CN108806086B - Columnar commodity identification system and method - Google Patents
Columnar commodity identification system and method Download PDFInfo
- Publication number
- CN108806086B CN108806086B CN201810880383.4A CN201810880383A CN108806086B CN 108806086 B CN108806086 B CN 108806086B CN 201810880383 A CN201810880383 A CN 201810880383A CN 108806086 B CN108806086 B CN 108806086B
- Authority
- CN
- China
- Prior art keywords
- tray
- trays
- columnar
- commodity
- camera
- 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
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000005516 engineering process Methods 0.000 claims abstract description 9
- 238000004891 communication Methods 0.000 claims description 18
- 230000005484 gravity Effects 0.000 claims description 12
- 235000013361 beverage Nutrition 0.000 description 7
- 238000012545 processing Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- ATJFFYVFTNAWJD-UHFFFAOYSA-N Tin Chemical compound [Sn] ATJFFYVFTNAWJD-UHFFFAOYSA-N 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000013136 deep learning model Methods 0.000 description 2
- 239000011521 glass Substances 0.000 description 2
- 238000003909 pattern recognition Methods 0.000 description 2
- 235000016795 Cola Nutrition 0.000 description 1
- 244000228088 Cola acuminata Species 0.000 description 1
- 235000011824 Cola pachycarpa Nutrition 0.000 description 1
- CDBYLPFSWZWCQE-UHFFFAOYSA-L Sodium Carbonate Chemical compound [Na+].[Na+].[O-]C([O-])=O CDBYLPFSWZWCQE-UHFFFAOYSA-L 0.000 description 1
- XAGFODPZIPBFFR-UHFFFAOYSA-N aluminium Chemical compound [Al] XAGFODPZIPBFFR-UHFFFAOYSA-N 0.000 description 1
- 229910052782 aluminium Inorganic materials 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 235000013405 beer Nutrition 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 229910003460 diamond Inorganic materials 0.000 description 1
- 239000010432 diamond Substances 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000001771 impaired effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000012856 packing Methods 0.000 description 1
- 239000004033 plastic Substances 0.000 description 1
- 235000013606 potato chips Nutrition 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07F—COIN-FREED OR LIKE APPARATUS
- G07F11/00—Coin-freed apparatus for dispensing, or the like, discrete articles
- G07F11/02—Coin-freed apparatus for dispensing, or the like, discrete articles from non-movable magazines
- G07F11/28—Coin-freed apparatus for dispensing, or the like, discrete articles from non-movable magazines in which the magazines are inclined
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/08—Payment architectures
- G06Q20/18—Payment architectures involving self-service terminals [SST], vending machines, kiosks or multimedia terminals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/00174—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys
- G07C9/00563—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys using personal physical data of the operator, e.g. finger prints, retinal images, voicepatterns
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/00174—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys
- G07C9/00896—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys specially adapted for particular uses
- G07C9/00912—Electronically operated locks; Circuits therefor; Nonmechanical keys therefor, e.g. passive or active electrical keys or other data carriers without mechanical keys specially adapted for particular uses for safes, strong-rooms, vaults or the like
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07G—REGISTERING THE RECEIPT OF CASH, VALUABLES, OR TOKENS
- G07G1/00—Cash registers
- G07G1/0036—Checkout procedures
- G07G1/0045—Checkout procedures with a code reader for reading of an identifying code of the article to be registered, e.g. barcode reader or radio-frequency identity [RFID] reader
- G07G1/0054—Checkout procedures with a code reader for reading of an identifying code of the article to be registered, e.g. barcode reader or radio-frequency identity [RFID] reader with control of supplementary check-parameters, e.g. weight or number of articles
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Multimedia (AREA)
- Details Of Rigid Or Semi-Rigid Containers (AREA)
Abstract
The invention relates to a columnar commodity identification system and a columnar commodity identification method, wherein the columnar commodity identification system comprises a first camera; and a first set of trays comprising staggered multi-layered trays; wherein the first camera is capable of capturing at least a portion of each tray of the first set of trays. According to the novel commodity identification system and the novel commodity identification method, the plurality of columnar commodities are identified based on the image identification technology through the matched use of the camera and the tray. The invention has high recognition rate of columnar commodity, can ensure the accuracy of recognition, and is safe and reliable.
Description
Technical Field
The invention relates to the technical field of identification, in particular to a columnar commodity identification system and method based on an image pick-up device.
Background
When the automatic vending machine sells columnar commodities such as beverages, the process is complicated, and the failure rate is high. The existing intelligent container often identifies columnar commodities such as beverages by adding RFID tags on the outer packaging of the beverages. However, RFID tags are disposable themselves and adding RFID tags to beverage outer packages is time consuming and labor intensive, which increases costs.
Disclosure of Invention
Aiming at the technical problems in the prior art, the invention provides a columnar commodity identification system and a columnar commodity identification method, which save time and cost for identifying columnar objects and improve identification accuracy.
One aspect of the present invention provides a column-shaped article identification system comprising: a first camera; and a first set of trays comprising staggered multi-layered trays; wherein the first camera is capable of capturing at least a portion of each tray of the first set of trays.
The system as described above, wherein the plurality of trays of the first set of trays comprises a first tray and a second tray, the first tray being positioned lower than the second tray, wherein the first tray protrudes at least 40-140mm towards the first camera compared to the second tray.
A system as above wherein the angle of the first tray and the second tray corresponds to any one of: the included angle of the second tray relative to the horizontal is equal to the included angle of the first tray relative to the horizontal; the included angle of the second tray relative to the horizontal is 5-10 degrees larger than the included angle of the first tray relative to the horizontal; and the included angle of the second tray relative to the horizontal is 2 times that of the first tray.
The system as described above wherein the lowermost tray of said multi-layered trays of the first set of trays is at an angle of 0-30 ° to the horizontal, preferably 5-10 °.
The system as described above, wherein the multi-layered tray of the first set of trays comprises a third tray positioned above the second tray, the second tray protruding at least 40-140mm toward the first camera direction as compared to the third tray.
A system as above wherein the angle of the third tray and the second tray corresponds to any one of: the included angle of the second tray relative to the horizontal is equal to the included angle of the first tray relative to the horizontal; the included angle of the third tray relative to the horizontal is 5-10 degrees larger than the included angle of the second tray relative to the horizontal; and the angle of the third tray relative to the horizontal is 2 times that of the second tray.
The system as described above, wherein the multi-layer trays of the first set of trays comprise one or more first length trays and one or more second length trays, wherein the first length trays are longer than the second length trays and the one or more second length trays are located above the one or more first length trays.
The system as described above, further comprising: a processor, coupled to the first camera, configured to identify a columnar commodity in an image from the first camera; and a communication interface, coupled to the processor, configured to transmit the columnar commodity identification result from the processor to the server.
The system as described above, further comprising: a processor coupled to the first camera configured to receive an image from the first camera; and a communication interface, coupled to the processor, configured to further transmit the image from the first camera to the server.
The system as described above, further comprising: a plurality of gravity sensors disposed below each tray in the first set of trays.
The system as described above, further comprising: a second camera; and a second set of trays comprising staggered multi-layered trays; wherein the second camera is capable of capturing at least a portion of each tray of the second set of trays.
According to another aspect of the invention, an intelligent container is provided, comprising a column-like article identification system as described in any of the above.
The intelligent container as described above, further comprising a plurality of sets of brackets disposed on the inner wall, the plurality of sets of brackets having different heights.
An intelligent container as described above, wherein the angle of at least one of the plurality of sets of brackets is adjustable.
An intelligent container as described above, wherein the sides of at least one tray include multiple sets of angularly distinct connectors corresponding to at least one set of brackets.
An intelligent container as described above, wherein the at least one set of brackets includes a bracket for a first length of pallet and a bracket for a second length of pallet.
An intelligent container as described above, wherein one or more of the trays in the at least one set of trays can be used for both the first length tray and the second length tray.
According to another aspect of the present invention, there is provided a column-shaped article identification method, comprising: acquiring images of columnar commodities, wherein the columnar commodities are placed on staggered multi-layer trays; identifying the columnar commodity according to the image of the columnar commodity; and based at least in part on the identification result of the columnar commodity, the type and number of columnar commodity obtained.
The method as described above, further comprising: the weight of the columnar commodity was obtained.
According to another aspect of the invention, a method of generating an order with an intelligent container is presented, comprising: acquiring information of unlocking a cabinet door; acquiring information of locking of a cabinet door; obtaining the types and the quantity of column-shaped commodities in the cabinet; wherein the type and number of the column-shaped commodities in the cabinet are obtained at least partially according to the images of the column-shaped commodities in the cabinet; obtaining the types and the quantity of columnar commodities taken by a user; generating an order; the images of the columnar commodities in the cabinet comprise multiple layers of columnar commodities, and the multiple layers of columnar commodities are placed on multiple layers of trays which are staggered.
According to the novel commodity identification system and the novel commodity identification method, the plurality of columnar commodities are identified based on the image identification technology through the matched use of the camera and the tray. The invention has high recognition rate on the columnar commodity, can ensure the accuracy of recognition, and is safe and reliable.
Drawings
Preferred embodiments of the present invention will be described in further detail below with reference to the attached drawing figures, wherein:
FIG. 1 is a schematic diagram of a column-shaped article identification system according to one embodiment of the invention;
FIG. 2 is a block diagram of a column-shaped article identification system according to one embodiment of the invention;
FIG. 3 is a schematic diagram of a column-shaped article identification system according to one embodiment of the invention;
FIG. 4 is a schematic view of the structure of a container including a column-shaped article identification system according to one embodiment of the invention;
FIG. 5 is a flow chart of a method of identifying cylindrical items according to one embodiment of the invention; and
FIG. 6 is a flow chart of a method of generating an order with a smart container according to one embodiment of the invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the following detailed description, reference is made to the accompanying drawings, which form a part hereof, and in which is shown by way of illustration specific embodiments of the application. In the drawings, like reference numerals describe substantially similar components throughout the different views. Various specific embodiments of the application are described in sufficient detail below to enable those skilled in the art to practice the teachings of the application. It is to be understood that other embodiments may be utilized or structural, logical, or electrical changes may be made to embodiments of the present application.
The present invention provides a new commodity identification system and a new commodity identification method, which are based on an image identification technology instead of an RFID technology, and identify a plurality of columnar commodities. The method has high recognition rate, can ensure the accuracy of recognition, and is safe and reliable.
By "cylindrical commodity" is meant herein a commodity having a generally cylindrical shape, including but not limited to aluminum cans, rubber bottles, glass bottles, paper-packaged beverages, foods, commodities, etc., such as tin beer, tin colas, rubber bottle pulses, glass bottles North ice soda, paper-case-packaged consumer potato chips, and the like. The columnar commodity can be a cylinder, a cuboid, a conical body or even a strip-shaped packing box with a round, square, diamond, triangle or polygon cross section. In some embodiments, the columnar commodity may be divided into a first length columnar commodity by length, with a length in the range of 12-30 cm; and a second length columnar commodity having a length in the range of 2-12 cm.
It will be appreciated by those skilled in the art that the first length column of merchandise and the second length column of merchandise may be divided in different ways, such as by finding the appropriate dividing point between 8 cm and 14 cm, and such ways are within the scope of the present invention.
It will also be appreciated by those skilled in the art that although the background art mentions a need in the art for identifying beverage products; however, it will be appreciated from the definition of cylindrical commodity, that the scope of application of the present invention is not limited to beverages, but extends to all commodity whose shape is generally cylindrical.
By "identifying" is meant herein a determination of a change in one or both of the quantity, type, or both of the columnar goods. For example, if a user has removed a columnar commodity from a smart container, a change in one or both of the number, type, or both of the columnar commodity before and after removal from the smart container can be confirmed by "identification".
Fig. 1 is a schematic structural view of a column-shaped article recognition system according to an embodiment of the present invention. As shown in fig. 1, the identification system 100 includes a camera 101 and a set of trays 102. The set of trays 102 includes staggered multi-layer trays 103-107. At least a portion of each of the trays 103-107 may be viewed from the camera 101. That is, although the tray at the upper layer among the respective trays in the group of trays 102 shields a part of the tray at the lower layer, the camera 101 can observe at least a part of the columnar commodity on the respective trays after the respective trays discharge the columnar commodity. In some embodiments of the present invention, camera 101 may be any device capable of capturing images or video. The shooting angle of the camera 101 is greater than 90 °; preferably, the camera 101 has an angle of capture greater than 120 °. The tray 102 may be any form of article capable of holding cylindrical items, including, but not limited to, shelves, brackets, plastic boxes, and the like.
Fig. 2 is a block diagram of a column-like article identification system according to one embodiment of the invention, as shown, the identification system 100 further includes a processor 108 coupled to the camera 101 for processing images from the camera 101. For example, the processor 108 may identify the number and type of cylindrical goods in the image by processing the image from the camera 101. Any image recognition technique known in the art may be applied to the processor 108 for recognizing cylindrical merchandise in an image.
In some embodiments, the processor 108 identifies only the number and location of the columnar merchandise, and determines the type of columnar merchandise based on the location of the columnar merchandise. In other embodiments, the processor 108 identifies the number of cylindrical shaped articles while also identifying the type of cylindrical shaped article by a shape, pattern, color, or combination thereof on the outer package of cylindrical shaped articles. The above are just two specific examples of image recognition. Those skilled in the art will appreciate that there are other ways of image recognition that may be employed for the type of columnar goods and that such ways are also included within the scope of the present invention.
In some embodiments, the processor 108 includes a memory for storing the results of the image recognition. The change in the columnar commodity in the area captured by the camera 101 can be understood by comparing the recognition result for the image from the camera 101 with the previously stored image recognition result.
As shown in fig. 2, the identification system 101 further comprises a communication interface 109. The communication interface 109 may communicate with a server over a communication network. The communication interface 109 can send the identified changes to the columnar merchandise to the server. The server may generate an order based on the change in the columnar merchandise.
In some embodiments, identifying the columnar merchandise in the image may be performed at the server side. The processor 108 obtains an image of the columnar commodity from the camera 101. The processor 108 may perform some processing on the image including, but not limited to: adjusting contrast, adjusting pixel size, adjusting color, normalizing, image compression, etc.; the processed image is then forwarded to the communication interface 109. In some cases, the processor 108 may also forward the image from the camera 101 directly to the communication interface 109 without any processing. The communication interface 109 may transmit the image to the server using a communication network. The server identifies the columnar commodity in the image by using an image identification technology. These techniques include, but are not limited to: pattern recognition technologies such as deep learning model-based, pattern comparison technology-based, three-dimensional lattice technology-based and the like. Any image recognition technique known in the art can be applied to the server for recognizing the columnar goods in the image. The processor 108 can include one or more Central Processing Units (CPUs), graphics Processing Units (GPUs), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs), or combinations thereof. The processor 108 is capable of executing software or computer readable instructions stored in the memory 205 to perform the methods or operations described herein. The processor 108 can be implemented in a number of different ways. For example, the processor 108 can include one or more embedded processors, processor cores, microprocessors, logic circuits, hardware Finite State Machines (FSMs), digital Signal Processors (DSPs), or combinations thereof.
The communication interface 109 can include one or more wired or wireless communication interfaces. Such as a communications interface network interface card, a wireless modem, or a wired modem. In one application, the communication interface 109 can be a WiFi modem. In other applications, the communication interface 109 can be a 3G modem, a 4G modem, an LTE modem, a bluetooth component, a radio frequency receiver, an antenna, or a combination thereof.
As shown in fig. 2, the identification system 100 further includes a gravity sensor 110. A gravity sensor 110 is mounted below the trays 103-107 to detect weight changes of the column of merchandise on each tray. A gravity sensor 110 is also coupled to the processor 108. The detection result of the gravity sensor 110 may assist the recognition result based on the camera 101, thereby improving the accuracy of recognition.
Fig. 3 is a schematic diagram of a column-shaped article identification system according to one embodiment of the invention, as shown in fig. 3, in some embodiments the identification system 100 further includes a camera 111 and a set of trays 112. The set of trays 112 includes multiple layers of staggered trays 113-116. At least a portion of each of the trays 113-116 may be viewed from camera 111. The camera 111 is connected to the processor 108. In some embodiments, as shown in FIG. 2, a gravity sensor 117 may be included below the trays 113-116. The gravity sensor 117 is connected to the processor 108. Other similarities to those between camera 101 and trays 103-107 are not described in detail herein.
According to one embodiment of the invention, the identification system 100 may be applied in an intelligent container. When a user wishes to purchase a commodity in an intelligent container, the door of the intelligent container first needs to be unlocked. For example, a user may use a mobile terminal to scan an identification code on a smart container and then log into a server using the mobile terminal. After successful login, if the user meets the conditions, the server instructs the intelligent container to unlock the cabinet door. It will be appreciated by those skilled in the art that the above is only one way of unlocking a cabinet door. Other ways, such as scanning the identity of the user's mobile terminal, scanning the user's fingerprint, scanning the user's palm print, scanning the user's iris, scanning the user's face, etc., may also be used to unlock the doors of the intelligent container. After the cabinet door of the intelligent container is unlocked, a user can open the cabinet door and take the columnar commodity in the intelligent container. When the user closes the cabinet door, the identification system 100 in the intelligent cabinet identifies the remaining cylindrical commodity in the intelligent cabinet. Thus, the columnar commodity taken by the user can be determined by comparing with the columnar commodity before the user opens the cabinet door. The columnar commodity information taken by the user is transmitted to the server by the communication interface 109. And the server generates an order according to the commodity fetched by the user. After the user pays the amount of the order, shopping by using the intelligent container once is completed.
Because the recognition rate of the camera to the columnar commodity is very high, even if the multi-layer tray is shielded, the camera can still recognize the columnar commodity very accurately. In order to improve the use efficiency of the space in the intelligent container, the columnar commodities are stored as much as possible without affecting the identification accuracy, and examples of multi-layer tray arrangement are given in the following embodiments of the invention.
Referring to a group of trays 102 in fig. 1, i.e. multi-layered trays 103-107, the lower tray is positioned at a certain distance in the direction of the cabinet door as compared to the upper tray. In some embodiments, this protrusion distance is 40-140mm, preferably 60-120mm, more preferably 80-100mm. Therefore, the size of the part of the tray, which is not shielded by the columnar commodity, in the visual field of the camera 101 is ensured, and the user can conveniently take the columnar commodity after observing the columnar commodity and opening the cabinet door. According to one embodiment of the invention, the camera 101 is located above the set of trays 102 near the middle of the cabinet door. Further, the camera's pick-up angle is directed toward the set of trays 102. So that the camera 101 can have the best field of view.
The lower tray may have the same inclination angle as the upper tray in terms of space. Or in the multi-layered tray, the tray under has the same inclination angle. In some embodiments, referring to a set of trays 102 in fig. 1, namely, multi-layered trays 103-107, the lower-layered trays are positioned at a smaller angle to the horizontal than the upper-layered trays. In other words, the multi-layered trays 103-107 are inclined more and more upwards from bottom to top. In one example of the invention, the lowermost tray is at an angle of 0-30, preferably 5-10, to the horizontal. From the lowest level, each level of trays increases in angle by 5-10 ° compared to its next level of trays. For example, the multi-layered trays 103-107 may be angled at 10 °,20 °, 30 °, 40 °, and 50 ° to the horizontal. In another example of the present invention, the lowermost tray is at an angle of 5-10 ° to the horizontal. Each layer of trays doubles in angle from the lowest layer compared to its next layer. For example, the multi-layered trays 113-116 may be angled at 5, 10, 20, and 40 with respect to horizontal.
Referring to a group of trays 102 in fig. 1, i.e., multi-layered trays 103-107, the multi-layered trays 103-107 may be divided into first length trays 103-105 for different lengths of the column-shaped articles to be accommodated; and second length trays 106 and 107; wherein, the first length tray 103-105 is used for containing columnar commodities with a first length, and the length range of the first length tray is 2-14 cm; the second length trays 106 and 107 are for holding second length cylindrical goods, which range in length from 12 cm to 40 cm.
It will be appreciated by those skilled in the art that the first length tray and the second length tray may be divided differently, for example, by finding the appropriate dividing point between 10 cm and 15 cm, and that such classification is within the scope of the present invention.
The invention has the advantage that the cylindrical commodity or the tray is classified according to the length, and the closer to the camera, the cylindrical commodity has a more inclined angle so as to be convenient for the camera to recognize. However, a larger angle of the columnar commodity deviating from the horizontal means that the larger the distance of the vertical space occupied by the columnar commodity in the intelligent container is, so that the number of layers of the tray capable of being placed is smaller, and the number of the placed commodities is smaller. In order to put more commodities, the second-length tray with smaller length is placed at a position close to the camera, namely a position higher than the position in the multi-layer tray, so that more commodities can be put.
According to one embodiment of the invention, the number of the first length trays which can be covered by one camera is 3-6 layers; preferably 4-5 layers. According to another embodiment of the invention, one camera may cover 2-5 layers of first length trays and 1-4 layers of second length trays; preferably 3-4 layers of first length trays and 2-3 layers of second length trays.
FIG. 4 is a schematic view of the structure of a container including a column-shaped article identification system according to one embodiment of the invention. As can be seen from fig. 4, after placing the columnar goods, the user can easily distinguish the columnar goods even when viewing from the front, and thus the convenience of use is not impaired. Further, as can also be seen from FIG. 2, the space utilization within the intelligent cabinet is very high. Compared with the traditional automatic vending machine, the number of columnar commodities which can be stored in the intelligent container can be doubled; moreover, the shopping mode of the intelligent container enables a user to contact the commodity more directly, so that better shopping experience is brought. This innovation can be similar to the change from traditional over-the-counter shopping to open supermarket shopping.
Referring to FIG. 4, the intelligent cabinet 200 includes two liners 201 and 202. In the first bladder 201, the camera 101 covers the multi-layered trays 103-107; wherein trays 103-105 are first length trays and trays 106-107 are second length trays. In the liner 202, the camera 101 covers the first length trays 113-116. The first liner 201 includes a plurality of sets of brackets mounted on an inner wall thereof. The sets of brackets have different heights. The trays may be arranged on a set of brackets so as to be positioned at different heights. In some embodiments, the angle of at least a portion of the set of brackets is adjustable. In other embodiments, the angle of the tray cannot be adjusted, but multiple sets of different angle connectors are included on the sides of the tray corresponding to the tray, thereby positioning the tray at different angles. In a more specific example, the set of brackets is a corresponding set of protrusions on the liner, and the sides of the tray include angled slots. Different angles of the tray can be realized by putting the protrusions on the liner into different sliding grooves. In another more specific embodiment, the tray is secured to the bracket by screws passing through securing holes in the tray.
In some embodiments, one or more sets of trays near the camera 101 or 102 include trays for a first length of trays, and may also include trays for a second length of trays. Or some of the one or more sets of trays may be used for both the first length of trays and the second length of trays. According to one embodiment of the invention, the load bearing of the set of carriages is between 5 and 10 kg. By the arrangement of multiple sets of brackets, trays of a first length and/or trays of a second length can be flexibly placed in the intelligent cabinet 200, thereby bringing a lot of flexibility for the use of the intelligent cabinet.
By utilizing the columnar commodity identification system, referring to the embodiment of the intelligent container, a columnar commodity identification mode with more flexibility and lower cost can be realized; moreover, the identification mode of the invention has high identification accuracy and can basically realize zero error. The matching of the gravity sensor can also have the function of preventing empty bottles from being confused.
Fig. 5 is a flowchart of a column-shaped article identification method according to an embodiment of the present invention. The columnar commodity identification method can be executed on a server or a processor local to the intelligent container.
As shown, the column-shaped article identification method 300 includes: at step 310, an image of a columnar commodity is acquired, wherein the columnar commodity is placed on a staggered multi-layered tray. That is, the camera may view at least a portion of each of the multiple trays. As previously indicated, the multi-layered trays may have a certain distance offset and may have different inclination angles. The multi-layered tray may include a first length tray and a second length tray, wherein the second length tray is above the first length tray.
In step 320, the columnar commodity is identified from the image of the columnar commodity. Those skilled in the art will appreciate that existing image recognition means, including but not limited to, pattern recognition techniques based on deep learning models, based on graphic comparison techniques, based on three-dimensional lattice techniques, etc., may be applied to the present invention to obtain a columnar commodity included in a columnar commodity image from a camera.
In step 330, the weight of the columnar commodity is obtained. Step 330 is optional. In the case of a gravity sensor, data from the gravity sensor may be acquired for assisting in the identification, in particular the identification of empty bottles on the tray.
In step 340, the type and number of the obtained columnar commodity are identified according to the result of step 320. In some embodiments, the image recognition recognizes only the number and location of the columnar commodity, and the kind of the columnar commodity is determined according to the location of the columnar commodity. In other embodiments, the image recognition identifies the type of the columnar commodity by a shape, pattern, color, or combination thereof on the outer package of the columnar commodity while obtaining the number of the columnar commodity. In the case where step 330 is included, weight data from the gravity sensor may also be used to assist in the identification of the type and quantity of columnar merchandise.
FIG. 6 is a flow chart of a method of generating an order with a smart container according to one embodiment of the invention. As shown, the method 400 of generating an order with an intelligent container includes the steps of:
In step 410, information is obtained that the door is unlocked. The user unlocking the cabinet door means the start of a shopping. In step 420, information about the locking of the door is obtained. The user locking the cabinet door means the end of one shopping. At step 430, after the cabinet door is locked, the type and number of column-shaped commodities in the cabinet are obtained; wherein, the type and the number of the column-shaped commodities in the cabinet are obtained at least partially according to the images of the column-shaped commodities in the cabinet through image recognition. In step 440, the type and number of the columnar commodity after the cabinet door is locked is compared with the type and number of the columnar commodity before the cabinet is unlocked, so as to obtain the type and number of the columnar commodity taken by the user. At step 450, an order is generated based on the type and quantity of columnar merchandise that the user has taken. After the user pays the amount of the order, the intelligent container shopping is completed. In some embodiments, the method 400 of generating an order for an intelligent container is performed on a server. In other embodiments, the method 400 of generating an order for an intelligent container may also be performed on an intelligent container.
The above embodiments are provided for illustrating the present invention and not for limiting the present invention, and various changes and modifications may be made by one skilled in the relevant art without departing from the scope of the present invention, therefore, all equivalent technical solutions shall fall within the scope of the present disclosure.
Claims (19)
1. A column-like article identification system comprising:
A first camera; and
A first set of trays comprising a plurality of trays arranged in a staggered arrangement such that at least a portion of each columnar commodity on each tray is unobstructed;
The first camera can capture at least one part of each tray in the first group of trays to obtain an image of each columnar commodity on each tray; identifying a plurality of columnar commodities based on an image identification technology;
The multi-layer tray of the first group of trays comprises a first tray and a second tray, the position of the first tray is lower than that of the second tray, and the first tray protrudes at least 40-140mm towards the first camera compared with the second tray;
the multi-layer trays of the first set of trays include one or more first length trays and one or more second length trays, wherein the first length trays are longer than the second length trays and the one or more second length trays are located above the one or more first length trays.
2. The system of claim 1, wherein the angle of the first tray and the second tray corresponds to any one of:
the included angle of the second tray relative to the horizontal is equal to the included angle of the first tray relative to the horizontal;
The included angle of the second tray relative to the horizontal is 5-10 degrees larger than the included angle of the first tray relative to the horizontal; and
The angle of the second tray relative to the horizontal is 2 times that of the first tray.
3. The system of claim 1, wherein the lowermost tray of the plurality of trays of the first set of trays is angled from horizontal by 0-30 °.
4. The system of claim 1, wherein the multi-layered trays of the first set of trays include a third tray positioned above the second tray, the second tray protruding at least 40-140mm toward the first camera compared to the third tray.
5. The system of claim 4, wherein the angle of the third tray and the second tray corresponds to any one of:
the included angle of the second tray relative to the horizontal is equal to the included angle of the first tray relative to the horizontal;
the included angle of the third tray relative to the horizontal is 5-10 degrees larger than the included angle of the second tray relative to the horizontal; and
The angle of the third tray relative to the horizontal is 2 times that of the second tray.
6. The system of claim 1, further comprising:
a processor, coupled to the first camera, configured to identify a columnar commodity in an image from the first camera; and
And the communication interface is connected with the processor and is configured to send the columnar commodity identification result from the processor to the server.
7. The system of claim 1, further comprising:
a processor coupled to the first camera configured to receive an image from the first camera; and
A communication interface, coupled to the processor, configured to further transmit the image from the first camera to the server.
8. The system of claim 1, further comprising: a plurality of gravity sensors disposed below each tray in the first set of trays.
9. The system of claim 1, further comprising:
a second camera; and
A second set of trays comprising staggered multi-layered trays;
Wherein the second camera is capable of capturing at least a portion of each tray of the second set of trays.
10. A system according to claim 3, wherein the lowermost tray of the plurality of trays of the first set of trays is at an angle of 5-10 ° to horizontal.
11. An intelligent container comprising the columnar commodity identification system of any one of claims 1-10.
12. The intelligent container of claim 11, further comprising a plurality of sets of brackets disposed on the inner wall, the plurality of sets of brackets having different heights.
13. The intelligent container of claim 12, wherein an angle of at least one of the plurality of sets of brackets is adjustable.
14. The intelligent container of claim 12, wherein the sides of at least one tray include multiple sets of angularly distinct connectors corresponding to at least one set of brackets.
15. The intelligent container of claim 12, wherein at least one set of brackets includes a bracket for a first length of tray and a bracket for a second length of tray.
16. The intelligent container of claim 12, wherein one or more of the at least one set of brackets can be used for both the first length of trays and the second length of trays.
17. A cylindrical commodity identification method, characterized in that it adopts the cylindrical commodity identification system according to any one of claims 1-10, comprising:
acquiring images of columnar commodities, wherein the columnar commodities are placed on staggered multi-layer trays;
identifying the columnar commodity according to the image of the columnar commodity; and
Based at least in part on the identification of the columnar merchandise, the type and quantity of columnar merchandise obtained.
18. The method of claim 17, further comprising: the weight of the columnar commodity was obtained.
19. A method of generating an order with an intelligent container, using an intelligent container as claimed in any one of claims 11-16, comprising:
acquiring information of unlocking a cabinet door;
Acquiring information of locking of a cabinet door;
obtaining the types and the quantity of column-shaped commodities in the cabinet; wherein the type and number of the column-shaped commodities in the cabinet are obtained at least partially according to the images of the column-shaped commodities in the cabinet;
Obtaining the types and the quantity of columnar commodities taken by a user; and
Generating an order;
the images of the columnar commodities in the cabinet comprise multiple layers of columnar commodities, and the multiple layers of columnar commodities are placed on multiple layers of trays which are staggered.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810880383.4A CN108806086B (en) | 2018-08-03 | 2018-08-03 | Columnar commodity identification system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810880383.4A CN108806086B (en) | 2018-08-03 | 2018-08-03 | Columnar commodity identification system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108806086A CN108806086A (en) | 2018-11-13 |
| CN108806086B true CN108806086B (en) | 2024-05-03 |
Family
ID=64079251
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810880383.4A Active CN108806086B (en) | 2018-08-03 | 2018-08-03 | Columnar commodity identification system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108806086B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7206104B2 (en) * | 2018-12-14 | 2023-01-17 | 東芝テック株式会社 | Wireless tag reader and program |
| CN110415464A (en) * | 2019-08-05 | 2019-11-05 | 李志高 | The method and apparatus for identifying commodity by multiple force snesor |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| ES252570A3 (en) * | 1959-09-25 | 1960-07-01 | Lepez Casado Dolores | Improvements in the construction of automated machines suppliers of items (Machine-translation by Google Translate, not legally binding) |
| US5728999A (en) * | 1994-06-14 | 1998-03-17 | Advanced Retail Systems Ltd. | Vending machine, a vending system and methods for operating same |
| JPH1175967A (en) * | 1997-09-12 | 1999-03-23 | Nohmi Bosai Ltd | Monitoring rack |
| CN2457926Y (en) * | 2001-01-10 | 2001-11-07 | 刘财友 | Goodsshelves |
| CN101770666A (en) * | 2009-12-21 | 2010-07-07 | 秦斌 | Bicycle leasing storage cabinet and leasing management system and method |
| JP2012155513A (en) * | 2011-01-26 | 2012-08-16 | Seiko Epson Corp | Automatic vending machine |
| JP2014026079A (en) * | 2012-07-26 | 2014-02-06 | Kyocera Document Solutions Inc | Sheet conveying device, and image forming apparatus including the same |
| WO2016181480A1 (en) * | 2015-05-12 | 2016-11-17 | 株式会社日立製作所 | Storage rack and picking system |
| CN205939921U (en) * | 2016-07-30 | 2017-02-08 | 杭州炬卡太阳能科技有限公司 | Automatic discernment and hotel's refrigerator that charges |
| WO2017030177A1 (en) * | 2015-08-20 | 2017-02-23 | 日本電気株式会社 | Exhibition device, display control device and exhibition system |
| CN107545381A (en) * | 2016-06-24 | 2018-01-05 | 北京京东尚科信息技术有限公司 | Manage the method and warehouse management system of warehouse inventory |
| JP2018045669A (en) * | 2016-09-12 | 2018-03-22 | 沖電気工業株式会社 | Production navigation system, support system therefor, and data management method |
| CN108171876A (en) * | 2017-12-01 | 2018-06-15 | 虫极科技（北京）有限公司 | Self-service counter, system and its good selling method |
| CN108320379A (en) * | 2018-02-28 | 2018-07-24 | 成都果小美网络科技有限公司 | Good selling method, device and the self-service machine compared based on image |
| CN208888938U (en) * | 2018-08-03 | 2019-05-21 | 虫极科技（北京）有限公司 | A kind of columnar goods identifying system and Intelligent cargo cabinet |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU2003251664A1 (en) * | 2003-07-29 | 2005-02-25 | Dometic Gmbh | Computerised-sensing system for a mini bar |
| JP5170554B2 (en) * | 2008-09-29 | 2013-03-27 | 株式会社ダイフク | Learning device in article storage facility |
| ES1077250Y (en) * | 2012-04-18 | 2012-09-18 | Crambo Sa | SALE MACHINE WITH TRANSLATED LCD ELEMENT INCORPORATED |
| US10453046B2 (en) * | 2014-06-13 | 2019-10-22 | Conduent Business Services, Llc | Store shelf imaging system |
| US9928438B2 (en) * | 2016-03-10 | 2018-03-27 | Conduent Business Services, Llc | High accuracy localization system and method for retail store profiling via product image recognition and its corresponding dimension database |
-
2018
- 2018-08-03 CN CN201810880383.4A patent/CN108806086B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| ES252570A3 (en) * | 1959-09-25 | 1960-07-01 | Lepez Casado Dolores | Improvements in the construction of automated machines suppliers of items (Machine-translation by Google Translate, not legally binding) |
| US5728999A (en) * | 1994-06-14 | 1998-03-17 | Advanced Retail Systems Ltd. | Vending machine, a vending system and methods for operating same |
| JPH1175967A (en) * | 1997-09-12 | 1999-03-23 | Nohmi Bosai Ltd | Monitoring rack |
| CN2457926Y (en) * | 2001-01-10 | 2001-11-07 | 刘财友 | Goodsshelves |
| CN101770666A (en) * | 2009-12-21 | 2010-07-07 | 秦斌 | Bicycle leasing storage cabinet and leasing management system and method |
| JP2012155513A (en) * | 2011-01-26 | 2012-08-16 | Seiko Epson Corp | Automatic vending machine |
| JP2014026079A (en) * | 2012-07-26 | 2014-02-06 | Kyocera Document Solutions Inc | Sheet conveying device, and image forming apparatus including the same |
| WO2016181480A1 (en) * | 2015-05-12 | 2016-11-17 | 株式会社日立製作所 | Storage rack and picking system |
| WO2017030177A1 (en) * | 2015-08-20 | 2017-02-23 | 日本電気株式会社 | Exhibition device, display control device and exhibition system |
| CN107545381A (en) * | 2016-06-24 | 2018-01-05 | 北京京东尚科信息技术有限公司 | Manage the method and warehouse management system of warehouse inventory |
| CN205939921U (en) * | 2016-07-30 | 2017-02-08 | 杭州炬卡太阳能科技有限公司 | Automatic discernment and hotel's refrigerator that charges |
| JP2018045669A (en) * | 2016-09-12 | 2018-03-22 | 沖電気工業株式会社 | Production navigation system, support system therefor, and data management method |
| CN108171876A (en) * | 2017-12-01 | 2018-06-15 | 虫极科技（北京）有限公司 | Self-service counter, system and its good selling method |
| CN108320379A (en) * | 2018-02-28 | 2018-07-24 | 成都果小美网络科技有限公司 | Good selling method, device and the self-service machine compared based on image |
| CN208888938U (en) * | 2018-08-03 | 2019-05-21 | 虫极科技（北京）有限公司 | A kind of columnar goods identifying system and Intelligent cargo cabinet |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108806086A (en) | 2018-11-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9741014B2 (en) | Automated asset management system with multiple sensing technologies | |
| CN109166000B (en) | Intelligent container and method for creating order | |
| CN109409291B (en) | Commodity identification method and system of intelligent container and shopping order generation method | |
| JP6222345B2 (en) | POS terminal device, POS system, image processing method and program | |
| CA2690831C (en) | Method and apparatus for assessing characteristics of liquids | |
| WO2016095777A1 (en) | Object security inspection method and system based on object identification tag | |
| CN108806086B (en) | Columnar commodity identification system and method | |
| US20200193404A1 (en) | An automatic in-store registration system | |
| CN103052343A (en) | A Checkout Counter | |
| US10661311B2 (en) | Automated tote routing system and methods | |
| US11328147B1 (en) | Identifying item barcodes | |
| US11393253B1 (en) | Using sensor data to determine activity | |
| US10242522B2 (en) | Electronic locker | |
| WO2017051278A1 (en) | System and method for automatic identification of products | |
| US11080676B2 (en) | Methods and systems for assisting a purchase at a physical point of sale | |
| CN108171876B (en) | Unmanned vending container, system and vending method thereof | |
| JP6552744B2 (en) | Transfer object identification system, transfer object identification method and transfer object identification program | |
| US11922486B2 (en) | Identifying items using cascading algorithms | |
| US20170243068A1 (en) | Method for the computer-aided recognition of a transport container being empty and device for the computer-aided recognition of a transport container being empty | |
| CN110533371B (en) | Intelligent logistics storage system and method of electric power Internet of things equipment with safety device | |
| CN209328138U (en) | A kind of Intelligent cargo cabinet of application image identification device and gravity sensor | |
| CN208888938U (en) | A kind of columnar goods identifying system and Intelligent cargo cabinet | |
| CN104477458B (en) | Efficient signal transmission method based on filling liquid food production | |
| WO2021091481A1 (en) | System for object identification and content quantity estimation through use of thermal and visible spectrum images | |
| CN214955172U (en) | Reusable cup, automatic station for preparing beverage and unmanned beverage service system |
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 |