CN109711337A - A method of realizing object using Background matching, whether there is or not detections - Google Patents
A method of realizing object using Background matching, whether there is or not detections Download PDFInfo
- Publication number
- CN109711337A CN109711337A CN201811603754.0A CN201811603754A CN109711337A CN 109711337 A CN109711337 A CN 109711337A CN 201811603754 A CN201811603754 A CN 201811603754A CN 109711337 A CN109711337 A CN 109711337A
- Authority
- CN
- China
- Prior art keywords
- background
- image
- cameras
- black
- holder
- 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
Links
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses it is a kind of using Background matching realize object whether there is or not the methods of detection, include the following steps, step 1, two cameras is installed in holder two sides, and two cameras is made to form diagonal line, allow the visual field of two cameras to realize all standing to entire holder；Step 2, the picture of black and white square is pasted as background in holder two sides；Step 3, it takes pictures to two sides background, the Background of shooting is handled, obtain range of the black and white square background in shooting image, and store Background；Step 4, the Background of storage cut according to the black and white square areas of label, the background area that gray proces, Gaussian Blur, edge detection are compared then is carried out to clipping region；Step 5, camera is opened, the operation of needs is executed, the present invention is able to solve traditional technology for the hardly possible detection in special circumstances such as small cargo, transparent cargo or undetectable problem.
Description
Technical field
The present invention relates to it is a kind of using Background matching realize object whether there is or not the methods of detection.
Background technique
New retail be enterprise with internet to rely on, it is right by using the advanced technological means such as big data, artificial intelligence
The production of commodity, circulation carries out upgrading with sales process, and then remolds industry situation and the ecosphere, and under online service, line
Experience and modern logistics carry out the retail new model of depth integration.
Self-help vending machine is a canonical form in new retail trade, and is that development is earliest and easy in new retail trade
In a form of development, Self-help vending machine is by several committed steps such as selecting goods, paying, fall goods, picking, wherein falling goods, picking
And etc. concerning user experience and product safety, for example shipment is slow, access section is turned off, detects not in time in the case where non-picking
Lead to situations such as having more goods to shipment.
It is by the infrared of sales counter loading holder two sides that existing automatic selling machine testing cargo, which falls and is removed with cargo,
It completes, can have the following problems to grating is penetrated: (1) can not judge smaller cargo；Infrared emission grating installation site is located at cloud
Still there are certain altitude in platform two sides apart from mesa base, if cargo is fallen on holder, along certain side, inner wall is slipped to holder,
But its height is lower than the mounting height of echelette, can not just detect that cargo is fallen, such as chewing gum, chocolate etc.；(2) nothing
Method judges transparent cargo；Echelette judges that cargo is fallen to penetrating to be blocked according to infrared light, if what is fallen down is
Transparent substance, echelette can still be formed to penetrating, and will result in can not judge that cargo has been fallen, such as the mineral spring of transparent wrapper
Water etc.；(3) at high cost；The cost of echelette is higher relative to camera cost.
Summary of the invention
For the above technical problems, the purpose of the present invention is: propose it is a kind of using Background matching realize object
Whether there is or not the methods of detection, and being able to solve traditional technology, hardly possible detects or can not in special circumstances for small cargo, transparent cargo etc.
The problem of detection.
The technical solution of the invention is as follows is achieved: a kind of using Background matching to realize object whether there is or not the side of detection
Method includes the following steps,
Step 1, two cameras are installed in holder two sides, and two cameras is made to form diagonal lines, allow two cameras
The visual field realize all standing to entire holder；
Step 2, the picture of black and white square is pasted as background in holder two sides；
Step 3, it takes pictures to two sides background, the Background of shooting is handled, obtain black and white square background and clapping
The range in image is taken the photograph, and stores Background；
Step 4, the Background of storage cut according to the black and white square areas of label, then to clipping region
Carry out the background area that gray proces, Gaussian Blur, edge detection are compared；
Step 5, camera is opened, the operation of needs is executed, to execute whether detection cargo falls to holder, then to two
The range for the black and white square areas that the preview image of side camera is marked according to Background is cut, to the area preview image Zhong Gai
Domain carries out gray proces, Gaussian Blur, the processing such as edge detection, then will treated image and back obtained in the previous step
The image that same treatment in scape figure obtains carries out difference, obtains the variation that the image is carried out relative to background area, that is, calculates
Ratio where the area of white area in difference diagram, if calculated ratio of any one camera in two cameras is high
In given threshold, then it is assumed that there is cargo to fall；To execute whether detection cargo is removed, also need to two sides camera
The range for the black and white square areas that preview image is marked according to Background is cut, and carries out gray scale to the region in preview image
The processing such as processing, Gaussian Blur, edge detection, then by treated image and the phase in Background obtained in the previous step
It handles obtained image together and carries out difference, obtain the variation that the image is carried out relative to background area, i.e., it is white in calculating difference diagram
Ratio where the area in color region, when the ratio value that two cameras calculate is both less than the threshold value being arranged, it is believed that cargo quilt
It is taken out from holder.
Due to the application of the above technical scheme, compared with the prior art, the invention has the following advantages:
It is of the invention a kind of to realize that object whether there is or not the method for detection, is taken the photograph in this way, can use using Background matching
As head falls the cargo in automatic vending machine and cargo is removed and detects, this method be able to solve traditional technology for
The hardly possible detection in special circumstances such as small cargo, transparent cargo or undetectable problem.
Specific embodiment
The present invention addressed below.
It is of the present invention it is a kind of using Background matching realize object whether there is or not the method for detection, include the following steps,
Step 1, two cameras are installed in holder two sides, and two cameras is made to form diagonal lines, allow two cameras
The visual field realize all standing to entire holder；
Step 2, the picture of black and white square is pasted as background in holder two sides；
Step 3, it takes pictures to two sides background, the Background of shooting is handled, obtain black and white square background and clapping
The range in image is taken the photograph, and stores Background；
Step 4, the Background of storage cut according to the black and white square areas of label, then to clipping region
Carry out the background area that gray proces, Gaussian Blur, edge detection are compared；
Step 5, camera is opened, the operation of needs is executed, to execute whether detection cargo falls to holder, then to two
The range for the black and white square areas that the preview image of side camera is marked according to Background is cut, to the area preview image Zhong Gai
Domain carries out gray proces, Gaussian Blur, the processing such as edge detection, then will treated image and back obtained in the previous step
The image that same treatment in scape figure obtains carries out difference, obtains the variation that the image is carried out relative to background area, that is, calculates
Ratio where the area of white area in difference diagram, if calculated ratio of any one camera in two cameras is high
In given threshold, then it is assumed that there is cargo to fall；To execute whether detection cargo is removed, also need to two sides camera
The range for the black and white square areas that preview image is marked according to Background is cut, and carries out gray scale to the region in preview image
The processing such as processing, Gaussian Blur, edge detection, then by treated image and the phase in Background obtained in the previous step
It handles obtained image together and carries out difference, obtain the variation that the image is carried out relative to background area, i.e., it is white in calculating difference diagram
Ratio where the area in color region, when the ratio value that two cameras calculate is both less than the threshold value being arranged, it is believed that cargo quilt
It is taken out from holder.
It is of the invention a kind of to realize that object whether there is or not the method for detection, is taken the photograph in this way, can use using Background matching
As head falls the cargo in automatic vending machine and cargo is removed and detects, this method be able to solve traditional technology for
The hardly possible detection in special circumstances such as small cargo, transparent cargo or undetectable problem.
The above embodiments merely illustrate the technical concept and features of the present invention, and its object is to allow person skilled in the art
Scholar can understand the contents of the present invention and be implemented, and it is not intended to limit the scope of the present invention, it is all according to the present invention
Equivalent change or modification made by Spirit Essence, should be covered by the scope of protection of the present invention.
Claims (1)
1. a kind of, using Background matching realization object, whether there is or not the methods of detection, it is characterised in that: include the following steps,
Step 1, two cameras are installed in holder two sides, and two cameras is made to form diagonal lines, allow the views of two cameras
Realize all standing to entire holder in open country；
Step 2, the picture of black and white square is pasted as background in holder two sides；
Step 3, it takes pictures to two sides background, the Background of shooting is handled, obtain black and white square background in shooting figure
Range as in, and store Background；
Step 4, the Background of storage cut according to the black and white square areas of label, then clipping region is carried out
The background area that gray proces, Gaussian Blur, edge detection are compared；
Step 5, camera is opened, the operation of needs is executed, to execute whether detection cargo falls to holder, then two sides are taken the photograph
The range of the black and white square areas marked according to Background as the preview image of head is cut, to the region in preview image into
The processing such as row gray proces, Gaussian Blur, edge detection, then will treated image and Background obtained in the previous step
In the obtained image of same treatment carry out difference, obtain the variation that the image is carried out relative to background area, that is, calculate difference
Ratio where the area of white area in figure, sets if calculated ratio of any one camera in two cameras is higher than
Determine threshold value, then it is assumed that there is cargo to fall；To execute whether detection cargo is removed, the preview to two sides camera is also needed
The range for the black and white square areas that image is marked according to Background is cut, and is carried out at gray scale to the region in preview image
The processing such as reason, Gaussian Blur, edge detection, then by treated, image is identical as in Background obtained in the previous step
It handles obtained image and carries out difference, obtain the variation that the image is carried out relative to background area, is i.e. white in calculating difference diagram
Ratio where the area in region, when the ratio value that two cameras calculate is both less than the threshold value being arranged, it is believed that cargo by from
Holder takes out.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811603754.0A CN109711337B (en) | 2018-12-26 | 2018-12-26 | Method for realizing object existence detection by using background matching |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811603754.0A CN109711337B (en) | 2018-12-26 | 2018-12-26 | Method for realizing object existence detection by using background matching |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109711337A true CN109711337A (en) | 2019-05-03 |
| CN109711337B CN109711337B (en) | 2021-08-31 |
Family
ID=66258452
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811603754.0A Active CN109711337B (en) | 2018-12-26 | 2018-12-26 | Method for realizing object existence detection by using background matching |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109711337B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110475046A (en) * | 2019-07-31 | 2019-11-19 | 浪潮金融信息技术有限公司 | A kind of method of vending machine installation phase orientation detection zone |
| CN112052701A (en) * | 2019-06-06 | 2020-12-08 | 杭州海康威视数字技术股份有限公司 | Article taking and placing detection system, method and device |
| CN112052707A (en) * | 2019-06-06 | 2020-12-08 | 杭州海康威视数字技术股份有限公司 | Article detection system, method and device |
| CN112052708A (en) * | 2019-06-06 | 2020-12-08 | 杭州海康威视数字技术股份有限公司 | Article detection method, device and system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN204791273U (en) * | 2015-06-02 | 2015-11-18 | 东南大学成贤学院 | Multi -functional interactive mode is accessed thing and is sold integrative device automatically |
| US20150363993A1 (en) * | 2011-05-04 | 2015-12-17 | Kiosk Information Systems, Inc. | Systems and methods for merchandise display, sale and inventory control |
| CN106372870A (en) * | 2016-08-11 | 2017-02-01 | 林捷 | Information coding method and reading device of network vending machine |
| CN107833361A (en) * | 2017-09-28 | 2018-03-23 | 中南大学 | A kind of method that automatic vending machine based on image recognition falls Cargo Inspection survey |
| US20180096555A1 (en) * | 2016-10-01 | 2018-04-05 | Cantaloupe Systems, Inc. | Method and device of automatically determining a planogram in vending |
| CN108765466A (en) * | 2018-05-31 | 2018-11-06 | 重庆科技学院 | A kind of intelligent video monitoring system and method based on IP Camera |
| CN108922039A (en) * | 2018-08-31 | 2018-11-30 | 杭州吧啦熊自动化科技有限公司 | A kind of the monitoring processing system and its method of automatic vending machine |
| CN108985359A (en) * | 2018-06-29 | 2018-12-11 | 深圳和而泰数据资源与云技术有限公司 | A kind of commodity recognition method, self-service machine and computer readable storage medium |
-
2018
- 2018-12-26 CN CN201811603754.0A patent/CN109711337B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150363993A1 (en) * | 2011-05-04 | 2015-12-17 | Kiosk Information Systems, Inc. | Systems and methods for merchandise display, sale and inventory control |
| CN204791273U (en) * | 2015-06-02 | 2015-11-18 | 东南大学成贤学院 | Multi -functional interactive mode is accessed thing and is sold integrative device automatically |
| CN106372870A (en) * | 2016-08-11 | 2017-02-01 | 林捷 | Information coding method and reading device of network vending machine |
| US20180096555A1 (en) * | 2016-10-01 | 2018-04-05 | Cantaloupe Systems, Inc. | Method and device of automatically determining a planogram in vending |
| CN107833361A (en) * | 2017-09-28 | 2018-03-23 | 中南大学 | A kind of method that automatic vending machine based on image recognition falls Cargo Inspection survey |
| CN108765466A (en) * | 2018-05-31 | 2018-11-06 | 重庆科技学院 | A kind of intelligent video monitoring system and method based on IP Camera |
| CN108985359A (en) * | 2018-06-29 | 2018-12-11 | 深圳和而泰数据资源与云技术有限公司 | A kind of commodity recognition method, self-service machine and computer readable storage medium |
| CN108922039A (en) * | 2018-08-31 | 2018-11-30 | 杭州吧啦熊自动化科技有限公司 | A kind of the monitoring processing system and its method of automatic vending machine |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112052701A (en) * | 2019-06-06 | 2020-12-08 | 杭州海康威视数字技术股份有限公司 | Article taking and placing detection system, method and device |
| CN112052707A (en) * | 2019-06-06 | 2020-12-08 | 杭州海康威视数字技术股份有限公司 | Article detection system, method and device |
| CN112052708A (en) * | 2019-06-06 | 2020-12-08 | 杭州海康威视数字技术股份有限公司 | Article detection method, device and system |
| WO2020244592A1 (en) * | 2019-06-06 | 2020-12-10 | 杭州海康威视数字技术股份有限公司 | Object pick and place detection system, method and apparatus |
| CN112052707B (en) * | 2019-06-06 | 2024-06-14 | 杭州海康威视数字技术股份有限公司 | Article detection system, method and device |
| CN112052708B (en) * | 2019-06-06 | 2024-06-18 | 杭州海康威视数字技术股份有限公司 | Article detection method, device and system |
| CN110475046A (en) * | 2019-07-31 | 2019-11-19 | 浪潮金融信息技术有限公司 | A kind of method of vending machine installation phase orientation detection zone |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109711337B (en) | 2021-08-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109711337A (en) | A method of realizing object using Background matching, whether there is or not detections | |
| TWI618916B (en) | Method and system for estimating stock on shelf | |
| CN108985359B (en) | Commodity identification method, unmanned vending machine and computer-readable storage medium | |
| US11551453B2 (en) | Method and apparatus for shelf feature and object placement detection from shelf images | |
| US10762331B1 (en) | Three-dimensional (3D) depth and two-dimensional (2D) imaging systems and methods for automatic container door status recognition | |
| US11640576B2 (en) | Shelf monitoring device, shelf monitoring method, and shelf monitoring program | |
| CN109117824B (en) | Commodity management method and device, electronic equipment and storage medium | |
| US11863869B1 (en) | Event detection using motion extracted image comparison | |
| CN114651506B (en) | System and method for automatic Camera Installation Guide (CIG) | |
| CN109446883A (en) | Condition of merchandise recognition methods, device, electronic equipment and readable storage medium storing program for executing | |
| CN110751079A (en) | Article detection method, apparatus, system and computer readable storage medium | |
| JP6751882B2 (en) | Product monitoring device, product monitoring system and product monitoring method | |
| US11915463B2 (en) | System and method for the automatic enrollment of object images into a gallery | |
| CN111161346B (en) | Method and device for layering commodities in goods shelves and electronic equipment | |
| US10534072B2 (en) | Object detection device, POS terminal device, object detection method, program, and program recording medium | |
| US20170278234A1 (en) | Method for detecting a defect on a surface of a tire | |
| JP2014229154A (en) | Article identification system and program for the same | |
| CN111145430A (en) | Method and device for detecting commodity placing state and computer storage medium | |
| CN110097510B (en) | Pure-color flower identification method, device and storage medium | |
| CN112184751B (en) | Object identification method and system and electronic equipment | |
| CN113298769B (en) | FPC flexible flat cable appearance defect detection method, system and medium | |
| JP2020017253A (en) | Commodity management system and commodity management method | |
| US20220051177A1 (en) | System and method for identifying misplaced products in a shelf management system | |
| US10410337B2 (en) | System and method for identifying the presence or absence of transparent pills in blister packer machines using high resolution 3D stereo reconstruction based on color linear cameras | |
| CN109829510A (en) | A kind of method, apparatus and equipment of product quality classification |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210728 Address after: 215100 818 Wusong Road, Wusong River Industrial Park, Wuzhong development area, Suzhou, Jiangsu Applicant after: INSPUR FINANCIAL INFORMATION TECHNOLOGY Co.,Ltd. Address before: 215100 Building 1, 178 Tayun Road, Yuexi street, Wuzhong District, Suzhou City, Jiangsu Province Applicant before: SUZHOU INSPUR INTELLIGENT SOFTWARE Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |