CN107742383B - Automatic settlement system and method based on smooth surface imaging - Google Patents
Automatic settlement system and method based on smooth surface imaging Download PDFInfo
- Publication number
- CN107742383B CN107742383B CN201711234552.9A CN201711234552A CN107742383B CN 107742383 B CN107742383 B CN 107742383B CN 201711234552 A CN201711234552 A CN 201711234552A CN 107742383 B CN107742383 B CN 107742383B
- Authority
- CN
- China
- Prior art keywords
- commodity
- smooth surface
- surface imaging
- commodities
- settled
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07G—REGISTERING THE RECEIPT OF CASH, VALUABLES, OR TOKENS
- G07G1/00—Cash registers
- G07G1/0036—Checkout procedures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Abstract
The invention discloses an automatic settlement system and a settlement method based on smooth surface imaging, which comprises a smooth surface imaging device, a camera device, a commodity conveying device and a calculation and analysis unit; the smooth surface imaging device comprises a line light source, a lens and an area array camera, wherein three planes of a plane illuminated by the line light source, a lens surface and an area array camera plane are intersected in a line; the smooth surface imaging device is arranged at one end or the side surface of the commodity conveying device and is higher than the commodity conveying device; the camera shooting device for shooting the commodity pictures is arranged at a plurality of parts of the commodity conveying device except the bottom; and the calculation and analysis unit matches the section contour and the section area obtained by the smooth surface imaging device with the picture information obtained by the camera device. The invention adopts the smooth surface imaging and image matching technology, and does not need to add extra marks to the commodities; compared with the method of directly comparing the commodity color photos, the method has the advantages that the cross-section images of the commodities are compared firstly, and then the photos of all sides of the commodities are compared, so that the calculation time of image matching is reduced.
Description
Technical Field
The invention relates to the technical field of settlement systems, in particular to an automatic settlement system and a settlement method based on smooth surface imaging and image matching.
Background
The unmanned supermarket is a new development trend of the future retail industry. In the operation of unmanned supermarkets, the settlement and cash collection are the most critical links. At present, the settlement of unmanned supermarkets mainly adopts two technologies: RFID (Radio frequency identification) technology and image matching technology. The RFID technology is to identify a commodity by using a tag on the commodity, thereby calculating the price of the commodity, and the RFID technology needs to be attached to the commodity to increase secondary workload. The image comparison method is to compare the pictures of the commodity with the pictures in the picture library and find the corresponding commodity for calculation, and the image comparison method is complex and has low speed.
Disclosure of Invention
1. The invention aims to provide a novel method.
The invention aims to solve the defects of the prior art and provides an automatic settlement system based on smooth surface imaging.
2. The technical scheme adopted by the invention is disclosed.
The invention discloses an automatic settlement system based on smooth surface imaging, which comprises a smooth surface imaging device, a camera device, a commodity conveying device and a calculation and analysis unit;
the smooth surface imaging device comprises a line light source, a lens and an area array camera, wherein three planes of a plane illuminated by the line light source, a lens surface and an area array camera plane are intersected in a line;
the smooth surface imaging device is arranged at one end or the side surface of the commodity conveying device and is higher than the commodity conveying device;
the camera device for taking the picture of the commodity is arranged at any one or more parts of the commodity conveying device except the bottom;
and the calculation and analysis unit matches the section contour and the section area obtained by the smooth surface imaging device with the picture information obtained by the camera device.
In a further embodiment, more than 2 smooth surface imaging devices are used.
In a more specific embodiment, the plurality of image capturing devices are installed above the commodity conveying device, and are also installed on the side surface and the front and back of the commodity conveying device.
In a further embodiment, the commodity conveying device is provided with an array sensor with LEDs and photodetectors arranged at intervals on the side surface to obtain the projected cross-sectional profile of the commodity.
In a further specific embodiment, the image capturing device uses an RGB-D camera of Ki nect to obtain information on the color and height distribution of the cargo.
In a further specific embodiment, a weighing module is further disposed on the goods conveying device.
The invention discloses an automatic settlement method based on smooth surface imaging and image matching technology, which comprises the following specific steps:
step 1, pre-collecting commodity information and recording
Placing the side with the largest area of the commodity on a commodity conveying device downwards, and obtaining the outline and the area of a cross section of the commodity at a certain height horizontal plane through a smooth surface imaging device;
shooting a picture of the commodity through a camera device;
the weight of the commodity is obtained through a weighing module on the conveying device;
and recording the information.
The side with the largest area of the commodity to be settled is placed on the commodity conveying device downwards, and a smooth surface imaging device and a camera device are still arranged around the commodity conveying device to obtain the section outline, the section area, the side-view color photo and the weight of the commodity to be settled.
And comparing the section outline, the section area, the overlook color picture, the photo and the weight of the commodity to be settled with commodity information stored in a background system by using a standard comparison algorithm, comparing the similarity of the two images by using a similarity algorithm, setting a similarity threshold value according to the commodity type, matching the images when the similarity threshold value is reached, searching the commodity corresponding to the commodity to be settled and the price thereof, and calculating.
In a further specific embodiment, the comparison algorithm in step 3 specifically comprises the following steps:
step 3.1, comparing the section outline and the section area, if a unique matching result is obtained, the result is the to-be-detected commodity, and if a plurality of matching results are obtained, comparing the to-be-settled commodity with the plurality of matching commodities continuously;
step 3.2, the overlook color photos of the commodities are compared, if the only matching result is obtained, the result is the commodity to be detected, and if a plurality of matching results still exist, the commodity to be settled and the commodities can be continuously compared;
and 3.3, comparing the side-looking color photos or the weights of the matched commodities, screening out a final result, matching the side-looking color photos or the matched commodities according to another parameter, namely the photos and the weights at different angles, and screening out error information.
3. The technical effect produced by the invention.
1) By adopting the smooth surface imaging technology and the image matching technology, no extra mark is required to be added to the commodity, and the secondary workload is reduced.
2) Compared with the method of directly comparing the commodity color photos, the method has the advantages that the cross-section images of the commodity are compared firstly, then the photos of all sides of the commodity are compared, the image matching calculation time is reduced, and the settlement speed is improved.
Drawings
Fig. 1 is a schematic structural diagram of a smooth surface imaging device in an automatic settlement system.
Fig. 2 is a side view of a smooth imaging device.
Fig. 3 is a schematic diagram of the automatic settlement system.
FIG. 4 is a flow chart of a method for searching prices of commodities to be settled during the settlement process.
Detailed Description
Example 1
The invention discloses an automatic settlement system based on smooth surface imaging, which comprises more than 2 smooth surface imaging devices, a camera device, a commodity conveying device and a calculation and analysis unit;
the smooth surface imaging device comprises a line light source, a lens and an area array camera, wherein three planes of a plane illuminated by the line light source, a lens surface and an area array camera plane are intersected in a line; the smooth surface imaging device is arranged at one end or the side surface of the commodity conveying device and is higher than the commodity conveying device; the camera device for taking the picture of the commodity is arranged at any one or more parts of the commodity conveying device except the bottom; and the calculation and analysis unit matches the section contour and the section area obtained by the smooth surface imaging device with the picture information obtained by the camera device. The commodity conveying device is provided with array sensors which are arranged by LEDs and photodetectors at intervals on the side surface to obtain the projection section profile of the commodity. The camera device can also adopt an RGB-D camera of Ki nect to obtain the information of the colors and the height distribution of the goods. And the commodity conveying device is also provided with a weighing module.
The invention discloses an automatic settlement method based on smooth surface imaging and image matching technology, which comprises the following specific steps:
step 1, pre-collecting commodity information and recording
Placing the side with the largest area of the commodity on a commodity conveying device downwards, and obtaining the outline and the area of a cross section of the commodity at a certain height horizontal plane through a smooth surface imaging device;
shooting a picture of the commodity through a camera device;
the weight of the commodity is obtained through a weighing module on the conveying device;
and recording the information.
The side with the largest area of the commodity to be settled is placed on the commodity conveying device downwards, and a smooth surface imaging device and a camera device are still arranged around the commodity conveying device to obtain the section outline, the section area, the photo and the weight of the commodity to be settled.
Comparing the cross section outline, the cross section area, the overlook color picture, the side view picture and the weight of the commodity to be settled with commodity information stored in a background system by using a standard comparison algorithm, comparing the similarity of the two images by using a similarity algorithm, setting a similarity threshold value according to the commodity type, finding the commodity corresponding to the commodity to be settled and the price thereof for calculation when the similarity threshold value image is matched, wherein the specific steps are as follows:
step 3.1, comparing the section outline and the section area, if a unique matching result is obtained, the result is the to-be-detected commodity, and if a plurality of matching results are obtained, comparing the to-be-settled commodity with the plurality of matching commodities continuously;
step 3.2, the overlook color photos of the commodities are compared, if the only matching result is obtained, the result is the commodity to be detected, and if a plurality of matching results still exist, the commodity to be settled and the commodities can be continuously compared;
and 3.3, comparing the side-looking color photos or the weights of the matched commodities, screening out a final result, matching the side-looking color photos or the matched commodities according to another parameter, namely the photos and the weights at different angles, and screening out error information.
Example 2
Fig. 1 is a schematic structural diagram of a smooth surface imaging device in an automatic settlement system. As shown in the figure, the smooth imaging device comprises a light source 1, a filter 2, a lens 3 and an area-array camera 4. The plane illuminated by the light source, the lens plane and the plane of the area-array camera intersect on a line; when the linear light source 1 illuminates an object on a plane, light is reflected by the object, the reflected light is imaged at a corresponding position of the area array camera 4 through the filter 2 and the lens 3, the shape of the image is the outline of the object illuminated by the linear light source, and then the object can be calculatedArea of the outline. One point A (X) on the plane illuminated by the light source, i.e. the object planeobj,Yobj0), the image point on the plane of the area-array camera, i.e., the image plane, is a (x, y, z).
Fig. 2 is a side view of a smooth imaging device. As shown in fig. 2, the position of the image plane (plane of the area-array camera 4) is determined by the included angle a between the lens 3 plane and the object plane (the plane illuminated by the linear light source 1), the distance L between the center of the lens and the intersection of the three planes, and the focal length f of the lens, and the included angle b between the image plane and the object plane can be obtained by the following formula:
u=sina·Xobj
h0=cosa·Xobj-L
fig. 3 is a schematic diagram of the automatic settlement system. As shown, the linear light source 10 of the smooth surface imaging device 5 is located at a fixed height H of the commodity conveying device 6, and the image pickup device 7 is installed above the commodity conveying device 6, and when there are a plurality of image pickup devices, it can be installed above, at the side of, and at the front and rear positions of the commodity conveying device. The goods conveyor 6 is provided with a weighing module 8. The calculation and analysis unit 9 is connected with the smooth surface imaging device 5, the camera device 7 and the weighing module 8, and records and processes data.
Collecting commodity information: placing the side with the largest commodity area on a commodity conveying device 6 downwards, and obtaining the outline and the area of a horizontal section of the commodity at a certain height H through a smooth surface imaging device 5; the overlooking and side-looking photos of the commodity are shot by the camera device 7; the weighing module 8 measures the weight of the goods. The cross section outline, cross section area, top view picture, side view picture, color and height distribution, weight and the like of the commodity are the collected commodity information.
Before goods are put on shelf, information is collected and recorded into the system. And acquiring information during settlement, comparing and searching in the system by utilizing the commodity information, and finding out the corresponding commodity and the price for settlement.
Fig. 4 is a flow chart of a method for searching for a commodity to be settled and a price in the settlement process, and the collected commodity information with settlement is compared with commodity information recorded in advance in the system. As shown in the figure, the sectional image, the enveloping sectional profile and the sectional area are firstly compared, if a unique matching result is obtained, the result is the commodity to be detected, and if a plurality of matching results are obtained, the commodity to be settled and the commodities are continuously compared. And then comparing the overlook photos of the commodities, if a unique matching result is obtained, the result is the commodity to be detected, and if a plurality of matching results still exist, the commodity to be settled is continuously compared with the commodities. And finally, comparing the side-looking photos to obtain a matching result. After the final result is obtained, comparing the total weight of all the commodities to be settled with the total weight of the matched commodities, wherein if the total weights are matched, the price of the matched commodity is the price of the commodity to be settled; if the weights are not matched, the system prompts that a problem occurs, and searching or human intervention is carried out again according to the flow.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.
In the description of the present invention, it is to be understood that the terms indicating an orientation or positional relationship are based on the orientation or positional relationship shown in the drawings only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention.
Claims (1)
1. An automatic settlement method based on smooth surface imaging and image matching technology is characterized in that: the system comprises a smooth surface imaging device, a camera device, a commodity conveying device and a calculation and analysis unit;
the smooth surface imaging device comprises a line light source, a lens and an area array camera, wherein three planes of a plane illuminated by the line light source, a lens surface and an area array camera plane are intersected in a line;
the method comprises the following specific steps:
step 1, pre-collecting commodity information and recording
Placing the side with the largest area of the commodity on a commodity conveying device downwards, and obtaining the outline and the area of a cross section of the commodity at a certain height horizontal plane through a smooth surface imaging device;
shooting a picture of the commodity through a camera device;
the weight of the commodity is obtained through a weighing module on the conveying device;
recording the information;
step 2, scanning information of commodities to be settled
Placing the side with the largest area of the commodity to be settled on a commodity conveying device downwards, and still installing a smooth surface imaging device and a camera device around the commodity conveying device to obtain the section outline, the section area, the photo and the weight of the commodity to be settled;
step 3, comparing the prices of the commodities to be settled by using a comparison algorithm
Comparing the cross section outline, the cross section area, the overlook color picture, the side view color picture and the weight of the commodity to be settled with commodity information stored in a background system by using a standard comparison algorithm, comparing the similarity of the two images by using a similarity algorithm, setting a similarity threshold value according to the commodity type, finding the commodity corresponding to the commodity to be settled and the price thereof, and calculating, wherein the specific steps are as follows:
step 3.1, comparing the section outline and the section area, if a unique matching result is obtained, the result is the to-be-detected commodity, and if a plurality of matching results are obtained, comparing the to-be-settled commodity with the plurality of matching commodities continuously;
step 3.2, the overlook color photos of the commodities are compared, if the only matching result is obtained, the result is the commodity to be detected, and if a plurality of matching results still exist, the commodity to be settled and the commodities can be continuously compared;
step 3.3, comparing the weights of the side-looking color photos or the matched commodities, screening out a final result, and obtaining a result through another parameter: and matching the photos and the weights at different angles, and screening error information.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711234552.9A CN107742383B (en) | 2017-11-30 | 2017-11-30 | Automatic settlement system and method based on smooth surface imaging |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711234552.9A CN107742383B (en) | 2017-11-30 | 2017-11-30 | Automatic settlement system and method based on smooth surface imaging |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107742383A CN107742383A (en) | 2018-02-27 |
CN107742383B true CN107742383B (en) | 2020-10-23 |
Family
ID=61238700
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711234552.9A Active CN107742383B (en) | 2017-11-30 | 2017-11-30 | Automatic settlement system and method based on smooth surface imaging |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107742383B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113111800A (en) * | 2021-04-19 | 2021-07-13 | 北京每日优鲜电子商务有限公司 | Commodity shelf-loading judging method and device for unmanned container and storage medium |
CN115601027B (en) * | 2022-12-12 | 2023-04-21 | 临沂中科英泰智能科技有限责任公司 | Self-service retail cashing system and method based on big data |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CA2179338C (en) * | 1995-08-07 | 2000-04-25 | Gordon Albert Thomas | Apparatus and method for spectroscopic product recognition and identification |
DE10313191A1 (en) * | 2003-03-25 | 2004-10-07 | Gutehoffnungshütte Radsatz Gmbh | Method for contactless, dynamic detection of the profile of a solid |
US7337960B2 (en) * | 2004-02-27 | 2008-03-04 | Evolution Robotics, Inc. | Systems and methods for merchandise automatic checkout |
RU2386956C1 (en) * | 2008-08-04 | 2010-04-20 | Виктор Яковлевич Маклашевский | Radiooptical endoscope |
CN104463167B (en) * | 2014-11-20 | 2017-08-25 | 中国科学院上海微系统与信息技术研究所 | A kind of dining room automatic settlement method and system |
CN104616183B (en) * | 2015-01-27 | 2017-11-07 | 杨芳 | Network trading identification system, client and discrimination method |
CN106934692B (en) * | 2017-03-03 | 2020-12-22 | 陈维龙 | Article information processing system, method and device |
-
2017
- 2017-11-30 CN CN201711234552.9A patent/CN107742383B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN107742383A (en) | 2018-02-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
KR102579783B1 (en) | Vision inspection system by using remote learning of product defects image | |
US11587195B2 (en) | Image processing methods and arrangements useful in automated store shelf inspections | |
US11189044B2 (en) | Method and device for detecting object stacking state and intelligent shelf | |
US10832436B2 (en) | Method, system and apparatus for recovering label positions | |
US9477955B2 (en) | Automatic learning in a merchandise checkout system with visual recognition | |
EP2843590B1 (en) | System and method for package dimensioning | |
US10229301B2 (en) | Optical code reading system with dynamic image regionalization | |
US8939369B2 (en) | Exception detection and handling in automated optical code reading systems | |
KR20190031431A (en) | Method and system for locating, identifying and counting articles | |
CN109357630A (en) | A kind of polymorphic type batch workpiece vision measurement system and method | |
US20130048722A1 (en) | Methods and arrangements for sensing identification information from objects | |
US11055659B2 (en) | System and method for automatic product enrollment | |
CN109040539B (en) | Image acquisition device, goods shelf and image identification method | |
JP2019133232A (en) | Commodity management server, automated register system, commodity management program and commodity management method | |
CN107742383B (en) | Automatic settlement system and method based on smooth surface imaging | |
CN111160450A (en) | Fruit and vegetable weighing method based on neural network, storage medium and device | |
US11450024B2 (en) | Mixed depth object detection | |
US11107238B2 (en) | Method, system and apparatus for detecting item facings | |
US20200380454A1 (en) | Method, System and Apparatus for Detecting Product Facings | |
CN110751780A (en) | Goods detection system based on RFID and detection method thereof | |
US11328140B2 (en) | Method for accurate object tracking with color camera in multi planar scanners | |
US11158075B2 (en) | Method, system and apparatus for depth sensor artifact removal | |
CN112489240B (en) | Commodity display inspection method, inspection robot and storage medium | |
RU2574806C2 (en) | Method and system for identifying product | |
WO2024054784A1 (en) | Image analysis methods and arrangements |
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 |