CN113674049A - Commodity shelf position identification method and system based on picture search and storage medium - Google Patents
Commodity shelf position identification method and system based on picture search and storage medium Download PDFInfo
- Publication number
- CN113674049A CN113674049A CN202110707724.XA CN202110707724A CN113674049A CN 113674049 A CN113674049 A CN 113674049A CN 202110707724 A CN202110707724 A CN 202110707724A CN 113674049 A CN113674049 A CN 113674049A
- Authority
- CN
- China
- Prior art keywords
- commodity
- main body
- commodity main
- image
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000010586 diagram Methods 0.000 claims abstract description 22
- 238000004590 computer program Methods 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 8
- 238000002407 reforming Methods 0.000 claims description 3
- 238000013527 convolutional neural network Methods 0.000 description 8
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000012733 comparative method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013479 data entry Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0639—Item locations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/53—Querying
- G06F16/532—Query formulation, e.g. graphical querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/587—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2219/00—Indexing scheme for manipulating 3D models or images for computer graphics
- G06T2219/004—Annotating, labelling
Abstract
The application provides a commodity shelf position identification method and system based on picture search and a storage medium. The identification method comprises the steps of obtaining a target picture containing a plurality of commodity main body images; acquiring relative position information of a plurality of commodity main body images in a target picture; drawing a distribution area of each commodity main body image in a target picture according to the relative position information of each commodity main body image; and newly forming a relative spatial position graph containing the commodity main body and other commodity main bodies; extracting the identification information of each commodity main body in the distribution area where each commodity main body image is located; searching whether the extracted identification information of the commodity main body exists in a product library; if the commodity main body exists in the product library, the commodity main body is associated with the corresponding relative spatial position diagram and stored in a database; and searching the relative space position map of the commodity body according to the identification information field of the commodity body.
Description
Technical Field
The application relates to the technical field of computers, in particular to a commodity shelf position identification method, system, equipment and storage medium based on picture search.
Background
The picture search technology is becoming more mature, and some technical companies are beginning to apply it to commodity search and commodity management. The commodity search means that a target picture is searched for similar pictures in a product library, and a search result is often a group of product pictures and is commonly used for commodity query of e-commerce websites. The commodity management refers to the commodity batch management that a plurality of target pictures are searched in a product library at the same time and is commonly found in a background system.
At present, the image search technology is only limited to simple application of commodity search, and application of deep scenization is not performed on commodity management. For scenes with very large inventory, such as supermarkets, large-scale stores, shopping malls and the like, commodities need to be displayed on a shelf, the positions of the commodities can be frequently adjusted, and after the positions are adjusted, if the commodity information is updated in a manual mode, time and labor are wasted. How to quickly establish the spatial position positioning during commodity management becomes a problem to be solved urgently in the field of offline article management.
Disclosure of Invention
An object of the embodiments of the present application is to provide a method for identifying a commodity shelf position based on picture search, which can quickly know whether a commodity is on a shelf and a commodity placing position, and is suitable for offline scenized commodity management.
In a first aspect, an embodiment of the present application provides a method for identifying a commodity shelf location based on picture search, including:
acquiring a target picture containing a plurality of commodity main body images;
acquiring relative position information of a plurality of commodity main body images in the target picture;
drawing a distribution area of each commodity main body image in the target picture according to the relative position information of each commodity main body image; and newly forming a relative spatial position graph containing the commodity main body and other commodity main bodies;
extracting the identification information of each commodity main body in the distribution area where each commodity main body image is located;
searching whether the extracted identification information of the commodity main body exists in a product library;
if the commodity main body exists in the product library, the commodity main body is associated with the corresponding relative spatial position diagram and stored in a database;
and searching the relative space position map of the commodity body according to the identification information field of the commodity body.
In one embodiment, the acquiring the relative position information of the plurality of commodity subject images in the target picture comprises:
performing image recognition on the image of each commodity main body in the target picture to obtain main body information of each commodity main body;
extracting coordinate information in each main body information;
and determining the relative position information of each commodity main body image in the target picture according to the coordinate information.
In one embodiment, the map is used for drawing an allocation area of each commodity main body image in the target picture according to the relative position information of each commodity main body image; and newly forming a relative spatial position graph containing the commodity main body and other commodity main bodies comprises the following steps:
drawing a rectangular frame where the commodity main image is located according to coordinate information in the main information, wherein the area framed by the rectangular frame is the distribution area;
intercepting the commodity main body image in the distribution area to form a screenshot of the commodity main body, and moving the screenshot of the commodity main body to a new drawing board;
moving the screenshots of other commodity main bodies into the new drawing board, wherein the position relationship between the screenshots of the other commodity main bodies and the screenshots of the commodity main bodies is arranged according to the relative position relationship of each commodity main body image in the target picture;
and after the screenshots of all the commodity main bodies are moved, forming a relative spatial position diagram of the commodity main body and other commodity main bodies.
In one embodiment, the acquiring the relative position information of the plurality of commodity subject images in the target picture comprises:
performing image recognition on the periphery of the image of each commodity main body in the target picture, and judging whether an outer frame image exists on the periphery of each commodity main body image;
if the periphery of the image of each commodity main body comprises the outer frame image, acquiring vertex coordinate information of each outer frame image; and determining the relative position information of each commodity main body image in the target picture according to the vertex coordinate information of the outer frame image.
In one embodiment, the searching for the identification information of the extracted commodity main body in the product library for the existence of the commodity main body comprises:
searching pictures in the product library according to the extracted identification information of the commodity main body to obtain a group of similar commodity pictures;
calculating the similarity value of each commodity picture and the commodity main body image in the relative space position graph in sequence;
and if the similarity value is larger than a set threshold value, the commodity main body is considered to exist in the product library.
In one embodiment, the identification information of the article main body includes: at least one of the kind, name, color and attribute of the commodity body.
In a second aspect, an embodiment of the present application further provides a system for identifying a commodity on-shelf position based on picture search, which is used for implementing the method for identifying a commodity on-shelf based on picture search according to any one of the above items, and includes:
the system comprises image acquisition equipment, a display device and a display device, wherein the image acquisition equipment is used for acquiring a target picture containing a plurality of commodity main body images;
the position information extraction module is used for acquiring relative position information of a plurality of commodity main body images in the target picture;
the picture extraction module is used for drawing a distribution area of each commodity main body image in the target picture according to the relative position information of each commodity main body image; and reforming a relative space position diagram containing the commodity main body and other commodity main bodies;
the identification information extraction module is used for extracting the identification information of each commodity main body in the distribution area where each commodity main body image is located;
the information comparison module is used for searching whether the extracted identification information of the commodity main body exists in the product library; when the commodity main body exists in the product library, the commodity main body is associated with the corresponding relative spatial position diagram and is stored in a database;
and the retrieval module is used for retrieving the relative spatial position map of the commodity body according to the identification information field of the commodity body.
In a third aspect, an embodiment of the present application further provides a device for identifying a commodity shelf location based on picture search, including:
a memory for storing a computer program;
a processor for implementing the steps of the picture search based item-on-shelf identification method as described in any one of the above when executing the computer program.
In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the method for identifying shelves of commodities based on picture search as described in any one of the above.
According to the technical scheme, the method for searching and positioning the space position of the article based on the picture search is provided, the space positioning picture can be automatically established through a plurality of commodity main bodies in one picture, the connection is established through the matching of the space positioning picture and the corresponding commodity, and a manager can quickly inquire whether the commodity is on the shelf and the space position information in the shelf through commodity information, so that the quick management of the off-line article is realized.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 is a flowchart illustrating steps of a method for identifying a shelf location of a commodity based on a picture search according to an embodiment of the present application;
fig. 2 is a flowchart illustrating a step of implementing step S103 according to an embodiment of the present application;
fig. 3 is a schematic flowchart illustrating a process of searching for whether a commodity main body exists in a product library according to an embodiment of the present application;
FIG. 4 is a block diagram illustrating a modular connection of an article on-shelf location identification system according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of a computer-readable storage medium according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
In order to more efficiently and timely know whether goods are placed on a shelf and the environment around the placement position, including but not limited to the type, number, shelf pattern, shelf position identification code, etc. of other goods, the inventor proposes a method, a system and a storage medium for identifying the positions of goods on shelf based on picture search through creative labor. It is worth to say that the method provided by the application is that the target picture of the commodity at the shooting position in the goods shelf is obtained, the image of each commodity in the target picture and the relative position of the commodity and other commodities are identified, and a relative position map is generated; the recognized product image is compared with a reference picture (a reserved picture is reserved for a product stored in the product library to indicate that the product exists in the product library), and if the product exists in the product library, a relative position map corresponding to the product is associated with the product and stored. When inquiring whether the commodity is on the shelf and the surrounding environment, the relative position graph of the commodity can be inquired through the retrieval field of the commodity, thereby realizing the identification and positioning of the spatial position of the commodity. And further realize the quick management of off-line article.
The method, system and storage medium for identifying the shelf location of a commodity based on picture search according to the present disclosure will be described in further detail with reference to the accompanying drawings and specific embodiments.
It is to be understood that the terminology used in the description is for the purpose of describing particular embodiments only, and is not intended to limit the application. All terms (including technical and scientific terms) used in the specification have the meaning commonly understood by one of ordinary skill in the art unless otherwise defined. Well-known functions or constructions may not be described in detail for brevity and/or clarity.
Referring to fig. 1, a flowchart illustrating steps of a method for identifying a shelf location of a commodity based on picture search according to an embodiment of the present application is shown.
Step S101: and acquiring a target picture containing a plurality of commodity main body images.
The target picture can be shot by a camera facing to a goods shelf on which goods are placed, and can also be shot in scenes such as a set-up table, a booth and the like which do not have the goods shelf and can display the goods. The actual scene can be a market supermarket, a small supermarket or a convenience store which is provided with a goods shelf; or a large-scale store with no or only a part of shelves, etc., it should be noted that the present application is not limited to the actual scene. The camera is also only used for exemplary purposes, and any intelligent terminal device with a shooting function, such as a mobile phone, can fall into the scope set forth in the present application. The content or type of the goods in the embodiments of the present invention is not particularly limited, and includes, but is not limited to, clothing, electric appliances, living goods, and the like.
The acquired target picture is denoted as a picture P, and the picture P includes a plurality of product bodies, which are individual articles included in the picture P.
Step S102: and acquiring relative position information of the plurality of commodity main body images in the target picture.
And performing image recognition on the image of each commodity main body in the target picture P to obtain main body information of each commodity main body.
The main body information of the product main body includes, but is not limited to, at least one of a kind, a name, a color, and an attribute of the product main body, and also includes information such as coordinates and a resolution of the product main body image in the map P.
In the present application, information about the type, name, color, attribute, and the like of the commodity body can be acquired using a preset article detection model. The article detection model adopts a convolutional neural network system to identify the commodities in the target picture to obtain the image characteristic information of the commodities and the size information corresponding to the commodities.
Specifically, a Convolutional Neural Network (CNN) is a recognition system that can extract image feature information from a collected image and perform deep learning by training using a large number of different types of images. Deep learning adopts Deep Neural Networks (DNN), the Deep model is an artificial Neural network comprising a plurality of hidden layers, and the multilayer nonlinear structure enables the Deep Neural network to have strong feature expression capability and complex task modeling capability. A convolutional neural network system developed from a deep neural network model utilizes the inherent characteristics that the local statistical characteristic information of the image is consistent with the characteristic information of other parts to analyze and identify the image, and is particularly suitable for large-size images with more pixels. The method for extracting image feature information in a picture by using a convolutional neural network system belongs to the known technology in the field, and is not specifically described in the present application.
Information on the coordinates, resolution, and the like of the commodity main body can be acquired using a preset image processing model. The image processing model can determine the coordinate information of each commodity main body in the target picture P and the information of pixels and the like in the area formed by the coordinate information according to the commodity size information acquired by the commodity detection model.
Since the determination of the coordinate information and the relative position in the body information of the commodity body is most direct, in one possible implementation, the coordinate information in each commodity body information is extracted, and the relative position information of each commodity body image in the target picture is determined according to the coordinate information.
For example, the coordinate information of a commodity main body may be location: { "top": 79, "left": 310, "width": 462, "heigth": 610}.
In another practical solution, obtaining the relative position information of the plurality of commodity subject images in the target picture may be further implemented by:
and performing image recognition on the periphery of the image of each commodity main body in the target picture, and judging whether the periphery of each commodity main body image has an outer frame image. If the periphery of the image of each commodity main body comprises the outer frame image, acquiring vertex coordinate information of each outer frame image, and determining the relative position information of each commodity main body image in the target picture according to the vertex coordinate information of the outer frame image. The coordinate information of the outer frame image obtained by image recognition can be realized through a convolutional neural network system, and the details are not repeated here.
And if the periphery of the image of each commodity main body does not have the outer frame image, determining the relative position information of each commodity main body image in the target picture according to the coordinate information of the commodity main body.
Step S103: drawing a distribution area of each commodity main body image in a target picture according to the relative position information of each commodity main body image; and newly forming a relative spatial position map containing the commodity main body and other commodity main bodies.
Referring to fig. 2, a flowchart of steps of one method for implementing step S103 in the present invention is shown, which specifically includes the following steps:
step S1031: and drawing a rectangular frame where the commodity main image is located according to the coordinate information in the main information, wherein the area framed by the rectangular frame is a distribution area.
In the target picture P, a plurality of commodity bodies G1, G2 … … Gn, n are determined as the number of commodities in the target picture. And for each commodity main body, drawing a rectangular frame according to the corresponding coordinate information, wherein the area enclosed by each rectangular frame is the distribution area.
Step S1032: and intercepting the commodity main body image in the distribution area to form a screenshot of the commodity main body, and moving the screenshot of the commodity main body to a new drawing board.
The image of the commodity body in each distribution area is cut out, and a plurality of screenshots Z1, Z2, … … Zn of the commodity body are formed.
Step S1033: and moving the screenshots of other commodity main bodies into a new drawing board, wherein the position relationship between the screenshots of the other commodity main bodies and the screenshots of the commodity main bodies is arranged according to the relative position relationship of each commodity main body image in the target picture.
Taking Z1 as an example, after the screenshot Z1 is moved to a new panel, Z2, … … Zn is moved to the new panel to form a new panel Z.
The relative position of each product subject image in the graph Z coincides with the relative positional relationship in the target picture P.
Step S1034: and after the screenshots of all the commodity main bodies are moved, forming a relative spatial position diagram of the commodity main body and other commodity main bodies.
Fig. Z is a diagram showing the relative spatial positions of the commercial subject G1 and the other commercial subject G2 … … Gn, and similarly, fig. Z is a diagram showing the relative spatial positions of the commercial subject G2 and the other commercial subject. The relative spatial position diagrams of the commercial bodies G1 and G2 … … Gn are both diagrams Z.
Step S104: the identification information of each commodity body is extracted from the distribution area where each commodity body image is located.
In step S102, only the size information corresponding to the commodity may be obtained by the convolutional neural network to obtain the coordinate information of each commodity theme. In this step, various information such as the kind, name, color, attribute, etc. of the commodity main body can be obtained through the convolutional neural network, and embodiments in the present application can use one or more information of the kind, name, color, attribute, etc. of the commodity main body as the identification information of the commodity main body; such as the goods number of the commodity main body, or a white goods shelf, a black goods shelf, etc. The commodity body can be uniquely determined by the identification information.
Step S105: and searching whether the extracted identification information of the commodity main body exists in a product library.
The product library is a database formed by data entry of all commodities operated by an operation subject, such as a supermarket, a store and the like.
Fig. 3 is a schematic flowchart illustrating a process of searching for whether a main product exists in a product library according to an embodiment of the present application, and referring to fig. 3, the process includes the following steps:
substep S1051: and searching pictures in the product library according to the extracted identification information of the commodity main body to obtain a group of similar commodity pictures. Taking the commercial subject G1 as an example, a group of similar commercial pictures M1, M2.
Substep S1052: and sequentially calculating the similarity value of each commodity picture and the commodity main body image in the relative space position graph. The image similarity value may be obtained by calculating any one or more of histogram method, image template matching, peak Signal to Noise ratio (psnr), structural similarity (ssim), and perceptual hash algorithm (perceptual hash algorithm).
Substep S1053: and if the similarity value is larger than a set threshold value, the commodity main body is considered to exist in the product library.
Pictures M1, M2..... Mx and the commodity subject G1 are sequentially calculated, and whether the consistency check is passed or not is judged. If the similarity value is larger than a set threshold value, the consistency check is considered to be passed, namely, the commodity main body exists in the product library. Similarly, for the other merchandise body G2 … … Gn, the same method is also used for the consistency check to identify whether or not the merchandise body exists in the product library.
Step S106: and if the commodity main body exists in the product library, associating the commodity main body with the corresponding relative spatial position diagram and storing the commodity main body and the corresponding relative spatial position diagram in a database.
The map Mx passed the consistency check is regarded as the same item as the brand main body G1, and the information association between the corresponding map Z and map Mx is established and stored in the database.
Step S107: and searching the relative space position map of the commodity body according to the identification information field of the commodity body.
The spatial position map Z of the product (map Mx) can be retrieved from the identification information field of the product.
According to the technical scheme, the method for searching and positioning the space position of the article based on the picture search is provided, the space positioning picture can be automatically established through a plurality of commodity main bodies in one picture, the connection is established through the matching of the space positioning picture and the corresponding commodity, and a manager can quickly inquire whether the commodity is on the shelf and the space position information in the shelf through commodity information, so that the quick management of the off-line article is realized.
The embodiment of the application also provides a commodity on-shelf position identification system based on picture search, and fig. 4 shows a module connection schematic diagram of the commodity on-shelf position identification system. The system can realize the commodity on-shelf identification method based on picture search in the application. In order to implement the identification method in the present application, the system includes:
the image acquisition device 401 is configured to acquire a target picture including a plurality of commodity main body images;
a position information extraction module 402, configured to obtain relative position information of multiple commodity subject images in the target picture;
a picture extracting module 403, configured to draw a distribution region of each commodity main image in the target picture according to the relative position information of each commodity main image; and reforming a relative space position diagram containing the commodity main body and other commodity main bodies;
an identification information extraction module 404, configured to extract identification information of each commodity main body in the distribution area where each commodity main body image is located;
an information comparison module 405, configured to search the extracted identification information of the commodity main body in a product library for whether the commodity main body exists; when the commodity main body exists in the product library, the commodity main body is associated with the corresponding relative spatial position diagram and is stored in a database;
the retrieving module 406 is configured to retrieve the relative spatial location map of the commodity body according to the identification information field of the commodity body.
The embodiment in the application also provides commodity shelf position identification equipment based on picture search.
The article on-shelf position recognition apparatus includes:
a memory for storing a computer program;
a processor for implementing the steps of the method for identifying goods on-shelf based on picture search as described in any one of the above when executing the computer program.
Various aspects of the present application may be implemented as a system, method or program product. Accordingly, various aspects of the present application may be embodied in the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, micro-code, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" platform.
An embodiment of the present application also provides a computer-readable storage medium, having a computer program stored thereon, where the computer program, when executed by a processor, can implement the steps of the above-mentioned picture-search-based commodity-on-shelf-position identifying method. Although this embodiment does not exhaustively enumerate other specific embodiments, in some possible embodiments, the various aspects illustrated in this disclosure can also be implemented in the form of a program product comprising program code means for causing a terminal device to carry out the steps of the embodiments according to the various embodiments of the present disclosure described in the comparative methods section of this disclosure when the program product is run on the terminal device.
Fig. 5 is a schematic structural diagram of a computer-readable storage medium according to an embodiment of the present application. As shown in fig. 5, a program product 500 for implementing the above method according to an embodiment of the present disclosure is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. Of course, the program product produced in accordance with the present embodiments is not limited in this respect, and in the present disclosure, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The program product may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CDROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
A computer readable storage medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable storage medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the C language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (9)
1. A commodity shelf position identification method based on picture search is characterized by comprising the following steps:
acquiring a target picture containing a plurality of commodity main body images;
acquiring relative position information of a plurality of commodity main body images in the target picture;
drawing a distribution area of each commodity main body image in the target picture according to the relative position information of each commodity main body image; and newly forming a relative spatial position graph containing the commodity main body and other commodity main bodies;
extracting the identification information of each commodity main body in the distribution area where each commodity main body image is located;
searching whether the extracted identification information of the commodity main body exists in a product library;
if the commodity main body exists in the product library, the commodity main body is associated with the corresponding relative spatial position diagram and stored in a database;
and searching the relative space position map of the commodity body according to the identification information field of the commodity body.
2. The method of claim 1, wherein the obtaining of the relative position information of the plurality of commodity subject images in the target picture comprises:
performing image recognition on the image of each commodity main body in the target picture to obtain main body information of each commodity main body;
extracting coordinate information in each main body information;
and determining the relative position information of each commodity main body image in the target picture according to the coordinate information.
3. The method according to claim 2, wherein the allocation area of each commodity main body image in the target picture is drawn according to the relative position information of each commodity main body image; and newly forming a relative spatial position graph containing the commodity main body and other commodity main bodies comprises the following steps:
drawing a rectangular frame where the commodity main image is located according to coordinate information in the main information, wherein the area framed by the rectangular frame is the distribution area;
intercepting the commodity main body image in the distribution area to form a screenshot of the commodity main body, and moving the screenshot of the commodity main body to a new drawing board;
moving the screenshots of other commodity main bodies into the new drawing board, wherein the position relationship between the screenshots of the other commodity main bodies and the screenshots of the commodity main bodies is arranged according to the relative position relationship of each commodity main body image in the target picture;
and after the screenshots of all the commodity main bodies are moved, forming a relative spatial position diagram of the commodity main body and other commodity main bodies.
4. The method of claim 2, wherein the obtaining of the relative position information of the plurality of commodity subject images in the target picture comprises:
performing image recognition on the periphery of the image of each commodity main body in the target picture, and judging whether an outer frame image exists on the periphery of each commodity main body image;
if the periphery of the image of each commodity main body comprises the outer frame image, acquiring vertex coordinate information of each outer frame image; and determining the relative position information of each commodity main body image in the target picture according to the vertex coordinate information of the outer frame image.
5. The method according to any one of claims 1 to 4, wherein the searching the extracted identification information of the commodity main body in a product library for whether the commodity main body exists comprises:
searching pictures in the product library according to the extracted identification information of the commodity main body to obtain a group of similar commodity pictures;
calculating the similarity value of each commodity picture and the commodity main body image in the relative space position graph in sequence;
and if the similarity value is larger than a set threshold value, the commodity main body is considered to exist in the product library.
6. The method of claim 5, wherein the identification information of the merchandise subject includes: at least one of the kind, name, color and attribute of the commodity body.
7. An on-shelf commodity identification system based on picture search, which is used for realizing the steps of the on-shelf commodity identification method based on picture search according to any one of claims 1 to 6, and is characterized by comprising the following steps:
the system comprises image acquisition equipment, a display device and a display device, wherein the image acquisition equipment is used for acquiring a target picture containing a plurality of commodity main body images;
the position information extraction module is used for acquiring relative position information of a plurality of commodity main body images in the target picture;
the picture extraction module is used for drawing a distribution area of each commodity main body image in the target picture according to the relative position information of each commodity main body image; and reforming a relative space position diagram containing the commodity main body and other commodity main bodies;
the identification information extraction module is used for extracting the identification information of each commodity main body in the distribution area where each commodity main body image is located;
the information comparison module is used for searching whether the extracted identification information of the commodity main body exists in the product library; when the commodity main body exists in the product library, the commodity main body is associated with the corresponding relative spatial position diagram and is stored in a database;
and the retrieval module is used for retrieving the relative spatial position map of the commodity body according to the identification information field of the commodity body.
8. An article on-shelf position recognition apparatus based on picture search, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the picture search based item-on-shelf identification method of any one of claims 1 to 6 when executing the computer program.
9. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when being executed by a processor, carries out the steps of the picture search based item-on-shelf identification method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110707724.XA CN113674049A (en) | 2021-06-24 | 2021-06-24 | Commodity shelf position identification method and system based on picture search and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110707724.XA CN113674049A (en) | 2021-06-24 | 2021-06-24 | Commodity shelf position identification method and system based on picture search and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113674049A true CN113674049A (en) | 2021-11-19 |
Family
ID=78538277
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110707724.XA Pending CN113674049A (en) | 2021-06-24 | 2021-06-24 | Commodity shelf position identification method and system based on picture search and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113674049A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114511964A (en) * | 2022-01-29 | 2022-05-17 | 上海商汤智能科技有限公司 | Abnormity reminding method and device, electronic equipment and storage medium |
| CN115661624A (en) * | 2022-11-07 | 2023-01-31 | 浙江莲荷科技有限公司 | Digital method and device for goods shelf and electronic equipment |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105917371A (en) * | 2013-11-27 | 2016-08-31 | 松下知识产权经营株式会社 | Product monitoring device, product monitoring system, and product monitoring method |
| CN106920141A (en) * | 2015-12-28 | 2017-07-04 | 阿里巴巴集团控股有限公司 | Page presentation content processing method and device |
| CN108734162A (en) * | 2018-04-12 | 2018-11-02 | 上海扩博智能技术有限公司 | Target identification method, system, equipment and storage medium in commodity image |
| CN109934093A (en) * | 2019-01-21 | 2019-06-25 | 创新奇智(南京)科技有限公司 | A kind of method, computer-readable medium and identifying system identifying commodity on shelf |
| CN110321797A (en) * | 2019-05-31 | 2019-10-11 | 苏宁云计算有限公司 | Commodity recognition method and device |
| CN110516628A (en) * | 2019-08-29 | 2019-11-29 | 上海扩博智能技术有限公司 | Shelf vacant locations merchandise news acquisition methods, system, equipment and storage medium |
| CN111553889A (en) * | 2020-04-16 | 2020-08-18 | 上海扩博智能技术有限公司 | Method, system, equipment and storage medium for comparing commodity placement positions on goods shelf |
| CN111738245A (en) * | 2020-08-27 | 2020-10-02 | 创新奇智(北京)科技有限公司 | Commodity identification management method, commodity identification management device, server and readable storage medium |
| US11030574B1 (en) * | 2018-08-29 | 2021-06-08 | Blue Yonder Group, Inc. | System and method for retail planning with smart product attributes |
-
2021
- 2021-06-24 CN CN202110707724.XA patent/CN113674049A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105917371A (en) * | 2013-11-27 | 2016-08-31 | 松下知识产权经营株式会社 | Product monitoring device, product monitoring system, and product monitoring method |
| CN106920141A (en) * | 2015-12-28 | 2017-07-04 | 阿里巴巴集团控股有限公司 | Page presentation content processing method and device |
| CN108734162A (en) * | 2018-04-12 | 2018-11-02 | 上海扩博智能技术有限公司 | Target identification method, system, equipment and storage medium in commodity image |
| US11030574B1 (en) * | 2018-08-29 | 2021-06-08 | Blue Yonder Group, Inc. | System and method for retail planning with smart product attributes |
| CN109934093A (en) * | 2019-01-21 | 2019-06-25 | 创新奇智(南京)科技有限公司 | A kind of method, computer-readable medium and identifying system identifying commodity on shelf |
| CN110321797A (en) * | 2019-05-31 | 2019-10-11 | 苏宁云计算有限公司 | Commodity recognition method and device |
| CN110516628A (en) * | 2019-08-29 | 2019-11-29 | 上海扩博智能技术有限公司 | Shelf vacant locations merchandise news acquisition methods, system, equipment and storage medium |
| CN111553889A (en) * | 2020-04-16 | 2020-08-18 | 上海扩博智能技术有限公司 | Method, system, equipment and storage medium for comparing commodity placement positions on goods shelf |
| CN111738245A (en) * | 2020-08-27 | 2020-10-02 | 创新奇智(北京)科技有限公司 | Commodity identification management method, commodity identification management device, server and readable storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114511964A (en) * | 2022-01-29 | 2022-05-17 | 上海商汤智能科技有限公司 | Abnormity reminding method and device, electronic equipment and storage medium |
| CN115661624A (en) * | 2022-11-07 | 2023-01-31 | 浙江莲荷科技有限公司 | Digital method and device for goods shelf and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103390075B (en) | Compare virtual and true picture in purchase experiences | |
| US10891465B2 (en) | Methods and apparatuses for searching for target person, devices, and media | |
| US20160180193A1 (en) | Image-based complementary item selection | |
| CN112927353B (en) | Three-dimensional scene reconstruction method, storage medium and terminal based on two-dimensional target detection and model alignment | |
| CN102609548A (en) | Video content retrieval method and system based on moving objects | |
| US8254678B2 (en) | Image segmentation | |
| CN107609056A (en) | A kind of question and answer processing method and equipment based on picture recognition | |
| CN105117399B (en) | Image searching method and device | |
| CN113674049A (en) | Commodity shelf position identification method and system based on picture search and storage medium | |
| CN111581423B (en) | Target retrieval method and device | |
| CN110020093A (en) | Video retrieval method, edge device, video frequency searching device and storage medium | |
| CN111414948B (en) | Target object detection method and related device | |
| CN114153795B (en) | Method and device for intelligently calling electronic archive, electronic equipment and storage medium | |
| JP7393472B2 (en) | Display scene recognition method, device, electronic device, storage medium and computer program | |
| CN115601672A (en) | VR intelligent shop patrol method and device based on deep learning | |
| CN111428743B (en) | Commodity identification method, commodity processing device and electronic equipment | |
| CN111126457A (en) | Information acquisition method and device, storage medium and electronic device | |
| CN111753614A (en) | Commodity shelf monitoring method and device | |
| CN114360057A (en) | Data processing method and related device | |
| CN113920306B (en) | Target re-identification method and device and electronic equipment | |
| CN115661624A (en) | Digital method and device for goods shelf and electronic equipment | |
| CN110738260A (en) | Method, device and equipment for detecting placement of space boxes of retail stores of types | |
| CN112102147B (en) | Background blurring identification method, device, equipment and storage medium | |
| CN111027326A (en) | Commodity classification method, storage medium and electronic device | |
| CN111461104A (en) | Visual recognition method, device, equipment and storage medium |
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 |