CN109409260A - Data mask method, device, equipment and storage medium - Google Patents
Data mask method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN109409260A CN109409260A CN201811182522.2A CN201811182522A CN109409260A CN 109409260 A CN109409260 A CN 109409260A CN 201811182522 A CN201811182522 A CN 201811182522A CN 109409260 A CN109409260 A CN 109409260A
- Authority
- CN
- China
- Prior art keywords
- interest
- data
- marked
- target region
- pedestrian
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/193—Preprocessing; Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Ophthalmology & Optometry (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
Data mask method, device, equipment and storage medium provided by the invention, belong to technical field of image processing.The data mask method includes: display data to be marked；The eye image of pedestrian is acquired, and obtains sight drop point of the pedestrian in the data to be marked by carrying out eye tracking to the eye image；The target region-of-interest of the data to be marked is obtained according to the sight drop point；The target region-of-interest is sent to server, so that the server determines mark answer according to the target region-of-interest.By by pedestrian come in the way of watching data to be marked shown by advertising equipment, to complete the mark of data by the advertising equipment and a large amount of pedestrian of public place, the mark of data is carried out without additionally employing special messenger, so relative to existing technologies, manpower and material resources can be greatly reduced.
Description
Technical field
The present invention relates to field of image processings, in particular to data mask method, device, equipment and storage medium.
Background technique
Crowdsourcing dimension model is one of most common data notation methods at present, widely supports common artificial intelligence
Or the mark task of deep learning.However crowdsourcing dimension model need to largely organize online mark personnel, and personal management stream
Journey is more time-consuming, and there is still a need for pay mark personnel.
Summary of the invention
Data mask method, device, equipment and storage medium provided in an embodiment of the present invention, can solve in the prior art
The technical problem that existing mark personal management is complicated and charge costs are larger.
To achieve the goals above, technical solution used in the embodiment of the present invention is as follows:
In a first aspect, a kind of data mask method provided in an embodiment of the present invention, is applied to advertising equipment, the method packet
It includes: showing data to be marked；The eye image of pedestrian is acquired, and by carrying out described in eye tracking acquisition to the eye image
Sight drop point of the pedestrian in the data to be marked；The target concern of the data to be marked is obtained according to the sight drop point
Region；The target region-of-interest is sent to server, is marked so that the server is determined according to the target region-of-interest
Infuse answer.
With reference to first aspect, the embodiment of the invention provides the first possible embodiment of first aspect, described
The target region-of-interest of the data to be marked is obtained according to the sight drop point, comprising: according to sight drop point determination
Pedestrian's each region-of-interest of interest；When calculating stop of the pedestrian to the sight drop point of each region-of-interest
Between；Target region-of-interest is determined according to the residence time.
The possible embodiment of with reference to first aspect the first, the embodiment of the invention provides second of first aspect
Possible embodiment, it is described that target region-of-interest is determined according to the residence time, comprising: will be described in the sight drop point
Residence time, longest region-of-interest was as target region-of-interest.
The possible embodiment of with reference to first aspect the first, the embodiment of the invention provides the third of first aspect
Possible embodiment, it is described that target region-of-interest is determined according to the residence time, comprising: if the residence time is greater than in advance
If when threshold value, using the corresponding region-of-interest of the sight drop point as target region-of-interest.
With reference to first aspect, the embodiment of the invention provides the 4th kind of possible embodiment of first aspect, the sides
Method further include: according to the display duration of the crowd is dense degree determines presently described data to be marked；It is aobvious according to the display duration
Show the data to be marked.
Second aspect, a kind of data mask method provided in an embodiment of the present invention are applied to server, the method packet
It includes: receiving the target region-of-interest for multiple pedestrians that advertising equipment is sent, each target region-of-interest is each for characterizing
The region that the pedestrian pays close attention to shown data to be marked；It is determined according to the target region-of-interest described to be marked
Mark answer corresponding to data.
In conjunction with second aspect, the embodiment of the invention provides the first possible embodiment of second aspect, described
Mark answer corresponding to the data to be marked is determined according to the target region-of-interest, comprising: determines that each target is closed
Infuse pedestrian's number corresponding to region；If pedestrian's number corresponding to the target region-of-interest is greater than or equal to preset value
When, using the corresponding target region-of-interest as mark answer.
In conjunction with second aspect, the embodiment of the invention provides second of possible embodiment of second aspect, described
Mark answer corresponding to the data to be marked is determined according to the target region-of-interest, comprising: is obtained each target and is closed
Infuse weight and pedestrian's number corresponding to region；If the product of the weight and pedestrian's number is greater than or equal to preset value
When, using the corresponding target region-of-interest as mark answer.
In conjunction with second aspect, the embodiment of the invention provides the third possible embodiment of second aspect, the sides
Method further include: the data to be marked are labeled according to the mark answer；Alternatively, the mark answer is sent to visitor
The labeling system at family end, so that the labeling system is labeled the data to be marked.
The third aspect, a kind of data annotation equipment provided in an embodiment of the present invention are applied to advertising equipment, described device packet
It includes: display unit, for showing data to be marked；Acquisition unit, for acquiring the eye image of pedestrian；First processing units,
For obtaining sight drop point of the pedestrian in the data to be marked by carrying out eye tracking to the eye image；The
Two processing units, for obtaining the target region-of-interest of the data to be marked according to the sight drop point；Transmission unit is used for
The target region-of-interest is sent to server, so that the server determines that mark is answered according to the target region-of-interest
Case.
Fourth aspect, a kind of data annotation equipment provided in an embodiment of the present invention are applied to server, described device packet
It includes: receiving unit, the target region-of-interest of multiple pedestrians for receiving advertising equipment transmission, each target region-of-interest
The region that shown data to be marked are paid close attention to for characterizing each pedestrian；Processing unit, for according to
Target region-of-interest determines mark answer corresponding to the data to be marked.
5th aspect, a kind of terminal device provided in an embodiment of the present invention, comprising: memory, processor and be stored in
In the memory and the computer program that can run on the processor, when the processor executes the computer program
It realizes as described in any one of first aspect the step of data mask method；Alternatively, the processor executes the computer program
Shi Shixian is as described in any one of second aspect the step of data mask method.
6th aspect, a kind of storage medium provided in an embodiment of the present invention are stored with instruction on the storage medium, work as institute
Instruction is stated when running on computers, so that the computer executes such as the described in any item data mask methods of first aspect；
Alternatively, when described instruction is run on computers, so that the computer executes such as the described in any item data of second aspect
Mask method.
Compared with prior art, the embodiment of the present invention bring it is following the utility model has the advantages that
Data mask method, device, equipment and storage medium provided in an embodiment of the present invention, by showing number to be marked
According to acquiring the eye image of pedestrian；And the pedestrian is obtained described wait mark by carrying out eye tracking to the eye image
Infuse the sight drop point in data；The target region-of-interest of the data to be marked is obtained according to the sight drop point；By the mesh
Mark region-of-interest is sent to server, so that the server determines mark answer according to the target region-of-interest.To utilize
Pedestrian watches the modes of data to be marked shown by advertising equipment, to pass through the advertising equipment of public place and a large amount of
Pedestrian complete the marks of data, carry out the mark of data without additionally employing special messenger, so relative to existing technologies,
Manpower and material resources can be greatly reduced.
Other feature and advantage of the disclosure will illustrate in the following description, alternatively, Partial Feature and advantage can be with
Deduce from specification or unambiguously determine, or by implement the disclosure above-mentioned technology it can be learnt that.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of range for those of ordinary skill in the art without creative efforts, can also be according to this
A little attached drawings obtain other relevant attached drawings.
Fig. 1 is the flow chart for the data mask method that first embodiment of the invention provides；
Fig. 2 is the flow chart for the data mask method that second embodiment of the invention provides；
Fig. 3 is the functional block diagram for the data annotation equipment that third embodiment of the invention provides；
Fig. 4 is the functional block diagram for the data annotation equipment that fourth embodiment of the invention provides；
Fig. 5 is a kind of schematic diagram of terminal device provided in an embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.Therefore,
The model of claimed invention is not intended to limit to the detailed description of the embodiment of the present invention provided in the accompanying drawings below
It encloses, but is merely representative of selected embodiment of the invention.Based on the embodiments of the present invention, those of ordinary skill in the art are not having
Every other embodiment obtained under the premise of creative work is made, shall fall within the protection scope of the present invention.
With reference to the accompanying drawing, it elaborates to some embodiments of the present invention.In the absence of conflict, following
Feature in embodiment and embodiment can be combined with each other.
First embodiment
Since existing data mark need to largely organize online mark personnel to carry out data mark, lead to personal management
Cumbersome and human cost is higher, and in order to reduce personal management fussy degree and human cost, the present embodiment provides firstly one
Kind data mask method, it should be noted that step shown in the flowchart of the accompanying drawings can be held in such as one group of computer
It is executed in the computer system of row instruction, although also, logical order is shown in flow charts, in some cases,
It can be with the steps shown or described are performed in an order that is different from the one herein.It describes in detail below to the present embodiment.
Referring to Fig. 1, being the flow chart of data mask method provided in an embodiment of the present invention.This method is set applied to advertisement
It is standby, detailed process shown in FIG. 1 will be described in detail below.
Step S101 shows data to be marked.
As a kind of application scenarios, the advertising equipment includes display screen, and the advertising equipment is connected with image collector
It sets, the display screen is for showing the data to be marked.
Wherein, advertising equipment is public place (such as bus stop, subway station, hospital, market) with the wide of display screen
Accuse board.
Optionally, the data to be marked, which can also be, is stored in advance in advertising equipment, is also possible to server hair
It send, for example, server sends a data to be marked in a preset time period, or regularly sends a data to be marked.
Optionally, the data to be marked can be picture, be also possible to text；Or the combination of picture and text.
As an implementation, step S101 includes: that degree determines presently described data to be marked according to the crowd is dense
Display duration；The data to be marked are shown according to the display duration.
Optionally, degree that the crowd is dense is used to characterize the number accommodated in unit area.
For example, show that the time is just shorter if the crowd is dense degree is greater than a preset threshold, for example, 5 minutes either 10 points
Clock etc., conversely, then showing that the time is just longer, for example, either 20 minutes etc. 15 minutes.
In actual use, the preset threshold can be generally configured according to specific requirements.For example, 0.75 square meter/
People.
In the present embodiment, the duration for showing data to be marked is determined according to the crowd is dense degree, can effectively improved
Display efficiency so that all data to be marked will not fix a certain duration of display, and wastes display resource, while can also have
Effect, which improves, obtains the accuracy of the mark answer of data to be marked.
Step S101 acquires the eye image of pedestrian, and by carrying out described in eye tracking acquisition to the eye image
Sight drop point of the pedestrian in the data to be marked.
Optionally, pass through the eye image of image acquisition device pedestrian.Wherein, image collecting device can be described
What advertising equipment carried, it is also possible to external.
Optionally, image collecting device can be camera.
Optionally, when the pedestrian of acquisition described image acquisition device acquisition sees the to be marked data shown into display screen
Eye image, and by the eye image carry out eye tracking obtain mesh of the pedestrian in the data to be marked
Light drop point.Determine sight that pedestrian is issued at current time in display screen by sight that human eye in eye image is issued
Drop point in the upper shown data to be marked, as the sight drop point.
Wherein, sight drop point indicate mark personnel (treating the pedestrian that labeled data is paid close attention to) sight and it is described to
The point of the position that crosses of the display plane of labeled data.Sight drop point reflects mark personnel screen of interest in annotation process
Curtain position, therefore the distribution of sight drop point is actually point of attention rate of the mark personnel in annotation process in annotation process
Cloth.
Optionally, sight drop point can be obtained by eye tracking, and so-called eye tracking is tracked and marked in annotation process
The sight motion profile of personnel.
Step S103 obtains the target region-of-interest of the data to be marked according to the sight drop point.
As an implementation, step S103 includes: to determine of interest every of the pedestrian according to the sight drop point
A region-of-interest；The pedestrian is calculated to the residence time of the sight drop point of each region-of-interest；Stopped according to described
The time is stayed to determine target region-of-interest.
Optionally, the pedestrian each region-of-interest of interest is determined according to the sight drop point, comprising: search each
Predeterminable area where sight drop point, using predeterminable area as region-of-interest.It wherein, include multiple coordinates in each predeterminable area
Point, if coordinate corresponding to sight drop point is located in the predeterminable area, the sight drop point is just corresponding with the predeterminable area.
As an example it is assumed that have tri- regions a, b, c on display screen, the corresponding coordinate in tri- regions a, b, c are as follows: a
Area coordinate a1, coordinate a2, coordinate a3, coordinate a4, b area coordinate b1, coordinate b2, coordinate b3, coordinate b4, c area coordinate c1,
Coordinate c2, coordinate c3, coordinate c4, it is assumed that the corresponding coordinate of sight drop point is a1, then the sight drop point belongs to the area a, i.e. pedestrian
Region-of-interest be the area a.
Optionally, described that target region-of-interest is determined according to the residence time, comprising: will be described in the sight drop point
Residence time, longest region-of-interest was as target region-of-interest.
Continuing for by taking above-mentioned example as an example, it is 2 seconds in the area the b residence time that pedestrian q1, which is 1 second in the area a residence time,
The area the c residence time is 3 seconds, then for pedestrian 1, target region-of-interest is the area c.
Optionally, it is described that target region-of-interest is determined according to the residence time, comprising: if the residence time is greater than in advance
If when threshold value, using the corresponding region-of-interest of the sight drop point as target region-of-interest.
Wherein it is possible to determine the mesh at the time of according to corresponding to variation of the acquisition pedestrian between each region-of-interest
Residence time corresponding to light drop point.
As an implementation, eye image is obtained using camera, then using the positioning of human eye in image with
Tracking, to estimate the sight drop point in user face on a display screen.
It certainly, in actual use, can also be based on (such as the sight estimation based on statistical-simulation spectrometry of traditional method
Algorithm；Algorithm based on the estimation of AAM (Active Apperance Model, movable submodel) model sight；Based on PCCR
The sight algorithm for estimating of (Pupil Center Cornel Reflection, pupil center's sky ear reflex) technology analyzes eyeball figure
As the sight drop point to estimate user face on a display screen.
It is, of course, also possible to using the method based on deep learning, such as convolution depth network analysis eyeball image is to estimate
Calculate the sight drop point in user face on a display screen.
The target region-of-interest is sent to server, so that the server is closed according to the target by step S104
It infuses region and determines mark answer.
Wherein, mark answer treats answer given by labeled data for characterizing pedestrian.For example, shown is to be marked
Data are a single choice, if the target region-of-interest of pedestrian is option C, marking answer is information corresponding to C option.
It is alternatively possible to be that every preset time period sends once target region-of-interest corresponding with data to be marked to clothes
Business device, is also possible to after having shown the data to be marked just immediately by target region-of-interest to server.
Wherein, the selection of preset time period can be arranged according to demand, for example, sending once, either every 30 minutes
It is every shown 4 data to be marked after, send one inferior.
Data mask method provided by the embodiment of the present invention acquires the human eye figure of pedestrian by showing data to be marked
Picture；And sight drop point of the pedestrian in the data to be marked is obtained by carrying out eye tracking to the eye image；
The target region-of-interest of the data to be marked is obtained according to the sight drop point；The target region-of-interest is sent to service
Device, so that the server determines mark answer according to the target region-of-interest.To watch advertising equipment institute using pedestrian
The mode of the data to be marked of display, to complete the mark of data by the advertising equipment and a large amount of pedestrian of public place
Note, carries out the mark of data without additionally employing special messenger, so relative to existing technologies, manpower object can be greatly reduced
Power.Secondly as the radix of pedestrian is big, same data to be marked also have more people and mark together, both ensure that mark in this way
The mark task of high number can be also rapidly completed in accuracy.And it is opposite be sitting in front of computer marked with mouse-keyboard it is different
Sample, the scene marked through the invention be all in real time, pedestrians mark when be all it is unconscious, can more embody use in this way
The true idea at family.
Second embodiment
Referring to Fig. 2, being the flow chart of data mask method provided in an embodiment of the present invention.This method is applied to service
Device.Detailed process shown in Fig. 2 will be described in detail below.
Step S201, receives the target region-of-interest for multiple pedestrians that advertising equipment is sent, and each target pays close attention to area
Domain is for characterizing the region that each pedestrian pays close attention to shown data to be marked.
Wherein, advertising equipment includes communication module, such as wireless communication chips, for sending target region-of-interest to service
Device.
As an implementation, the target region-of-interest that the advertising equipment in preset time period is sent is received.Count
All pedestrians target region-of-interest of interest in preset time period.
Wherein, the setting of preset time period is referred to first embodiment, here, repeating no more.
Step S202, according to the target region-of-interest determine the data to be marked corresponding to mark answer.
As an implementation, step S202 comprises determining that pedestrian people corresponding to each target region-of-interest
Number；If the number is greater than or equal to preset value, using the corresponding target region-of-interest as mark answer.
Wherein, the setting of preset value can be configured according to user demand.
Certainly, in actual use, general preset value setting is relatively large, to improve the authenticity of data.
As an example it is assumed that data to be marked are a multiple-choice question, including two options of A and B, A option corresponding first
Predeterminable area, corresponding second predeterminable area of B option, if target region-of-interest is the first predeterminable area, target region-of-interest
Corresponding data is A option, judges to pay close attention to pedestrian's number corresponding to A option, if pedestrian's number corresponding to concern A option is big
When preset value, by the corresponding target region-of-interest (i.e. A option) as mark answer, i.e. mark answer is A
Option.If pay close attention to pedestrian's number corresponding to A option less than preset value, the target region-of-interest is abandoned, to redefine
Target region-of-interest.
As another embodiment, step S202 includes: to obtain weight corresponding to each target region-of-interest
And pedestrian's number；If the product of the weight and pedestrian's number is greater than or equal to preset value, by the corresponding target
Region-of-interest is as mark answer.
Optionally, the weight is pre-set for according to data to be marked.
Wherein, the setting of preset value can be configured according to user demand.
Certainly, in actual use, general preset value setting is relatively large, to improve the authenticity of data.
In a possible embodiment, the method also includes: Xiang Suoshu advertising equipment sends the data to be marked.
Optionally, Xiang Suoshu advertising equipment sends the data to be marked, comprising: if current data to be marked are marked
Note completes, and Xiang Suoshu advertising equipment sends next data to be marked.
Optionally, Xiang Suoshu advertising equipment sends the data to be marked, comprising: is all issued to data to be marked extensively
Equipment is accused, so that the length of time of advertising equipment control display, to show all data to be marked one by one, such as one to be marked
Data are shown 10 minutes, to show all data to be marked one by one.
In a possible embodiment, the method also includes: according to the mark answer to the data to be marked into
Rower note；Alternatively, the mark answer to be sent to the labeling system of client, so that the labeling system is to described to be marked
Data are labeled.
Optionally, when being labeled according to the mark answer to the data to be marked, labeling system setting is being taken
It is engaged on device.
Optionally, the labeling system can be cloud labeling system.
Data mask method provided in an embodiment of the present invention, the target by receiving multiple pedestrians that advertising equipment is sent are closed
Infuse region；Mark answer corresponding to the data to be marked is determined according to each target region-of-interest.So that nothing
The artificial of profession need to employed to carry out data mark, and then effectively reduce human cost, and effectively reduce personnel's pipe
The fussy degree of reason.
3rd embodiment
Corresponding to the data mask method in first embodiment, Fig. 3 is shown using data mark shown in first embodiment
The one-to-one data annotation equipment of injecting method.As shown in figure 3, the data annotation equipment 400 is applied to advertising equipment, data
Annotation equipment 400 includes display unit 410, acquisition unit 420, first processing units 430, the second processing unit 440 and sends
Unit 450.Wherein, display unit 410, acquisition unit 420, first processing units 430, the second processing unit 440 and transmission are single
The realization function of member 450 is gathered with step corresponding in first embodiment to be corresponded, and to avoid repeating, the present embodiment is not detailed one by one
It states.
Display unit 410, for showing data to be marked.
Optionally, display unit 410 is also used to: according to the display of the crowd is dense degree determines presently described data to be marked
Duration；The data to be marked are shown according to the display duration.
Acquisition unit 420, for acquiring the eye image of pedestrian.
First processing units 430, for obtaining the pedestrian described by carrying out eye tracking to the eye image
Sight drop point in data to be marked.
The second processing unit 440, for obtaining the target region-of-interest of the data to be marked according to the sight drop point.
Optionally, the second processing unit 440 are also used to: determining of interest every of the pedestrian according to the sight drop point
A region-of-interest；The pedestrian is calculated to the residence time of the sight drop point of each region-of-interest；Stopped according to described
The time is stayed to determine target region-of-interest.
Optionally, described that target region-of-interest is determined according to the residence time, comprising: will be described in the sight drop point
Residence time, longest region-of-interest was as target region-of-interest.
Optionally, it is described that target region-of-interest is determined according to the residence time, comprising: if the residence time is greater than in advance
If when threshold value, using the corresponding region-of-interest of the sight drop point as target region-of-interest.
Transmission unit 450, for the target region-of-interest to be sent to server, so that the server is according to
Target region-of-interest determines mark answer.
Fourth embodiment
Corresponding to the data mask method in second embodiment, Fig. 4 is shown using data mark shown in second embodiment
The one-to-one data annotation equipment of injecting method.As shown in figure 4, the data annotation equipment 500 is applied to server, the number
It include receiving unit 510 and processing unit 520 according to annotation equipment 500.Wherein, the realization of receiving unit 510 and processing unit 520
Function is gathered with step corresponding in second embodiment to be corresponded, and to avoid repeating, the present embodiment is not described in detail one by one.
Receiving unit 510, the target region-of-interest of multiple pedestrians for receiving advertising equipment transmission, each target
Region-of-interest is for characterizing the region that each pedestrian pays close attention to shown data to be marked.
Optionally, receiving unit 510 are also used to: receiving the every for characterizing of the advertising equipment transmission in preset time period
The target region-of-interest that a pedestrian pays close attention to data to be marked shown by display screen.
Processing unit 520, for according to the target region-of-interest determine the data to be marked corresponding to mark answer
Case.Optionally, processing unit 520 are also used to: determining pedestrian's number corresponding to each target region-of-interest；If described
When number is greater than or equal to preset value, using the corresponding target region-of-interest as mark answer.
Optionally, processing unit 520 are also used to: obtaining weight and row corresponding to each target region-of-interest
Everybody counts；If the product of the weight and pedestrian's number is greater than or equal to preset value, the corresponding target is paid close attention into area
Domain is as mark answer.
In an optional embodiment, described device further include: mark unit is used for according to the mark answer to described
Data to be marked are labeled；Alternatively, the mark answer to be sent to the labeling system of client, so that the labeling system
The data to be marked are labeled.
5th embodiment
As shown in figure 5, being the schematic diagram of terminal device 300.The terminal device 300 includes memory 302, processor
304 and it is stored in the computer program 303 that can be run in the memory 302 and on the processor 304.
When the terminal device 300 is advertising equipment, the computer program 303 is realized when being executed by processor 304
The data mask method in first embodiment, to avoid repeating, details are not described herein again.Alternatively, the computer program 303
The function of each module/unit in data annotation equipment described in 3rd embodiment is realized when being executed by processor 304, to avoid weight
Multiple, details are not described herein again.
When the terminal device 300 is server, the computer program 303 realizes the when being executed by processor 304
The data mask method in two embodiments, to avoid repeating, details are not described herein again.Alternatively, 303 quilt of computer program
The function of each module/unit in data annotation equipment described in fourth embodiment is realized when processor 304 executes, to avoid repeating,
Details are not described herein again.
Illustratively, computer program 303 can be divided into one or more module/units, one or more mould
Block/unit is stored in memory 302, and is executed by processor 304, to complete the present invention.One or more module/units
It can be the series of computation machine program instruction section that can complete specific function, the instruction segment is for describing computer program 303
Implementation procedure in terminal device 300.For example, computer program 303 can be divided into the display list in 3rd embodiment
Member 410, acquisition unit 420, first processing units 430, the second processing unit 440 and transmission unit 450, the specific function of each module
It can will not repeat them here as described in first embodiment or 3rd embodiment.
Wherein, memory 302 may be, but not limited to, random access memory (Random Access Memory,
RAM), read-only memory (Read Only Memory, ROM), programmable read only memory (Programmable Read-
Only Memory, PROM), erasable read-only memory (Erasable Programmable Read-Only Memory,
EPROM), electricallyerasable ROM (EEROM) (Electric Erasable Programmable Read-Only Memory,
EEPROM) etc..Wherein, memory 302 is for storing program, and the processor 304 is after receiving and executing instruction, described in execution
The method of program, the flow definition that aforementioned any embodiment of the embodiment of the present invention discloses can be applied in processor 304, or
It is realized by processor 304.
Processor 304 may be a kind of IC chip, the processing capacity with signal.Above-mentioned processor 304 can
To be general processor, including central processing unit (Central Processing Unit, CPU), network processing unit (Network
Processor, NP) etc.；It can also be digital signal processor (Digital Signal Processor, DSP), dedicated integrated
Circuit (Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components.It may be implemented or execute disclosed each method, step and the logic diagram in the embodiment of the present invention.It is general
Processor can be microprocessor or the processor is also possible to any conventional processor etc..
It is understood that structure shown in fig. 5 is only a kind of structural schematic diagram of terminal device 300, terminal device 300
It can also include than more or fewer components shown in Fig. 5, for example, it is also possible to include image collecting device.It is each shown in Fig. 5
Component can be realized using hardware, software, or its combination.
Sixth embodiment
The embodiment of the present invention also provides a kind of storage medium, and instruction is stored on the storage medium, when described instruction exists
The data mark side in first embodiment is realized when running on computer, when the computer program is executed by processor
Method, to avoid repeating, details are not described herein again.Alternatively, being realized in second embodiment when the computer program is executed by processor
The data mask method, to avoid repeating, details are not described herein again.Alternatively, when the computer program is executed by processor
Realize the function of each module/unit in data annotation equipment described in 3rd embodiment, to avoid repeating, details are not described herein again.Or
Person realizes each module/unit in data annotation equipment described in fourth embodiment when the computer program is executed by processor
Function, to avoid repeating, details are not described herein again.
Through the above description of the embodiments, those skilled in the art can be understood that the present invention can lead to
Hardware realization is crossed, the mode of necessary general hardware platform can also be added to realize by software, based on this understanding, this hair
Bright technical solution can be embodied in the form of software products, which can store in a non-volatile memories
In medium (can be CD-ROM, USB flash disk, mobile hard disk etc.), including some instructions are used so that computer equipment (can be with
It is personal computer, server or the network equipment etc.) method that executes each implement scene of the present invention.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.It should also be noted that similar label and letter exist
Similar terms are indicated in following attached drawing, therefore, once being defined in a certain Xiang Yi attached drawing, are then not required in subsequent attached drawing
It is further defined and explained.
Claims (13)
1. a kind of data mask method, which is characterized in that be applied to advertising equipment, which comprises
Show data to be marked；
The eye image of pedestrian is acquired, and obtains the pedestrian described wait mark by carrying out eye tracking to the eye image
Infuse the sight drop point in data；
The target region-of-interest of the data to be marked is obtained according to the sight drop point；
The target region-of-interest is sent to server, is marked so that the server is determined according to the target region-of-interest
Answer.
2. the method according to claim 1, wherein described obtain the number to be marked according to the sight drop point
According to target region-of-interest, comprising:
The pedestrian each region-of-interest of interest is determined according to the sight drop point；
The pedestrian is calculated to the residence time of the sight drop point of each region-of-interest；
Target region-of-interest is determined according to the residence time.
3. according to the method described in claim 2, it is characterized in that, described determine that target pays close attention to area according to the residence time
Domain, comprising:
Using the residence time longest region-of-interest of the sight drop point as target region-of-interest.
4. according to the method described in claim 2, it is characterized in that, described determine that target pays close attention to area according to the residence time
Domain, comprising:
If the residence time is greater than preset threshold, area is paid close attention to using the corresponding region-of-interest of the sight drop point as target
Domain.
5. the method according to claim 1, wherein the display data to be marked, comprising:
According to the display duration of the crowd is dense degree determines presently described data to be marked；
The data to be marked are shown according to the display duration.
6. a kind of data mask method, which is characterized in that be applied to server, which comprises
The target region-of-interest for multiple pedestrians that advertising equipment is sent is received, each target region-of-interest is each for characterizing
The region that the pedestrian pays close attention to shown data to be marked；
According to the target region-of-interest determine the data to be marked corresponding to mark answer.
7. according to the method described in claim 6, it is characterized in that, described determining described wait mark according to the target region-of-interest
Infuse mark answer corresponding to data, comprising:
Determine pedestrian's number corresponding to each target region-of-interest；
If pedestrian's number corresponding to the target region-of-interest is greater than or equal to preset value, by the corresponding target
Region-of-interest is as mark answer.
8. according to the method described in claim 6, it is characterized in that, described determining described wait mark according to the target region-of-interest
Infuse mark answer corresponding to data, comprising:
Obtain weight and pedestrian's number corresponding to each target region-of-interest；
If the product of weight corresponding to the target region-of-interest and pedestrian's number is greater than or equal to preset value, it will correspond to
The target region-of-interest as mark answer.
9. according to method described in claim 6-8 any one, which is characterized in that the method also includes:
The data to be marked are labeled according to the mark answer；Alternatively,
The mark answer is sent to the labeling system of client, so that the labeling system carries out the data to be marked
Mark.
10. a kind of data annotation equipment, which is characterized in that be applied to advertising equipment, described device includes:
Display unit, for showing data to be marked；
Acquisition unit, for acquiring the eye image of pedestrian；
First processing units, for obtaining the pedestrian in the number to be marked by carrying out eye tracking to the eye image
According to upper sight drop point；
The second processing unit, for obtaining the target region-of-interest of the data to be marked according to the sight drop point；
Transmission unit, for the target region-of-interest to be sent to server, so that the server is closed according to the target
It infuses region and determines mark answer.
11. a kind of data annotation equipment, which is characterized in that be applied to server, described device includes:
Receiving unit, the target region-of-interest of multiple pedestrians for receiving advertising equipment transmission, each target pay close attention to area
Domain is for characterizing the region that each pedestrian pays close attention to shown data to be marked；
Processing unit, for according to the target region-of-interest determine the data to be marked corresponding to mark answer.
12. a kind of terminal device characterized by comprising memory, processor and storage are in the memory and can be
The computer program run on the processor, the processor realize such as claim 1 to 5 when executing the computer program
The step of described in any item data mask methods；Alternatively, the processor realizes such as right when executing the computer program
It is required that the step of 6 to 9 described in any item data mask methods.
13. a kind of storage medium, which is characterized in that instruction is stored on the storage medium, when described instruction on computers
When operation, so that the computer executes such as data mask method described in any one of claim 1 to 5；Alternatively, working as the finger
When order is run on computers, so that the computer executes such as the described in any item data mask methods of claim 6 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811182522.2A CN109409260A (en) | 2018-10-10 | 2018-10-10 | Data mask method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811182522.2A CN109409260A (en) | 2018-10-10 | 2018-10-10 | Data mask method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109409260A true CN109409260A (en) | 2019-03-01 |
Family
ID=65467628
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811182522.2A Pending CN109409260A (en) | 2018-10-10 | 2018-10-10 | Data mask method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109409260A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102024029A (en) * | 2010-11-30 | 2011-04-20 | 辽宁师范大学 | Local visual attention-based color image retrieving method |
| CN104317490A (en) * | 2014-09-30 | 2015-01-28 | 联想(北京)有限公司 | Promoting method and electronic equipment |
| CN104883515A (en) * | 2015-05-22 | 2015-09-02 | 广东威创视讯科技股份有限公司 | Video annotation processing method and video annotation processing server |
| CN106651430A (en) * | 2016-10-19 | 2017-05-10 | 天津工业大学 | Objective advertisement design evaluation method based on visual attention mechanism |
| CN106778687A (en) * | 2017-01-16 | 2017-05-31 | 大连理工大学 | Method for viewing points detecting based on local evaluation and global optimization |
| CN108062341A (en) * | 2016-11-08 | 2018-05-22 | 中国移动通信有限公司研究院 | The automatic marking method and device of data |
| CN108197658A (en) * | 2018-01-11 | 2018-06-22 | 阿里巴巴集团控股有限公司 | Image labeling information processing method, device, server and system |
-
2018
- 2018-10-10 CN CN201811182522.2A patent/CN109409260A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102024029A (en) * | 2010-11-30 | 2011-04-20 | 辽宁师范大学 | Local visual attention-based color image retrieving method |
| CN104317490A (en) * | 2014-09-30 | 2015-01-28 | 联想(北京)有限公司 | Promoting method and electronic equipment |
| CN104883515A (en) * | 2015-05-22 | 2015-09-02 | 广东威创视讯科技股份有限公司 | Video annotation processing method and video annotation processing server |
| CN106651430A (en) * | 2016-10-19 | 2017-05-10 | 天津工业大学 | Objective advertisement design evaluation method based on visual attention mechanism |
| CN108062341A (en) * | 2016-11-08 | 2018-05-22 | 中国移动通信有限公司研究院 | The automatic marking method and device of data |
| CN106778687A (en) * | 2017-01-16 | 2017-05-31 | 大连理工大学 | Method for viewing points detecting based on local evaluation and global optimization |
| CN108197658A (en) * | 2018-01-11 | 2018-06-22 | 阿里巴巴集团控股有限公司 | Image labeling information processing method, device, server and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108460362B (en) | System and method for detecting human body part | |
| BR112020001729A2 (en) | gesture recognition device, apparatus and device | |
| ES2704277T3 (en) | Facial recognition with self-learning using depth-based tracking for the generation and updating of databases | |
| CN108171152A (en) | Deep learning human eye sight estimation method, equipment, system and readable storage medium storing program for executing | |
| CN111045814B (en) | Resource scheduling method and terminal equipment | |
| CN110163076A (en) | A kind of image processing method and relevant apparatus | |
| KR20200132833A (en) | Virtual avatar generation method and apparatus, and storage medium | |
| CN110309060B (en) | Detection method and device for updating identification algorithm, storage medium and computer equipment | |
| CN105556539A (en) | Detection devices and methods for detecting regions of interest | |
| CN107590474B (en) | Unlocking control method and related product | |
| CN109447006A (en) | Image processing method, device, equipment and storage medium | |
| CN111079507B (en) | Behavior recognition method and device, computer device and readable storage medium | |
| CN109215037A (en) | Destination image partition method, device and terminal device | |
| CN105959593B (en) | A kind of exposure method and photographing device of photographing device | |
| CN109840491A (en) | Video stream playing method, system, computer installation and readable storage medium storing program for executing | |
| CN109474785A (en) | The focus of electronic device and electronic device tracks photographic method | |
| CN105468161A (en) | Instruction execution method and device | |
| CN106503631A (en) | A kind of population analysis method and computer equipment | |
| EP3859591A1 (en) | Identity identification method, computer-readable storage medium, terminal device, and apparatus | |
| US10791321B2 (en) | Constructing a user's face model using particle filters | |
| CN111899279A (en) | Method and device for detecting motion speed of target object | |
| CN109299641A (en) | A kind of train dispatcher's fatigue monitoring image adaptive Processing Algorithm | |
| CN109427038A (en) | A kind of cell phone pictures display methods and system | |
| CN104978583A (en) | Person action recognition method and person action recognition device | |
| CN114187392A (en) | Virtual even image generation method and device 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190301 |