CN112613358A - Article identification method, article identification device, storage medium, and electronic device - Google Patents
Article identification method, article identification device, storage medium, and electronic device Download PDFInfo
- Publication number
- CN112613358A CN112613358A CN202011425560.3A CN202011425560A CN112613358A CN 112613358 A CN112613358 A CN 112613358A CN 202011425560 A CN202011425560 A CN 202011425560A CN 112613358 A CN112613358 A CN 112613358A
- Authority
- CN
- China
- Prior art keywords
- image
- article
- sub
- item
- difference 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 71
- 238000004590 computer program Methods 0.000 claims description 19
- 230000008859 change Effects 0.000 claims description 12
- 230000011218 segmentation Effects 0.000 claims description 9
- 230000008569 process Effects 0.000 abstract description 14
- 238000004422 calculation algorithm Methods 0.000 abstract description 13
- 238000005516 engineering process Methods 0.000 abstract description 13
- 230000000694 effects Effects 0.000 abstract description 12
- 238000004891 communication Methods 0.000 description 14
- 238000012423 maintenance Methods 0.000 description 11
- 238000013473 artificial intelligence Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 230000005540 biological transmission Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000007726 management method Methods 0.000 description 4
- 238000010295 mobile communication Methods 0.000 description 4
- 238000007405 data analysis Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 241000531116 Blitum bonus-henricus Species 0.000 description 2
- 235000008645 Chenopodium bonus henricus Nutrition 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 239000011248 coating agent Substances 0.000 description 2
- 238000000576 coating method Methods 0.000 description 2
- 238000013500 data storage Methods 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000001681 protective effect Effects 0.000 description 2
- 238000013481 data capture Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/35—Categorising the entire scene, e.g. birthday party or wedding scene
- G06V20/36—Indoor scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention provides an article identification method, an article identification device, a storage medium and an electronic device, wherein the method comprises the following steps: the method comprises the steps of acquiring a first article image acquired by image acquisition equipment after a target area is shot, determining image difference information between the first article image and a second article image, and sending image difference information to a server under the condition that the image difference information does not reach a preset condition so that the server can identify an article which is changed between the first article image and the second article image according to the image difference information, therefore, the technical problem that the identification efficiency of the article to be identified in the identification process is low in the related technology can be solved, and the technical effects of improving the identification efficiency of the article, reducing the identification cost of the article and increasing the application range of the article identification algorithm are achieved.
Description
Technical Field
The embodiment of the invention relates to the field of communication, in particular to an article identification method, an article identification device, a storage medium and an electronic device.
Background
The current datamation mode of new retail goods is as follows: the special edge camera shoots the picture, and then the picture is uploaded to an artificial intelligence platform through a mobile communication network to identify the article, so that the datamation of the article information is completed, and the requirement for the clarity of the shot picture of the article reaches above 720P.
The goods of retail enterprises are generally distributed in various shops, supermarkets, schools and shopping malls, so that a wired or wireless network environment cannot be guaranteed, and most of edge deployment gateways need to return data through a mobile communication network to guarantee availability and reliability, so that uploading of display photos of the goods to be identified consumes a large amount of communication traffic.
In order to control the traffic cost, a reporting frequency control mode is mostly adopted to save the traffic, for example, uploading is taken hourly or daily, and the uploading frequency of the shot photos directly determines the accuracy of the statistical information of the articles, so that in an actual application scene, a large amount of traffic cost is generated or a lot of useful data is lost.
Aiming at the technical problem that the identification efficiency of an object to be identified in the identification process is low in the related technology, an effective solution is not provided at present.
Disclosure of Invention
The embodiment of the invention provides an article identification method, an article identification device, a storage medium and an electronic device, which are used for at least solving the technical problem that the identification efficiency of an article to be identified in the identification process is low in the related technology.
According to an embodiment of the present invention, there is provided an identification method of an article, including: acquiring a first article image acquired by image acquisition equipment after shooting a target area; determining image difference information between the first article image and a second article image, wherein the second article image is a pre-shot image; and under the condition that the image difference information does not reach the preset condition, sending the image difference information to a server so that the server can identify the changed article between the first article image and the second article image according to the image difference information.
According to another embodiment of the present invention, there is provided an identification apparatus of an article, including: the acquisition module is used for acquiring a first article image acquired by the image acquisition equipment after the target area is shot; the determining module is used for determining image difference information between the first article image and a second article image, wherein the second article image is a pre-shot image; the sending module is used for sending the image difference information to a server under the condition that the image difference information does not reach a preset condition, so that the server can identify the changed article between the first article image and the second article image according to the image difference information.
According to yet another embodiment of the invention, a computer-readable storage medium is also provided, in which a computer program is stored, wherein the computer program, when executed by a processor, performs the steps in any of the above method embodiments.
According to yet another embodiment of the present invention, there is also provided an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the steps in any of the above method embodiments when executing the computer program.
According to the invention, the first article image acquired by the image acquisition equipment after the target area is shot is acquired, the image difference information between the first article image and the second article image is determined, and the image difference information is sent to the server under the condition that the image difference information does not reach the preset condition, so that the server can identify the changed article between the first article image and the second article image according to the image difference information, therefore, the technical problem that the identification efficiency of the article to be identified in the identification process is low in the related technology can be solved, and the technical effects of improving the identification efficiency of the article, reducing the identification cost of the article and increasing the application range of the article identification algorithm are achieved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
fig. 1 is a block diagram of a hardware configuration of a mobile terminal according to an alternative article identification method of an embodiment of the present invention;
FIG. 2 is a schematic flow chart diagram of an alternative method of identifying an item in accordance with an embodiment of the present invention;
FIG. 3 is a schematic illustration of an alternative method of identifying an item according to an embodiment of the present invention;
FIG. 4 is a schematic illustration of yet another alternative method of identifying an item according to an embodiment of the present invention;
fig. 5 is a block diagram of an alternative article identification device according to an embodiment of the present invention.
Detailed Description
Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings in conjunction with the embodiments.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
The method embodiments provided in the embodiments of the present application may be executed in a mobile terminal, a computer terminal, or a similar computing device. Taking an example of the method running on a mobile terminal, fig. 1 is a hardware structure block diagram of the mobile terminal of the method for identifying an article according to the embodiment of the present invention. As shown in fig. 1, the mobile terminal may include one or more (only one shown in fig. 1) processors 102 (the processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA), and a memory 104 for storing data, wherein the mobile terminal may further include a transmission device 106 for communication functions and an input-output device 108. It will be understood by those skilled in the art that the structure shown in fig. 1 is only an illustration, and does not limit the structure of the mobile terminal. For example, the mobile terminal may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.
The memory 104 may be used for storing computer programs, for example, software programs and modules of application software, such as computer programs corresponding to the article identification method in the embodiment of the present invention, and the processor 102 executes various functional applications and data processing by running the computer programs stored in the memory 104, so as to implement the above-mentioned method. The memory 104 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory located remotely from the processor 102, which may be connected to the mobile terminal over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device 106 is used for receiving or transmitting data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a Network adapter (NIC), which can be connected to other Network devices through a base station so as to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
In this embodiment, a method for identifying an article running on a mobile terminal, a computer terminal or a similar computing device is provided, and fig. 2 is a schematic flow chart of an alternative method for identifying an article according to an embodiment of the present invention, as shown in fig. 2, the flow includes the following steps:
s202, acquiring a first article image acquired by shooting a target area by image acquisition equipment;
s204, determining image difference information between the first article image and a second article image, wherein the second article image is a pre-shot image;
and S206, under the condition that the image difference information does not reach the preset condition, sending the image difference information to the server so that the server can identify the changed article between the first article image and the second article image according to the image difference information.
Optionally, in this embodiment, the main body of the above steps may be a server, a terminal, a combination of the server and the terminal, and the like, but is not limited thereto.
Fig. 3 is a schematic diagram of an alternative method for identifying an article according to an embodiment of the present invention, and the method for identifying an article is further explained with reference to fig. 3 by taking an example that an execution subject of the manner of identifying the article is an edge gateway:
s302, the edge gateway 302 acquires a first article image acquired by the image acquisition equipment 304 after shooting a target area;
s304, the edge gateway 302 determines image difference information between a first article image and a second article image, wherein the second article image is a pre-shot image;
s306, the edge gateway 302 sends the image difference information to the server 306 when the image difference information does not meet the preset condition, so that the server 306 identifies the changed article between the first article image and the second article image according to the image difference information.
The artificial intelligence goods identification system for performing the above-mentioned identification method of the goods may include, but is not limited to, the edge gateway 302, the cloud platform (server 306), the client application 308, and the maintenance tool application 310.
The edge gateway 302 may include, but is not limited to, a plurality of interfaces for providing power to a plurality of cameras 312 (image capture devices) connected thereto, and may also be configured to perform data communication with the cameras 312, for example, sending control management and picture data capture messages to the cameras 312 through the edge gateway 302.
The edge gateway 302 may further include, but is not limited to, a communication module, and performs data interaction with the camera 312, the cloud platform 306, the client application 308, and the maintenance tool 310 through a network, where the network may include, but is not limited to: a wired network, a wireless network, wherein the wired network comprises: a local area network, a metropolitan area network, and a wide area network, the wireless network comprising: bluetooth, WIFI and other networks for realizing wireless communication and the like to access a cloud platform to realize data reporting and remote control.
The edge gateway 302 may further include, but is not limited to, an artificial intelligence calculation module configured to perform artificial intelligence recognition on a first article image captured in the target area through image capture equipment, locate all article positions in the photo, and extract key article information, where the article information includes, but is not limited to, position information (initial coordinates, width, height in the photo), and article photo.
The edge gateway 302 may further include, but is not limited to, an external antenna provided with a communication module;
the edge gateway 302 may further include, but is not limited to, an indicator light for displaying an operating status of the edge gateway 302, where the operating status includes, but is not limited to, connection, operating status, and engineering mode, and the status of the packet is indicated by flashing when the data packet is received or sent.
The edge gateway 302 may also include, but is not limited to, a reset button configured to control the edge gateway 302 to enter an engineering mode and to initiate bluetooth local maintenance services for software communication with the maintenance tool application 310.
Optionally, in this embodiment, the image capturing device may include, but is not limited to, a camera, a scanner, an unmanned aerial vehicle, and the like for capturing a photograph of an article.
The image capturing device may include, but is not limited to, a USB connection line for accessing the edge gateway 302 to obtain power and data communication.
The image capturing device may include, but is not limited to, a camera sensor for capturing a photograph of an article display or video data.
The image capturing apparatus may include, but is not limited to, a protection device provided to prevent fogging of the lens, the protection device including, but not limited to, a heating coil, an anti-fog coating, and the like.
The image capturing device may include, but is not limited to, a fisheye lens for capturing a wide-angle shot.
Optionally, in this embodiment, the cloud platform 306 is a central platform of the edge gateway 302, and is also a service platform for executing the article identification method, and is used for gateway access, data acquisition, data storage, data analysis, service presentation, and the like.
Optionally, in this embodiment, the client application software 308 is a client application of an item identification service, and is configured to access data of item identification and service statistical information, where the data includes a web client application software and a mobile client application software.
Optionally, in this embodiment, the maintenance tool application 310 supports local management and maintenance of the edge gateway 302 through bluetooth, including functions of parameter configuration, firmware upgrade, and the like.
Optionally, in this embodiment, the target area may include, but is not limited to, a target area that can be acquired by the image acquisition device, and may also include, but is not limited to, a target area that is configured in advance by a worker.
Optionally, in this embodiment, the first article image is an article image acquired by the image acquisition device this time, the second article image is a pre-stored article image, and the second article image may include, but is not limited to, an image acquired by the image acquisition device in a previous round so as to be stored in an associated database.
Alternatively, in the present embodiment, the above-mentioned articles may include but are not limited to identifiable articles such as goods, commodities, containers, and the like.
Optionally, in this embodiment, the image difference information may include, but is not limited to, extracting a feature vector for representing image information through a feature extraction algorithm, obtaining a difference vector after comparing the feature vector corresponding to the first item image with the feature vector corresponding to the second item image, so as to determine the difference vector as the image difference information, and may also include, but is not limited to, determining a pixel value difference of each position in the first item image and the second item image, and determining the pixel value difference as the image difference information. The above is merely an example, and the present embodiment is not limited in any way.
According to the embodiment, the first article image acquired by the image acquisition equipment after the target area is shot is acquired, the image difference information between the first article image and the second article image is determined, and the image difference information is sent to the server under the condition that the image difference information does not reach the preset condition, so that the server can identify the changed article between the first article image and the second article image according to the image difference information, therefore, the technical problem that the identification efficiency of the article to be identified in the identification process is low in the related technology can be solved, and the technical effects of improving the identification efficiency of the article, reducing the identification cost of the article and increasing the application range of the article identification algorithm are achieved.
As an alternative, determining image difference information between the first item image information and the second item image information includes: segmenting the first article image according to a preset segmentation mode to obtain a preset number of first sub-images; comparing each first sub-image with a second sub-image of a corresponding area included in the second object image, determining a first sub-image which is different from the second sub-image of the corresponding area, and determining the first sub-image which is different from the second sub-image of the corresponding area as a target sub-image; determining the image difference information based on the target sub-image.
Optionally, in this embodiment, the predetermined dividing manner may include, but is not limited to, equally dividing the first item image into a plurality of regions, and may also include, but is not limited to, dividing the first item image into a plurality of regions equal to the number of items according to the number of identified items, where the predetermined number may be configured in advance by a system or a server, and may also be determined according to the number of identified items.
Optionally, in this embodiment, the method may include, but is not limited to, segmenting the second item image in the same manner as the first item image to obtain a second sub-image of the included corresponding area, and further determining the image difference information by comparing the first sub-image and the second sub-image.
Optionally, in this embodiment, the image difference information may include, but is not limited to, a position, a color, a function, a shape, and the like of the article.
According to the embodiment, the first article image acquired by the image acquisition equipment after the target area is shot is acquired, the image difference information between the first article image and the second article image is determined, and the image difference information is sent to the server under the condition that the image difference information does not reach the preset condition, so that the server can identify the changed article between the first article image and the second article image according to the image difference information, therefore, the technical problem that the identification efficiency of the article to be identified in the identification process is low in the related technology can be solved, and the technical effects of improving the identification efficiency of the article, reducing the identification cost of the article and increasing the application range of the article identification algorithm are achieved.
As an alternative, segmenting the first article image according to a predetermined segmentation manner to obtain a predetermined number of first sub-images includes: identifying the first article image, and acquiring the number of articles contained in the first article image and an area corresponding to each article; and segmenting the first item image based on the area corresponding to each item in the first item image to obtain first sub-images with the same quantity as the items.
Optionally, in this embodiment, the number of items included in the first item image may be determined by including, but not limited to, an identification algorithm, and the area corresponding to each item may include, but is not limited to, obtaining location information of the item to determine, for example, by obtaining a start coordinate, a width, a height, and the like of each item in the first item image to determine the area corresponding to each item lock.
Optionally, in this embodiment, the number of the first sub-images may be the same as the number of the items, in other words, after the first item image is identified, the first item image may be divided into a form in which each first sub-image contains one item.
According to the embodiment, the number of the articles contained in the first article image and the area corresponding to each article are acquired by identifying the first article image; the first article image is segmented based on the area corresponding to each article in the first article image to obtain the first sub-images with the number equal to the number of the articles, so that the technical problem that the identification efficiency of the article to be identified in the identification process is low in the related technology can be solved, and the technical effects of improving the identification efficiency of the article, reducing the identification cost of the article and increasing the application range of the article identification algorithm are achieved.
As an optional scheme, comparing each of the first sub-images with a second sub-image of a corresponding area included in the second item image, determining a first sub-image that differs from the second sub-image of the corresponding area, and determining the first sub-image that differs from the second sub-image of the corresponding area as a target sub-image, includes: comparing the area corresponding to each first sub-image with a second sub-image of the corresponding area included in the second object image, determining the changed first sub-image as the target sub-image, and determining the number of the target sub-images; determining a ratio of the number of the target sub-images to the number of the first sub-images as the image difference information.
Optionally, in this embodiment, the determining that the changed first sub-image is the target sub-image may include, but is not limited to, comparing the first sub-image with the second sub-image, and recording that the feature information of the article has changed or the position of the article has changed.
Optionally, in this embodiment, the changed first sub-image is determined as the target sub-image, and a ratio between the target sub-image and the number of the first sub-images is determined as the image difference information.
According to the embodiment, the area corresponding to each first sub-image is compared with the second sub-image of the corresponding area in the second object image, the changed first sub-image is determined to be the target sub-image, and the number of the target sub-images is determined; the ratio of the number of the target sub-images to the number of the first sub-images is determined as image difference information, and the image difference information is sent to the server under the condition that the image difference information does not reach a preset condition, so that the server identifies the changed article between the first article image and the second article image according to the image difference information, therefore, the technical problem that the identification efficiency of the article to be identified is low in the identification process in the related technology can be solved, and the technical effects of improving the identification efficiency of the article, reducing the identification cost of the article and increasing the application range of the article identification algorithm are achieved.
As an alternative, segmenting the first article image according to a predetermined segmentation manner to obtain a predetermined number of first sub-images includes: identifying the first article image, and acquiring a plurality of preset areas contained in the first article image; and segmenting the first article image based on the preset areas to obtain a plurality of first sub-images corresponding to the preset areas in number.
Optionally, in this embodiment, the first article image may be divided into a plurality of preset regions according to a predetermined dividing manner, so as to obtain a plurality of first sub-images corresponding to the number of the preset regions.
According to the embodiment, the method comprises the steps of identifying a first article image to obtain a plurality of preset areas contained in the first article image; the first article image is segmented based on the preset areas to obtain a plurality of first sub-images corresponding to the preset areas in number, so that the server can identify the article with the change between the first article image and the second article image according to the image difference information, therefore, the technical problem that the identification efficiency of the article to be identified in the identification process is low in the related technology can be solved, and the technical effects of improving the identification efficiency of the article, reducing the identification cost of the article and increasing the application range of the article identification algorithm are achieved.
As an optional scheme, comparing each of the first sub-images with a second sub-image of a corresponding area included in the second item image, determining a first sub-image that differs from the second sub-image of the corresponding area, and determining the first sub-image that differs from the second sub-image of the corresponding area as a target sub-image, includes: comparing each preset area with a plurality of preset areas included in the second object image, determining the changed preset areas as the target sub-images, and determining the number of the target sub-images; determining a ratio of the number of the target sub-images to the number of the first sub-images as the image difference information.
Optionally, in this embodiment, the determining that the changed preset region is the target sub-image may include, but is not limited to, comparing the preset region of the first sub-image with the preset region of the second sub-image, and recording that the feature information of the article has changed or the position of the article has changed.
Optionally, in this embodiment, the changed first sub-image is determined as the target sub-image, and a ratio between the target sub-image and the number of the first sub-images is determined as the image difference information.
According to the embodiment, each preset area is compared with a plurality of preset areas included in the second object image, the changed preset area is determined to be the target sub-image, and the number of the target sub-images is determined; the ratio of the number of the target sub-images to the number of the first sub-images is determined as the image difference information, so that the server identifies the changed article between the first article image and the second article image according to the image difference information, therefore, the technical problem that the identification efficiency of the article to be identified is low in the identification process in the related technology can be solved, and the technical effects of improving the identification efficiency of the article, reducing the identification cost of the article and increasing the application range of the article identification algorithm are achieved.
As an alternative, after determining image difference information between the first item image and the second item image, the method further comprises: and when the image difference information reaches the preset condition, sending the first article image to the server so that the server identifies the article with the change between the first article image and the second article image received in advance.
Optionally, in this embodiment, the preset condition may be determined according to a statistical manner including, but not limited to, image difference information, for example, when the image difference information is a ratio of the number of the target sub-images to the number of the first sub-images, the preset condition is configured as a ratio threshold, and when the image difference information is greater than or equal to the ratio threshold corresponding to the preset condition, the first item image is sent to the server, so that the server identifies the first item image.
In other words, when the image difference information exceeds the threshold corresponding to the preset condition, the first article image is completely sent to the server, so that the server re-identifies the first article image to obtain a corresponding identification result.
As an alternative, determining image difference information between the first item image and the second item image comprises: determining first image information of the first item image; comparing the first image information with second image information of the second object image determined in advance to determine the image difference information; after determining image difference information between the first and second item images, the method further comprises: and when the image difference information reaches the preset condition, sending the first image information to a server so that the server can identify the changed article between the first article image and the second article image according to the first image information and the predetermined second image information.
Optionally, in this embodiment, the preset condition may be determined according to a statistical manner including, but not limited to, image difference information, for example, when the image difference information is a ratio of the number of the target sub-images to the number of the first sub-images, the preset condition is configured as a ratio threshold, and when the image difference information is smaller than the ratio threshold corresponding to the preset condition, the first image information is sent to the server, so that the server identifies the first article image.
When the image difference information does not exceed the threshold corresponding to the preset condition, the image information that only includes the change area and is obtained after the first article image is identified is sent to the server, so that the server obtains a corresponding identification result based on the image information of the change area.
According to the embodiment, under the condition that the image difference information reaches the preset condition, the first image information is sent to the server, so that the server can identify the changed article between the first article image and the second article image according to the first image information and the predetermined second image information, therefore, the technical problem that the identification efficiency of the article to be identified in the identification process is low in the related technology can be solved, and the technical effects of improving the identification efficiency of the article, reducing the identification cost of the article and increasing the application range of the article identification algorithm are achieved.
As an alternative, before determining image difference information between the first item image and the second item image, the method further comprises: acquiring the second article image acquired by the image acquisition equipment after shooting the target area; and sending the second article image to the server.
Optionally, in this embodiment, the second item image may include, but is not limited to, an item image sent to the server after the recognition result reaches the preset condition in the last recognition process, and may also include, but is not limited to, a second item image obtained after the target area is photographed by the image capturing device and stored in a preconfigured database.
According to the embodiment, a second object image obtained after the target area is shot by the image acquisition equipment is obtained; the second article image is sent to the server, so that the target area can be monitored, the technical problem that the identification efficiency of the article to be identified in the identification process is low in the related technology is solved, and the technical effects of improving the identification efficiency of the article, reducing the identification cost of the article and enlarging the application range of the article identification algorithm are achieved.
As an optional scheme, after acquiring the first article image obtained by capturing the target area by the image capturing device, the method further includes: determining a storage time of the second item image; and sending the first item image to the server when the storage time exceeds a preset time.
Optionally, in this embodiment, the storage time of the second item image may include, but is not limited to, a length of time stored in the database, and may also include, but is not limited to, a storage time generated after comparing the timestamp recorded after the second item image is acquired with the system time.
As an optional scheme, after the difference information is sent to a server under the condition that the difference information does not meet a preset condition, the method further includes: the server identifies the image difference information to determine an item which is changed between the first item image and the second item image; the server determines information of an item included in the first item image based on information of the item that is changed between the first item image and the second item image, and information of an item included in the second item image.
Optionally, in this embodiment, the server may include, but is not limited to, determining a name or a type of an item stored in the target area based on information of the item that is changed between the first item image and the second item image.
Alternatively, in this embodiment, after the server determines the information of the item included in the first item image based on the information of the item that is changed between the first item image and the second item image and the information of the item included in the second item image, it may include, but is not limited to, performing saving, analyzing, and displaying the present item identification result, for example, saving an item name, an item type, and the like included in the first item image.
According to the embodiment, the server is adopted to identify the image difference information so as to determine the changed article between the first article image and the second article image; the server determines information of the item included in the first item image based on the information of the item that is changed between the first item image and the second item image, and the information of the item included in the second item image. Therefore, the technical problem that the identification efficiency of the to-be-identified article in the identification process is low in the related technology can be solved, and the technical effects of improving the identification efficiency of the article, reducing the identification cost of the article and increasing the application range of the article identification algorithm are achieved.
The invention is further explained below with reference to specific examples:
the artificial intelligent commodity identification system comprises an edge gateway, a cloud platform, a client application and a maintenance tool application.
The edge gateway of the present invention comprises:
an edge gateway body;
the edge gateway body is provided with a plurality of USB interfaces for supplying power to the plurality of camera bodies;
the edge gateway body is provided with a plurality of USB interfaces for carrying out data communication with the camera body, including control management and picture data acquisition;
the edge gateway body is provided with a communication module (including but not limited to a wireless network and a mobile communication network) for accessing a cloud platform to realize data reporting and remote control;
the edge gateway body is provided with an artificial intelligence calculation module which is used for artificial intelligence recognition of shot pictures, positioning all goods positions in the pictures and extracting key goods information, wherein the goods information comprises position information (initial coordinates, width and height in the pictures) and goods pictures;
the edge gateway body is provided with an external antenna of a communication module;
the edge gateway body is provided with an indicator light for displaying the working state of the edge gateway body, wherein the working state comprises but is not limited to connection, working state and engineering mode, and the flashing indicates the state of a receiving and sending packet when the data packet is received and sent;
the edge gateway body is provided with a reset key for controlling the edge gateway body to enter an engineering mode, starting Bluetooth local maintenance service and communicating with maintenance tool application software;
a camera module body;
the camera module body is provided with a USB connecting line for accessing the edge gateway body to obtain power supply and data communication;
the camera module body is provided with a camera sensor for collecting goods display photos or video data;
the camera module body is provided with a protective device for preventing the lens from fogging and blurring, and the protective device comprises a heating coil and an antifogging coating;
the camera module body is provided with a fisheye lens for acquiring a wide-angle shot picture;
the cloud platform is a central platform of an edge gateway, is also a service platform for goods identification, and is used for gateway access, data acquisition, data storage, data analysis and service presentation;
the client application software is a client application of goods identification service, is used for accessing data of goods identification and service statistical information, and comprises webpage client application software and mobile client application software.
The maintenance tool application software supports local management and maintenance of the edge gateway through Bluetooth, and comprises functions of parameter configuration, firmware upgrading and the like;
fig. 4 is a schematic diagram of an alternative method for identifying an item according to an embodiment of the present invention, as shown in fig. 4, the flow includes, but is not limited to, the following steps:
s1, the edge gateway obtains the shot current photo 402 through the camera module;
s2, the edge gateway carries out artificial intelligence recognition on the shot picture, positions and frames each goods in the picture;
s3, the edge gateway compares the current recognition result (current photo 402) with the last recognition result (last photo 406) and calculates the difference (differential goods photo 404);
s4, when the difference reaches the threshold value, reporting all the identified goods information, and when the difference does not reach the threshold value, reporting the goods information identified by the change area;
s5, the edge gateway reports goods information to the cloud platform, wherein the goods information comprises goods position information (initial coordinates, width and height in the photo), goods photo and the like;
s6, the cloud platform receives each item information reported by the edge gateway, carries out artificial intelligent item identification on the item photo, and determines the item name specifically;
s7, the cloud platform updates the identification result of the goods in the change area by combining the identification result of the goods with the difference and the last identification result to obtain the complete identification result;
and S8, the cloud platform stores, analyzes and presents the recognition result data.
Wherein, the identifying the goods reporting mechanism (corresponding to the aforementioned sending the first goods image to the server or sending the first image information to the server) comprises at least one of the following:
reporting the total amount for the first time: when the edge gateway is started for the first time, reporting all goods identified in the photo;
and (3) reporting the whole quantity periodically: the edge gateway judges that all the goods identified in the picture are reported when the time interval from the last reporting of all the goods reaches a certain time interval threshold;
reporting the total amount of large-scale change: the edge gateway judges that when the proportion of the change of the goods identified last time reaches a certain proportion threshold value, all the goods information identified in the photo is reported;
reporting a small amount of change difference: and the edge gateway only reports the information of the changed goods identified in the photo when the proportion of the change of the goods identified last time is judged to be smaller than a certain proportion threshold value.
According to the technical scheme, the artificial intelligent commodity identification method and the artificial intelligent commodity identification system are combined with the edge gateway and the cloud platform, the edge gateway with the artificial intelligent computing capability is used for completing basic identification of goods in the photo, picture information of a goods area is extracted, and then the picture information is handed to the cloud platform to complete identification of specific goods names; through the edge gateway differential judgment mechanism, only the goods information of the changed area is reported, so that the uploaded picture data volume can be greatly reduced, the communication flow is saved, the useful service information is greatly improved, the identification and differential reporting mechanism is met, the actual condition that customers take goods from containers and freezers in service scenes is met, continuous and reliable information datamation is provided for big data analysis of new retail enterprises, and the technical effect of improving the overall operation efficiency of the retail enterprises is finally helped.
Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
In this embodiment, an article identification apparatus is further provided, and the apparatus is used to implement the foregoing embodiments and preferred embodiments, and the description that has been given is omitted. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
Fig. 5 is a block diagram illustrating an alternative item identification apparatus according to an embodiment of the present invention, as shown in fig. 5, the apparatus including:
an obtaining module 502, configured to obtain a first article image obtained by capturing a target area by an image capturing device;
a determining module 504, configured to determine image difference information between the first item image and a second item image, where the second item image is a pre-shot image;
a sending module 506, configured to send the image difference information to a server when the image difference information does not meet a preset condition, so that the server identifies an item, which is changed between the first item image and the second item image, according to the image difference information.
As an alternative, the apparatus is configured to determine image difference information between the first item image information and the second item image information by: segmenting the first article image according to a preset segmentation mode to obtain a preset number of first sub-images; comparing each first sub-image with a second sub-image of a corresponding area included in the second object image, determining a first sub-image which is different from the second sub-image of the corresponding area, and determining the first sub-image which is different from the second sub-image of the corresponding area as a target sub-image; determining the image difference information based on the target sub-image.
As an alternative, the apparatus is configured to segment the first image of the item according to a predetermined segmentation scheme to obtain a predetermined number of first sub-images by: identifying the first article image, and acquiring the number of articles contained in the first article image and an area corresponding to each article; and segmenting the first item image based on the area corresponding to each item in the first item image to obtain first sub-images with the same quantity as the items.
As an alternative, the apparatus is configured to compare each of the first sub-images with a second sub-image of a corresponding area included in the second image of the item, determine a first sub-image that is different from the second sub-image of the corresponding area, and determine the first sub-image that is different from the second sub-image of the corresponding area as the target sub-image: comparing the area corresponding to each first sub-image with a second sub-image of the corresponding area included in the second object image, determining the changed first sub-image as the target sub-image, and determining the number of the target sub-images; determining a ratio of the number of the target sub-images to the number of the first sub-images as the image difference information.
As an alternative, the apparatus is configured to segment the first image of the item according to a predetermined segmentation scheme to obtain a predetermined number of first sub-images by: identifying the first article image, and acquiring a plurality of preset areas contained in the first article image; and segmenting the first article image based on the preset areas to obtain a plurality of first sub-images corresponding to the preset areas in number.
As an alternative, the apparatus is configured to compare each of the first sub-images with a second sub-image of a corresponding area included in the second image of the item, determine a first sub-image that is different from the second sub-image of the corresponding area, and determine the first sub-image that is different from the second sub-image of the corresponding area as the target sub-image: comparing each preset area with a plurality of preset areas included in the second object image, determining the changed preset areas as the target sub-images, and determining the number of the target sub-images; determining a ratio of the number of the target sub-images to the number of the first sub-images as the image difference information.
As an optional solution, the apparatus is further configured to: after determining image difference information between the first article image and a second article image, if the image difference information reaches the preset condition, the first article image is sent to the server, so that the server identifies an article with a change between the first article image and the second article image received in advance.
As an alternative, the apparatus is configured to determine image difference information between the first item image and the second item image by: determining first image information of the first item image; comparing the first image information with second image information of the second object image determined in advance to determine the image difference information; after determining image difference information between the first and second item images, the method further comprises: and when the image difference information reaches the preset condition, sending the first image information to a server so that the server can identify the changed article between the first article image and the second article image according to the first image information and the predetermined second image information.
As an optional solution, the apparatus is further configured to: before determining image difference information between the first article image and a second article image, acquiring the second article image acquired by the image acquisition equipment after shooting the target area; and sending the second article image to the server.
As an optional solution, the apparatus is further configured to: after a first article image acquired by image acquisition equipment and obtained by shooting a target area is acquired, determining the storage time of the second article image; and sending the first item image to the server when the storage time exceeds a preset time.
As an optional solution, the apparatus is further configured to: under the condition that the difference information does not reach the preset condition, after the difference information is sent to a server, the server identifies the image difference information to determine an article which is changed between the first article image and the second article image; the server determines information of an item included in the first item image based on information of the item that is changed between the first item image and the second item image, and information of an item included in the second item image.
It should be noted that, the above modules may be implemented by software or hardware, and for the latter, the following may be implemented, but not limited to: the modules are all positioned in the same processor; alternatively, the modules are respectively located in different processors in any combination.
Embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program is arranged to perform the steps of any of the above-mentioned method embodiments when executed.
In the present embodiment, the above-mentioned computer-readable storage medium may be configured to store a computer program for executing the steps of:
s1, acquiring a first article image acquired by the image acquisition equipment after the target area is shot;
s2, determining image difference information between the first article image and a second article image, wherein the second article image is a pre-shot image;
and S3, when the image difference information does not reach the preset condition, sending the image difference information to the server so that the server can identify the changed article between the first article image and the second article image according to the image difference information.
The computer readable storage medium is further arranged to store a computer program for performing the steps of:
s1, acquiring a first article image acquired by the image acquisition equipment after the target area is shot;
s2, determining image difference information between the first article image and a second article image, wherein the second article image is a pre-shot image;
and S3, when the image difference information does not reach the preset condition, sending the image difference information to the server so that the server can identify the changed article between the first article image and the second article image according to the image difference information.
In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to: various media capable of storing computer programs, such as a usb disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk.
Embodiments of the present invention also provide an electronic device comprising a memory having a computer program stored therein and a processor arranged to run the computer program to perform the steps of any of the above method embodiments.
In an exemplary embodiment, the electronic apparatus may further include a transmission device and an input/output device, wherein the transmission device is connected to the processor, and the input/output device is connected to the processor.
In an exemplary embodiment, the processor may be configured to execute the following steps by a computer program:
s1, acquiring a first article image acquired by the image acquisition equipment after the target area is shot;
s2, determining image difference information between the first article image and a second article image, wherein the second article image is a pre-shot image;
and S3, when the image difference information does not reach the preset condition, sending the image difference information to the server so that the server can identify the changed article between the first article image and the second article image according to the image difference information.
For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary embodiments, and details of this embodiment are not repeated herein.
It will be apparent to those skilled in the art that the various modules or steps of the invention described above may be implemented using a general purpose computing device, they may be centralized on a single computing device or distributed across a network of computing devices, and they may be implemented using program code executable by the computing devices, such that they may be stored in a memory device and executed by the computing device, and in some cases, the steps shown or described may be performed in an order different than that described herein, or they may be separately fabricated into various integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the principle of the present invention should be included in the protection scope of the present invention.
Claims (14)
1. A method of identifying an item, comprising:
acquiring a first article image acquired by image acquisition equipment after shooting a target area;
determining image difference information between the first article image and a second article image, wherein the second article image is a pre-shot image;
and under the condition that the image difference information does not reach the preset condition, sending the image difference information to a server so that the server can identify the changed article between the first article image and the second article image according to the image difference information.
2. The method of claim 1, wherein determining image difference information between the first item image information and second item image information comprises:
segmenting the first article image according to a preset segmentation mode to obtain a preset number of first sub-images;
comparing each first sub-image with a second sub-image of a corresponding area included in the second object image, determining a first sub-image which is different from the second sub-image of the corresponding area, and determining the first sub-image which is different from the second sub-image of the corresponding area as a target sub-image;
determining the image difference information based on the target sub-image.
3. The method of claim 2, wherein segmenting the first image of the item according to a predetermined segmentation to obtain a predetermined number of first sub-images comprises:
identifying the first article image, and acquiring the number of articles contained in the first article image and an area corresponding to each article;
and segmenting the first item image based on the area corresponding to each item in the first item image to obtain first sub-images with the same quantity as the items.
4. The method of claim 3, wherein comparing each of the first sub-images with a second sub-image of a corresponding region included in the second image of the item, determining a first sub-image that differs from the second sub-image of the corresponding region, and determining the first sub-image that differs from the second sub-image of the corresponding region as the target sub-image comprises:
comparing the area corresponding to each first sub-image with a second sub-image of the corresponding area included in the second object image, determining the changed first sub-image as the target sub-image, and determining the number of the target sub-images;
determining a ratio of the number of the target sub-images to the number of the first sub-images as the image difference information.
5. The method of claim 2, wherein segmenting the first image of the item according to a predetermined segmentation to obtain a predetermined number of first sub-images comprises:
identifying the first article image, and acquiring a plurality of preset areas contained in the first article image;
and segmenting the first article image based on the preset areas to obtain a plurality of first sub-images corresponding to the preset areas in number.
6. The method of claim 5, wherein comparing each of the first sub-images with a second sub-image of a corresponding region included in the second image of the item, determining a first sub-image that differs from the second sub-image of the corresponding region, and determining the first sub-image that differs from the second sub-image of the corresponding region as the target sub-image comprises:
comparing each preset area with a plurality of preset areas included in the second object image, determining the changed preset areas as the target sub-images, and determining the number of the target sub-images;
determining a ratio of the number of the target sub-images to the number of the first sub-images as the image difference information.
7. The method of claim 1, wherein after determining image difference information between the first and second item images, the method further comprises:
and when the image difference information reaches the preset condition, sending the first article image to the server so that the server identifies the article with the change between the first article image and the second article image received in advance.
8. The method of claim 1,
determining image difference information between the first and second item images comprises: determining first image information of the first item image; comparing the first image information with second image information of the second object image determined in advance to determine the image difference information;
after determining image difference information between the first and second item images, the method further comprises: and when the image difference information reaches the preset condition, sending the first image information to a server so that the server can identify the changed article between the first article image and the second article image according to the first image information and the predetermined second image information.
9. The method of claim 1, wherein prior to determining image difference information between the first and second item images, the method further comprises:
acquiring the second article image obtained after the image acquisition equipment shoots the target area;
and sending the second article image to the server.
10. The method of claim 1, wherein after acquiring the first item image captured by the image capture device after capturing the target area, the method further comprises:
determining a storage time of the second item image;
and sending the first item image to the server when the storage time exceeds a preset time.
11. The method according to claim 1, wherein after sending the difference information to a server if the difference information does not meet a preset condition, the method further comprises:
the server identifies the image difference information to determine an item which is changed between the first item image and the second item image;
the server determines information of an item included in the first item image based on information of the item that is changed between the first item image and the second item image, and information of an item included in the second item image.
12. An article identification device, comprising:
the acquisition module is used for acquiring a first article image acquired by the image acquisition equipment after the target area is shot;
the determining module is used for determining image difference information between the first article image and a second article image, wherein the second article image is a pre-shot image;
the sending module is used for sending the image difference information to a server under the condition that the image difference information does not reach a preset condition, so that the server can identify the changed article between the first article image and the second article image according to the image difference information.
13. A computer-readable storage medium, in which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 11.
14. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method as claimed in any of claims 1 to 11 are implemented when the computer program is executed by the processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011425560.3A CN112613358B (en) | 2020-12-08 | 2020-12-08 | Article identification method, article identification device, storage medium and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011425560.3A CN112613358B (en) | 2020-12-08 | 2020-12-08 | Article identification method, article identification device, storage medium and electronic device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112613358A true CN112613358A (en) | 2021-04-06 |
| CN112613358B CN112613358B (en) | 2024-06-21 |
Family
ID=75229401
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011425560.3A Active CN112613358B (en) | 2020-12-08 | 2020-12-08 | Article identification method, article identification device, storage medium and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112613358B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113610004A (en) * | 2021-08-09 | 2021-11-05 | 上海擎朗智能科技有限公司 | Image processing method, robot and medium |
| CN113627323A (en) * | 2021-08-09 | 2021-11-09 | 上海擎朗智能科技有限公司 | Image processing method, robot and medium |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120320223A1 (en) * | 2011-06-15 | 2012-12-20 | Hon Hai Precision Industry Co., Ltd. | Computing device, storage medium and method for identifying differences between two images |
| US20140003655A1 (en) * | 2012-06-29 | 2014-01-02 | Praveen Gopalakrishnan | Method, apparatus and system for providing image data to represent inventory |
| CN108320379A (en) * | 2018-02-28 | 2018-07-24 | 成都果小美网络科技有限公司 | Good selling method, device and the self-service machine compared based on image |
| CN108416902A (en) * | 2018-02-28 | 2018-08-17 | 成都果小美网络科技有限公司 | Real-time object identification method based on difference identification and device |
| CN108648377A (en) * | 2018-04-10 | 2018-10-12 | 合肥美的智能科技有限公司 | Automatically vending system based on unmanned retail units and method |
| CN109064636A (en) * | 2018-07-10 | 2018-12-21 | 安徽豆智智能装备制造有限公司 | A kind of purchase method of the automatic selling cabinet system based on image recognition |
| CN109272647A (en) * | 2018-08-29 | 2019-01-25 | 北京华沁智联科技有限公司 | The update method and device of automatic vending warehouse item state |
| WO2019111501A1 (en) * | 2017-12-04 | 2019-06-13 | 日本電気株式会社 | Image processing device |
| CN109949479A (en) * | 2019-03-18 | 2019-06-28 | 成都好享你网络科技有限公司 | Data processing method, device and intelligent vending machine based on image difference |
| US20190236530A1 (en) * | 2018-01-31 | 2019-08-01 | Walmart Apollo, Llc | Product inventorying using image differences |
| CN110490516A (en) * | 2019-08-01 | 2019-11-22 | 广州织点智能科技有限公司 | A kind of unmanned store shelf article detection method and device |
| CN110751028A (en) * | 2019-09-10 | 2020-02-04 | 深圳码隆科技有限公司 | Transaction method and device based on intelligent sales counter |
| CN111062415A (en) * | 2019-11-12 | 2020-04-24 | 中南大学 | Target object image extraction method and system based on contrast difference and storage medium |
| CN111340009A (en) * | 2020-05-15 | 2020-06-26 | 支付宝(杭州)信息技术有限公司 | Identification method and device |
-
2020
- 2020-12-08 CN CN202011425560.3A patent/CN112613358B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120320223A1 (en) * | 2011-06-15 | 2012-12-20 | Hon Hai Precision Industry Co., Ltd. | Computing device, storage medium and method for identifying differences between two images |
| US20140003655A1 (en) * | 2012-06-29 | 2014-01-02 | Praveen Gopalakrishnan | Method, apparatus and system for providing image data to represent inventory |
| WO2019111501A1 (en) * | 2017-12-04 | 2019-06-13 | 日本電気株式会社 | Image processing device |
| US20190236530A1 (en) * | 2018-01-31 | 2019-08-01 | Walmart Apollo, Llc | Product inventorying using image differences |
| CN108416902A (en) * | 2018-02-28 | 2018-08-17 | 成都果小美网络科技有限公司 | Real-time object identification method based on difference identification and device |
| CN108320379A (en) * | 2018-02-28 | 2018-07-24 | 成都果小美网络科技有限公司 | Good selling method, device and the self-service machine compared based on image |
| CN108648377A (en) * | 2018-04-10 | 2018-10-12 | 合肥美的智能科技有限公司 | Automatically vending system based on unmanned retail units and method |
| CN109064636A (en) * | 2018-07-10 | 2018-12-21 | 安徽豆智智能装备制造有限公司 | A kind of purchase method of the automatic selling cabinet system based on image recognition |
| CN109272647A (en) * | 2018-08-29 | 2019-01-25 | 北京华沁智联科技有限公司 | The update method and device of automatic vending warehouse item state |
| CN109949479A (en) * | 2019-03-18 | 2019-06-28 | 成都好享你网络科技有限公司 | Data processing method, device and intelligent vending machine based on image difference |
| CN110490516A (en) * | 2019-08-01 | 2019-11-22 | 广州织点智能科技有限公司 | A kind of unmanned store shelf article detection method and device |
| CN110751028A (en) * | 2019-09-10 | 2020-02-04 | 深圳码隆科技有限公司 | Transaction method and device based on intelligent sales counter |
| CN111062415A (en) * | 2019-11-12 | 2020-04-24 | 中南大学 | Target object image extraction method and system based on contrast difference and storage medium |
| CN111340009A (en) * | 2020-05-15 | 2020-06-26 | 支付宝(杭州)信息技术有限公司 | Identification method and device |
Non-Patent Citations (2)
| Title |
|---|
| M. MARDER等: "Using image analytics to monitor retail store shelves", 《IBM J. RES. & DEV.》, vol. 59, no. 3, 31 May 2015 (2015-05-31), pages 1 - 11 * |
| 周诺亚: "无人零售环境下的深度学习商品检测研究", 《中国优秀硕士学位论文全文数据库信息科技辑》, no. 3, 15 March 2020 (2020-03-15), pages 138 - 1214 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113610004A (en) * | 2021-08-09 | 2021-11-05 | 上海擎朗智能科技有限公司 | Image processing method, robot and medium |
| CN113627323A (en) * | 2021-08-09 | 2021-11-09 | 上海擎朗智能科技有限公司 | Image processing method, robot and medium |
| CN113610004B (en) * | 2021-08-09 | 2024-04-05 | 上海擎朗智能科技有限公司 | Image processing method, robot and medium |
| CN113627323B (en) * | 2021-08-09 | 2024-05-07 | 上海擎朗智能科技有限公司 | Image processing method, robot and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112613358B (en) | 2024-06-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108521808B (en) | Obstacle information display method, display device, unmanned aerial vehicle and system | |
| CN109607031B (en) | Intelligent warehousing system and method based on unmanned aerial vehicle panorama | |
| CN109299703B (en) | Method and device for carrying out statistics on mouse conditions and image acquisition equipment | |
| US9875411B2 (en) | Video monitoring method, video monitoring apparatus and video monitoring system | |
| CN109255568A (en) | A kind of intelligent warehousing system based on image recognition | |
| CN111294563B (en) | Video monitoring method and device, storage medium and electronic device | |
| CN112613358B (en) | Article identification method, article identification device, storage medium and electronic device | |
| US11037303B2 (en) | Optical flow based detection and tracking of multiple moving objects in successive frames | |
| CN109960969B (en) | Method, device and system for generating moving route | |
| CN111291646A (en) | People flow statistical method, device, equipment and storage medium | |
| CN111310727A (en) | Object detection method and device, storage medium and electronic device | |
| CN110446082B (en) | Advertisement pushing method, information processing method and related product | |
| CN115861236A (en) | Method and device for determining dripping event, storage medium and electronic device | |
| CN113938674B (en) | Video quality detection method, device, electronic equipment and readable storage medium | |
| CN114782899A (en) | Image processing method and device and electronic equipment | |
| CN107845105A (en) | A kind of monitoring method, smart machine and storage medium based on the linkage of panorama rifle ball | |
| CN110505438B (en) | Queuing data acquisition method and camera | |
| US11704516B2 (en) | Electronic label management apparatus and method | |
| CN111246110B (en) | Image output method and device, storage medium and electronic device | |
| US9875549B2 (en) | Change detection in video data | |
| CN114827464B (en) | Target tracking method and system based on mobile camera | |
| CN113472998B (en) | Image processing method, image processing device, electronic equipment and storage medium | |
| CN112580379A (en) | Data processing system and method, electronic device, and computer-readable storage medium | |
| CN113658229B (en) | Method and device for determining abnormal object, storage medium and electronic device | |
| CN111669614A (en) | Video shooting method, device and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20220425 Address after: 310053 Block C, 3D building, 581 torch Avenue, Binjiang District, Hangzhou City, Zhejiang Province Applicant after: SUNWAVE COMMUNICATIONS Co.,Ltd. Address before: 310053 Room C, 3D building, 581 torch Avenue, Binjiang District, Hangzhou City, Zhejiang Province 310053 Applicant before: Zhejiang Sanwei wanyilian Technology Co.,Ltd. Applicant before: SUNWAVE COMMUNICATIONS Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant |