CN110059753A - Model training method, interlayer are every recognition methods, device, equipment and medium - Google Patents
Model training method, interlayer are every recognition methods, device, equipment and medium Download PDFInfo
- Publication number
- CN110059753A CN110059753A CN201910319329.7A CN201910319329A CN110059753A CN 110059753 A CN110059753 A CN 110059753A CN 201910319329 A CN201910319329 A CN 201910319329A CN 110059753 A CN110059753 A CN 110059753A
- Authority
- CN
- China
- Prior art keywords
- interlayer
- subject image
- training
- label
- model
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (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
Application discloses a kind of model training method, comprising: obtains training sample, the training sample includes subject image and interlayer every label, and the interlayer is used for the interlayer of object in the subject image every label every being labeled；Using training sample training example parted pattern, the example parted pattern for meeting training objective is determined as interlayer every identification model, the interlayer is input with subject image every identification model, with interlayer every recognition result be output.Based on this model, disclosed herein as well is a kind of interlayers every recognition methods.By marking sample learning, it realizes to the target position detection and classification identification in image, to realize the interlayer to objects in images every identification, due to its accuracy of identification with higher, therefore, layer positioning is carried out based on the recognition result and layer counts precision with higher.Disclosed herein as well is corresponding device, equipment and media.
Description
Technical field
This application involves computer fields more particularly to a kind of model training method, interlayer every recognition methods, device, sets
Standby and medium.
Background technique
Computer vision and big data technology are widely applied to retail business, and enterprise is helped quickly to grasp condition of sales and city
Field trend analysis enhances enterprise efficiency and competitiveness.Large-scale Shang Chaozhong, shelf are a kind of main commodity display facilities, are passed through
Shelf image information collection is carried out by the mode that camera is taken pictures, and uses Visual intelligent and big data analysis method, it can be with
Carry out express statistic and the analysis of the display and sales data of commodity.
Wherein, the put number of plies, the particular commodity of shelf are important index in statistical values such as the retail store conditions of the shelf number of plies.
Industry mainly carries out lines detection to picture using computer vision technique at present, selects longer lines as shelf layer level
The edge line of partition carries out shelf layer positioning, to estimate the number of plies in full figure.
This method has problems in the specific implementation process, for example, quotient of the lines detection by shelf presence in image
Product influence very much, and the commodity top edge successively put is easy to be misidentified into the edge line of lattice gear.In addition, for it is multiple not
With the number of plies shelf lay out in parallel the case where, the edge line that accurate shelf lattice gear can not be made according to line length is chosen.
Based on this, it is urgent to provide a kind of interlayers every recognition methods, makes it possible to accurately identification layer interval, and then realize essence
Quasi- stratum positioning or layer count.
Summary of the invention
In view of this, it includes subject image and its interlayer that this method, which utilizes, this application provides a kind of model training method
Interlayer is obtained every identification model every the training sample training example parted pattern of label, which is applied to interlayer every identification,
It can be realized accurate stratum positioning or layer count.Accordingly, present invention also provides interlayers every recognition methods, device, equipment, Jie
Matter and computer program product.
The application first aspect provides a kind of model training method, which comprises
Training sample is obtained, the training sample includes subject image and interlayer every label, and the interlayer is used every label
The interlayer of object is every being labeled in the subject image；
Using training sample training example parted pattern, the example parted pattern for meeting training objective is determined as layer
Be spaced identification model, the interlayer every identification model with subject image be input, with interlayer every recognition result be output.
Optionally, the interlayer includes the posting that polygon is formed every label, and the polygon passes through the N positioned at edge
The point set of a point composition is characterized, and the N is the positive integer greater than 1；
The layer interval region that the interlayer is surrounded every the polygon that recognition result includes N number of point formation.
Optionally, the layer interval region is shown by bitmap form.
Optionally, the example parted pattern includes that target detection convolutional neural networks model based on mask or path are poly-
Close network model.
Optionally, the training sample generates in the following way:
The interlayer of subject image and the subject image is acquired every label, the interlayer every label is divided using example
Sample annotation tool marks gained to the subject image；
According to the subject image and the interlayer every label, the training sample is generated.
Optionally, the method also includes:
The subject image is corrected using image flame detection algorithm；
Then the interlayer is to mark gained to the subject image after correction using example segmentation sample annotation tool every label；
It is then described to include: every the label generation training sample according to the subject image and the interlayer
According to after the correction subject image and the interlayer every label generate the training sample.
Optionally, the object includes shelf or locker.
The application second aspect provides a kind of interlayer every recognition methods, which comprises
Obtain subject image；
By subject image input layer interval identification model, the object that the interlayer is exported every identification model is obtained
The interlayer of image is based on model training method described in the application first aspect every identification model every recognition result, the interlayer
What training generated.
Optionally, the method also includes:
Layer counting and/or layer positioning are carried out every recognition result according to the interlayer.
The application third aspect provides a kind of model training apparatus, and described device includes:
Module is obtained, for obtaining training sample, the training sample includes subject image and interlayer every label, described
Interlayer is used for the interlayer of object in the subject image every label every being labeled；
Training module, for the example point of training objective will to be met using training sample training example parted pattern
It cuts model and is determined as interlayer every identification model, the interlayer is input with subject image every identification model, is tied with interlayer every identification
Fruit is output.
Optionally, the interlayer includes the posting that polygon is formed every label, and the polygon passes through the N positioned at edge
The point set of a point composition is characterized, and the N is the positive integer greater than 1；
The layer interval region that the interlayer is surrounded every the polygon that recognition result includes N number of point formation.
Optionally, the layer interval region is shown by bitmap form.
Optionally, the example parted pattern includes that target detection convolutional neural networks model based on mask or path are poly-
Close network model.
Optionally, described device further include:
Generation module, for acquiring the interlayer of subject image and the subject image every label, the interlayer is every label
That gained is marked to the subject image using example segmentation sample annotation tool, according to the subject image and the interlayer every
Label generates the training sample.
Optionally, described device further include:
Rectification module, for being corrected using image flame detection algorithm to the subject image；
Then the interlayer is to mark gained to the subject image after correction using example segmentation sample annotation tool every label；
Then the generation module is specifically used for:
According to after the correction subject image and the interlayer every label generate the training sample.
Optionally, the object includes shelf or locker.
The application fourth aspect provides a kind of interlayer every identification device, and described device includes:
Module is obtained, for obtaining subject image；
Identification module, for obtaining the interlayer every identification model for subject image input layer interval identification model
The interlayer of the subject image of output is based on described in the application first aspect every identification model every recognition result, the interlayer
Model training method training generate.
Optionally, described device further include:
Processing module, for carrying out layer counting and/or layer positioning every recognition result according to the interlayer.
The 5th aspect of the application provides a kind of equipment, and the equipment includes memory and processor:
The memory is for storing computer program；
The processor be used for according to the computer program execute the application first aspect described in model training method
Or interlayer described in second aspect is every recognition methods.
The 6th aspect of the application provides a kind of computer readable storage medium, is stored with computer in the storage medium
Program, wherein the computer program be arranged to operation when execute model training method described in the application first aspect or
Interlayer described in the application second aspect is every recognition methods.
The 7th aspect of the application provides a kind of computer program product comprising computer-readable instruction, when the computer
When readable instruction is run on computers, so that computer executes model training method described in above-mentioned first aspect or second party
Interlayer described in face is every recognition methods.
As can be seen from the above technical solutions, the embodiment of the present application has the advantage that
The embodiment of the present application provides a kind of model training method, this method by with include subject image and interlayer every
The training sample training example parted pattern of label, the interlayer every label be used for the interlayer of object in the subject image every
It is labeled, by marking sample learning, realizes to the target position detection and classification identification in image, to realize to image
The interlayer of middle object is every identification, due to its accuracy of identification with higher, layer positioning and layer are carried out based on the recognition result
Count precision with higher.
Detailed description of the invention
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of application without any creative labor, may be used also for those of ordinary skill in the art
To obtain other drawings based on these drawings.
Fig. 1 is a kind of scene framework figure of model training method in the embodiment of the present application；
Fig. 2 is a kind of flow chart of model training method in the embodiment of the present application；
Fig. 3 is the schematic diagram of the embodiment of the present application middle layer interval label；
Fig. 4 is the schematic diagram of the embodiment of the present application middle layer interval recognition result；
Fig. 5 is the scene framework figure of the embodiment of the present application middle layer interval recognition methods；
Fig. 6 is the flow chart of the embodiment of the present application middle layer interval recognition methods；
Fig. 7 is the structural schematic diagram of model training apparatus in the embodiment of the present application；
Fig. 8 is the structural schematic diagram of the embodiment of the present application middle layer interval identification device；
Fig. 9 is a structural schematic diagram of server in the embodiment of the present application；
Figure 10 is a structural schematic diagram of terminal in the embodiment of the present application.
Specific embodiment
In order to make those skilled in the art more fully understand application scheme, below in conjunction in the embodiment of the present application
Attached drawing, the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described embodiment is only this
Apply for a part of the embodiment, instead of all the embodiments.Based on the embodiment in the application, those of ordinary skill in the art exist
Every other embodiment obtained under the premise of creative work is not made, shall fall in the protection scope of this application.
The description and claims of this application and term " first ", " second ", " third ", " in above-mentioned attached drawing
The (if present)s such as four " are to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should manage
The data that solution uses in this way are interchangeable under appropriate circumstances, so that embodiments herein described herein for example can be to remove
Sequence other than those of illustrating or describe herein is implemented.In addition, term " includes " and " having " and theirs is any
Deformation, it is intended that cover it is non-exclusive include, for example, containing the process, method of a series of steps or units, system, production
Product or equipment those of are not necessarily limited to be clearly listed step or unit, but may include be not clearly listed or for this
A little process, methods, the other step or units of product or equipment inherently.
Detecting for lines in the prior art is influenced on the commodity much successively put by the commodity of shelf presence in image
Portion edge is easy to the case where being misidentified into the shelf lay out in parallel of the edge line that lattice are kept off and multiple and different numbers of plies, can not
It is chosen according to the edge line that line length makes accurate shelf lattice gear, causing cannot accurate asking of counting of stratum positioning or layer
Topic identifies the interlayer in image every to realize that accurate stratum is fixed this application provides a kind of by training example parted pattern
The method that position or layer count.
Specifically, the training sample for including subject image and interlayer every label is obtained, it is right in training sample by utilizing
The markup information at object layer interval, training example parted pattern, so that point that example parted pattern is split subject image
Cut result and to cut zone whether be interlayer every classification results level off to interlayer every the markup information of label, then will expire
The example parted pattern of sufficient training objective is determined as interlayer every identification model, which is defeated with subject image every identification model
Enter, with interlayer every recognition result to export, interlayer is carried out every identification, Neng Goushi to subject image every identification model using the interlayer
Now accurate stratum positioning or layer count.
Method provided by the embodiments of the present application will be introduced from the angle that model training and model are applied respectively below.
It is appreciated that model training method provided by the present application can be applied to processing arbitrarily with image-capable
Equipment such as has central processing unit (Central Processing Unit/Processor, CPU) and/or graphics processor
The terminal or server of (Graphics Processing Unit, GPU).Wherein, terminal can be desktop computer, laptop
Equal desktop terminals, are also possible to the mobile terminals such as smart phone, tablet computer, can also be car-mounted terminal, wearable intelligence eventually
End etc..
Model training method provided by the present application can be stored in processing equipment in the form of a computer program, and processing is set
Standby pass through executes above-mentioned computer program, to realize model training method provided by the present application.
In order to enable the technical solution of the application it is clearer, it can be readily appreciated that below by from the angle of server, in conjunction with tool
The model training method of the application is introduced in body scene.
Scene framework figure shown in Figure 1 includes terminal 10 and server 20 in the scene, wherein terminal 10 can be with
Using crawl tool from network and crawl including interlayer every subject image, then using annotation tool to the object of subject image
Interlayer every being labeled, to generate training sample, then terminal 10 sends training sample, 20 benefit of server to server 20
With training sample training example parted pattern, the example parted pattern for meeting training objective is determined as interlayer every identification model,
The interlayer every identification model with subject image be input, with interlayer every recognition result be output.
Next, being carried out specifically from the angle of server to each step of model training method provided by the present application
It is bright.
The flow chart of model training method shown in Figure 2, this method comprises:
S201: training sample is obtained.
The training sample includes subject image and interlayer every label, and the interlayer is used for every label to the object figure
The interlayer of object is every being labeled as in.Wherein, subject image be have interlayer every object corresponding to image, so-called interlayer
Object is divided at least two layers of baffle or partition every referring to.Specifically, object can be shelf or locker etc. with layer
The object at interval, certain object be also possible to other with interlayer every object, the present embodiment is not construed as limiting this.It needs to illustrate
, subject image can be the image of an object, is also possible to the image of multiple objects lay out in parallel.
The interlayer of object, which is interposed between on picture, generally has certain vision general character, and by taking shelf as an example, each layer of shelf is used for
The partition shape for putting commodity is usually strip, further, price tag is usually posted on partition, these common features can
With by deep learning for interlayer every detection and identification.
Wherein, deep learning includes a variety of implementations such as supervised learning, unsupervised learning and intensified learning.Specifically
To the present embodiment, interlayer can be realized every detection and identification using supervised learning mode.Supervised learning mode is based on packet
Include what the training sample including label was realized, for this purpose, server first obtains training sample, the training sample include subject image and
Its interlayer is every label.
The embodiment of the present application also provides generate training sample implementation, specifically, first acquisition subject image with
And the interlayer of the subject image is every label, wherein interlayer divides sample after label can be acquisition subject image, using example
This annotation tool marks gained to the subject image, and example segmentation sample annotation tool specifically can be lableme, mark pair
As example can be the interlayer of object in subject image every then according to the subject image and the interlayer every label, generation
The training sample.In order to enable model has preferable Generalization Capability, various types and various can be acquired as much as possible
The object picture of scene is put, to enrich training sample.
It should be noted that there may be visual angle inclinations for subject image, in acquisition object figure based on reasons such as shooting angle
As after, object can also be corrected using image flame detection algorithm, such as correction based on vanishing point etc., in this way, being instructed generating
When practicing sample, can according to after correction subject image and the interlayer every label generate the training sample.
In view of interlayer every true shape, interlayer when being labeled, can be labeled using polygon.It changes
Yan Zhi, the interlayer can be the posting of polygon formation every label, and the layer of object is located at interval at what the polygon was formed
In posting, the polygon is characterized by being located at the point set that N number of point at edge forms, and the N is just whole greater than 1
Number.It is formed when object is shelf as shown in figure 3, its interlayer can be rectangle every label as the example of the application
Posting, which is specifically characterized by the point set that forms of 12 points for being located at 4 sides of rectangle, 31 in Fig. 3
It is shown in which a posting, 32 show a point for forming the point concentration of the posting.
It should be noted that in order to determine polygon, it is desirable that positioned at each side of N number of point covering polygon at edge.
S202: using training sample training example parted pattern, the example parted pattern for meeting training objective is true
It is set to interlayer every identification model.
The interlayer every identification model with subject image be input, with interlayer every recognition result be output.When interlayer is every mark
When label are the posting that polygon is formed, the interlayer includes N number of interlayer putting the polygon formed and being surrounded every recognition result
Septal area domain.Specifically, this layer of interval region can be characterized by being located at the polygon posting of layer spaced peripheral, be embodied in
Positioned at N number of point at polygon posting edge coordinate and whether be interlayer every tag along sort.
Further, which further includes the coordinate for all pixels point that polygon posting includes every recognition result.Such as
This is showing the interlayer when recognition result, as shown in figure 4, can also be shown by bitmap form, 41 in Fig. 4 are with bitmap
Form illustrate an interlayer every recognition result, wherein layer interval region can be identified using pre-set color, such as use
Green is identified.It should be noted that Fig. 4 is the schematic diagram after converting gradation, the true colors of layer interval region are in Fig. 4
It is not shown.
It can only include interlayer in subject image every also may include multiple interlayers every interlayer exists every identification model
When the recognition result of output layer interval, export subject image in each interlayer every recognition result.
Due to interlayer every on the image have vision general character, can by training example parted pattern, utilize example
Parted pattern learns common feature, realizes interlayer every identification.Wherein, example parted pattern may include include the mesh based on mask
Mark detection convolutional neural networks model mask rcnn or path converging network model panet.
When being trained to example parted pattern, its objective function can be set according to actual needs, wherein the target
Function includes at least loss function item, may determine that model training situation by the situation of change of objective function.In some possibility
Implementation in, the training objective of example parted pattern can tend to restrain for the objective function of the example parted pattern, or
Person's objective function is less than preset value.When example parted pattern after training meets above-mentioned training objective, it can determine it as
Interlayer is every identification model, for carrying out interlayer every identification to subject image.
From the foregoing, it will be observed that the embodiment of the present application provides a kind of model training method, this method passes through to include subject image
And interlayer, every the training sample training example parted pattern of label, the interlayer is used for every label to object in the subject image
The interlayer of body is every being labeled, and by marking sample learning, realization detects the target position in image and classification identifies, thus
It realizes to the interlayer of objects in images every identification, due to its accuracy of identification with higher, carried out based on the recognition result
Layer positioning and layer count precision with higher.
Based on above-mentioned model training method, the embodiment of the present application also provides a kind of interlayers every recognition methods.Next, right
Interlayer provided by the embodiments of the present application based on above-mentioned interlayer every identification model is introduced every recognition methods.
It is appreciated that the interlayer can be applied to processing equipment arbitrarily with image-capable every recognition methods, such as
The terminal or server of CPU and/or GPU.Wherein, terminal can be the desktop terminals such as desktop computer, laptop, be also possible to
The mobile terminals such as smart phone, tablet computer can also be car-mounted terminal, wearable intelligent terminal etc..
Interlayer provided by the present application can be stored in processing equipment in the form of a computer program every recognition methods, processing
Equipment realizes interlayer provided by the present application every recognition methods by executing above-mentioned computer program, calling layer interval identification model.
In order to enable the technical solution of the application it is clearer, it can be readily appreciated that below by from the angle of terminal, in conjunction with specific
The interlayer of the application is introduced every recognition methods for scene.
Interlayer shown in Figure 5 includes terminal 10 in the scene every the scene framework figure of recognition methods, and terminal 10 obtains
Subject image, then will be by subject image input layer interval identification model, which is by shown in Fig. 2 every identification model
What the model training method training that embodiment provides generated, terminal 10 obtains the object that the interlayer is exported every identification model again
The interlayer of body image is every recognition result, to realize interlayer every detection and identification.
Next, interlayer provided by the embodiments of the present application is introduced every recognition methods from the angle of terminal.
Interlayer shown in Figure 6 every recognition methods flow chart, this method comprises:
S601: subject image is obtained.
The subject image be specifically to interlayer every object shooting gained image.In practical application, can pass through
Camera is installed in the pre-configured orientation of object, wherein pre-configured orientation is arranged according to actual needs, and terminal can be clapped from camera
Subject image is obtained in the video flowing taken the photograph, camera captured in real-time can also be directly controlled and obtain subject image.
By taking store shelf as an example, the video flowing that terminal can call camera to shoot extracts subject image from video flowing.
It should be noted that also available several frame images, lead in practical application, terminal can only obtain a frame subject image
It crosses and layer positioning and layer counting accuracy rate can be improved using multiple image.
S602: by subject image input layer interval identification model, the institute that the interlayer is exported every identification model is obtained
The interlayer of subject image is stated every recognition result.
The interlayer is that the model training method training based on embodiment illustrated in fig. 2 generates every identification model.By object
After the identification model of body image input layer interval, level can learn the common feature in subject image every identification model, to know
Not Chu layer interval region, and export the interlayer and make every the coordinate of point N number of on area periphery posting and corresponding tag along sort
It is interlayer every recognition result.
Accordingly, which can also be including the coordinate for all pixels point that posting includes every recognition result.In this way, can
Layer interval region is determined with the coordinate based on all pixels point.Show the interlayer when recognition result, it is aobvious by bitmap form
Show interlayer every recognition result.Wherein, layer interval region can be identified using pre-set color.
Each interlayer of object is being identified after every identification model by interlayer, and terminal can also be according to the interlayer
Layer counting and/or layer positioning are carried out every recognition result.By taking shelf as an example, with the example cutting techniques based on deep learning, pass through
The sample learning of model can after determining partition to the Goods shelf partition plate progress example cutting operation for putting commodity in shelf picture
Using the foundation for being layered partition as shelf, it is based on partition information, determining for shelf layer can be easily achieved by simple count
Position and statistics.
From the foregoing, it will be observed that the embodiment of the present application provides a kind of interlayer every recognition methods, which is based on layer every recognition methods
It is spaced what identification model was realized, and the interlayer is by including training sample training example point of the interlayer every label every identification model
It cuts what model obtained, to interlayer every discrimination with higher, therefore, the layer of object can be accurately identified by this method
Interval carries out layer positioning based on the recognition result or layer counts accuracy rate with higher.
The above are model training methods provided by the embodiments of the present application and interlayer every some specific implementation sides of recognition methods
Formula is based on this, and the embodiment of the present application also provides corresponding devices, will implement below from the angle of function modoularization to the application
The above-mentioned apparatus that example provides is introduced.
Firstly, model training apparatus provided by the embodiments of the present application is introduced.Model training dress shown in Figure 7
The structural schematic diagram set, the device 700 include:
Module 710 is obtained, for obtaining training sample, the training sample includes subject image and interlayer every label,
The interlayer is used for the interlayer of object in the subject image every label every being labeled；
Training module 720, for the example of training objective will to be met using training sample training example parted pattern
Parted pattern is determined as interlayer every identification model, and the interlayer is input with subject image every identification model, with interlayer every identification
It as a result is output.
Optionally, the interlayer includes the posting that polygon is formed every label, and the polygon passes through the N positioned at edge
The point set of a point composition is characterized, and the N is the positive integer greater than 1；
The layer interval region that the interlayer is surrounded every the polygon that recognition result includes N number of point formation.
Optionally, the layer interval region is shown by bitmap form.
Optionally, the example parted pattern includes that target detection convolutional neural networks model based on mask or path are poly-
Close network model.
Optionally, described device 700 further include:
Generation module, for acquiring the interlayer of subject image and the subject image every label, the interlayer is every label
That gained is marked to the subject image using example segmentation sample annotation tool, according to the subject image and the interlayer every
Label generates the training sample.
Optionally, described device 700 further include:
Rectification module, for being corrected using image flame detection algorithm to the subject image；
Then the interlayer is to mark gained to the subject image after correction using example segmentation sample annotation tool every label；
Then the generation module is specifically used for:
According to after the correction subject image and the interlayer every label generate the training sample.
Optionally, the object includes shelf or locker.
Secondly, interlayer provided by the embodiments of the present application is introduced every identification device.Interlayer shown in Figure 8 is every knowledge
The structural schematic diagram of other device, the device 800 include:
Module 810 is obtained, for obtaining subject image；
Identification module 820, for obtaining the interlayer every identification mould for subject image input layer interval identification model
The interlayer of the subject image of type output is based on embodiment illustrated in fig. 2 institute every identification model every recognition result, the interlayer
What the model training method training stated generated.
Optionally, described device 800 further include:
Processing module, for carrying out layer counting and/or layer positioning every recognition result according to the interlayer.
The embodiment of the present application also provides a kind of equipment, which includes processor and memory:
The memory is for storing computer program；
The processor be used to be executed according to the computer program model training method provided by the embodiments of the present application or
Person's interlayer is every recognition methods.
Equipment provided by the embodiments of the present application will be introduced from the angle of hardware entities below.
Fig. 9 is a kind of server architecture schematic diagram provided by the embodiments of the present application, which can be because of configuration or performance
It is different and generate bigger difference, it may include one or more central processing units (central processing
Units, CPU) 922 (for example, one or more processors) and memory 932, one or more storages apply journey
The storage medium 930 (such as one or more mass memory units) of sequence 942 or data 944.Wherein, 932 He of memory
Storage medium 930 can be of short duration storage or persistent storage.The program for being stored in storage medium 930 may include one or one
With upper module (diagram does not mark), each module may include to the series of instructions operation in server.Further, in
Central processor 922 can be set to communicate with storage medium 930, execute on server 900 a series of in storage medium 930
Instruction operation.
Server 900 can also include one or more power supplys 926, one or more wired or wireless networks
Interface 950, one or more input/output interfaces 958, and/or, one or more operating systems 941, such as
Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM etc..
The step as performed by server can be based on the server architecture shown in Fig. 9 in above-described embodiment.
Wherein, CPU 922 is for executing following steps:
Training sample is obtained, the training sample includes subject image and interlayer every label, and the interlayer is used every label
The interlayer of object is every being labeled in the subject image；
Using training sample training example parted pattern, the example parted pattern for meeting training objective is determined as layer
Be spaced identification model, the interlayer every identification model with subject image be input, with interlayer every recognition result be output.
Optionally, the CPU922 is also used to execute any one reality of model training method provided by the embodiments of the present application
The step of existing mode.
The embodiment of the present application also provides another equipment, as shown in Figure 10, for ease of description, illustrate only and this Shen
Please the relevant part of embodiment, it is disclosed by specific technical details, please refer to the embodiment of the present application method part.The terminal can be with
Be include mobile phone, tablet computer, personal digital assistant (full name in English: PersonalDigital Assistant, english abbreviation:
PDA), any terminal device such as point-of-sale terminal (full name in English: Point of Sales, english abbreviation: POS), vehicle-mounted computer, with
Terminal is for mobile phone:
Figure 10 shows the block diagram of the part-structure of mobile phone relevant to terminal provided by the embodiments of the present application.With reference to figure
10, mobile phone includes: radio frequency (full name in English: Radio Frequency, english abbreviation: RF) circuit 1010, memory 1020, defeated
Enter unit 1030, display unit 1040, sensor 1050, voicefrequency circuit 1060, Wireless Fidelity (full name in English: wireless
Fidelity, english abbreviation: WiFi) components such as module 1070, processor 1080 and power supply 1090.Those skilled in the art
It is appreciated that handset structure shown in Figure 10 does not constitute the restriction to mobile phone, it may include more more or fewer than illustrating
Component perhaps combines certain components or different component layouts.
It is specifically introduced below with reference to each component parts of the Figure 10 to mobile phone:
RF circuit 1010 can be used for receiving and sending messages or communication process in, signal sends and receivees, particularly, by base station
After downlink information receives, handled to processor 1080；In addition, the data for designing uplink are sent to base station.In general, RF circuit
1010 include but is not limited to antenna, at least one amplifier, transceiver, coupler, low-noise amplifier (full name in English: Low
Noise Amplifier, english abbreviation: LNA), duplexer etc..In addition, RF circuit 1010 can also by wireless communication with net
Network and other equipment communication.Any communication standard or agreement can be used in above-mentioned wireless communication, and including but not limited to the whole world is mobile
Communication system (full name in English: Global System of Mobile communication, english abbreviation: GSM), general point
Group wireless service (full name in English: General Packet Radio Service, GPRS), CDMA (full name in English: Code
Division Multiple Access, english abbreviation: CDMA), wideband code division multiple access (full name in English: Wideband Code
Division Multiple Access, english abbreviation: WCDMA), long term evolution (full name in English: Long Term
Evolution, english abbreviation: LTE), Email, short message service (full name in English: Short Messaging Service,
SMS) etc..
Memory 1020 can be used for storing software program and module, and processor 1080 is stored in memory by operation
1020 software program and module, thereby executing the various function application and data processing of mobile phone.Memory 1020 can be led
It to include storing program area and storage data area, wherein storing program area can be needed for storage program area, at least one function
Application program (such as sound-playing function, image player function etc.) etc.；Storage data area, which can be stored, uses institute according to mobile phone
Data (such as audio data, phone directory etc.) of creation etc..In addition, memory 1020 may include high random access storage
Device, can also include nonvolatile memory, and a for example, at least disk memory, flush memory device or other volatibility are solid
State memory device.
Input unit 1030 can be used for receiving the number or character information of input, and generate with the user setting of mobile phone with
And the related key signals input of function control.Specifically, input unit 1030 may include touch panel 1031 and other inputs
Equipment 1032.Touch panel 1031, also referred to as touch screen collect touch operation (such as the user of user on it or nearby
Use the behaviour of any suitable object or attachment such as finger, stylus on touch panel 1031 or near touch panel 1031
Make), and corresponding attachment device is driven according to preset formula.Optionally, touch panel 1031 may include touch detection
Two parts of device and touch controller.Wherein, the touch orientation of touch detecting apparatus detection user, and detect touch operation band
The signal come, transmits a signal to touch controller；Touch controller receives touch information from touch detecting apparatus, and by it
It is converted into contact coordinate, then gives processor 1080, and order that processor 1080 is sent can be received and executed.In addition,
Touch panel 1031 can be realized using multiple types such as resistance-type, condenser type, infrared ray and surface acoustic waves.In addition to touch surface
Plate 1031, input unit 1030 can also include other input equipments 1032.Specifically, other input equipments 1032 may include
But in being not limited to physical keyboard, function key (such as volume control button, switch key etc.), trace ball, mouse, operating stick etc.
It is one or more.
Display unit 1040 can be used for showing information input by user or be supplied to user information and mobile phone it is each
Kind menu.Display unit 1040 may include display panel 1041, optionally, can using liquid crystal display (full name in English:
Liquid Crystal Display, english abbreviation: LCD), Organic Light Emitting Diode (full name in English: Organic Light-
Emitting Diode, english abbreviation: OLED) etc. forms configure display panel 1041.Further, touch panel 1031 can
Covering display panel 1041 sends processor to after touch panel 1031 detects touch operation on it or nearby
1080, to determine the type of touch event, are followed by subsequent processing device 1080 and are provided on display panel 1041 according to the type of touch event
Corresponding visual output.Although touch panel 1031 and display panel 1041 are come as two independent components in Figure 10
Realize the input and input function of mobile phone, but in some embodiments it is possible to by touch panel 1031 and display panel 1041
It is integrated and that realizes mobile phone output and input function.
Mobile phone may also include at least one sensor 1050, such as optical sensor, motion sensor and other sensors.
Specifically, optical sensor may include ambient light sensor and proximity sensor, wherein ambient light sensor can be according to ambient light
Light and shade adjust the brightness of display panel 1041, proximity sensor can close display panel when mobile phone is moved in one's ear
1041 and/or backlight.As a kind of motion sensor, accelerometer sensor can detect in all directions (generally three axis) and add
The size of speed can detect that size and the direction of gravity when static, can be used to identify application (such as the horizontal/vertical screen of mobile phone posture
Switching, dependent game, magnetometer pose calibrating), Vibration identification correlation function (such as pedometer, tap) etc.；Also as mobile phone
The other sensors such as configurable gyroscope, barometer, hygrometer, thermometer, infrared sensor, details are not described herein.
Voicefrequency circuit 1060, loudspeaker 1061, microphone 1062 can provide the audio interface between user and mobile phone.Audio
Electric signal after the audio data received conversion can be transferred to loudspeaker 1061, be converted by loudspeaker 1061 by circuit 1060
For voice signal output；On the other hand, the voice signal of collection is converted to electric signal by microphone 1062, by voicefrequency circuit 1060
Audio data is converted to after reception, then by after the processing of audio data output processor 1080, through RF circuit 1010 to be sent to ratio
Such as another mobile phone, or audio data is exported to memory 1020 to be further processed.
WiFi belongs to short range wireless transmission technology, and mobile phone can help user's transceiver electronics postal by WiFi module 1070
Part, browsing webpage and access streaming video etc., it provides wireless broadband internet access for user.Although Figure 10 is shown
WiFi module 1070, but it is understood that, and it is not belonging to must be configured into for mobile phone, it can according to need do not changing completely
Become in the range of the essence of invention and omits.
Processor 1080 is the control centre of mobile phone, using the various pieces of various interfaces and connection whole mobile phone,
By running or execute the software program and/or module that are stored in memory 1020, and calls and be stored in memory 1020
Interior data execute the various functions and processing data of mobile phone, to carry out integral monitoring to mobile phone.Optionally, processor
1080 may include one or more processing units；Preferably, processor 1080 can integrate application processor and modulation /demodulation processing
Device, wherein the main processing operation system of application processor, user interface and application program etc., modem processor is mainly located
Reason wireless communication.It is understood that above-mentioned modem processor can not also be integrated into processor 1080.
Mobile phone further includes the power supply 1090 (such as battery) powered to all parts, it is preferred that power supply can pass through power supply
Management system and processor 1080 are logically contiguous, to realize management charging, electric discharge and power consumption pipe by power-supply management system
The functions such as reason.
Although being not shown, mobile phone can also include camera, bluetooth module etc., and details are not described herein.
In the embodiment of the present application, processor 1080 included by the terminal is also with the following functions:
Obtain subject image；
By subject image input layer interval identification model, the object that the interlayer is exported every identification model is obtained
The interlayer of image is based on model training method described in embodiment illustrated in fig. 2 every identification model every recognition result, the interlayer
What training generated.
Optionally, the processor 1080 is also used to execute interlayer provided by the embodiments of the present application every any of recognition methods
A kind of the step of implementation.
The embodiment of the present application also provides a kind of computer readable storage medium, for storing program code, the program code
For executing any one embodiment or each implementation in a kind of model training method described in foregoing individual embodiments
A kind of any one embodiment of interlayer described in example every recognition methods.
The embodiment of the present application also provides a kind of computer program product including instruction, when run on a computer,
So that computer executes any one embodiment or each in a kind of model training method described in foregoing individual embodiments
A kind of any one embodiment of interlayer described in a embodiment every recognition methods.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In several embodiments provided herein, it should be understood that disclosed device and method can pass through it
Its mode is realized.For example, the apparatus embodiments described above are merely exemplary, for example, the division of the unit, only
Only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components can be tied
Another system is closed or is desirably integrated into, or some features can be ignored or not executed.Another point, it is shown or discussed
Mutual coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or logical of device or unit
Letter connection can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It should be appreciated that in this application, " at least one (item) " refers to one or more, and " multiple " refer to two or two
More than a."and/or" indicates may exist three kinds of relationships, for example, " A and/or B " for describing the incidence relation of affiliated partner
It can indicate: only exist A, only exist B and exist simultaneously tri- kinds of situations of A and B, wherein A, B can be odd number or plural number.Word
Symbol "/" typicallys represent the relationship that forward-backward correlation object is a kind of "or"." at least one of following (a) " or its similar expression, refers to
Any combination in these, any combination including individual event (a) or complex item (a).At least one of for example, in a, b or c
(a) can indicate: a, b, c, " a and b ", " a and c ", " b and c ", or " a and b and c ", and wherein a, b, c can be individually, can also
To be multiple.
The above, above embodiments are only to illustrate the technical solution of the application, rather than its limitations；Although referring to before
Embodiment is stated the application is described in detail, those skilled in the art should understand that: it still can be to preceding
Technical solution documented by each embodiment is stated to modify or equivalent replacement of some of the technical features；And these
It modifies or replaces, the spirit and scope of each embodiment technical solution of the application that it does not separate the essence of the corresponding technical solution.
Claims (13)
1. a kind of model training method, which is characterized in that the described method includes:
Obtain training sample, the training sample includes subject image and interlayer every label, the interlayer every label for pair
The interlayer of object is every being labeled in the subject image；
Using the training sample training example parted pattern, by the example parted pattern for meeting training objective be determined as interlayer every
Identification model, the interlayer every identification model with subject image be input, with interlayer every recognition result be output.
2. the method according to claim 1, wherein the interlayer is every the positioning that label includes that polygon is formed
Frame, the polygon are characterized by being located at the point set that N number of point at edge forms, and the N is the positive integer greater than 1；
The layer interval region that the interlayer is surrounded every the polygon that recognition result includes N number of point formation.
3. according to the method described in claim 2, it is characterized in that, the layer interval region is shown by bitmap form.
4. method according to any one of claims 1 to 4, which is characterized in that the example parted pattern includes being based on covering
The target detection convolutional neural networks model or path converging network model of code.
5. method according to any one of claims 1 to 4, which is characterized in that the training sample is given birth in the following way
At:
The interlayer of subject image and the subject image is acquired every label, the interlayer is to divide sample using example every label
Annotation tool marks gained to the subject image；
According to the subject image and the interlayer every label, the training sample is generated.
6. according to the method described in claim 5, it is characterized in that, the method also includes:
The subject image is corrected using image flame detection algorithm；
Then the interlayer is to mark gained to the subject image after correction using example segmentation sample annotation tool every label；
It is then described to include: every the label generation training sample according to the subject image and the interlayer
According to after the correction subject image and the interlayer every label generate the training sample.
7. method according to any one of claims 1 to 4, which is characterized in that the object includes shelf or locker.
8. a kind of interlayer is every recognition methods, which is characterized in that the described method includes:
Obtain subject image；
By subject image input layer interval identification model, the subject image that the interlayer is exported every identification model is obtained
Interlayer every recognition result, the interlayer is based on model training side as described in any one of claim 1 to 7 every identification model
Method training generates.
9. interlayer according to claim 8 is every recognition methods, which is characterized in that the method also includes:
Layer counting and/or layer positioning are carried out every recognition result according to the interlayer.
10. a kind of model training apparatus, which is characterized in that described device includes:
Module is obtained, for obtaining training sample, the training sample includes subject image and interlayer every label, the interlayer
It is used for the interlayer of object in the subject image every label every being labeled；
Training module, for using training sample training example parted pattern, the example for meeting training objective to be divided mould
Type is determined as interlayer every identification model, and the interlayer is input with subject image every identification model, is every recognition result with interlayer
Output.
11. a kind of interlayer is every identification device, which is characterized in that described device includes:
Module is obtained, for obtaining subject image；
Identification module, for obtaining the subject image input layer interval identification model interlayer and being exported every identification model
The subject image interlayer every recognition result, the interlayer is based on such as any one of claim 1 to 7 institute every identification model
What the model training method training stated generated.
12. a kind of equipment, which is characterized in that the equipment includes memory and processor:
The memory is for storing computer program；
The processor is used to execute the described in any item models of the claim of this application 1 to 7 according to the computer program and instruct
Practice interlayer described in method or claim 8 to 9 every recognition methods.
13. a kind of computer readable storage medium, which is characterized in that be stored with computer program in the storage medium, wherein
The computer program is arranged to execute the described in any item model training methods of the claim 1 to 7 or power when operation
Benefit require 8 to 9 described in interlayer every recognition methods.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910319329.7A CN110059753A (en) | 2019-04-19 | 2019-04-19 | Model training method, interlayer are every recognition methods, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910319329.7A CN110059753A (en) | 2019-04-19 | 2019-04-19 | Model training method, interlayer are every recognition methods, device, equipment and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110059753A true CN110059753A (en) | 2019-07-26 |
Family
ID=67319792
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910319329.7A Pending CN110059753A (en) | 2019-04-19 | 2019-04-19 | Model training method, interlayer are every recognition methods, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110059753A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111882606A (en) * | 2020-07-01 | 2020-11-03 | 上海品览数据科技有限公司 | Goods shelf commodity layering method based on deep learning |
| CN112270331A (en) * | 2020-11-04 | 2021-01-26 | 哈尔滨理工大学 | Improved billboard detection method based on YOLOV5 |
| CN112990239A (en) * | 2019-12-13 | 2021-06-18 | 中移(成都)信息通信科技有限公司 | Recognition model training method, pepper scab recognition method and device |
| CN113762292A (en) * | 2020-06-03 | 2021-12-07 | 杭州海康威视数字技术股份有限公司 | Training data acquisition method and device and model training method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102184405A (en) * | 2011-04-19 | 2011-09-14 | 清华大学 | Image acquisition-analysis method |
| CN108537215A (en) * | 2018-03-23 | 2018-09-14 | 清华大学 | A kind of flame detecting method based on image object detection |
| CN108549893A (en) * | 2018-04-04 | 2018-09-18 | 华中科技大学 | A kind of end-to-end recognition methods of the scene text of arbitrary shape |
| CN108564029A (en) * | 2018-04-12 | 2018-09-21 | 厦门大学 | Face character recognition methods based on cascade multi-task learning deep neural network |
| CN108898141A (en) * | 2018-06-14 | 2018-11-27 | 中山大学 | Commodity shelf segmentation and layer information statistical method based on image detection |
| CN109522933A (en) * | 2018-10-19 | 2019-03-26 | 北京陌上花科技有限公司 | Commodity detection method and device for shelf |
-
2019
- 2019-04-19 CN CN201910319329.7A patent/CN110059753A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102184405A (en) * | 2011-04-19 | 2011-09-14 | 清华大学 | Image acquisition-analysis method |
| CN108537215A (en) * | 2018-03-23 | 2018-09-14 | 清华大学 | A kind of flame detecting method based on image object detection |
| CN108549893A (en) * | 2018-04-04 | 2018-09-18 | 华中科技大学 | A kind of end-to-end recognition methods of the scene text of arbitrary shape |
| CN108564029A (en) * | 2018-04-12 | 2018-09-21 | 厦门大学 | Face character recognition methods based on cascade multi-task learning deep neural network |
| CN108898141A (en) * | 2018-06-14 | 2018-11-27 | 中山大学 | Commodity shelf segmentation and layer information statistical method based on image detection |
| CN109522933A (en) * | 2018-10-19 | 2019-03-26 | 北京陌上花科技有限公司 | Commodity detection method and device for shelf |
Non-Patent Citations (1)
| Title |
|---|
| 白雅贤: "货架商品图像分割与识别方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112990239A (en) * | 2019-12-13 | 2021-06-18 | 中移(成都)信息通信科技有限公司 | Recognition model training method, pepper scab recognition method and device |
| CN113762292A (en) * | 2020-06-03 | 2021-12-07 | 杭州海康威视数字技术股份有限公司 | Training data acquisition method and device and model training method and device |
| CN113762292B (en) * | 2020-06-03 | 2024-02-02 | 杭州海康威视数字技术股份有限公司 | Training data acquisition method and device and model training method and device |
| CN111882606A (en) * | 2020-07-01 | 2020-11-03 | 上海品览数据科技有限公司 | Goods shelf commodity layering method based on deep learning |
| CN112270331A (en) * | 2020-11-04 | 2021-01-26 | 哈尔滨理工大学 | Improved billboard detection method based on YOLOV5 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111368934B (en) | Image recognition model training method, image recognition method and related device | |
| CN110059753A (en) | Model training method, interlayer are every recognition methods, device, equipment and medium | |
| CN110070034A (en) | Model training method, section recognition methods, device, equipment and medium | |
| CN109241431A (en) | A kind of resource recommendation method and device | |
| CN109918975A (en) | A kind of processing method of augmented reality, the method for Object identifying and terminal | |
| CN106027108B (en) | A kind of indoor orientation method, device and wearable device and mobile terminal | |
| CN106446797A (en) | Image clustering method and device | |
| CN107341006A (en) | Screen locking wallpaper recommends method and Related product | |
| CN107748856A (en) | Two-dimensional code identification method, terminal and computer-readable recording medium | |
| CN108334539A (en) | Object recommendation method, mobile terminal and computer readable storage medium | |
| CN109670174A (en) | A kind of training method and device of event recognition model | |
| CN109495616B (en) | Photographing method and terminal equipment | |
| CN109376781A (en) | A kind of training method, image-recognizing method and the relevant apparatus of image recognition model | |
| CN109189300A (en) | A kind of view circularly exhibiting method and apparatus | |
| CN108236785A (en) | A kind of method and device for obtaining object information | |
| CN108038431A (en) | Image processing method, device, computer equipment and computer-readable recording medium | |
| CN103714316B (en) | Image-recognizing method, device and electronic equipment | |
| CN106204552A (en) | The detection method of a kind of video source and device | |
| CN109213407A (en) | A kind of screenshot method and terminal device | |
| CN110347858A (en) | A kind of generation method and relevant apparatus of picture | |
| CN110263729A (en) | A kind of method of shot boundary detector, model training method and relevant apparatus | |
| CN110363785A (en) | A kind of super frame detection method and device of text | |
| CN109471571A (en) | Display methods, mobile terminal and the computer readable storage medium of suspension control | |
| CN110209245A (en) | Face identification method and Related product | |
| CN109067981A (en) | Split screen application switching method, device, storage medium and electronic equipment |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190726 |
|
| RJ01 | Rejection of invention patent application after publication |