CN116362798A - Method, system, medium and electronic equipment for acquiring attention of footwear product - Google Patents
Method, system, medium and electronic equipment for acquiring attention of footwear product Download PDFInfo
- Publication number
- CN116362798A CN116362798A CN202310258939.7A CN202310258939A CN116362798A CN 116362798 A CN116362798 A CN 116362798A CN 202310258939 A CN202310258939 A CN 202310258939A CN 116362798 A CN116362798 A CN 116362798A
- Authority
- CN
- China
- Prior art keywords
- image
- shoe
- change
- coordinate set
- attention
- 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
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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0203—Market surveys; Market polls
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
- G06K17/0022—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisions for transferring data to distant stations, e.g. from a sensing device
- G06K17/0025—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisions for transferring data to distant stations, e.g. from a sensing device the arrangement consisting of a wireless interrogation device in combination with a device for optically marking the record carrier
-
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0224—Discounts or incentives, e.g. coupons or rebates based on user history
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The application provides a method, a system, a medium and electronic equipment for acquiring attention of a footwear product; the method comprises the following steps: acquiring an image to be detected, a background image and a reference image; the background image comprises a shoe rack image corresponding to the shoe rack when the shoe rack is empty; the reference image comprises a corresponding shoe rack image when the shoe rack is full of shoes; acquiring a shoe region coordinate set based on the reference image; acquiring a first change region coordinate set according to an image to be detected and a background image; acquiring a second change region coordinate set according to the image to be detected and the reference image; determining the current state of shoes on the shoe rack according to the shoe region coordinate set, the first change region coordinate set and the second change region coordinate set; calculating the attention degree of the shoe according to the current state; according to the method, related hardware devices such as RFID tags and card readers are not required to be installed, the cost is low, the problem that tag information is easy to be illegally read and maliciously tampered with due to the fact that the attention degree of a shoe product is acquired by the RFID tags is avoided, and the safety performance is higher.
Description
Technical Field
The application belongs to the technical field of computer vision, relates to an image processing technology, and particularly relates to a method, a system, a medium and electronic equipment for acquiring attention of a shoe product.
Background
In the big data age, data analysis is carried out, and the method is a strategic point for improving the competitiveness of off-line physical stores. For the shoe industry, knowing the attention of customers to various shoes in the selection process can enable operators to know the demand preference of customers, so that sales of shoes can be prejudged. For shoes with high attention, the stock of the shoes is timely increased to prevent the shoes from being out of stock; for the shoes with low attention, marketing means such as time-limited discount, replacement sales area and the like can be adopted to improve sales volume, prevent commodity backlog and further greatly improve store sales performance.
With the development of the internet of things industry, many shoe stores introduce RFID (Radio Frequency Identification, radio frequency identification technology) technology, which is a non-contact automatic identification technology, and can monitor the attention of a shoe product in real time through an RFID reader and an RFID tag arranged on the shoe product. When a customer picks up an article with an RFID tag, the RFID reader can acquire relevant information of the article and the time of picking and putting down. The attention degree of the commodity is acquired by counting the times that the commodity is taken and put down in a certain period, and more reference data are provided for terminal operators to purchase free-selling shoes.
Although the technology can accurately acquire the attention of the footwear products in real time, the technology has short appearance time, is not mature in technology, has insufficient safety and has the risks of illegal reading and malicious tampering of tag information; meanwhile, the RFID technology does not form a unified technical standard at present, and the phenomenon that a plurality of standards coexist exists, so that RFID labels of different enterprise products are incompatible with each other, and the application of the RFID technology is disordered to a certain extent; in addition, the price of the RFID tag is higher, which is tens times that of a common bar code tag, a lot of expenses are required for purchasing the RFID tag in a large quantity, and the deployment of the technology needs to be provided with related hardware equipment, so that the deployment cost of the whole system is too high for most stores.
Disclosure of Invention
The purpose of the application is to provide a method, a system, a medium and electronic equipment for obtaining the attention of a footwear product, which are used for solving the problem of high cost existing in the prior art that the attention of the footwear product is obtained by utilizing an RFID technology.
In a first aspect, the present application provides a method of obtaining a footwear product interest level, the method comprising: acquiring an image to be detected, a background image and a reference image; the background image comprises a shoe rack image corresponding to the shoe rack when the shoe rack is empty; the reference image comprises a shoe rack image corresponding to the shoe rack when the shoe rack is full of shoes; acquiring a shoe region coordinate set based on the reference image; acquiring a first change region coordinate set according to the image to be detected and the background image; acquiring a second change region coordinate set according to the image to be detected and the reference image; determining the current state of shoes on the shoe rack according to the shoe region coordinate set, the first change region coordinate set and the second change region coordinate set; and calculating the attention degree of the shoe according to the current state.
In the application, the method for acquiring the attention of the footwear product based on the image processing mode is provided, related hardware equipment such as an RFID tag and a card reader are not required to be installed, the cost is low, the problem that tag information is easy to be illegally read and maliciously tampered when the attention of the footwear product is acquired by using the RFID tag in the prior art is effectively solved, and the safety performance is higher.
In an implementation manner of the first aspect, the acquiring an image to be detected includes: acquiring a frame of target image every second preset time period within a first preset time period so as to form the image to be detected based on multiple frames of target images; the second preset time period is smaller than the first preset time period.
In one implementation of the first aspect, the set of footwear region coordinates is expressed as:
S＝{(1,x 1 ,y 1 ,w 1 ,h 1 ),(2,x 2 ,y 2 ,w 2 ,h 2 ),...(i,x i ,y i ,w i ,h i )...,(n,x n ,y n ,w n ,h n )}；
wherein S represents the set of shoe region coordinates; i represents the ith shoe when the shoe rack is full of shoes; x is x i And y i Respectively representing the abscissa and the ordinate of the upper left corner of the region where the ith shoe is positioned; w (w) i And h i Respectively representing the width and the height of the area where the ith shoe is positioned; i has a value from 1 to n; n represents the total number of all shoes when the shoe rack is full of shoes.
In an implementation manner of the first aspect, the acquiring a first change region coordinate set according to the image to be detected and the background image includes: detecting the image to be detected and the background image by using a scene change detection algorithm to obtain a first change mapping chart; binarizing the first change mapping graph to obtain a first binary image; acquiring coordinate information of circumscribed rectangular frames corresponding to all change areas in the first binary image to construct a first change area coordinate set; the obtaining a second change region coordinate set according to the image to be detected and the reference image comprises: detecting the image to be detected and the reference image by using the scene change detection algorithm to obtain a second change mapping chart; performing binarization processing on the second change mapping graph to obtain a second binary image; and acquiring coordinate information of circumscribed rectangular frames corresponding to all the change areas in the second binary image to construct a second change area coordinate set.
In the implementation mode, the attention degree of the footwear product is obtained by utilizing a scene change detection algorithm based on the visible light image, the RFID related technology is not needed, the risks of illegal reading and malicious tampering of tag information and the like are avoided, and the safety performance is high; in addition, the method does not need related hardware equipment such as RFID tags, card readers and the like, so that the deployment cost is low, and the fund pressure of operators can be reduced.
In an implementation manner of the first aspect, the current state includes: on the shoe rack and removed; the determining the current state of the shoe on the shoe rack according to the shoe region coordinate set, the first change region coordinate set and the second change region coordinate set comprises: aiming at a target shoe in the shoe region coordinate set, if a change region exists in the first change region coordinate set in a position region corresponding to the target shoe and all change regions in the second change region coordinate set are not in the position region corresponding to the target shoe, determining that the current state of the target shoe is on the shoe rack; if all the change areas in the first change area coordinate set are not in the corresponding position area of the target shoe and the change areas in the second change area coordinate set are in the corresponding position area of the target shoe, determining that the current state of the target shoe is taken away; if a change area exists in the first change area coordinate set in the corresponding position area of the target shoe and a change area also exists in the second change area coordinate set in the corresponding position area of the target shoe, one of the target shoes is determined to be taken away, and the other one of the target shoes is still on the shoe rack or other shoes are misplaced in the corresponding position area of the target shoe.
In the implementation mode, the to-be-detected image is compared with the background image and the reference image respectively, so that the accuracy and reliability of the acquisition of the current state of the shoe are ensured, and the accuracy of the follow-up calculation of the attention degree of the shoe is further improved.
In an implementation manner of the first aspect, the calculating the attention of the shoe according to the current state includes: acquiring the attention times and/or the attention duration of the shoes according to the current state; and calculating the attention degree according to the attention times and/or the attention duration.
In the implementation manner, the attention times and/or the attention duration of the shoes are obtained, so that an attention times list and/or an attention duration list of the footwear products can be provided for operators; in addition, the attention times and/or the attention duration are timely and accurately provided to store operators, and important data support and even profitability can be provided for subsequent operation decisions.
In a second aspect, the present application provides a footwear attention acquisition system, the footwear attention acquisition system comprising: the image acquisition module is used for acquiring an image to be detected, a background image and a reference image; the background image comprises a shoe rack image corresponding to the shoe rack when the shoe rack is empty; the reference image comprises a shoe rack image corresponding to the shoe rack when the shoe rack is full of shoes; the first coordinate acquisition module is used for acquiring a coordinate set of the shoe region based on the reference image; the second coordinate acquisition module is used for acquiring a first change region coordinate set according to the image to be detected and the background image; the third coordinate acquisition module is used for acquiring a second change region coordinate set according to the image to be detected and the reference image; the state determining module is used for determining the current state of the shoes on the shoe rack according to the shoe region coordinate set, the first change region coordinate set and the second change region coordinate set; and the attention calculating module is used for calculating the attention of the shoe according to the current state.
In a third aspect, the present application provides an electronic device, including: a memory for storing a computer program; and the processor is used for executing the computer program to enable the electronic equipment to execute the method for acquiring the attention degree of the footwear product.
In a fourth aspect, the present application provides a computer-readable storage medium having stored thereon a computer program that, when executed by an electronic device, implements the above-described footwear attention acquisition method.
In a fifth aspect, the present application provides a footwear attention acquisition system, an image acquisition device, and the electronic device described above; the image acquisition equipment is connected with the electronic equipment and is used for acquiring an image to be detected and sending the image to be detected to the electronic equipment.
In the application, the system for acquiring the attention of the footwear products based on the image processing mode is provided, compared with the prior art, the system does not need to install related hardware equipment such as RFID tags, card readers and the like, only needs to install one front-end image acquisition equipment, and is simple to install and low in cost; in addition, the RFID tag has risks of illegal reading and malicious tampering of tag information, and the security performance is higher by adopting an image processing mode.
As described above, the method, system, medium and electronic device for obtaining attention of footwear products described in the present application have the following
The beneficial effects are that:
compared with the prior art, the application provides a method for acquiring the attention of a shoe product based on a scene change detection algorithm, which belongs to the field of computer vision, and judges whether the shoe is taken away or not by detecting a change area in a visible light image of a shoe rack area, so as to count the attention times and/or attention duration of the shoe product and finally acquire the attention of the shoe product; the method does not need RFID related technology, does not have the risks of illegal reading and malicious tampering of tag information and the like, and has high safety performance; in addition, the method does not need related hardware equipment such as RFID tags, card readers and the like, has low deployment cost, and can lighten the fund pressure of operators.
Drawings
FIG. 1 is a flow chart illustrating a method for obtaining a focus of a footwear product according to an embodiment of the present application.
Fig. 2 is a schematic structural diagram of a reference image according to an embodiment of the present application.
Fig. 3 is a flowchart illustrating detection of a change region according to an embodiment of the present application.
FIG. 4 is a flow chart illustrating a method of obtaining a focus of a footwear product according to another embodiment of the present application.
Fig. 5 is a flowchart of acquiring a first change region coordinate set according to an image to be detected and a background image according to an embodiment of the present application.
Fig. 6 is a flowchart of acquiring a second change region coordinate set according to an embodiment of the present application according to an image to be detected and a reference image.
Fig. 7 is a flowchart illustrating calculation of a degree of attention of a shoe according to a current state according to an embodiment of the present application.
FIG. 8 is a schematic diagram illustrating a system for obtaining attention to a footwear product according to an embodiment of the present application.
FIG. 9 is a schematic diagram illustrating a configuration of a footwear attention acquisition system according to another embodiment of the present application.
Description of the reference numerals
81. Image acquisition module
82. First coordinate acquisition module
83. Second coordinate acquisition module
84. Third coordinate acquisition module
85. State determination module
86. Attention calculating module
91. Image acquisition device
92. Electronic equipment
S1 to S5 steps
S31 to S33 steps
S41 to S46 steps
S431 to S433 steps
Steps S441 to S443
Steps S461 to S462
Detailed Description
Other advantages and effects of the present application will become apparent to those skilled in the art from the present disclosure, when the following description of the embodiments is taken in conjunction with the accompanying drawings. The present application may be embodied or carried out in other specific embodiments, and the details of the present application may be modified or changed from various points of view and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments may be combined with each other without conflict.
It should be noted that, the illustrations provided in the following embodiments merely illustrate the basic concepts of the application by way of illustration, and only the components related to the application are shown in the drawings and are not drawn according to the number, shape and size of the components in actual implementation, and the form, number and proportion of the components in actual implementation may be arbitrarily changed, and the layout of the components may be more complex.
See fig. 1-9. Compared with the prior art, the method for acquiring the attention of the footwear product based on the scene change detection algorithm belongs to the field of computer vision, and judges whether the shoe is taken away or not by detecting a change area in a visible light image of a shoe rack area, so that the attention times and/or attention duration of the footwear product are counted, and finally the attention of the footwear product is acquired; the method does not need RFID related technology, does not have the risks of illegal reading and malicious tampering of tag information and the like, and has high safety performance; in addition, the method does not need related hardware equipment such as RFID tags, card readers and the like, has low deployment cost, and can lighten the fund pressure of operators.
In one embodiment, the method for acquiring the attention of the footwear product is applied to a terminal; specifically, as shown in fig. 1, the method for acquiring the attention of the footwear comprises the following steps:
and S1, collecting image data.
The image data is a top view angle image acquired by image acquisition equipment arranged above the shoe rack area obliquely, and mainly comprises a background image of a frame of empty shoe rack, a reference image of all shoes on a frame of shoe rack which are orderly placed and an image to be detected, wherein the image to be detected consists of continuous multi-frame images.
The image to be detected is all the images acquired by the image acquisition equipment in one period or a plurality of periods according to fixed time intervals; the "one cycle" may be selected as a business period of one day of a store, the "multiple cycles" may be selected as a business period of ten or more consecutive days, one month or several months, and the "fixed time interval" may be selected as several tens of seconds or several minutes.
And S2, designating a shoe area.
As shown in fig. 2, for the reference image in step S1, a rectangular area where each pair of shoes is located in the reference image is manually framed and corresponding coordinate information is acquired.
And then, carrying out numerical marks on each shoe region in sequence from left to right and from top to bottom, combining the rectangular region coordinate information of the shoe with the corresponding numerical marks, and constructing a shoe region coordinate set.
Specifically, the format of the shoe region coordinate set is as follows:
S＝{(1,x 1 ,y 1 ,w 1 ,h 1 ),(2,x 2 ,y 2 ,w 2 ,h 2 ),...(i,x i ,y i ,w i ,h i )...,(n,x n ,y n ,w n ,h n )}；
wherein S represents the set of shoe region coordinates; i represents the ith shoe when the shoe rack is full of shoes; x is x i And y i Respectively representing the abscissa and the ordinate of the upper left corner of the region where the ith shoe is positioned; w (w) i And h i Respectively representing the width and the height of the area where the ith shoe is positioned; the value of i is taken from 1 to n; n represents the total number of all shoes when the shoe rack is full of shoes; n is an integer greater than or equal to 2.
In the present embodiment, n is 8 as shown in fig. 2.
And S3, detecting a change area.
When a pair of shoes on the shoe rack are taken away, only the empty shoe rack is left at the position corresponding to the area where the shoes are located in the shoe area coordinate set in the image to be detected, and at the moment, the scene at the corresponding position is identical to the scene at the corresponding position in the background image and is different from the scene at the corresponding position in the reference image.
When the shoes are placed on the shoe rack, the positions of the to-be-detected images corresponding to the areas where the shoes are located in the shoe area coordinate sets contain the shoes, and at the moment, the scenes of the to-be-detected images are different from the scenes of the corresponding positions in the background images and the scenes of the corresponding positions in the reference images are the same.
In view of the above, it may be further determined whether the shoe on the current shoe rack is on the shoe rack or is taken away by determining whether the scene corresponding to the image to be detected, the background image, and the reference image is the same or changes.
The scene change detection algorithm is used for acquiring change information of scenes in two frames of images acquired at different time under the same scene; in the embodiment, a scene change detection algorithm is adopted to respectively solve scene change information between an image to be detected and a background image and between the image to be detected and a reference image, and a change area is solved according to the scene change information; and finally, combining the coordinate information in the coordinate set of the shoe region to judge the state of each pair of shoes on the shoe rack.
The shoe state includes two states of being placed on the shoe rack and being taken away.
It should be noted that the scene change detection algorithm may be a conventional image difference method, such as a frame difference method, or may be a scene change detection algorithm based on a neural network, such as FCN, transform, siamese, such as a common CosimNet algorithm or a TransCD algorithm.
Wherein, FCN, english is fully called: fully Convolutional Networks, chinese translation: a fully convolutional neural network, as the name implies, is a network in which all convolutional layers are linked.
transform, a sequence based on the seq2seq structure, generates a neural network.
Siamese, siamese neural network, a twin neural network, is a coupling framework established based on two artificial neural networks, and the twin neural network takes two samples as input and outputs a representation of the two samples embedded in a high-dimensional space so as to compare the similarity of the two samples.
As shown in fig. 3, the specific steps of this step S3 are as follows:
step S31, inputting the image to be detected, the background image and the reference image into a scene change detection algorithm to obtain a change map.
Specifically, for each frame of image in the image to be detected, firstly, taking the image and the background image as an input image pair, sending the input image pair into a scene change detection algorithm, and solving to obtain a first change map; and secondly, taking the image and the reference image as an input image pair, sending the input image pair and the reference image pair into a scene change detection algorithm, and solving to obtain a second change mapping chart.
Step S32, threshold binarization processing is carried out, and a binarized image is obtained.
Specifically, threshold binarization processing is performed on the first change map and the second change map respectively, and a first binary image and a second binary image are obtained through solving.
It should be noted that, the pixels of the first change map and the second change map are continuously changed from 0 to 1; after threshold binarization processing, the pixel points of the obtained first binary image and the second binary image are 0 and 1; in the first binary image, a region (darker color, black) with a pixel point of 0 represents a region which is unchanged between the image to be detected and the background image, and a region (lighter color, white) with a pixel point of 1 represents a region which is changed between the image to be detected and the background image; in the second binary image, a region (darker color, black) with a pixel point of 0 represents a region between the image to be detected and the reference image, which is unchanged, and a region (lighter color, white) with a pixel point of 1 represents a region between the image to be detected and the reference image, which is changed.
The threshold binarization processing method in the step S32 may be a fixed threshold method or an adaptive threshold method, where the fixed threshold method is to directly set a fixed threshold (the threshold is set as a condition not to limit the application, and in practical application, may be set according to a specific application scenario); the self-adaptive threshold method solves the threshold according to the gray information of the image or the neighborhood information of the pixels, and the common self-adaptive threshold method comprises a maximum inter-class variance method, a triangle threshold segmentation method and the like.
And S33, morphological filtering and contour extraction to obtain a change region coordinate set.
Specifically, morphological filtering and contour extraction are adopted for a first binary image, coordinate information of a minimum circumscribed rectangular frame corresponding to all change areas in the image is obtained, and a first change area coordinate set is constructed; and aiming at the second binary image, morphological filtering and contour extraction processing are adopted to acquire the coordinate information of the minimum circumscribed rectangular frame corresponding to all the change areas in the image, and a second change area coordinate set is constructed.
The formats of the first change area coordinate set and the second change area coordinate set are as follows:
C＝{(x′ 1 ,y′ 1 ,w′ 1 ,h′ 1 ),...,(x′ j ,y′ j ,w′ j ,h′ j ),...,(x′ m ,y′ m ,w′ m ,h′ m )}；
wherein C represents the first change region coordinate set or the second change region coordinate set; x's' j And y' j Respectively representing an abscissa and an ordinate corresponding to the upper left corner of a j-th change region (which is a minimum circumscribed rectangular frame corresponding to a region where a certain shoe is located) in the first change region coordinate set or the second change region coordinate set; w' j And h' j The corresponding width and height of the jth change region in the first change region coordinate set or the second change region coordinate set are respectively represented; the value of j is taken from 1 to m; m represents the total number of all the change areas in the first change area coordinate set or the second change area coordinate set, and m is an integer greater than or equal to 1.
Particularly, the first change region coordinate set and the second change region coordinate set may be empty, where the first change region coordinate set is empty, which indicates that there is no change region between the image to be detected and the background image; and the second change region coordinate set is empty, which indicates that no change region exists between the image to be detected and the reference image.
It should be noted that each variation area corresponds to a shoe.
It should be noted that the purpose of the foregoing "morphological filtering" is to remove the clutter in the first binary image and the second binary image, so that the extracted coordinate information is more accurate when the contour extraction is performed subsequently.
The morphological filtering and contour extraction are all conventional technical means in the field, and the specific working principle is not used as a condition for limiting the application, so that detailed description is omitted here.
And S4, determining the state of the shoes.
And (3) judging the current state of each pair of shoes on the shoe rack by combining the coordinate information of the shoe region coordinate set in the step S2, the first change region coordinate set and the second change region coordinate set in the step S3.
Wherein the current state of the shoe includes both on the shoe rack and removed.
The method comprises the following specific steps:
and respectively judging whether the first change region coordinate set and the second change region coordinate set have change regions in the position region of each pair of shoes in the shoe region coordinate set.
And then, determining the current state of the pair of shoes according to the judging results of the two change area sets.
Specifically, according to the judging result of the two change area sets, the current state of the pair of shoes is determined, and the method mainly comprises the following conditions:
1) A certain change area in the first change area coordinate set is in the corresponding position area of the pair of shoes, but all change areas in the second change area set are not in the corresponding position area of the pair of shoes, so that the pair of shoes are not taken away on the shoe rack at present or taken away, but are put back on the shoe rack.
2) All the change areas in the first change area set are not in the corresponding position area of the pair of shoes, but a certain change area in the second change area coordinate set is in the corresponding position area of the pair of shoes, so that the pair of shoes is taken away.
3) A certain change area in the first change area coordinate set is in the corresponding position area of the pair of shoes, and a certain change area in the second change area set is also in the corresponding position area of the pair of shoes, at the moment, two conditions exist, namely, in the pair of shoes, one shoe is taken away, and the other shoe is still on the shoe rack; secondly, shoes with other colors or styles are misplaced in the current shoe area.
For both cases in case 3), the intersection ratio between a certain change region in the first change region set and a change region at a corresponding position in the second change region set may be calculated (english full: intersection Over Union, IOU for short), if the IOU is less than a preset threshold, it indicates that one of the pair of shoes is removed, otherwise, it indicates that shoes of other colors or styles are misplaced in the current shoe region.
The overlap ratio refers to the ratio of the overlapping ratio of the two changing regions, i.e., the ratio of the intersection to the union.
And S5, solving the attention of the footwear.
In particular, footwear concerns may be resolved by the number of times the footwear is concerned and the duration of the concerned.
Wherein, define a valid concern as shoes are taken away by customers until they are placed on the shoe rack again; the effective attention duration is defined as the duration of time that the shoes are taken by the customer to be placed on the shoe rack again, and the duration is obtained by multiplying the total number of frames that the shoes are taken by the customer to be placed on the shoe rack again by the fixed time interval when the image acquisition device at the front end acquires the image.
The current state of the shoe can be obtained in step S4, and when the state of the same pair of shoes in two continuous images of the image to be detected is changed from the shoe rack to the shoe rack, the frame number corresponding to the current image is recorded and used as the starting frame number when the current shoe is taken.
Then, the image to be detected is continuously processed, and when the state of the shoes is changed from being taken away to being on the shoe rack, the frame number corresponding to the current image is recorded and is used as the end frame number when the current shoes are taken away.
As a valid concern for the shoe from the time the shoe is removed until replaced on the shoe rack; meanwhile, the starting frame number is subtracted from the ending frame number to obtain the total frame number corresponding to the effective attention of the shoe at one time, and then the total frame number is multiplied by a fixed time interval when the image acquisition equipment at the front end acquires images, so that the effective attention duration at one time can be obtained.
According to the attention times and the attention duration, the attention degree of the shoe can be calculated.
In one embodiment, the list of interest levels for footwear may be obtained by sorting from a top to a bottom order.
In one embodiment, the orders of the times of interest for the shoes of interest are sorted in order from large to small, and the operator may be provided with a list of times of interest for the shoes.
In one embodiment, the time duration of interest for the footwear of interest is ordered in a long to short order, which may provide the operator with a list of time durations of interest for the footwear.
It should be noted that, by providing the information to the store operator timely and accurately, important data support and even profitability can be provided for subsequent operating decisions.
Specifically, according to the attention times and the attention duration, the attention degree of the shoe can be calculated; the two calculation modes are respectively as follows:
1) According to the attention times, the formula for calculating the attention degree is as follows:
wherein, attenionN i Indicating the ith numberAttention of the shoe; num (Num) i Indicating the number of attention of the ith shoe.
2) According to the attention duration, the formula for calculating the attention degree is as follows:
wherein, attenionT i Representing the attention of the ith shoe; time i Indicating the length of time of interest for the ith shoe.
Compared with the prior art, the method for acquiring the attention of the shoe product based on the image processing mode, in particular to a scene change detection algorithm based on a visible light image, does not need to install related hardware equipment such as an RFID tag and a card reader, is low in cost, effectively solves the problems that in the prior art, the attention of the shoe product is acquired by utilizing the RFID tag, tag information is easy to be illegally read and maliciously tampered, and is higher in safety performance.
The following describes the technical solutions in the embodiments of the present application in detail with reference to the drawings in the embodiments of the present application.
As shown in fig. 4, the present embodiment provides a method for acquiring a degree of attention of a footwear product, the method comprising:
Step S41, an image to be detected, a background image and a reference image are acquired.
In one embodiment, the image to be detected is obtained by reading a video captured by an image capturing device mounted above the shoe rack area.
The background image comprises a shoe rack image corresponding to the shoe rack when the shoe rack is empty; the reference image comprises a corresponding shoe rack image when the shoe rack is full of shoes.
In an embodiment, the acquiring the image to be detected includes: and acquiring a frame of target image every second preset time period within the first preset time period so as to form the image to be detected based on multiple frames of target images.
In this embodiment, the second preset time period is smaller than the first preset time period.
It should be noted that, the first preset time period and the second preset time period are preset, and the specific setting of the first preset time period and the second preset time period is not a condition for limiting the application, and in practical application, the first preset time period and the second preset time period can be set according to specific application scenes; for example, in the above-described embodiment, "a business period of one day of a store", "a business period of ten consecutive days", "a business period of one month", or "a business period of several months" corresponds to the first preset period; the "fixed time interval" corresponds to the second preset time period (such as several tens of seconds or several minutes).
In one embodiment, a video of a store in normal business hours is acquired, and a target image is extracted every 1 minute to form a plurality of continuous frames of images to be detected.
Step S42, acquiring a coordinate set of the shoe region based on the reference image.
In one embodiment, as shown in fig. 2, the rectangular area of each pair of shoes in the reference image is manually framed, and corresponding coordinate information is obtained.
In an embodiment, the manually framed shoe regions are numbered in a sequence from left to right and from top to bottom, and the numbers are combined with the obtained coordinate information to form a shoe region coordinate set.
It should be noted that, when numbering the shoe areas in the reference image, the method is not limited to the sequence from left to right and from top to bottom, and only needs to ensure that all shoes in the reference image can be respectively and uniquely numbered.
In one embodiment, the set of footwear region coordinates is represented as:
S＝{(1,x 1 ,y 1 ,w 1 ,h 1 ),(2,x 2 ,y 2 ,w 2 ,h 2 ),...(i,x i ,y i ,w i ,h i )...,(n,x n ,y n ,w n ,h n )}；
wherein S represents the set of shoe region coordinates; i represents the ith shoe when the shoe rack is full of shoes; x is x i And y i Respectively representing the abscissa and the ordinate of the upper left corner of the region where the ith shoe is positioned; w (w) i And h i Respectively representing the width and the height of the area where the ith shoe is positioned; the value of i is taken from 1 to n; n represents the total number of all shoes when the shoe rack is full of shoes.
And S43, acquiring a first change region coordinate set according to the image to be detected and the background image.
As shown in fig. 5, in an embodiment, the acquiring a first change region coordinate set according to the image to be detected and the background image includes:
step S431, detecting the image to be detected and the background image by using a scene change detection algorithm, and obtaining a first change map.
In one embodiment, the scene change detection algorithm employs a TransCD algorithm.
Step S432, performing binarization processing on the first variation map to obtain a first binary image.
In one embodiment, the first binary image is obtained by binarizing the first variation map using a fixed threshold method.
In one embodiment, the fixed threshold is set to 128 when the first change map is binarized using the fixed threshold method.
Step S433, obtaining coordinate information of circumscribed rectangular frames corresponding to all the change regions in the first binary image, so as to construct the first change region coordinate set.
In one embodiment, the circumscribed rectangle frame in step S433 is the smallest circumscribed rectangle frame corresponding to all the variation regions in the first binary image.
In one embodiment, the first binary image is morphologically filtered to remove the outliers.
In one embodiment, the morphological filtering uses an open operation.
In an embodiment, contour extraction is performed on the first binary image to obtain coordinate information of circumscribed rectangular frames corresponding to all the variation regions in the first binary image.
In an embodiment, contour extraction is performed on the morphologically filtered first binary image to obtain coordinate information of circumscribed rectangular frames corresponding to all the changed regions in the morphologically filtered first binary image.
In one embodiment, in the profile extraction, the structural element is a rectangular structural element with a size of 7×7.
And S44, acquiring a second change region coordinate set according to the image to be detected and the reference image.
As shown in FIG. 6, in one embodiment, the acquiring the second change region coordinate set according to the image to be detected and the reference image includes
Step S441, detecting the image to be detected and the reference image by using the scene change detection algorithm, and obtaining a second change map.
Step S442, performing binarization processing on the second variation map to obtain a second binary image.
And step S443, acquiring coordinate information of circumscribed rectangular frames corresponding to all the change areas in the second binary image to construct a second change area coordinate set.
It should be noted that, the principle of acquiring the second change region coordinate set is the same as that of acquiring the first change region coordinate set, so that detailed description thereof is omitted.
And step S45, determining the current state of the shoes on the shoe rack according to the shoe region coordinate set, the first change region coordinate set and the second change region coordinate set.
In one embodiment, the current state includes: on the shoe rack and removed.
In this embodiment, the determining the current state of the shoe on the shoe rack according to the shoe region coordinate set, the first change region coordinate set and the second change region coordinate set includes the following cases:
for a target shoe in the set of shoe region coordinates,
1) And if the change areas in the first change area coordinate set are in the corresponding position areas of the target shoes and all the change areas in the second change area coordinate set are not in the corresponding position areas of the target shoes, determining that the current state of the target shoes is on the shoe rack.
2) If all the change areas in the first change area coordinate set are not in the corresponding position area of the target shoe and the change areas in the second change area coordinate set are in the corresponding position area of the target shoe, determining that the current state of the target shoe is taken away.
3) If a change area exists in the first change area coordinate set in the corresponding position area of the target shoe and a change area also exists in the second change area coordinate set in the corresponding position area of the target shoe, one of the target shoes is determined to be taken away, and the other one of the target shoes is still on the shoe rack or other shoes are misplaced in the corresponding position area of the target shoe.
In an embodiment, an IOU between a certain change area in the first change area set (the change area is in the corresponding location area of the target shoe) and a change area in the second change area set (the change area is also in the corresponding location area of the target shoe) is calculated, so as to determine, based on the IOU, whether one of the target shoes is removed, the other one is still on the shoe rack, or whether other shoes are currently misplaced in the corresponding location area of the target shoe.
In one embodiment, a preset threshold is set, and by comparing the preset threshold with the calculated IOU, it is achieved that whether one of the target shoes is taken away, the other is still on the shoe rack, or other shoes are misplaced in the corresponding location area of the target shoe.
In particular, the method comprises the steps of,
31 If the IOU is less than the preset threshold, indicating that one of the target shoes is removed and the other is still on the shoe rack.
32 If the IOU is greater than or equal to the preset threshold value, indicating that the shoes with other colors or styles are misplaced in the corresponding position area of the target shoe at the current moment.
It should be noted that, the preset threshold is preset, and the specific setting of the preset threshold is not limited to the condition of the application, and in practical application, the preset threshold may be set according to a specific application scenario.
Step S46, calculating the attention degree of the shoe according to the current state.
As shown in fig. 7, in an embodiment, the calculating the attention of the shoe according to the current state includes:
step S461, obtaining the attention times and/or attention duration of the shoe according to the current state.
Step S462, calculating the attention degree according to the attention times and/or the attention duration.
Specifically, the working principle of calculating the attention degree of the shoe according to the attention times or the attention duration may refer to the solution of the attention degree of the shoe described in step S5 of the above embodiment, so that detailed descriptions thereof are omitted herein.
In one embodiment, a degree of attention is calculated according to the number of times of attention, and another degree of attention is calculated according to the duration of attention; then, by weighted averaging these two degrees of attention, the obtained result is taken as the degree of attention of the shoe to be calculated in step S46.
The protection scope of the method for obtaining the attention of the footwear product according to the embodiments of the present application is not limited to the execution sequence of the steps listed in the embodiments, and all the schemes implemented by adding or removing steps and replacing steps according to the principles of the present application in the prior art are included in the protection scope of the present application.
The embodiment of the application also provides a system for acquiring the attention of the footwear product, which can realize the method for acquiring the attention of the footwear product, but the implementation device of the method for acquiring the attention of the footwear product comprises but is not limited to the structure of the system for acquiring the attention of the footwear product listed in the embodiment, and all structural modifications and substitutions of the prior art according to the principles of the application are included in the protection scope of the application.
As shown in fig. 8, the present embodiment provides a footwear attention acquisition system including:
an image acquisition module 81, configured to acquire an image to be detected, a background image, and a reference image; the background image comprises a shoe rack image corresponding to the shoe rack when the shoe rack is empty; the reference image comprises a corresponding shoe rack image when the shoe rack is full of shoes.
A first coordinate acquisition module 82 is configured to acquire a set of coordinates of the shoe region based on the reference image.
The second coordinate acquiring module 83 is configured to acquire a first change region coordinate set according to the image to be detected and the background image.
A third coordinate acquiring module 84, configured to acquire a second change region coordinate set according to the image to be detected and the reference image.
The state determining module 85 is configured to determine a current state of the shoe on the shoe rack according to the shoe region coordinate set, the first change region coordinate set, and the second change region coordinate set.
And a attention calculating module 86, configured to calculate an attention of the shoe according to the current state.
It should be noted that, the structures and principles of the image obtaining module 81, the first coordinate obtaining module 82, the second coordinate obtaining module 83, the third coordinate obtaining module 84, the state determining module 85, and the attention calculating module 86 are in one-to-one correspondence with the steps (step S41 to step S46) in the method for obtaining the attention of the footwear product, and the specific working principle thereof may refer to the description of the method for obtaining the attention of the footwear product in the foregoing embodiment, so that the description is omitted here.
As shown in fig. 9, the present embodiment provides a footwear attention acquisition system including: an image capturing device 91 and the above-described electronic device 92.
Specifically, the image capturing device 91 is connected to the electronic device 92, and is configured to capture an image to be detected, and send the image to be detected to the electronic device 92.
It should be noted that, the working principle of the attention acquiring system for footwear products may refer to the description of the attention acquiring method for footwear products in the above embodiments, so that detailed descriptions thereof are omitted herein.
In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, or methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of modules/units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple modules or units may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or modules or units, which may be in electrical, mechanical or other forms.
The modules/units illustrated as separate components may or may not be physically separate, and components shown as modules/units may or may not be physical modules, i.e., may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules/units may be selected according to actual needs to achieve the purposes of the embodiments of the present application. For example, functional modules/units in various embodiments of the present application may be integrated into one processing module, or each module/unit may exist alone physically, or two or more modules/units may be integrated into one module/unit.
Those of ordinary skill would further appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, in computer software, or in a combination of the two, and that the elements and steps of the examples have been generally described in terms of function in the foregoing description to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The application also provides an electronic device comprising: a memory for storing a computer program; and the processor is used for executing the computer program to enable the electronic equipment to execute the method for acquiring the attention degree of the footwear product.
Embodiments of the present application also provide a computer-readable storage medium having stored thereon a computer program that, when executed by an electronic device, implements the above-described method of obtaining a degree of attention of an article of footwear.
Those of ordinary skill in the art will appreciate that all or part of the steps in the method implementing the above embodiments may be implemented by a program to instruct a processor, where the program may be stored in a computer readable storage medium, where the storage medium is a non-transitory (non-transitory) medium, such as a random access memory, a read only memory, a flash memory, a hard disk, a solid state disk, a magnetic tape (magnetic tape), a floppy disk (floppy disk), an optical disk (optical disk), and any combination thereof. The storage media may be any available media that can be accessed by a computer or a data storage device such as a server, data center, or the like that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a digital video disc (digital video disc, DVD)), or a semiconductor medium (e.g., a Solid State Disk (SSD)), or the like.
The descriptions of the processes or structures corresponding to the drawings have emphasis, and the descriptions of other processes or structures may be referred to for the parts of a certain process or structure that are not described in detail.
The foregoing embodiments are merely illustrative of the principles of the present application and their effectiveness, and are not intended to limit the application. Modifications and variations may be made to the above-described embodiments by those of ordinary skill in the art without departing from the spirit and scope of the present application. Accordingly, it is intended that all equivalent modifications and variations which may be accomplished by persons skilled in the art without departing from the spirit and technical spirit of the disclosure be covered by the claims of this application.
Claims (10)
1. A method of obtaining a degree of interest of a footwear product, the method comprising:
acquiring an image to be detected, a background image and a reference image; the background image comprises a shoe rack image corresponding to the shoe rack when the shoe rack is empty; the reference image comprises a shoe rack image corresponding to the shoe rack when the shoe rack is full of shoes;
acquiring a shoe region coordinate set based on the reference image;
acquiring a first change region coordinate set according to the image to be detected and the background image;
Acquiring a second change region coordinate set according to the image to be detected and the reference image;
determining the current state of shoes on the shoe rack according to the shoe region coordinate set, the first change region coordinate set and the second change region coordinate set;
and calculating the attention degree of the shoe according to the current state.
2. The method of claim 1, wherein the acquiring an image to be detected comprises: acquiring a frame of target image every second preset time period within a first preset time period so as to form the image to be detected based on multiple frames of target images; the second preset time period is smaller than the first preset time period.
3. The footwear item focus acquisition method according to claim 1, wherein the set of footwear region coordinates is represented as:
S＝{(1,x 1 ,y 1 ,w 1 ,h 1 ),(2,x 2 ,y 2 ,w 2 ,h 2 ),...(i,x i ,y i ,w i ,h i )...,(n,x n ,y n ,w n ,h n )}；
wherein S represents the set of shoe region coordinates; i represents the ith shoe when the shoe rack is full of shoes; x is x i And y i Respectively representing the abscissa and the ordinate of the upper left corner of the region where the ith shoe is positioned; w (w) i And h i Respectively representing the width and the height of the area where the ith shoe is positioned; the value of i is taken from 1 to n; n represents the total number of all shoes when the shoe rack is full of shoes.
4. The method of claim 1, wherein the acquiring a first set of variation region coordinates from the image to be detected and the background image comprises:
detecting the image to be detected and the background image by using a scene change detection algorithm to obtain a first change mapping chart;
binarizing the first change mapping graph to obtain a first binary image;
acquiring coordinate information of circumscribed rectangular frames corresponding to all change areas in the first binary image to construct a first change area coordinate set;
the obtaining a second change region coordinate set according to the image to be detected and the reference image comprises:
detecting the image to be detected and the reference image by using the scene change detection algorithm to obtain a second change mapping chart;
performing binarization processing on the second change mapping graph to obtain a second binary image;
and acquiring coordinate information of circumscribed rectangular frames corresponding to all the change areas in the second binary image to construct a second change area coordinate set.
5. The method of claim 1, wherein the current state comprises: on the shoe rack and removed; the determining the current state of the shoe on the shoe rack according to the shoe region coordinate set, the first change region coordinate set and the second change region coordinate set comprises:
For a target shoe in the set of shoe region coordinates,
if the first change region coordinate set has a change region in the position region corresponding to the target shoe and all the change regions in the second change region coordinate set are not in the position region corresponding to the target shoe, determining that the current state of the target shoe is on the shoe rack;
if all the change areas in the first change area coordinate set are not in the corresponding position area of the target shoe and the change areas in the second change area coordinate set are in the corresponding position area of the target shoe, determining that the current state of the target shoe is taken away;
if a change area exists in the first change area coordinate set in the corresponding position area of the target shoe and a change area also exists in the second change area coordinate set in the corresponding position area of the target shoe, one of the target shoes is determined to be taken away, and the other one of the target shoes is still on the shoe rack or other shoes are misplaced in the corresponding position area of the target shoe.
6. The method of claim 1, wherein the calculating the focus of the shoe based on the current state comprises:
Acquiring the attention times and/or the attention duration of the shoes according to the current state;
and calculating the attention degree according to the attention times and/or the attention duration.
7. A footwear attention acquisition system, the footwear attention acquisition system comprising:
the image acquisition module is used for acquiring an image to be detected, a background image and a reference image; the background image comprises a shoe rack image corresponding to the shoe rack when the shoe rack is empty; the reference image comprises a shoe rack image corresponding to the shoe rack when the shoe rack is full of shoes;
the first coordinate acquisition module is used for acquiring a coordinate set of the shoe region based on the reference image;
the second coordinate acquisition module is used for acquiring a first change region coordinate set according to the image to be detected and the background image;
the third coordinate acquisition module is used for acquiring a second change region coordinate set according to the image to be detected and the reference image;
the state determining module is used for determining the current state of the shoes on the shoe rack according to the shoe region coordinate set, the first change region coordinate set and the second change region coordinate set;
and the attention calculating module is used for calculating the attention of the shoe according to the current state.
8. An electronic device, the electronic device comprising:
a memory for storing a computer program;
a processor for executing the computer program to cause the electronic device to perform the footwear product attention acquisition method of any one of claims 1 to 6.
9. A computer-readable storage medium having stored thereon a computer program, characterized in that the program, when executed by an electronic device, implements the footwear attention acquisition method of claims 1 to 6.
10. A footwear attention acquisition system, characterized by an image acquisition device and an electronic device as recited in claim 8;
the image acquisition equipment is connected with the electronic equipment and is used for acquiring an image to be detected and sending the image to be detected to the electronic equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310258939.7A CN116362798A (en) | 2023-03-16 | 2023-03-16 | Method, system, medium and electronic equipment for acquiring attention of footwear product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310258939.7A CN116362798A (en) | 2023-03-16 | 2023-03-16 | Method, system, medium and electronic equipment for acquiring attention of footwear product |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116362798A true CN116362798A (en) | 2023-06-30 |
Family
ID=86906192
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310258939.7A Pending CN116362798A (en) | 2023-03-16 | 2023-03-16 | Method, system, medium and electronic equipment for acquiring attention of footwear product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116362798A (en) |
-
2023
- 2023-03-16 CN CN202310258939.7A patent/CN116362798A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11335092B2 (en) | Item identification method, system and electronic device | |
| CN107292248B (en) | Commodity management method and system based on image recognition technology | |
| CN108416403B (en) | Method, system, equipment and storage medium for automatically associating commodity with label | |
| US9785898B2 (en) | System and method for identifying retail products and determining retail product arrangements | |
| US8983200B2 (en) | Object segmentation at a self-checkout | |
| CN108416902B (en) | Real-time object identification method and device based on difference identification | |
| US20150262116A1 (en) | Machine vision technology for shelf inventory management | |
| US20140003655A1 (en) | Method, apparatus and system for providing image data to represent inventory | |
| US9288450B2 (en) | Methods for detecting and recognizing a moving object in video and devices thereof | |
| EP3139321A1 (en) | Analytics system and method | |
| CN111369317B (en) | Order generation method, order generation device, electronic equipment and storage medium | |
| US20210166028A1 (en) | Automated product recognition, analysis and management | |
| JP2016181159A (en) | System, search method and program | |
| CN111784675A (en) | Method and device for processing article texture information, storage medium and electronic equipment | |
| CN110619308A (en) | Aisle sundry detection method, device, system and equipment | |
| CN113468914B (en) | Method, device and equipment for determining purity of commodity | |
| CN113627415B (en) | Method and device for determining placement information of target object | |
| CN115661624A (en) | Digital method and device for goods shelf and electronic equipment | |
| CN111145224A (en) | Human body tracking system | |
| CN116362798A (en) | Method, system, medium and electronic equipment for acquiring attention of footwear product | |
| WO2021138451A1 (en) | A system and method for tracking wine in a wine-cellar and monitoring inventory | |
| CN115565117B (en) | Data processing method, device, equipment and storage medium | |
| CN211699033U (en) | Human body tracking system | |
| CN113191356A (en) | State identification method and related device for switch cabinet pressing plate equipment | |
| US12211319B2 (en) | Method, apparatus and system for customer group analysis, 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 |