipment and readable storage medium | |
| TWM592541U (en) | Image recognition system | |
| Devi et al. | Driver drowsiness detection using skin color algorithm and circular hough transform | |
| CN103049748A (en) | Behavior-monitoring method and behavior-monitoring system | |
| Derman et al. | Short term face recognition for Automatic Teller Machine (ATM) users | |
| Hu et al. | Fast face detection based on skin color segmentation using single chrominance Cr | |
| CN111708907B (en) | Target person query method, device, equipment and storage medium | |
| US11132778B2 (en) | Image analysis apparatus, image analysis method, and recording medium | |
| Ilao et al. | Crowd estimation using region-specific HOG With SVM | |
| Cristani et al. | A spatial sampling mechanism for effective background subtraction. | |
| Archana et al. | Face recognition using Deep Neural Network and Support Based Anchor Boxes Methods in video frames | |
| TWI748908B (en) | Image recognition system based on features points of five senses | |
| TWI726470B (en) | Image recognition system | |
| KR100729265B1 (en) | A face detection method using difference image and color information | |
| KR20160017152A (en) | Gender Classification Based on Binary Haar Cascade |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170405 |
|
| WD01 | Invention patent application deemed withdrawn after publication |